summary refs log tree commit diff
diff options
context:
space:
mode:
-rw-r--r--.github/workflows/release-artifacts.yml21
-rw-r--r--.github/workflows/tests.yml14
-rw-r--r--changelog.d/10250.bugfix1
-rw-r--r--changelog.d/10276.bugfix1
-rw-r--r--changelog.d/10289.misc1
-rw-r--r--changelog.d/10298.feature1
-rw-r--r--changelog.d/10305.feature1
-rw-r--r--changelog.d/10313.doc1
-rw-r--r--changelog.d/10315.misc1
-rw-r--r--changelog.d/10316.misc1
-rw-r--r--changelog.d/10317.bugfix1
-rw-r--r--changelog.d/10322.doc1
-rw-r--r--changelog.d/10324.misc1
-rw-r--r--changelog.d/10337.doc1
-rw-r--r--changelog.d/10343.bugfix1
-rw-r--r--changelog.d/10344.bugfix1
-rw-r--r--changelog.d/10345.misc1
-rw-r--r--changelog.d/10347.misc1
-rw-r--r--changelog.d/10349.misc1
-rw-r--r--changelog.d/10350.misc1
-rw-r--r--changelog.d/10353.doc1
-rw-r--r--changelog.d/10355.bugfix1
-rw-r--r--changelog.d/10357.misc1
-rw-r--r--changelog.d/10360.feature1
-rw-r--r--changelog.d/10367.bugfix1
-rw-r--r--changelog.d/10368.doc1
-rw-r--r--changelog.d/10370.doc1
-rw-r--r--changelog.d/10380.misc1
-rw-r--r--changelog.d/10383.misc1
-rw-r--r--changelog.d/10385.misc1
-rw-r--r--changelog.d/10391.misc1
-rw-r--r--changelog.d/10393.misc1
-rw-r--r--changelog.d/10396.doc1
-rw-r--r--changelog.d/10398.misc1
-rw-r--r--changelog.d/10399.doc1
-rw-r--r--changelog.d/10400.bugfix1
-rw-r--r--changelog.d/9721.removal1
-rw-r--r--changelog.d/9971.doc1
-rw-r--r--contrib/docker/docker-compose.yml2
-rw-r--r--contrib/grafana/README.md4
-rw-r--r--contrib/prometheus/README.md2
-rw-r--r--contrib/purge_api/README.md10
-rw-r--r--contrib/purge_api/purge_history.sh2
-rw-r--r--contrib/systemd-with-workers/README.md3
-rw-r--r--docker/build_debian.sh14
-rw-r--r--docs/MSC1711_certificates_FAQ.md4
-rw-r--r--docs/admin_api/media_admin_api.md4
-rw-r--r--docs/admin_api/rooms.md69
-rw-r--r--docs/admin_api/server_notices.md2
-rw-r--r--docs/consent_tracking.md2
-rw-r--r--docs/delegate.md2
-rw-r--r--docs/federate.md8
-rw-r--r--docs/log_contexts.md331
-rw-r--r--docs/replication.md2
-rw-r--r--docs/reverse_proxy.md29
-rw-r--r--docs/room_and_user_statistics.md50
-rw-r--r--docs/sample_config.yaml5
-rw-r--r--docs/server_notices.md4
-rw-r--r--docs/setup/installation.md40
-rw-r--r--docs/systemd-with-workers/README.md16
-rw-r--r--docs/usage/configuration/logging_sample_config.md2
-rw-r--r--docs/workers.md6
-rw-r--r--mypy.ini1
-rw-r--r--synapse/api/auth.py41
-rw-r--r--synapse/api/errors.py4
-rw-r--r--synapse/api/filtering.py2
-rw-r--r--synapse/api/ratelimiting.py4
-rw-r--r--synapse/api/room_versions.py4
-rw-r--r--synapse/app/generic_worker.py2
-rw-r--r--synapse/appservice/api.py4
-rw-r--r--synapse/config/appservice.py4
-rw-r--r--synapse/config/cache.py4
-rw-r--r--synapse/config/emailconfig.py4
-rw-r--r--synapse/config/experimental.py6
-rw-r--r--synapse/config/federation.py2
-rw-r--r--synapse/config/oidc.py2
-rw-r--r--synapse/config/password_auth_providers.py2
-rw-r--r--synapse/config/repository.py4
-rw-r--r--synapse/config/server.py16
-rw-r--r--synapse/config/spam_checker.py2
-rw-r--r--synapse/config/sso.py2
-rw-r--r--synapse/config/stats.py9
-rw-r--r--synapse/config/tls.py6
-rw-r--r--synapse/crypto/keyring.py20
-rw-r--r--synapse/event_auth.py11
-rw-r--r--synapse/events/__init__.py26
-rw-r--r--synapse/events/builder.py16
-rw-r--r--synapse/events/spamcheck.py4
-rw-r--r--synapse/federation/federation_client.py10
-rw-r--r--synapse/federation/federation_server.py34
-rw-r--r--synapse/federation/send_queue.py26
-rw-r--r--synapse/federation/sender/__init__.py110
-rw-r--r--synapse/federation/sender/per_destination_queue.py34
-rw-r--r--synapse/federation/transport/client.py8
-rw-r--r--synapse/federation/transport/server.py120
-rw-r--r--synapse/groups/groups_server.py12
-rw-r--r--synapse/handlers/directory.py5
-rw-r--r--synapse/handlers/federation.py25
-rw-r--r--synapse/handlers/message.py18
-rw-r--r--synapse/handlers/receipts.py15
-rw-r--r--synapse/handlers/room_list.py26
-rw-r--r--synapse/handlers/space_summary.py68
-rw-r--r--synapse/handlers/stats.py27
-rw-r--r--synapse/handlers/typing.py14
-rw-r--r--synapse/http/__init__.py2
-rw-r--r--synapse/http/client.py18
-rw-r--r--synapse/http/matrixfederationclient.py40
-rw-r--r--synapse/http/proxyagent.py12
-rw-r--r--synapse/http/server.py8
-rw-r--r--synapse/http/servlet.py2
-rw-r--r--synapse/http/site.py14
-rw-r--r--synapse/logging/_remote.py14
-rw-r--r--synapse/logging/_structured.py2
-rw-r--r--synapse/logging/context.py16
-rw-r--r--synapse/logging/opentracing.py10
-rw-r--r--synapse/metrics/__init__.py6
-rw-r--r--synapse/metrics/_exposition.py2
-rw-r--r--synapse/metrics/background_process_metrics.py4
-rw-r--r--synapse/module_api/__init__.py2
-rw-r--r--synapse/notifier.py18
-rw-r--r--synapse/push/bulk_push_rule_evaluator.py4
-rw-r--r--synapse/push/clientformat.py4
-rw-r--r--synapse/push/emailpusher.py6
-rw-r--r--synapse/push/httppusher.py2
-rw-r--r--synapse/push/mailer.py12
-rw-r--r--synapse/push/presentable_names.py2
-rw-r--r--synapse/push/push_rule_evaluator.py4
-rw-r--r--synapse/push/pusher.py6
-rw-r--r--synapse/push/pusherpool.py2
-rw-r--r--synapse/python_dependencies.py4
-rw-r--r--synapse/replication/http/_base.py10
-rw-r--r--synapse/replication/slave/storage/_base.py6
-rw-r--r--synapse/replication/slave/storage/client_ips.py4
-rw-r--r--synapse/replication/tcp/client.py10
-rw-r--r--synapse/replication/tcp/commands.py6
-rw-r--r--synapse/replication/tcp/handler.py16
-rw-r--r--synapse/replication/tcp/protocol.py14
-rw-r--r--synapse/replication/tcp/redis.py8
-rw-r--r--synapse/replication/tcp/streams/_base.py14
-rw-r--r--synapse/replication/tcp/streams/events.py28
-rw-r--r--synapse/replication/tcp/streams/federation.py6
-rw-r--r--synapse/rest/admin/rooms.py9
-rw-r--r--synapse/rest/client/v1/room.py157
-rw-r--r--synapse/server.py6
-rw-r--r--synapse/server_notices/consent_server_notices.py2
-rw-r--r--synapse/server_notices/resource_limits_server_notices.py2
-rw-r--r--synapse/server_notices/server_notices_sender.py6
-rw-r--r--synapse/state/__init__.py20
-rw-r--r--synapse/state/v1.py2
-rw-r--r--synapse/state/v2.py18
-rw-r--r--synapse/storage/databases/main/event_federation.py4
-rw-r--r--synapse/storage/databases/main/events.py4
-rw-r--r--synapse/storage/databases/main/metrics.py4
-rw-r--r--synapse/storage/databases/main/purge_events.py2
-rw-r--r--synapse/storage/databases/main/room.py104
-rw-r--r--synapse/storage/databases/main/roommember.py13
-rw-r--r--synapse/storage/databases/main/stats.py299
-rw-r--r--synapse/storage/schema/__init__.py6
-rw-r--r--synapse/storage/schema/main/delta/61/01change_appservices_txns.sql.postgres23
-rw-r--r--synapse/storage/schema/main/delta/61/02drop_redundant_room_depth_index.sql18
-rw-r--r--synapse/storage/schema/main/delta/61/03recreate_min_depth.py70
-rw-r--r--synapse/streams/events.py4
-rw-r--r--synapse/types.py10
-rw-r--r--synapse/visibility.py2
-rw-r--r--sytest-blacklist5
-rw-r--r--tests/app/test_phone_stats_home.py153
-rw-r--r--tests/config/test_load.py4
-rw-r--r--tests/events/test_presence_router.py14
-rw-r--r--tests/handlers/test_profile.py2
-rw-r--r--tests/handlers/test_space_summary.py391
-rw-r--r--tests/handlers/test_stats.py203
-rw-r--r--tests/handlers/test_typing.py37
-rw-r--r--tests/http/federation/test_matrix_federation_agent.py2
-rw-r--r--tests/http/test_fedclient.py8
-rw-r--r--tests/http/test_proxyagent.py65
-rw-r--r--tests/module_api/test_api.py16
-rw-r--r--tests/replication/_base.py18
-rw-r--r--tests/replication/tcp/streams/test_events.py14
-rw-r--r--tests/replication/tcp/streams/test_receipts.py4
-rw-r--r--tests/replication/tcp/streams/test_typing.py4
-rw-r--r--tests/replication/test_multi_media_repo.py6
-rw-r--r--tests/replication/test_sharded_event_persister.py6
-rw-r--r--tests/rest/admin/test_admin.py6
-rw-r--r--tests/rest/admin/test_room.py21
-rw-r--r--tests/rest/client/test_third_party_rules.py4
-rw-r--r--tests/rest/client/v1/test_login.py14
-rw-r--r--tests/rest/client/v1/test_rooms.py14
-rw-r--r--tests/rest/client/v2_alpha/test_relations.py2
-rw-r--r--tests/rest/client/v2_alpha/test_report_event.py2
-rw-r--r--tests/rest/media/v1/test_media_storage.py2
-rw-r--r--tests/server.py8
-rw-r--r--tests/storage/test_background_update.py4
-rw-r--r--tests/storage/test_directory.py2
-rw-r--r--tests/storage/test_id_generators.py6
-rw-r--r--tests/storage/test_profile.py12
-rw-r--r--tests/storage/test_purge.py2
-rw-r--r--tests/storage/test_room.py2
-rw-r--r--tests/test_event_auth.py23
-rw-r--r--tests/test_state.py2
-rw-r--r--tests/test_types.py4
-rw-r--r--tests/test_utils/html_parsers.py6
-rw-r--r--tests/unittest.py4
-rw-r--r--tests/util/caches/test_descriptors.py2
-rw-r--r--tests/util/test_itertools.py18
204 files changed, 2134 insertions, 1539 deletions
diff --git a/.github/workflows/release-artifacts.yml b/.github/workflows/release-artifacts.yml
index f292d703ed..325c1f7d39 100644
--- a/.github/workflows/release-artifacts.yml
+++ b/.github/workflows/release-artifacts.yml
@@ -3,28 +3,33 @@
 name: Build release artifacts
 
 on:
+  # we build on PRs and develop to (hopefully) get early warning
+  # of things breaking (but only build one set of debs)
+  pull_request:
   push:
-    # we build on develop and release branches to (hopefully) get early warning
-    # of things breaking
-    branches: ["develop", "release-*"]
+    branches: ["develop"]
 
-    # we also rebuild on tags, so that we can be sure of picking the artifacts
-    # from the right tag.
+    # we do the full build on tags.
     tags: ["v*"]
 
 permissions:
   contents: write
 
 jobs:
-  # first get the list of distros to build for.
   get-distros:
+    name: "Calculate list of debian distros"
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v2
       - uses: actions/setup-python@v2
       - id: set-distros
         run: |
-          echo "::set-output name=distros::$(scripts-dev/build_debian_packages --show-dists-json)"
+          # if we're running from a tag, get the full list of distros; otherwise just use debian:sid
+          dists='["debian:sid"]'
+          if [[ $GITHUB_REF == refs/tags/* ]]; then
+              dists=$(scripts-dev/build_debian_packages --show-dists-json)
+          fi
+          echo "::set-output name=distros::$dists"
     # map the step outputs to job outputs
     outputs:
       distros: ${{ steps.set-distros.outputs.distros }}
@@ -66,7 +71,7 @@ jobs:
   # if it's a tag, create a release and attach the artifacts to it
   attach-assets:
     name: "Attach assets to release"
-    if: startsWith(github.ref, 'refs/tags/')
+    if: ${{ !failure() && !cancelled() && startsWith(github.ref, 'refs/tags/') }}
     needs:
       - build-debs
       - build-sdist
diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml
index bf36ee1cdf..505bac1308 100644
--- a/.github/workflows/tests.yml
+++ b/.github/workflows/tests.yml
@@ -65,14 +65,14 @@ jobs:
 
   # Dummy step to gate other tests on without repeating the whole list
   linting-done:
-    if: ${{ always() }} # Run this even if prior jobs were skipped
+    if: ${{ !cancelled() }} # Run this even if prior jobs were skipped
     needs: [lint, lint-crlf, lint-newsfile, lint-sdist]
     runs-on: ubuntu-latest
     steps:
       - run: "true"
 
   trial:
-    if: ${{ !failure() }} # Allow previous steps to be skipped, but not fail
+    if: ${{ !cancelled() && !failure() }} # Allow previous steps to be skipped, but not fail
     needs: linting-done
     runs-on: ubuntu-latest
     strategy:
@@ -131,7 +131,7 @@ jobs:
           || true
 
   trial-olddeps:
-    if: ${{ !failure() }} # Allow previous steps to be skipped, but not fail
+    if: ${{ !cancelled() && !failure() }} # Allow previous steps to be skipped, but not fail
     needs: linting-done
     runs-on: ubuntu-latest
     steps:
@@ -156,7 +156,7 @@ jobs:
 
   trial-pypy:
     # Very slow; only run if the branch name includes 'pypy'
-    if: ${{ contains(github.ref, 'pypy') && !failure() }}
+    if: ${{ contains(github.ref, 'pypy') && !failure() && !cancelled() }}
     needs: linting-done
     runs-on: ubuntu-latest
     strategy:
@@ -185,7 +185,7 @@ jobs:
           || true
 
   sytest:
-    if: ${{ !failure() }}
+    if: ${{ !failure() && !cancelled() }}
     needs: linting-done
     runs-on: ubuntu-latest
     container:
@@ -245,7 +245,7 @@ jobs:
             /logs/**/*.log*
 
   portdb:
-    if: ${{ !failure() }} # Allow previous steps to be skipped, but not fail
+    if: ${{ !failure() && !cancelled() }} # Allow previous steps to be skipped, but not fail
     needs: linting-done
     runs-on: ubuntu-latest
     strategy:
@@ -286,7 +286,7 @@ jobs:
       - run: .buildkite/scripts/test_synapse_port_db.sh
 
   complement:
-    if: ${{ !failure() }}
+    if: ${{ !failure() && !cancelled() }}
     needs: linting-done
     runs-on: ubuntu-latest
     container:
diff --git a/changelog.d/10250.bugfix b/changelog.d/10250.bugfix
new file mode 100644
index 0000000000..a8107dafb2
--- /dev/null
+++ b/changelog.d/10250.bugfix
@@ -0,0 +1 @@
+Add base starting insertion event when no chunk ID is specified in the historical batch send API.
diff --git a/changelog.d/10276.bugfix b/changelog.d/10276.bugfix
new file mode 100644
index 0000000000..42adc57ad1
--- /dev/null
+++ b/changelog.d/10276.bugfix
@@ -0,0 +1 @@
+Fix historical batch send endpoint (MSC2716) rejecting batches with messages from multiple senders.
diff --git a/changelog.d/10289.misc b/changelog.d/10289.misc
new file mode 100644
index 0000000000..2df30e7a7a
--- /dev/null
+++ b/changelog.d/10289.misc
@@ -0,0 +1 @@
+Convert `room_depth.min_depth` column to a `BIGINT`.
diff --git a/changelog.d/10298.feature b/changelog.d/10298.feature
new file mode 100644
index 0000000000..7059db5075
--- /dev/null
+++ b/changelog.d/10298.feature
@@ -0,0 +1 @@
+The spaces summary API now returns any joinable rooms, not only rooms which are world-readable.
diff --git a/changelog.d/10305.feature b/changelog.d/10305.feature
new file mode 100644
index 0000000000..7059db5075
--- /dev/null
+++ b/changelog.d/10305.feature
@@ -0,0 +1 @@
+The spaces summary API now returns any joinable rooms, not only rooms which are world-readable.
diff --git a/changelog.d/10313.doc b/changelog.d/10313.doc
new file mode 100644
index 0000000000..44086e3d9d
--- /dev/null
+++ b/changelog.d/10313.doc
@@ -0,0 +1 @@
+Simplify structure of room admin API.
\ No newline at end of file
diff --git a/changelog.d/10315.misc b/changelog.d/10315.misc
new file mode 100644
index 0000000000..2c78644e20
--- /dev/null
+++ b/changelog.d/10315.misc
@@ -0,0 +1 @@
+Add tests to characterise the current behaviour of R30 phone-home metrics.
diff --git a/changelog.d/10316.misc b/changelog.d/10316.misc
new file mode 100644
index 0000000000..1fd0810fde
--- /dev/null
+++ b/changelog.d/10316.misc
@@ -0,0 +1 @@
+Rebuild event context and auth when processing specific results from `ThirdPartyEventRules` modules.
diff --git a/changelog.d/10317.bugfix b/changelog.d/10317.bugfix
new file mode 100644
index 0000000000..826c269eff
--- /dev/null
+++ b/changelog.d/10317.bugfix
@@ -0,0 +1 @@
+Fix purging rooms that other homeservers are still sending events for. Contributed by @ilmari.
diff --git a/changelog.d/10322.doc b/changelog.d/10322.doc
new file mode 100644
index 0000000000..db604cf2aa
--- /dev/null
+++ b/changelog.d/10322.doc
@@ -0,0 +1 @@
+Fix a broken link in the admin api docs.
diff --git a/changelog.d/10324.misc b/changelog.d/10324.misc
new file mode 100644
index 0000000000..3c3ee6d6fc
--- /dev/null
+++ b/changelog.d/10324.misc
@@ -0,0 +1 @@
+Minor change to the code that populates `user_daily_visits`.
diff --git a/changelog.d/10337.doc b/changelog.d/10337.doc
new file mode 100644
index 0000000000..f305bdb3ba
--- /dev/null
+++ b/changelog.d/10337.doc
@@ -0,0 +1 @@
+Fix formatting in the logcontext documentation.
diff --git a/changelog.d/10343.bugfix b/changelog.d/10343.bugfix
new file mode 100644
index 0000000000..53ccf79a81
--- /dev/null
+++ b/changelog.d/10343.bugfix
@@ -0,0 +1 @@
+Fix errors during backfill caused by previously purged redaction events. Contributed by Andreas Rammhold (@andir).
diff --git a/changelog.d/10344.bugfix b/changelog.d/10344.bugfix
new file mode 100644
index 0000000000..ab6eb4999f
--- /dev/null
+++ b/changelog.d/10344.bugfix
@@ -0,0 +1 @@
+Fix the user directory becoming broken (and noisy errors being logged) when knocking and room statistics are in use.
diff --git a/changelog.d/10345.misc b/changelog.d/10345.misc
new file mode 100644
index 0000000000..7424486e87
--- /dev/null
+++ b/changelog.d/10345.misc
@@ -0,0 +1 @@
+Re-enable Sytests that were disabled for the 1.37.1 release.
diff --git a/changelog.d/10347.misc b/changelog.d/10347.misc
new file mode 100644
index 0000000000..b2275a1350
--- /dev/null
+++ b/changelog.d/10347.misc
@@ -0,0 +1 @@
+Run `pyupgrade` on the codebase.
\ No newline at end of file
diff --git a/changelog.d/10349.misc b/changelog.d/10349.misc
new file mode 100644
index 0000000000..5b014e7416
--- /dev/null
+++ b/changelog.d/10349.misc
@@ -0,0 +1 @@
+Switch `application_services_txns.txn_id` database column to `BIGINT`.
diff --git a/changelog.d/10350.misc b/changelog.d/10350.misc
new file mode 100644
index 0000000000..eed2d8552a
--- /dev/null
+++ b/changelog.d/10350.misc
@@ -0,0 +1 @@
+Convert internal type variable syntax to reflect wider ecosystem use.
\ No newline at end of file
diff --git a/changelog.d/10353.doc b/changelog.d/10353.doc
new file mode 100644
index 0000000000..274ac83549
--- /dev/null
+++ b/changelog.d/10353.doc
@@ -0,0 +1 @@
+Refresh the logcontext dev documentation.
diff --git a/changelog.d/10355.bugfix b/changelog.d/10355.bugfix
new file mode 100644
index 0000000000..92df612011
--- /dev/null
+++ b/changelog.d/10355.bugfix
@@ -0,0 +1 @@
+Fix newly added `synapse_federation_server_oldest_inbound_pdu_in_staging` prometheus metric to measure age rather than timestamp.
diff --git a/changelog.d/10357.misc b/changelog.d/10357.misc
new file mode 100644
index 0000000000..7424486e87
--- /dev/null
+++ b/changelog.d/10357.misc
@@ -0,0 +1 @@
+Re-enable Sytests that were disabled for the 1.37.1 release.
diff --git a/changelog.d/10360.feature b/changelog.d/10360.feature
new file mode 100644
index 0000000000..904221cb6d
--- /dev/null
+++ b/changelog.d/10360.feature
@@ -0,0 +1 @@
+Allow providing credentials to `http_proxy`.
\ No newline at end of file
diff --git a/changelog.d/10367.bugfix b/changelog.d/10367.bugfix
new file mode 100644
index 0000000000..b445556084
--- /dev/null
+++ b/changelog.d/10367.bugfix
@@ -0,0 +1 @@
+Bugfix `make_room_admin` fails for users that have left a private room.
\ No newline at end of file
diff --git a/changelog.d/10368.doc b/changelog.d/10368.doc
new file mode 100644
index 0000000000..10297aa424
--- /dev/null
+++ b/changelog.d/10368.doc
@@ -0,0 +1 @@
+Add delegation example for caddy in the reverse proxy documentation. Contributed by @moritzdietz.
diff --git a/changelog.d/10370.doc b/changelog.d/10370.doc
new file mode 100644
index 0000000000..8c59d98ee8
--- /dev/null
+++ b/changelog.d/10370.doc
@@ -0,0 +1 @@
+Fix some links in `docs` and `contrib`.
\ No newline at end of file
diff --git a/changelog.d/10380.misc b/changelog.d/10380.misc
new file mode 100644
index 0000000000..eed2d8552a
--- /dev/null
+++ b/changelog.d/10380.misc
@@ -0,0 +1 @@
+Convert internal type variable syntax to reflect wider ecosystem use.
\ No newline at end of file
diff --git a/changelog.d/10383.misc b/changelog.d/10383.misc
new file mode 100644
index 0000000000..952c1e77a8
--- /dev/null
+++ b/changelog.d/10383.misc
@@ -0,0 +1 @@
+Make the Github Actions workflow configuration more efficient.
diff --git a/changelog.d/10385.misc b/changelog.d/10385.misc
new file mode 100644
index 0000000000..e515ac09fd
--- /dev/null
+++ b/changelog.d/10385.misc
@@ -0,0 +1 @@
+Add type hints to `get_{domain,localpart}_from_id`.
diff --git a/changelog.d/10391.misc b/changelog.d/10391.misc
new file mode 100644
index 0000000000..3f191b520a
--- /dev/null
+++ b/changelog.d/10391.misc
@@ -0,0 +1 @@
+When building Debian packages for prerelease versions, set the Section accordingly.
diff --git a/changelog.d/10393.misc b/changelog.d/10393.misc
new file mode 100644
index 0000000000..e80f16d607
--- /dev/null
+++ b/changelog.d/10393.misc
@@ -0,0 +1 @@
+Add type hints and comments to event auth code.
diff --git a/changelog.d/10396.doc b/changelog.d/10396.doc
new file mode 100644
index 0000000000..b521ad9cbf
--- /dev/null
+++ b/changelog.d/10396.doc
@@ -0,0 +1 @@
+Add instructructions on installing Debian packages for release candidates.
diff --git a/changelog.d/10398.misc b/changelog.d/10398.misc
new file mode 100644
index 0000000000..326e54655a
--- /dev/null
+++ b/changelog.d/10398.misc
@@ -0,0 +1 @@
+Stagger sending of presence update to remote servers, reducing CPU spikes caused by starting many connections to remote servers at once.
diff --git a/changelog.d/10399.doc b/changelog.d/10399.doc
new file mode 100644
index 0000000000..b596ac5627
--- /dev/null
+++ b/changelog.d/10399.doc
@@ -0,0 +1 @@
+Rewrite the text of links to be clearer in the documentation.
diff --git a/changelog.d/10400.bugfix b/changelog.d/10400.bugfix
new file mode 100644
index 0000000000..bfebed8d29
--- /dev/null
+++ b/changelog.d/10400.bugfix
@@ -0,0 +1 @@
+Fix a number of logged errors caused by remote servers being down.
diff --git a/changelog.d/9721.removal b/changelog.d/9721.removal
new file mode 100644
index 0000000000..da2ba48c84
--- /dev/null
+++ b/changelog.d/9721.removal
@@ -0,0 +1 @@
+Remove functionality associated with the unused `room_stats_historical` and `user_stats_historical` tables. Contributed by @xmunoz.
diff --git a/changelog.d/9971.doc b/changelog.d/9971.doc
new file mode 100644
index 0000000000..ada68f70ca
--- /dev/null
+++ b/changelog.d/9971.doc
@@ -0,0 +1 @@
+Updated installation dependencies for newer macOS versions and ARM Macs. Contributed by Luke Walsh.
diff --git a/contrib/docker/docker-compose.yml b/contrib/docker/docker-compose.yml
index d1ecd453db..26d640c448 100644
--- a/contrib/docker/docker-compose.yml
+++ b/contrib/docker/docker-compose.yml
@@ -56,7 +56,7 @@ services:
       - POSTGRES_USER=synapse
       - POSTGRES_PASSWORD=changeme
       # ensure the database gets created correctly
-      # https://github.com/matrix-org/synapse/blob/master/docs/postgres.md#set-up-database
+      # https://matrix-org.github.io/synapse/latest/postgres.html#set-up-database
       - POSTGRES_INITDB_ARGS=--encoding=UTF-8 --lc-collate=C --lc-ctype=C
     volumes:
       # You may store the database tables in a local folder..
diff --git a/contrib/grafana/README.md b/contrib/grafana/README.md
index 4608793394..0d4e1b59b2 100644
--- a/contrib/grafana/README.md
+++ b/contrib/grafana/README.md
@@ -1,6 +1,6 @@
 # Using the Synapse Grafana dashboard
 
 0. Set up Prometheus and Grafana. Out of scope for this readme. Useful documentation about using Grafana with Prometheus: http://docs.grafana.org/features/datasources/prometheus/
-1. Have your Prometheus scrape your Synapse. https://github.com/matrix-org/synapse/blob/master/docs/metrics-howto.md
+1. Have your Prometheus scrape your Synapse. https://matrix-org.github.io/synapse/latest/metrics-howto.html
 2. Import dashboard into Grafana. Download `synapse.json`. Import it to Grafana and select the correct Prometheus datasource. http://docs.grafana.org/reference/export_import/
-3. Set up required recording rules. https://github.com/matrix-org/synapse/tree/master/contrib/prometheus
+3. Set up required recording rules. [contrib/prometheus](../prometheus)
diff --git a/contrib/prometheus/README.md b/contrib/prometheus/README.md
index b3f23bcc80..4dbf648df8 100644
--- a/contrib/prometheus/README.md
+++ b/contrib/prometheus/README.md
@@ -34,7 +34,7 @@ Add a new job to the main prometheus.yml file:
 ```
 
 An example of a Prometheus configuration with workers can be found in
-[metrics-howto.md](https://github.com/matrix-org/synapse/blob/master/docs/metrics-howto.md).
+[metrics-howto.md](https://matrix-org.github.io/synapse/latest/metrics-howto.html).
 
 To use `synapse.rules` add
 
diff --git a/contrib/purge_api/README.md b/contrib/purge_api/README.md
index 06b4cdb9f7..2f2e5c58cd 100644
--- a/contrib/purge_api/README.md
+++ b/contrib/purge_api/README.md
@@ -3,8 +3,9 @@ Purge history API examples
 
 # `purge_history.sh`
 
-A bash file, that uses the [purge history API](/docs/admin_api/purge_history_api.rst) to 
-purge all messages in a list of rooms up to a certain event. You can select a 
+A bash file, that uses the
+[purge history API](https://matrix-org.github.io/synapse/latest/admin_api/purge_history_api.html)
+to purge all messages in a list of rooms up to a certain event. You can select a 
 timeframe or a number of messages that you want to keep in the room.
 
 Just configure the variables DOMAIN, ADMIN, ROOMS_ARRAY and TIME at the top of
@@ -12,5 +13,6 @@ the script.
 
 # `purge_remote_media.sh`
 
-A bash file, that uses the [purge history API](/docs/admin_api/purge_history_api.rst) to 
-purge all old cached remote media.
+A bash file, that uses the
+[purge history API](https://matrix-org.github.io/synapse/latest/admin_api/purge_history_api.html)
+to purge all old cached remote media.
diff --git a/contrib/purge_api/purge_history.sh b/contrib/purge_api/purge_history.sh
index c45136ff53..9d5324ea1c 100644
--- a/contrib/purge_api/purge_history.sh
+++ b/contrib/purge_api/purge_history.sh
@@ -1,7 +1,7 @@
 #!/usr/bin/env bash
 
 # this script will use the api:
-#    https://github.com/matrix-org/synapse/blob/master/docs/admin_api/purge_history_api.rst
+#    https://matrix-org.github.io/synapse/latest/admin_api/purge_history_api.html
 # 
 # It will purge all messages in a list of rooms up to a cetrain event
 
diff --git a/contrib/systemd-with-workers/README.md b/contrib/systemd-with-workers/README.md
index 8d21d532bd..9b19b042e9 100644
--- a/contrib/systemd-with-workers/README.md
+++ b/contrib/systemd-with-workers/README.md
@@ -1,2 +1,3 @@
 The documentation for using systemd to manage synapse workers is now part of
-the main synapse distribution. See [docs/systemd-with-workers](../../docs/systemd-with-workers).
+the main synapse distribution. See
+[docs/systemd-with-workers](https://matrix-org.github.io/synapse/latest/systemd-with-workers/index.html).
diff --git a/docker/build_debian.sh b/docker/build_debian.sh
index f426d2b77b..f572ed9aa0 100644
--- a/docker/build_debian.sh
+++ b/docker/build_debian.sh
@@ -15,6 +15,20 @@ cd /synapse/build
 dch -M -l "+$DIST" "build for $DIST"
 dch -M -r "" --force-distribution --distribution "$DIST"
 
+# if this is a prerelease, set the Section accordingly.
+#
+# When the package is later added to the package repo, reprepro will use the
+# Section to determine which "component" it should go into (see
+# https://manpages.debian.org/stretch/reprepro/reprepro.1.en.html#GUESSING)
+
+DEB_VERSION=`dpkg-parsechangelog -SVersion`
+case $DEB_VERSION in
+    *rc*|*a*|*b*|*c*)
+        sed -ie '/^Section:/c\Section: prerelease' debian/control
+        ;;
+esac
+
+
 dpkg-buildpackage -us -uc
 
 ls -l ..
diff --git a/docs/MSC1711_certificates_FAQ.md b/docs/MSC1711_certificates_FAQ.md
index 283f288aaf..7d71c190ab 100644
--- a/docs/MSC1711_certificates_FAQ.md
+++ b/docs/MSC1711_certificates_FAQ.md
@@ -132,7 +132,7 @@ your domain, you can simply route all traffic through the reverse proxy by
 updating the SRV record appropriately (or removing it, if the proxy listens on
 8448).
 
-See [reverse_proxy.md](reverse_proxy.md) for information on setting up a
+See [the reverse proxy documentation](reverse_proxy.md) for information on setting up a
 reverse proxy.
 
 #### Option 3: add a .well-known file to delegate your matrix traffic
@@ -303,7 +303,7 @@ We no longer actively recommend against using a reverse proxy. Many admins will
 find it easier to direct federation traffic to a reverse proxy and manage their
 own TLS certificates, and this is a supported configuration.
 
-See [reverse_proxy.md](reverse_proxy.md) for information on setting up a
+See [the reverse proxy documentation](reverse_proxy.md) for information on setting up a
 reverse proxy.
 
 ### Do I still need to give my TLS certificates to Synapse if I am using a reverse proxy?
diff --git a/docs/admin_api/media_admin_api.md b/docs/admin_api/media_admin_api.md
index b033fc03ef..61bed1e0d5 100644
--- a/docs/admin_api/media_admin_api.md
+++ b/docs/admin_api/media_admin_api.md
@@ -47,7 +47,7 @@ The API returns a JSON body like the following:
 ## List all media uploaded by a user
 
 Listing all media that has been uploaded by a local user can be achieved through
-the use of the [List media of a user](user_admin_api.rst#list-media-of-a-user)
+the use of the [List media of a user](user_admin_api.md#list-media-of-a-user)
 Admin API.
 
 # Quarantine media
@@ -257,7 +257,7 @@ URL Parameters
 * `server_name`: string - The name of your local server (e.g `matrix.org`).
 * `before_ts`: string representing a positive integer - Unix timestamp in ms.
 Files that were last used before this timestamp will be deleted. It is the timestamp of
-last access and not the timestamp creation. 
+last access and not the timestamp creation.
 * `size_gt`: Optional - string representing a positive integer - Size of the media in bytes.
 Files that are larger will be deleted. Defaults to `0`.
 * `keep_profiles`: Optional - string representing a boolean - Switch to also delete files
diff --git a/docs/admin_api/rooms.md b/docs/admin_api/rooms.md
index bb7828a525..48777dd231 100644
--- a/docs/admin_api/rooms.md
+++ b/docs/admin_api/rooms.md
@@ -1,13 +1,9 @@
 # Contents
 - [List Room API](#list-room-api)
-  * [Parameters](#parameters)
-  * [Usage](#usage)
 - [Room Details API](#room-details-api)
 - [Room Members API](#room-members-api)
 - [Room State API](#room-state-api)
 - [Delete Room API](#delete-room-api)
-  * [Parameters](#parameters-1)
-  * [Response](#response)
   * [Undoing room shutdowns](#undoing-room-shutdowns)
 - [Make Room Admin API](#make-room-admin-api)
 - [Forward Extremities Admin API](#forward-extremities-admin-api)
@@ -19,7 +15,7 @@ The List Room admin API allows server admins to get a list of rooms on their
 server. There are various parameters available that allow for filtering and
 sorting the returned list. This API supports pagination.
 
-## Parameters
+**Parameters**
 
 The following query parameters are available:
 
@@ -46,6 +42,8 @@ The following query parameters are available:
 * `search_term` - Filter rooms by their room name. Search term can be contained in any
                   part of the room name. Defaults to no filtering.
 
+**Response**
+
 The following fields are possible in the JSON response body:
 
 * `rooms` - An array of objects, each containing information about a room.
@@ -79,17 +77,15 @@ The following fields are possible in the JSON response body:
                  Use `prev_batch` for the `from` value in the next request to
                  get the "previous page" of results.
 
-## Usage
+The API is:
 
 A standard request with no filtering:
 
 ```
 GET /_synapse/admin/v1/rooms
-
-{}
 ```
 
-Response:
+A response body like the following is returned:
 
 ```jsonc
 {
@@ -137,11 +133,9 @@ Filtering by room name:
 
 ```
 GET /_synapse/admin/v1/rooms?search_term=TWIM
-
-{}
 ```
 
-Response:
+A response body like the following is returned:
 
 ```json
 {
@@ -172,11 +166,9 @@ Paginating through a list of rooms:
 
 ```
 GET /_synapse/admin/v1/rooms?order_by=size
-
-{}
 ```
 
-Response:
+A response body like the following is returned:
 
 ```jsonc
 {
@@ -228,11 +220,9 @@ parameter to the value of `next_token`.
 
 ```
 GET /_synapse/admin/v1/rooms?order_by=size&from=100
-
-{}
 ```
 
-Response:
+A response body like the following is returned:
 
 ```jsonc
 {
@@ -304,17 +294,13 @@ The following fields are possible in the JSON response body:
 * `history_visibility` - Who can see the room history. One of: ["invited", "joined", "shared", "world_readable"].
 * `state_events` - Total number of state_events of a room. Complexity of the room.
 
-## Usage
-
-A standard request:
+The API is:
 
 ```
 GET /_synapse/admin/v1/rooms/<room_id>
-
-{}
 ```
 
-Response:
+A response body like the following is returned:
 
 ```json
 {
@@ -347,17 +333,13 @@ The response includes the following fields:
 * `members` - A list of all the members that are present in the room, represented by their ids.
 * `total` - Total number of members in the room.
 
-## Usage
-
-A standard request:
+The API is:
 
 ```
 GET /_synapse/admin/v1/rooms/<room_id>/members
-
-{}
 ```
 
-Response:
+A response body like the following is returned:
 
 ```json
 {
@@ -378,17 +360,13 @@ The response includes the following fields:
 
 * `state` - The current state of the room at the time of request.
 
-## Usage
-
-A standard request:
+The API is:
 
 ```
 GET /_synapse/admin/v1/rooms/<room_id>/state
-
-{}
 ```
 
-Response:
+A response body like the following is returned:
 
 ```json
 {
@@ -432,6 +410,7 @@ DELETE /_synapse/admin/v1/rooms/<room_id>
 ```
 
 with a body of:
+
 ```json
 {
     "new_room_user_id": "@someuser:example.com",
@@ -461,7 +440,7 @@ A response body like the following is returned:
 }
 ```
 
-## Parameters
+**Parameters**
 
 The following parameters should be set in the URL:
 
@@ -491,7 +470,7 @@ The following JSON body parameters are available:
 
 The JSON body must not be empty. The body must be at least `{}`.
 
-## Response
+**Response**
 
 The following fields are returned in the JSON response body:
 
@@ -548,10 +527,10 @@ By default the server admin (the caller) is granted power, but another user can
 optionally be specified, e.g.:
 
 ```
-    POST /_synapse/admin/v1/rooms/<room_id_or_alias>/make_room_admin
-    {
-        "user_id": "@foo:example.com"
-    }
+POST /_synapse/admin/v1/rooms/<room_id_or_alias>/make_room_admin
+{
+    "user_id": "@foo:example.com"
+}
 ```
 
 # Forward Extremities Admin API
@@ -565,7 +544,7 @@ extremities accumulate in a room, performance can become degraded. For details,
 To check the status of forward extremities for a room:
 
 ```
-    GET /_synapse/admin/v1/rooms/<room_id_or_alias>/forward_extremities
+GET /_synapse/admin/v1/rooms/<room_id_or_alias>/forward_extremities
 ```
 
 A response as follows will be returned:
@@ -581,7 +560,7 @@ A response as follows will be returned:
       "received_ts": 1611263016761
     }
   ]
-}    
+}
 ```
 
 ## Deleting forward extremities
@@ -594,7 +573,7 @@ If a room has lots of forward extremities, the extra can be
 deleted as follows:
 
 ```
-    DELETE /_synapse/admin/v1/rooms/<room_id_or_alias>/forward_extremities
+DELETE /_synapse/admin/v1/rooms/<room_id_or_alias>/forward_extremities
 ```
 
 A response as follows will be returned, indicating the amount of forward extremities
diff --git a/docs/admin_api/server_notices.md b/docs/admin_api/server_notices.md
index 858b052b84..323138491a 100644
--- a/docs/admin_api/server_notices.md
+++ b/docs/admin_api/server_notices.md
@@ -45,4 +45,4 @@ Once the notice has been sent, the API will return the following response:
 ```
 
 Note that server notices must be enabled in `homeserver.yaml` before this API
-can be used. See [server_notices.md](../server_notices.md) for more information.
+can be used. See [the server notices documentation](../server_notices.md) for more information.
diff --git a/docs/consent_tracking.md b/docs/consent_tracking.md
index 3f997e5903..911a1f95db 100644
--- a/docs/consent_tracking.md
+++ b/docs/consent_tracking.md
@@ -152,7 +152,7 @@ version of the policy. To do so:
 
  * ensure that the consent resource is configured, as in the previous section
 
- * ensure that server notices are configured, as in [server_notices.md](server_notices.md).
+ * ensure that server notices are configured, as in [the server notice documentation](server_notices.md).
 
  * Add `server_notice_content` under `user_consent` in `homeserver.yaml`. For
    example:
diff --git a/docs/delegate.md b/docs/delegate.md
index 208ddb6277..05cb635047 100644
--- a/docs/delegate.md
+++ b/docs/delegate.md
@@ -74,7 +74,7 @@ We no longer actively recommend against using a reverse proxy. Many admins will
 find it easier to direct federation traffic to a reverse proxy and manage their
 own TLS certificates, and this is a supported configuration.
 
-See [reverse_proxy.md](reverse_proxy.md) for information on setting up a
+See [the reverse proxy documentation](reverse_proxy.md) for information on setting up a
 reverse proxy.
 
 ### Do I still need to give my TLS certificates to Synapse if I am using a reverse proxy?
diff --git a/docs/federate.md b/docs/federate.md
index 89c2b19638..5107f995be 100644
--- a/docs/federate.md
+++ b/docs/federate.md
@@ -14,7 +14,7 @@ you set the `server_name` to match your machine's public DNS hostname.
 
 For this default configuration to work, you will need to listen for TLS
 connections on port 8448. The preferred way to do that is by using a
-reverse proxy: see [reverse_proxy.md](reverse_proxy.md) for instructions
+reverse proxy: see [the reverse proxy documentation](reverse_proxy.md) for instructions
 on how to correctly set one up.
 
 In some cases you might not want to run Synapse on the machine that has
@@ -23,7 +23,7 @@ traffic to use a different port than 8448. For example, you might want to
 have your user names look like `@user:example.com`, but you want to run
 Synapse on `synapse.example.com` on port 443. This can be done using
 delegation, which allows an admin to control where federation traffic should
-be sent. See [delegate.md](delegate.md) for instructions on how to set this up.
+be sent. See [the delegation documentation](delegate.md) for instructions on how to set this up.
 
 Once federation has been configured, you should be able to join a room over
 federation. A good place to start is `#synapse:matrix.org` - a room for
@@ -44,8 +44,8 @@ a complicated dance which requires connections in both directions).
 
 Another common problem is that people on other servers can't join rooms that
 you invite them to. This can be caused by an incorrectly-configured reverse
-proxy: see [reverse_proxy.md](reverse_proxy.md) for instructions on how to correctly
-configure a reverse proxy.
+proxy: see [the reverse proxy documentation](reverse_proxy.md) for instructions on how
+to correctly configure a reverse proxy.
 
 ### Known issues
 
diff --git a/docs/log_contexts.md b/docs/log_contexts.md
index fe30ca2791..d49dce8830 100644
--- a/docs/log_contexts.md
+++ b/docs/log_contexts.md
@@ -14,12 +14,16 @@ The `synapse.logging.context` module provides a facilities for managing
 the current log context (as well as providing the `LoggingContextFilter`
 class).
 
-Deferreds make the whole thing complicated, so this document describes
+Asynchronous functions make the whole thing complicated, so this document describes
 how it all works, and how to write code which follows the rules.
 
-##Logcontexts without Deferreds
+In this document, "awaitable" refers to any object which can be `await`ed. In the context of
+Synapse, that normally means either a coroutine or a Twisted 
+[`Deferred`](https://twistedmatrix.com/documents/current/api/twisted.internet.defer.Deferred.html).
 
-In the absence of any Deferred voodoo, things are simple enough. As with
+## Logcontexts without asynchronous code
+
+In the absence of any asynchronous voodoo, things are simple enough. As with
 any code of this nature, the rule is that our function should leave
 things as it found them:
 
@@ -55,126 +59,109 @@ def do_request_handling():
     logger.debug("phew")
 ```
 
-## Using logcontexts with Deferreds
+## Using logcontexts with awaitables
 
-Deferreds --- and in particular, `defer.inlineCallbacks` --- break the
-linear flow of code so that there is no longer a single entry point
-where we should set the logcontext and a single exit point where we
-should remove it.
+Awaitables break the linear flow of code so that there is no longer a single entry point
+where we should set the logcontext and a single exit point where we should remove it.
 
 Consider the example above, where `do_request_handling` needs to do some
-blocking operation, and returns a deferred:
+blocking operation, and returns an awaitable:
 
 ```python
-@defer.inlineCallbacks
-def handle_request(request_id):
+async def handle_request(request_id):
     with context.LoggingContext() as request_context:
         request_context.request = request_id
-        yield do_request_handling()
+        await do_request_handling()
         logger.debug("finished")
 ```
 
 In the above flow:
 
 -   The logcontext is set
--   `do_request_handling` is called, and returns a deferred
--   `handle_request` yields the deferred
--   The `inlineCallbacks` wrapper of `handle_request` returns a deferred
+-   `do_request_handling` is called, and returns an awaitable
+-   `handle_request` awaits the awaitable
+-   Execution of `handle_request` is suspended
 
 So we have stopped processing the request (and will probably go on to
 start processing the next), without clearing the logcontext.
 
 To circumvent this problem, synapse code assumes that, wherever you have
-a deferred, you will want to yield on it. To that end, whereever
-functions return a deferred, we adopt the following conventions:
+an awaitable, you will want to `await` it. To that end, whereever
+functions return awaitables, we adopt the following conventions:
 
-**Rules for functions returning deferreds:**
+**Rules for functions returning awaitables:**
 
-> -   If the deferred is already complete, the function returns with the
+> -   If the awaitable is already complete, the function returns with the
 >     same logcontext it started with.
-> -   If the deferred is incomplete, the function clears the logcontext
->     before returning; when the deferred completes, it restores the
+> -   If the awaitable is incomplete, the function clears the logcontext
+>     before returning; when the awaitable completes, it restores the
 >     logcontext before running any callbacks.
 
 That sounds complicated, but actually it means a lot of code (including
 the example above) "just works". There are two cases:
 
--   If `do_request_handling` returns a completed deferred, then the
+-   If `do_request_handling` returns a completed awaitable, then the
     logcontext will still be in place. In this case, execution will
-    continue immediately after the `yield`; the "finished" line will
+    continue immediately after the `await`; the "finished" line will
     be logged against the right context, and the `with` block restores
     the original context before we return to the caller.
--   If the returned deferred is incomplete, `do_request_handling` clears
+-   If the returned awaitable is incomplete, `do_request_handling` clears
     the logcontext before returning. The logcontext is therefore clear
-    when `handle_request` yields the deferred. At that point, the
-    `inlineCallbacks` wrapper adds a callback to the deferred, and
-    returns another (incomplete) deferred to the caller, and it is safe
-    to begin processing the next request.
-
-    Once `do_request_handling`'s deferred completes, it will reinstate
-    the logcontext, before running the callback added by the
-    `inlineCallbacks` wrapper. That callback runs the second half of
-    `handle_request`, so again the "finished" line will be logged
-    against the right context, and the `with` block restores the
-    original context.
+    when `handle_request` `await`s the awaitable.
+
+    Once `do_request_handling`'s awaitable completes, it will reinstate
+    the logcontext, before running the second half of `handle_request`,
+    so again the "finished" line will be logged against the right context,
+    and the `with` block restores the original context.
 
 As an aside, it's worth noting that `handle_request` follows our rules
--though that only matters if the caller has its own logcontext which it
+- though that only matters if the caller has its own logcontext which it
 cares about.
 
 The following sections describe pitfalls and helpful patterns when
 implementing these rules.
 
-Always yield your deferreds
----------------------------
+Always await your awaitables
+----------------------------
 
-Whenever you get a deferred back from a function, you should `yield` on
-it as soon as possible. (Returning it directly to your caller is ok too,
-if you're not doing `inlineCallbacks`.) Do not pass go; do not do any
-logging; do not call any other functions.
+Whenever you get an awaitable back from a function, you should `await` on
+it as soon as possible. Do not pass go; do not do any logging; do not
+call any other functions.
 
 ```python
-@defer.inlineCallbacks
-def fun():
+async def fun():
     logger.debug("starting")
-    yield do_some_stuff()       # just like this
+    await do_some_stuff()       # just like this
 
-    d = more_stuff()
-    result = yield d            # also fine, of course
+    coro = more_stuff()
+    result = await coro         # also fine, of course
 
     return result
-
-def nonInlineCallbacksFun():
-    logger.debug("just a wrapper really")
-    return do_some_stuff()      # this is ok too - the caller will yield on
-                                # it anyway.
 ```
 
 Provided this pattern is followed all the way back up to the callchain
 to where the logcontext was set, this will make things work out ok:
 provided `do_some_stuff` and `more_stuff` follow the rules above, then
-so will `fun` (as wrapped by `inlineCallbacks`) and
-`nonInlineCallbacksFun`.
+so will `fun`.
 
-It's all too easy to forget to `yield`: for instance if we forgot that
-`do_some_stuff` returned a deferred, we might plough on regardless. This
+It's all too easy to forget to `await`: for instance if we forgot that
+`do_some_stuff` returned an awaitable, we might plough on regardless. This
 leads to a mess; it will probably work itself out eventually, but not
 before a load of stuff has been logged against the wrong context.
 (Normally, other things will break, more obviously, if you forget to
-`yield`, so this tends not to be a major problem in practice.)
+`await`, so this tends not to be a major problem in practice.)
 
 Of course sometimes you need to do something a bit fancier with your
-Deferreds - not all code follows the linear A-then-B-then-C pattern.
+awaitable - not all code follows the linear A-then-B-then-C pattern.
 Notes on implementing more complex patterns are in later sections.
 
-## Where you create a new Deferred, make it follow the rules
+## Where you create a new awaitable, make it follow the rules
 
-Most of the time, a Deferred comes from another synapse function.
-Sometimes, though, we need to make up a new Deferred, or we get a
-Deferred back from external code. We need to make it follow our rules.
+Most of the time, an awaitable comes from another synapse function.
+Sometimes, though, we need to make up a new awaitable, or we get an awaitable
+back from external code. We need to make it follow our rules.
 
-The easy way to do it is with a combination of `defer.inlineCallbacks`,
-and `context.PreserveLoggingContext`. Suppose we want to implement
+The easy way to do it is by using `context.make_deferred_yieldable`. Suppose we want to implement
 `sleep`, which returns a deferred which will run its callbacks after a
 given number of seconds. That might look like:
 
@@ -186,25 +173,12 @@ def get_sleep_deferred(seconds):
     return d
 ```
 
-That doesn't follow the rules, but we can fix it by wrapping it with
-`PreserveLoggingContext` and `yield` ing on it:
+That doesn't follow the rules, but we can fix it by calling it through
+`context.make_deferred_yieldable`:
 
 ```python
-@defer.inlineCallbacks
-def sleep(seconds):
-    with PreserveLoggingContext():
-        yield get_sleep_deferred(seconds)
-```
-
-This technique works equally for external functions which return
-deferreds, or deferreds we have made ourselves.
-
-You can also use `context.make_deferred_yieldable`, which just does the
-boilerplate for you, so the above could be written:
-
-```python
-def sleep(seconds):
-    return context.make_deferred_yieldable(get_sleep_deferred(seconds))
+async def sleep(seconds):
+    return await context.make_deferred_yieldable(get_sleep_deferred(seconds))
 ```
 
 ## Fire-and-forget
@@ -213,20 +187,18 @@ Sometimes you want to fire off a chain of execution, but not wait for
 its result. That might look a bit like this:
 
 ```python
-@defer.inlineCallbacks
-def do_request_handling():
-    yield foreground_operation()
+async def do_request_handling():
+    await foreground_operation()
 
     # *don't* do this
     background_operation()
 
     logger.debug("Request handling complete")
 
-@defer.inlineCallbacks
-def background_operation():
-    yield first_background_step()
+async def background_operation():
+    await first_background_step()
     logger.debug("Completed first step")
-    yield second_background_step()
+    await second_background_step()
     logger.debug("Completed second step")
 ```
 
@@ -235,13 +207,13 @@ The above code does a couple of steps in the background after
 against the `request_context` logcontext, which may or may not be
 desirable. There are two big problems with the above, however. The first
 problem is that, if `background_operation` returns an incomplete
-Deferred, it will expect its caller to `yield` immediately, so will have
+awaitable, it will expect its caller to `await` immediately, so will have
 cleared the logcontext. In this example, that means that 'Request
 handling complete' will be logged without any context.
 
 The second problem, which is potentially even worse, is that when the
-Deferred returned by `background_operation` completes, it will restore
-the original logcontext. There is nothing waiting on that Deferred, so
+awaitable returned by `background_operation` completes, it will restore
+the original logcontext. There is nothing waiting on that awaitable, so
 the logcontext will leak into the reactor and possibly get attached to
 some arbitrary future operation.
 
@@ -254,9 +226,8 @@ deferred completes will be the empty logcontext), and will restore the
 current logcontext before continuing the foreground process:
 
 ```python
-@defer.inlineCallbacks
-def do_request_handling():
-    yield foreground_operation()
+async def do_request_handling():
+    await foreground_operation()
 
     # start background_operation off in the empty logcontext, to
     # avoid leaking the current context into the reactor.
@@ -274,16 +245,15 @@ Obviously that option means that the operations done in
 
 The second option is to use `context.run_in_background`, which wraps a
 function so that it doesn't reset the logcontext even when it returns
-an incomplete deferred, and adds a callback to the returned deferred to
+an incomplete awaitable, and adds a callback to the returned awaitable to
 reset the logcontext. In other words, it turns a function that follows
-the Synapse rules about logcontexts and Deferreds into one which behaves
+the Synapse rules about logcontexts and awaitables into one which behaves
 more like an external function --- the opposite operation to that
 described in the previous section. It can be used like this:
 
 ```python
-@defer.inlineCallbacks
-def do_request_handling():
-    yield foreground_operation()
+async def do_request_handling():
+    await foreground_operation()
 
     context.run_in_background(background_operation)
 
@@ -294,152 +264,53 @@ def do_request_handling():
 ## Passing synapse deferreds into third-party functions
 
 A typical example of this is where we want to collect together two or
-more deferred via `defer.gatherResults`:
+more awaitables via `defer.gatherResults`:
 
 ```python
-d1 = operation1()
-d2 = operation2()
-d3 = defer.gatherResults([d1, d2])
+a1 = operation1()
+a2 = operation2()
+a3 = defer.gatherResults([a1, a2])
 ```
 
 This is really a variation of the fire-and-forget problem above, in that
-we are firing off `d1` and `d2` without yielding on them. The difference
+we are firing off `a1` and `a2` without awaiting on them. The difference
 is that we now have third-party code attached to their callbacks. Anyway
 either technique given in the [Fire-and-forget](#fire-and-forget)
 section will work.
 
-Of course, the new Deferred returned by `gatherResults` needs to be
+Of course, the new awaitable returned by `gather` needs to be
 wrapped in order to make it follow the logcontext rules before we can
-yield it, as described in [Where you create a new Deferred, make it
+yield it, as described in [Where you create a new awaitable, make it
 follow the
-rules](#where-you-create-a-new-deferred-make-it-follow-the-rules).
+rules](#where-you-create-a-new-awaitable-make-it-follow-the-rules).
 
 So, option one: reset the logcontext before starting the operations to
 be gathered:
 
 ```python
-@defer.inlineCallbacks
-def do_request_handling():
+async def do_request_handling():
     with PreserveLoggingContext():
-        d1 = operation1()
-        d2 = operation2()
-        result = yield defer.gatherResults([d1, d2])
+        a1 = operation1()
+        a2 = operation2()
+        result = await defer.gatherResults([a1, a2])
 ```
 
 In this case particularly, though, option two, of using
-`context.preserve_fn` almost certainly makes more sense, so that
+`context.run_in_background` almost certainly makes more sense, so that
 `operation1` and `operation2` are both logged against the original
 logcontext. This looks like:
 
 ```python
-@defer.inlineCallbacks
-def do_request_handling():
-    d1 = context.preserve_fn(operation1)()
-    d2 = context.preserve_fn(operation2)()
+async def do_request_handling():
+    a1 = context.run_in_background(operation1)
+    a2 = context.run_in_background(operation2)
 
-    with PreserveLoggingContext():
-        result = yield defer.gatherResults([d1, d2])
+    result = await make_deferred_yieldable(defer.gatherResults([a1, a2]))
 ```
 
-## Was all this really necessary?
-
-The conventions used work fine for a linear flow where everything
-happens in series via `defer.inlineCallbacks` and `yield`, but are
-certainly tricky to follow for any more exotic flows. It's hard not to
-wonder if we could have done something else.
-
-We're not going to rewrite Synapse now, so the following is entirely of
-academic interest, but I'd like to record some thoughts on an
-alternative approach.
-
-I briefly prototyped some code following an alternative set of rules. I
-think it would work, but I certainly didn't get as far as thinking how
-it would interact with concepts as complicated as the cache descriptors.
-
-My alternative rules were:
-
--   functions always preserve the logcontext of their caller, whether or
-    not they are returning a Deferred.
--   Deferreds returned by synapse functions run their callbacks in the
-    same context as the function was orignally called in.
-
-The main point of this scheme is that everywhere that sets the
-logcontext is responsible for clearing it before returning control to
-the reactor.
-
-So, for example, if you were the function which started a
-`with LoggingContext` block, you wouldn't `yield` within it --- instead
-you'd start off the background process, and then leave the `with` block
-to wait for it:
-
-```python
-def handle_request(request_id):
-    with context.LoggingContext() as request_context:
-        request_context.request = request_id
-        d = do_request_handling()
-
-    def cb(r):
-        logger.debug("finished")
-
-    d.addCallback(cb)
-    return d
-```
-
-(in general, mixing `with LoggingContext` blocks and
-`defer.inlineCallbacks` in the same function leads to slighly
-counter-intuitive code, under this scheme).
-
-Because we leave the original `with` block as soon as the Deferred is
-returned (as opposed to waiting for it to be resolved, as we do today),
-the logcontext is cleared before control passes back to the reactor; so
-if there is some code within `do_request_handling` which needs to wait
-for a Deferred to complete, there is no need for it to worry about
-clearing the logcontext before doing so:
-
-```python
-def handle_request():
-    r = do_some_stuff()
-    r.addCallback(do_some_more_stuff)
-    return r
-```
-
---- and provided `do_some_stuff` follows the rules of returning a
-Deferred which runs its callbacks in the original logcontext, all is
-happy.
-
-The business of a Deferred which runs its callbacks in the original
-logcontext isn't hard to achieve --- we have it today, in the shape of
-`context._PreservingContextDeferred`:
-
-```python
-def do_some_stuff():
-    deferred = do_some_io()
-    pcd = _PreservingContextDeferred(LoggingContext.current_context())
-    deferred.chainDeferred(pcd)
-    return pcd
-```
-
-It turns out that, thanks to the way that Deferreds chain together, we
-automatically get the property of a context-preserving deferred with
-`defer.inlineCallbacks`, provided the final Defered the function
-`yields` on has that property. So we can just write:
-
-```python
-@defer.inlineCallbacks
-def handle_request():
-    yield do_some_stuff()
-    yield do_some_more_stuff()
-```
-
-To conclude: I think this scheme would have worked equally well, with
-less danger of messing it up, and probably made some more esoteric code
-easier to write. But again --- changing the conventions of the entire
-Synapse codebase is not a sensible option for the marginal improvement
-offered.
-
-## A note on garbage-collection of Deferred chains
+## A note on garbage-collection of awaitable chains
 
-It turns out that our logcontext rules do not play nicely with Deferred
+It turns out that our logcontext rules do not play nicely with awaitable
 chains which get orphaned and garbage-collected.
 
 Imagine we have some code that looks like this:
@@ -451,13 +322,12 @@ def on_something_interesting():
     for d in listener_queue:
         d.callback("foo")
 
-@defer.inlineCallbacks
-def await_something_interesting():
-    new_deferred = defer.Deferred()
-    listener_queue.append(new_deferred)
+async def await_something_interesting():
+    new_awaitable = defer.Deferred()
+    listener_queue.append(new_awaitable)
 
     with PreserveLoggingContext():
-        yield new_deferred
+        await new_awaitable
 ```
 
 Obviously, the idea here is that we have a bunch of things which are
@@ -476,18 +346,19 @@ def reset_listener_queue():
     listener_queue.clear()
 ```
 
-So, both ends of the deferred chain have now dropped their references,
-and the deferred chain is now orphaned, and will be garbage-collected at
-some point. Note that `await_something_interesting` is a generator
-function, and when Python garbage-collects generator functions, it gives
-them a chance to clean up by making the `yield` raise a `GeneratorExit`
+So, both ends of the awaitable chain have now dropped their references,
+and the awaitable chain is now orphaned, and will be garbage-collected at
+some point. Note that `await_something_interesting` is a coroutine, 
+which Python implements as a generator function.  When Python
+garbage-collects generator functions, it gives them a chance to 
+clean up by making the `async` (or `yield`) raise a `GeneratorExit`
 exception. In our case, that means that the `__exit__` handler of
 `PreserveLoggingContext` will carefully restore the request context, but
 there is now nothing waiting for its return, so the request context is
 never cleared.
 
-To reiterate, this problem only arises when *both* ends of a deferred
-chain are dropped. Dropping the the reference to a deferred you're
-supposed to be calling is probably bad practice, so this doesn't
+To reiterate, this problem only arises when *both* ends of a awaitable
+chain are dropped. Dropping the the reference to an awaitable you're
+supposed to be awaiting is bad practice, so this doesn't
 actually happen too much. Unfortunately, when it does happen, it will
 lead to leaked logcontexts which are incredibly hard to track down.
diff --git a/docs/replication.md b/docs/replication.md
index ed88233157..e82df0de8a 100644
--- a/docs/replication.md
+++ b/docs/replication.md
@@ -28,7 +28,7 @@ minimal.
 
 ### The Replication Protocol
 
-See [tcp_replication.md](tcp_replication.md)
+See [the TCP replication documentation](tcp_replication.md).
 
 ### The Slaved DataStore
 
diff --git a/docs/reverse_proxy.md b/docs/reverse_proxy.md
index 01db466f96..76bb45aff2 100644
--- a/docs/reverse_proxy.md
+++ b/docs/reverse_proxy.md
@@ -21,7 +21,7 @@ port 8448. Where these are different, we refer to the 'client port' and the
 'federation port'. See [the Matrix
 specification](https://matrix.org/docs/spec/server_server/latest#resolving-server-names)
 for more details of the algorithm used for federation connections, and
-[delegate.md](delegate.md) for instructions on setting up delegation.
+[Delegation](delegate.md) for instructions on setting up delegation.
 
 **NOTE**: Your reverse proxy must not `canonicalise` or `normalise`
 the requested URI in any way (for example, by decoding `%xx` escapes).
@@ -98,6 +98,33 @@ example.com:8448 {
   reverse_proxy http://localhost:8008
 }
 ```
+[Delegation](delegate.md) example:
+```
+(matrix-well-known-header) {
+    # Headers
+    header Access-Control-Allow-Origin "*"
+    header Access-Control-Allow-Methods "GET, POST, PUT, DELETE, OPTIONS"
+    header Access-Control-Allow-Headers "Origin, X-Requested-With, Content-Type, Accept, Authorization"
+    header Content-Type "application/json"
+}
+
+example.com {
+    handle /.well-known/matrix/server {
+        import matrix-well-known-header
+        respond `{"m.server":"matrix.example.com:443"}`
+    }
+
+    handle /.well-known/matrix/client {
+        import matrix-well-known-header
+        respond `{"m.homeserver":{"base_url":"https://matrix.example.com"},"m.identity_server":{"base_url":"https://identity.example.com"}}`
+    }
+}
+
+matrix.example.com {
+    reverse_proxy /_matrix/* http://localhost:8008
+    reverse_proxy /_synapse/client/* http://localhost:8008
+}
+```
 
 ### Apache
 
diff --git a/docs/room_and_user_statistics.md b/docs/room_and_user_statistics.md
index e1facb38d4..cc38c890bb 100644
--- a/docs/room_and_user_statistics.md
+++ b/docs/room_and_user_statistics.md
@@ -1,9 +1,9 @@
 Room and User Statistics
 ========================
 
-Synapse maintains room and user statistics (as well as a cache of room state),
-in various tables. These can be used for administrative purposes but are also
-used when generating the public room directory.
+Synapse maintains room and user statistics in various tables. These can be used
+for administrative purposes but are also used when generating the public room
+directory.
 
 
 # Synapse Developer Documentation
@@ -15,48 +15,8 @@ used when generating the public room directory.
 * **subject**: Something we are tracking stats about – currently a room or user.
 * **current row**: An entry for a subject in the appropriate current statistics
     table. Each subject can have only one.
-* **historical row**: An entry for a subject in the appropriate historical
-    statistics table. Each subject can have any number of these.
 
 ### Overview
 
-Stats are maintained as time series. There are two kinds of column:
-
-* absolute columns – where the value is correct for the time given by `end_ts`
-    in the stats row. (Imagine a line graph for these values)
-    * They can also be thought of as 'gauges' in Prometheus, if you are familiar.
-* per-slice columns – where the value corresponds to how many of the occurrences
-    occurred within the time slice given by `(end_ts − bucket_size)
end_ts`
-    or `start_ts
end_ts`. (Imagine a histogram for these values)
-
-Stats are maintained in two tables (for each type): current and historical.
-
-Current stats correspond to the present values. Each subject can only have one
-entry.
-
-Historical stats correspond to values in the past. Subjects may have multiple
-entries.
-
-## Concepts around the management of stats
-
-### Current rows
-
-Current rows contain the most up-to-date statistics for a room.
-They only contain absolute columns
-
-### Historical rows
-
-Historical rows can always be considered to be valid for the time slice and
-end time specified.
-
-* historical rows will not exist for every time slice – they will be omitted
-    if there were no changes. In this case, the following assumptions can be
-    made to interpolate/recreate missing rows:
-    - absolute fields have the same values as in the preceding row
-    - per-slice fields are zero (`0`)
-* historical rows will not be retained forever – rows older than a configurable
-    time will be purged.
-
-#### Purge
-
-The purging of historical rows is not yet implemented.
+Stats correspond to the present values. Current rows contain the most up-to-date
+statistics for a room. Each subject can only have one entry.
diff --git a/docs/sample_config.yaml b/docs/sample_config.yaml
index 054770f71f..a45732a246 100644
--- a/docs/sample_config.yaml
+++ b/docs/sample_config.yaml
@@ -2653,11 +2653,6 @@ stats:
   #
   #enabled: false
 
-  # The size of each timeslice in the room_stats_historical and
-  # user_stats_historical tables, as a time period. Defaults to "1d".
-  #
-  #bucket_size: 1h
-
 
 # Server Notices room configuration
 #
diff --git a/docs/server_notices.md b/docs/server_notices.md
index 950a6608e9..339d10a0ab 100644
--- a/docs/server_notices.md
+++ b/docs/server_notices.md
@@ -3,8 +3,8 @@
 'Server Notices' are a new feature introduced in Synapse 0.30. They provide a
 channel whereby server administrators can send messages to users on the server.
 
-They are used as part of communication of the server polices(see
-[consent_tracking.md](consent_tracking.md)), however the intention is that
+They are used as part of communication of the server polices (see
+[Consent Tracking](consent_tracking.md)), however the intention is that
 they may also find a use for features such as "Message of the day".
 
 This is a feature specific to Synapse, but it uses standard Matrix
diff --git a/docs/setup/installation.md b/docs/setup/installation.md
index d041d08333..8540a7b0c1 100644
--- a/docs/setup/installation.md
+++ b/docs/setup/installation.md
@@ -166,13 +166,16 @@ sudo dnf groupinstall "Development Tools"
 
 Installing prerequisites on macOS:
 
+You may need to install the latest Xcode developer tools:
 ```sh
 xcode-select --install
-sudo easy_install pip
-sudo pip install virtualenv
-brew install pkg-config libffi
 ```
 
+On ARM-based Macs you may need to explicitly install libjpeg which is a pillow dependency. You can use Homebrew (https://brew.sh):
+```sh
+ brew install jpeg
+ ```
+
 On macOS Catalina (10.15) you may need to explicitly install OpenSSL
 via brew and inform `pip` about it so that `psycopg2` builds:
 
@@ -268,9 +271,8 @@ For more details, see
 
 ##### Matrix.org packages
 
-Matrix.org provides Debian/Ubuntu packages of the latest stable version of
-Synapse via <https://packages.matrix.org/debian/>. They are available for Debian
-9 (Stretch), Ubuntu 16.04 (Xenial), and later. To use them:
+Matrix.org provides Debian/Ubuntu packages of Synapse via
+<https://packages.matrix.org/debian/>.  To install the latest release:
 
 ```sh
 sudo apt install -y lsb-release wget apt-transport-https
@@ -281,12 +283,16 @@ sudo apt update
 sudo apt install matrix-synapse-py3
 ```
 
-**Note**: if you followed a previous version of these instructions which
-recommended using `apt-key add` to add an old key from
-`https://matrix.org/packages/debian/`, you should note that this key has been
-revoked. You should remove the old key with `sudo apt-key remove
-C35EB17E1EAE708E6603A9B3AD0592FE47F0DF61`, and follow the above instructions to
-update your configuration.
+Packages are also published for release candidates. To enable the prerelease
+channel, add `prerelease` to the `sources.list` line. For example:
+
+```sh
+sudo wget -O /usr/share/keyrings/matrix-org-archive-keyring.gpg https://packages.matrix.org/debian/matrix-org-archive-keyring.gpg
+echo "deb [signed-by=/usr/share/keyrings/matrix-org-archive-keyring.gpg] https://packages.matrix.org/debian/ $(lsb_release -cs) main prerelease" |
+    sudo tee /etc/apt/sources.list.d/matrix-org.list
+sudo apt update
+sudo apt install matrix-synapse-py3
+```
 
 The fingerprint of the repository signing key (as shown by `gpg
 /usr/share/keyrings/matrix-org-archive-keyring.gpg`) is
@@ -409,7 +415,7 @@ instead. Advantages include:
 - allowing the DB to be run on separate hardware
 
 For information on how to install and use PostgreSQL in Synapse, please see
-[docs/postgres.md](../postgres.md)
+[Using Postgres](../postgres.md)
 
 SQLite is only acceptable for testing purposes. SQLite should not be used in
 a production server. Synapse will perform poorly when using
@@ -424,7 +430,7 @@ over HTTPS.
 
 The recommended way to do so is to set up a reverse proxy on port
 `8448`. You can find documentation on doing so in
-[docs/reverse_proxy.md](../reverse_proxy.md).
+[the reverse proxy documentation](../reverse_proxy.md).
 
 Alternatively, you can configure Synapse to expose an HTTPS port. To do
 so, you will need to edit `homeserver.yaml`, as follows:
@@ -451,7 +457,7 @@ so, you will need to edit `homeserver.yaml`, as follows:
   `cert.pem`).
 
 For a more detailed guide to configuring your server for federation, see
-[federate.md](../federate.md).
+[Federation](../federate.md).
 
 ### Client Well-Known URI
 
@@ -563,9 +569,7 @@ on your server even if `enable_registration` is `false`.
 ### Setting up a TURN server
 
 For reliable VoIP calls to be routed via this homeserver, you MUST configure
-a TURN server. See
-[docs/turn-howto.md](../turn-howto.md)
-for details.
+a TURN server. See [TURN setup](../turn-howto.md) for details.
 
 ### URL previews
 
diff --git a/docs/systemd-with-workers/README.md b/docs/systemd-with-workers/README.md
index a7de2de88a..b160d93528 100644
--- a/docs/systemd-with-workers/README.md
+++ b/docs/systemd-with-workers/README.md
@@ -14,10 +14,12 @@ contains an example configuration for the `federation_reader` worker.
 
 ## Synapse configuration files
 
-See [workers.md](../workers.md) for information on how to set up the
-configuration files and reverse-proxy correctly. You can find an example worker
-config in the [workers](https://github.com/matrix-org/synapse/tree/develop/docs/systemd-with-workers/workers/)
-folder.
+See [the worker documentation](../workers.md) for information on how to set up the
+configuration files and reverse-proxy correctly.
+Below is a sample `federation_reader` worker configuration file.
+```yaml
+{{#include workers/federation_reader.yaml}}
+```
 
 Systemd manages daemonization itself, so ensure that none of the configuration
 files set either `daemonize` or `worker_daemonize`.
@@ -72,12 +74,12 @@ systemctl restart matrix-synapse.target
 
 **Optional:** If further hardening is desired, the file
 `override-hardened.conf` may be copied from
-`contrib/systemd/override-hardened.conf` in this repository to the location
+[contrib/systemd/override-hardened.conf](https://github.com/matrix-org/synapse/tree/develop/contrib/systemd/)
+in this repository to the location
 `/etc/systemd/system/matrix-synapse.service.d/override-hardened.conf` (the
 directory may have to be created). It enables certain sandboxing features in
 systemd to further secure the synapse service. You may read the comments to
-understand what the override file is doing. The same file will need to be copied
-to
+understand what the override file is doing. The same file will need to be copied to
 `/etc/systemd/system/matrix-synapse-worker@.service.d/override-hardened-worker.conf`
 (this directory may also have to be created) in order to apply the same
 hardening options to any worker processes.
diff --git a/docs/usage/configuration/logging_sample_config.md b/docs/usage/configuration/logging_sample_config.md
index 4c4bc6fc16..a673d487b8 100644
--- a/docs/usage/configuration/logging_sample_config.md
+++ b/docs/usage/configuration/logging_sample_config.md
@@ -11,4 +11,4 @@ a fresh config using Synapse by following the instructions in
 
 ```yaml
 {{#include ../../sample_log_config.yaml}}
-``__`
\ No newline at end of file
+```
\ No newline at end of file
diff --git a/docs/workers.md b/docs/workers.md
index 797758ee84..d8672324c3 100644
--- a/docs/workers.md
+++ b/docs/workers.md
@@ -73,7 +73,7 @@ https://hub.docker.com/r/matrixdotorg/synapse/.
 To make effective use of the workers, you will need to configure an HTTP
 reverse-proxy such as nginx or haproxy, which will direct incoming requests to
 the correct worker, or to the main synapse instance. See
-[reverse_proxy.md](reverse_proxy.md) for information on setting up a reverse
+[the reverse proxy documentation](reverse_proxy.md) for information on setting up a reverse
 proxy.
 
 When using workers, each worker process has its own configuration file which
@@ -170,8 +170,8 @@ Finally, you need to start your worker processes. This can be done with either
 `synctl` or your distribution's preferred service manager such as `systemd`. We
 recommend the use of `systemd` where available: for information on setting up
 `systemd` to start synapse workers, see
-[systemd-with-workers](systemd-with-workers). To use `synctl`, see
-[synctl_workers.md](synctl_workers.md).
+[Systemd with Workers](systemd-with-workers). To use `synctl`, see
+[Using synctl with Workers](synctl_workers.md).
 
 
 ## Available worker applications
diff --git a/mypy.ini b/mypy.ini
index 72ce932d73..8717ae738e 100644
--- a/mypy.ini
+++ b/mypy.ini
@@ -83,6 +83,7 @@ files =
   synapse/util/stringutils.py,
   synapse/visibility.py,
   tests/replication,
+  tests/test_event_auth.py,
   tests/test_utils,
   tests/handlers/test_password_providers.py,
   tests/rest/client/v1/test_login.py,
diff --git a/synapse/api/auth.py b/synapse/api/auth.py
index 307f5f9a94..8916e6fa2f 100644
--- a/synapse/api/auth.py
+++ b/synapse/api/auth.py
@@ -63,9 +63,9 @@ class Auth:
         self.store = hs.get_datastore()
         self.state = hs.get_state_handler()
 
-        self.token_cache = LruCache(
+        self.token_cache: LruCache[str, Tuple[str, bool]] = LruCache(
             10000, "token_cache"
-        )  # type: LruCache[str, Tuple[str, bool]]
+        )
 
         self._auth_blocking = AuthBlocking(self.hs)
 
@@ -240,6 +240,37 @@ class Auth:
         except KeyError:
             raise MissingClientTokenError()
 
+    async def validate_appservice_can_control_user_id(
+        self, app_service: ApplicationService, user_id: str
+    ):
+        """Validates that the app service is allowed to control
+        the given user.
+
+        Args:
+            app_service: The app service that controls the user
+            user_id: The author MXID that the app service is controlling
+
+        Raises:
+            AuthError: If the application service is not allowed to control the user
+                (user namespace regex does not match, wrong homeserver, etc)
+                or if the user has not been registered yet.
+        """
+
+        # It's ok if the app service is trying to use the sender from their registration
+        if app_service.sender == user_id:
+            pass
+        # Check to make sure the app service is allowed to control the user
+        elif not app_service.is_interested_in_user(user_id):
+            raise AuthError(
+                403,
+                "Application service cannot masquerade as this user (%s)." % user_id,
+            )
+        # Check to make sure the user is already registered on the homeserver
+        elif not (await self.store.get_user_by_id(user_id)):
+            raise AuthError(
+                403, "Application service has not registered this user (%s)" % user_id
+            )
+
     async def _get_appservice_user_id(
         self, request: Request
     ) -> Tuple[Optional[str], Optional[ApplicationService]]:
@@ -261,13 +292,11 @@ class Auth:
             return app_service.sender, app_service
 
         user_id = request.args[b"user_id"][0].decode("utf8")
+        await self.validate_appservice_can_control_user_id(app_service, user_id)
+
         if app_service.sender == user_id:
             return app_service.sender, app_service
 
-        if not app_service.is_interested_in_user(user_id):
-            raise AuthError(403, "Application service cannot masquerade as this user.")
-        if not (await self.store.get_user_by_id(user_id)):
-            raise AuthError(403, "Application service has not registered this user")
         return user_id, app_service
 
     async def get_user_by_access_token(
diff --git a/synapse/api/errors.py b/synapse/api/errors.py
index 4cb8bbaf70..054ab14ab6 100644
--- a/synapse/api/errors.py
+++ b/synapse/api/errors.py
@@ -118,7 +118,7 @@ class RedirectException(CodeMessageException):
         super().__init__(code=http_code, msg=msg)
         self.location = location
 
-        self.cookies = []  # type: List[bytes]
+        self.cookies: List[bytes] = []
 
 
 class SynapseError(CodeMessageException):
@@ -160,7 +160,7 @@ class ProxiedRequestError(SynapseError):
     ):
         super().__init__(code, msg, errcode)
         if additional_fields is None:
-            self._additional_fields = {}  # type: Dict
+            self._additional_fields: Dict = {}
         else:
             self._additional_fields = dict(additional_fields)
 
diff --git a/synapse/api/filtering.py b/synapse/api/filtering.py
index ce49a0ad58..ad1ff6a9df 100644
--- a/synapse/api/filtering.py
+++ b/synapse/api/filtering.py
@@ -289,7 +289,7 @@ class Filter:
             room_id = None
             ev_type = "m.presence"
             contains_url = False
-            labels = []  # type: List[str]
+            labels: List[str] = []
         else:
             sender = event.get("sender", None)
             if not sender:
diff --git a/synapse/api/ratelimiting.py b/synapse/api/ratelimiting.py
index b9a10283f4..3e3d09bbd2 100644
--- a/synapse/api/ratelimiting.py
+++ b/synapse/api/ratelimiting.py
@@ -46,9 +46,7 @@ class Ratelimiter:
         #   * How many times an action has occurred since a point in time
         #   * The point in time
         #   * The rate_hz of this particular entry. This can vary per request
-        self.actions = (
-            OrderedDict()
-        )  # type: OrderedDict[Hashable, Tuple[float, int, float]]
+        self.actions: OrderedDict[Hashable, Tuple[float, int, float]] = OrderedDict()
 
     async def can_do_action(
         self,
diff --git a/synapse/api/room_versions.py b/synapse/api/room_versions.py
index f6c1c97b40..a20abc5a65 100644
--- a/synapse/api/room_versions.py
+++ b/synapse/api/room_versions.py
@@ -195,7 +195,7 @@ class RoomVersions:
     )
 
 
-KNOWN_ROOM_VERSIONS = {
+KNOWN_ROOM_VERSIONS: Dict[str, RoomVersion] = {
     v.identifier: v
     for v in (
         RoomVersions.V1,
@@ -209,4 +209,4 @@ KNOWN_ROOM_VERSIONS = {
         RoomVersions.V7,
     )
     # Note that we do not include MSC2043 here unless it is enabled in the config.
-}  # type: Dict[str, RoomVersion]
+}
diff --git a/synapse/app/generic_worker.py b/synapse/app/generic_worker.py
index 5b041fcaad..b43d858f59 100644
--- a/synapse/app/generic_worker.py
+++ b/synapse/app/generic_worker.py
@@ -270,7 +270,7 @@ class GenericWorkerServer(HomeServer):
             site_tag = port
 
         # We always include a health resource.
-        resources = {"/health": HealthResource()}  # type: Dict[str, IResource]
+        resources: Dict[str, IResource] = {"/health": HealthResource()}
 
         for res in listener_config.http_options.resources:
             for name in res.names:
diff --git a/synapse/appservice/api.py b/synapse/appservice/api.py
index 61152b2c46..935f24263c 100644
--- a/synapse/appservice/api.py
+++ b/synapse/appservice/api.py
@@ -88,9 +88,9 @@ class ApplicationServiceApi(SimpleHttpClient):
         super().__init__(hs)
         self.clock = hs.get_clock()
 
-        self.protocol_meta_cache = ResponseCache(
+        self.protocol_meta_cache: ResponseCache[Tuple[str, str]] = ResponseCache(
             hs.get_clock(), "as_protocol_meta", timeout_ms=HOUR_IN_MS
-        )  # type: ResponseCache[Tuple[str, str]]
+        )
 
     async def query_user(self, service, user_id):
         if service.url is None:
diff --git a/synapse/config/appservice.py b/synapse/config/appservice.py
index 746fc3cc02..a39d457c56 100644
--- a/synapse/config/appservice.py
+++ b/synapse/config/appservice.py
@@ -57,8 +57,8 @@ def load_appservices(hostname, config_files):
         return []
 
     # Dicts of value -> filename
-    seen_as_tokens = {}  # type: Dict[str, str]
-    seen_ids = {}  # type: Dict[str, str]
+    seen_as_tokens: Dict[str, str] = {}
+    seen_ids: Dict[str, str] = {}
 
     appservices = []
 
diff --git a/synapse/config/cache.py b/synapse/config/cache.py
index 7789b40323..8d5f38b5d9 100644
--- a/synapse/config/cache.py
+++ b/synapse/config/cache.py
@@ -25,7 +25,7 @@ from ._base import Config, ConfigError
 _CACHE_PREFIX = "SYNAPSE_CACHE_FACTOR"
 
 # Map from canonicalised cache name to cache.
-_CACHES = {}  # type: Dict[str, Callable[[float], None]]
+_CACHES: Dict[str, Callable[[float], None]] = {}
 
 # a lock on the contents of _CACHES
 _CACHES_LOCK = threading.Lock()
@@ -157,7 +157,7 @@ class CacheConfig(Config):
         self.event_cache_size = self.parse_size(
             config.get("event_cache_size", _DEFAULT_EVENT_CACHE_SIZE)
         )
-        self.cache_factors = {}  # type: Dict[str, float]
+        self.cache_factors: Dict[str, float] = {}
 
         cache_config = config.get("caches") or {}
         self.global_factor = cache_config.get(
diff --git a/synapse/config/emailconfig.py b/synapse/config/emailconfig.py
index 5564d7d097..bcecbfec03 100644
--- a/synapse/config/emailconfig.py
+++ b/synapse/config/emailconfig.py
@@ -134,9 +134,9 @@ class EmailConfig(Config):
 
                 # trusted_third_party_id_servers does not contain a scheme whereas
                 # account_threepid_delegate_email is expected to. Presume https
-                self.account_threepid_delegate_email = (
+                self.account_threepid_delegate_email: Optional[str] = (
                     "https://" + first_trusted_identity_server
-                )  # type: Optional[str]
+                )
                 self.using_identity_server_from_trusted_list = True
             else:
                 raise ConfigError(
diff --git a/synapse/config/experimental.py b/synapse/config/experimental.py
index 7fb1f7021f..e25ccba9ac 100644
--- a/synapse/config/experimental.py
+++ b/synapse/config/experimental.py
@@ -25,10 +25,10 @@ class ExperimentalConfig(Config):
         experimental = config.get("experimental_features") or {}
 
         # MSC2858 (multiple SSO identity providers)
-        self.msc2858_enabled = experimental.get("msc2858_enabled", False)  # type: bool
+        self.msc2858_enabled: bool = experimental.get("msc2858_enabled", False)
 
         # MSC3026 (busy presence state)
-        self.msc3026_enabled = experimental.get("msc3026_enabled", False)  # type: bool
+        self.msc3026_enabled: bool = experimental.get("msc3026_enabled", False)
 
         # MSC2716 (backfill existing history)
-        self.msc2716_enabled = experimental.get("msc2716_enabled", False)  # type: bool
+        self.msc2716_enabled: bool = experimental.get("msc2716_enabled", False)
diff --git a/synapse/config/federation.py b/synapse/config/federation.py
index cdd7a1ef05..7d64993e22 100644
--- a/synapse/config/federation.py
+++ b/synapse/config/federation.py
@@ -22,7 +22,7 @@ class FederationConfig(Config):
 
     def read_config(self, config, **kwargs):
         # FIXME: federation_domain_whitelist needs sytests
-        self.federation_domain_whitelist = None  # type: Optional[dict]
+        self.federation_domain_whitelist: Optional[dict] = None
         federation_domain_whitelist = config.get("federation_domain_whitelist", None)
 
         if federation_domain_whitelist is not None:
diff --git a/synapse/config/oidc.py b/synapse/config/oidc.py
index 942e2672a9..ba89d11cf0 100644
--- a/synapse/config/oidc.py
+++ b/synapse/config/oidc.py
@@ -460,7 +460,7 @@ def _parse_oidc_config_dict(
             ) from e
 
     client_secret_jwt_key_config = oidc_config.get("client_secret_jwt_key")
-    client_secret_jwt_key = None  # type: Optional[OidcProviderClientSecretJwtKey]
+    client_secret_jwt_key: Optional[OidcProviderClientSecretJwtKey] = None
     if client_secret_jwt_key_config is not None:
         keyfile = client_secret_jwt_key_config.get("key_file")
         if keyfile:
diff --git a/synapse/config/password_auth_providers.py b/synapse/config/password_auth_providers.py
index fd90b79772..0f5b2b3977 100644
--- a/synapse/config/password_auth_providers.py
+++ b/synapse/config/password_auth_providers.py
@@ -25,7 +25,7 @@ class PasswordAuthProviderConfig(Config):
     section = "authproviders"
 
     def read_config(self, config, **kwargs):
-        self.password_providers = []  # type: List[Any]
+        self.password_providers: List[Any] = []
         providers = []
 
         # We want to be backwards compatible with the old `ldap_config`
diff --git a/synapse/config/repository.py b/synapse/config/repository.py
index a7a82742ac..0dfb3a227a 100644
--- a/synapse/config/repository.py
+++ b/synapse/config/repository.py
@@ -62,7 +62,7 @@ def parse_thumbnail_requirements(thumbnail_sizes):
         Dictionary mapping from media type string to list of
         ThumbnailRequirement tuples.
     """
-    requirements = {}  # type: Dict[str, List]
+    requirements: Dict[str, List] = {}
     for size in thumbnail_sizes:
         width = size["width"]
         height = size["height"]
@@ -141,7 +141,7 @@ class ContentRepositoryConfig(Config):
         #
         # We don't create the storage providers here as not all workers need
         # them to be started.
-        self.media_storage_providers = []  # type: List[tuple]
+        self.media_storage_providers: List[tuple] = []
 
         for i, provider_config in enumerate(storage_providers):
             # We special case the module "file_system" so as not to need to
diff --git a/synapse/config/server.py b/synapse/config/server.py
index 6bff715230..b9e0c0b300 100644
--- a/synapse/config/server.py
+++ b/synapse/config/server.py
@@ -505,7 +505,7 @@ class ServerConfig(Config):
                 " greater than 'allowed_lifetime_max'"
             )
 
-        self.retention_purge_jobs = []  # type: List[Dict[str, Optional[int]]]
+        self.retention_purge_jobs: List[Dict[str, Optional[int]]] = []
         for purge_job_config in retention_config.get("purge_jobs", []):
             interval_config = purge_job_config.get("interval")
 
@@ -688,23 +688,21 @@ class ServerConfig(Config):
         # not included in the sample configuration file on purpose as it's a temporary
         # hack, so that some users can trial the new defaults without impacting every
         # user on the homeserver.
-        users_new_default_push_rules = (
+        users_new_default_push_rules: list = (
             config.get("users_new_default_push_rules") or []
-        )  # type: list
+        )
         if not isinstance(users_new_default_push_rules, list):
             raise ConfigError("'users_new_default_push_rules' must be a list")
 
         # Turn the list into a set to improve lookup speed.
-        self.users_new_default_push_rules = set(
-            users_new_default_push_rules
-        )  # type: set
+        self.users_new_default_push_rules: set = set(users_new_default_push_rules)
 
         # Whitelist of domain names that given next_link parameters must have
-        next_link_domain_whitelist = config.get(
+        next_link_domain_whitelist: Optional[List[str]] = config.get(
             "next_link_domain_whitelist"
-        )  # type: Optional[List[str]]
+        )
 
-        self.next_link_domain_whitelist = None  # type: Optional[Set[str]]
+        self.next_link_domain_whitelist: Optional[Set[str]] = None
         if next_link_domain_whitelist is not None:
             if not isinstance(next_link_domain_whitelist, list):
                 raise ConfigError("'next_link_domain_whitelist' must be a list")
diff --git a/synapse/config/spam_checker.py b/synapse/config/spam_checker.py
index cb7716c837..a233a9ce03 100644
--- a/synapse/config/spam_checker.py
+++ b/synapse/config/spam_checker.py
@@ -34,7 +34,7 @@ class SpamCheckerConfig(Config):
     section = "spamchecker"
 
     def read_config(self, config, **kwargs):
-        self.spam_checkers = []  # type: List[Tuple[Any, Dict]]
+        self.spam_checkers: List[Tuple[Any, Dict]] = []
 
         spam_checkers = config.get("spam_checker") or []
         if isinstance(spam_checkers, dict):
diff --git a/synapse/config/sso.py b/synapse/config/sso.py
index e4346e02aa..d0f04cf8e6 100644
--- a/synapse/config/sso.py
+++ b/synapse/config/sso.py
@@ -39,7 +39,7 @@ class SSOConfig(Config):
     section = "sso"
 
     def read_config(self, config, **kwargs):
-        sso_config = config.get("sso") or {}  # type: Dict[str, Any]
+        sso_config: Dict[str, Any] = config.get("sso") or {}
 
         # The sso-specific template_dir
         self.sso_template_dir = sso_config.get("template_dir")
diff --git a/synapse/config/stats.py b/synapse/config/stats.py
index 78f61fe9da..6f253e00c0 100644
--- a/synapse/config/stats.py
+++ b/synapse/config/stats.py
@@ -38,13 +38,9 @@ class StatsConfig(Config):
 
     def read_config(self, config, **kwargs):
         self.stats_enabled = True
-        self.stats_bucket_size = 86400 * 1000
         stats_config = config.get("stats", None)
         if stats_config:
             self.stats_enabled = stats_config.get("enabled", self.stats_enabled)
-            self.stats_bucket_size = self.parse_duration(
-                stats_config.get("bucket_size", "1d")
-            )
         if not self.stats_enabled:
             logger.warning(ROOM_STATS_DISABLED_WARN)
 
@@ -59,9 +55,4 @@ class StatsConfig(Config):
           # correctly.
           #
           #enabled: false
-
-          # The size of each timeslice in the room_stats_historical and
-          # user_stats_historical tables, as a time period. Defaults to "1d".
-          #
-          #bucket_size: 1h
         """
diff --git a/synapse/config/tls.py b/synapse/config/tls.py
index 9a16a8fbae..fed05ac7be 100644
--- a/synapse/config/tls.py
+++ b/synapse/config/tls.py
@@ -80,7 +80,7 @@ class TlsConfig(Config):
             fed_whitelist_entries = []
 
         # Support globs (*) in whitelist values
-        self.federation_certificate_verification_whitelist = []  # type: List[Pattern]
+        self.federation_certificate_verification_whitelist: List[Pattern] = []
         for entry in fed_whitelist_entries:
             try:
                 entry_regex = glob_to_regex(entry.encode("ascii").decode("ascii"))
@@ -132,8 +132,8 @@ class TlsConfig(Config):
             "use_insecure_ssl_client_just_for_testing_do_not_use"
         )
 
-        self.tls_certificate = None  # type: Optional[crypto.X509]
-        self.tls_private_key = None  # type: Optional[crypto.PKey]
+        self.tls_certificate: Optional[crypto.X509] = None
+        self.tls_private_key: Optional[crypto.PKey] = None
 
     def is_disk_cert_valid(self, allow_self_signed=True):
         """
diff --git a/synapse/crypto/keyring.py b/synapse/crypto/keyring.py
index e5a4685ed4..9e9b1c1c86 100644
--- a/synapse/crypto/keyring.py
+++ b/synapse/crypto/keyring.py
@@ -170,11 +170,13 @@ class Keyring:
             )
         self._key_fetchers = key_fetchers
 
-        self._server_queue = BatchingQueue(
+        self._server_queue: BatchingQueue[
+            _FetchKeyRequest, Dict[str, Dict[str, FetchKeyResult]]
+        ] = BatchingQueue(
             "keyring_server",
             clock=hs.get_clock(),
             process_batch_callback=self._inner_fetch_key_requests,
-        )  # type: BatchingQueue[_FetchKeyRequest, Dict[str, Dict[str, FetchKeyResult]]]
+        )
 
     async def verify_json_for_server(
         self,
@@ -330,7 +332,7 @@ class Keyring:
         # First we need to deduplicate requests for the same key. We do this by
         # taking the *maximum* requested `minimum_valid_until_ts` for each pair
         # of server name/key ID.
-        server_to_key_to_ts = {}  # type: Dict[str, Dict[str, int]]
+        server_to_key_to_ts: Dict[str, Dict[str, int]] = {}
         for request in requests:
             by_server = server_to_key_to_ts.setdefault(request.server_name, {})
             for key_id in request.key_ids:
@@ -355,7 +357,7 @@ class Keyring:
 
         # We now convert the returned list of results into a map from server
         # name to key ID to FetchKeyResult, to return.
-        to_return = {}  # type: Dict[str, Dict[str, FetchKeyResult]]
+        to_return: Dict[str, Dict[str, FetchKeyResult]] = {}
         for (request, results) in zip(deduped_requests, results_per_request):
             to_return_by_server = to_return.setdefault(request.server_name, {})
             for key_id, key_result in results.items():
@@ -455,7 +457,7 @@ class StoreKeyFetcher(KeyFetcher):
         )
 
         res = await self.store.get_server_verify_keys(key_ids_to_fetch)
-        keys = {}  # type: Dict[str, Dict[str, FetchKeyResult]]
+        keys: Dict[str, Dict[str, FetchKeyResult]] = {}
         for (server_name, key_id), key in res.items():
             keys.setdefault(server_name, {})[key_id] = key
         return keys
@@ -603,7 +605,7 @@ class PerspectivesKeyFetcher(BaseV2KeyFetcher):
             ).addErrback(unwrapFirstError)
         )
 
-        union_of_keys = {}  # type: Dict[str, Dict[str, FetchKeyResult]]
+        union_of_keys: Dict[str, Dict[str, FetchKeyResult]] = {}
         for result in results:
             for server_name, keys in result.items():
                 union_of_keys.setdefault(server_name, {}).update(keys)
@@ -656,8 +658,8 @@ class PerspectivesKeyFetcher(BaseV2KeyFetcher):
         except HttpResponseException as e:
             raise KeyLookupError("Remote server returned an error: %s" % (e,))
 
-        keys = {}  # type: Dict[str, Dict[str, FetchKeyResult]]
-        added_keys = []  # type: List[Tuple[str, str, FetchKeyResult]]
+        keys: Dict[str, Dict[str, FetchKeyResult]] = {}
+        added_keys: List[Tuple[str, str, FetchKeyResult]] = []
 
         time_now_ms = self.clock.time_msec()
 
@@ -805,7 +807,7 @@ class ServerKeyFetcher(BaseV2KeyFetcher):
         Raises:
             KeyLookupError if there was a problem making the lookup
         """
-        keys = {}  # type: Dict[str, FetchKeyResult]
+        keys: Dict[str, FetchKeyResult] = {}
 
         for requested_key_id in key_ids:
             # we may have found this key as a side-effect of asking for another.
diff --git a/synapse/event_auth.py b/synapse/event_auth.py
index 89bcf81515..137dff2513 100644
--- a/synapse/event_auth.py
+++ b/synapse/event_auth.py
@@ -48,6 +48,9 @@ def check(
         room_version_obj: the version of the room
         event: the event being checked.
         auth_events: the existing room state.
+        do_sig_check: True if it should be verified that the sending server
+            signed the event.
+        do_size_check: True if the size of the event fields should be verified.
 
     Raises:
         AuthError if the checks fail
@@ -528,7 +531,7 @@ def _check_power_levels(
     user_level = get_user_power_level(event.user_id, auth_events)
 
     # Check other levels:
-    levels_to_check = [
+    levels_to_check: List[Tuple[str, Optional[str]]] = [
         ("users_default", None),
         ("events_default", None),
         ("state_default", None),
@@ -536,7 +539,7 @@ def _check_power_levels(
         ("redact", None),
         ("kick", None),
         ("invite", None),
-    ]  # type: List[Tuple[str, Optional[str]]]
+    ]
 
     old_list = current_state.content.get("users", {})
     for user in set(list(old_list) + list(user_list)):
@@ -566,12 +569,12 @@ def _check_power_levels(
             new_loc = new_loc.get(dir, {})
 
         if level_to_check in old_loc:
-            old_level = int(old_loc[level_to_check])  # type: Optional[int]
+            old_level: Optional[int] = int(old_loc[level_to_check])
         else:
             old_level = None
 
         if level_to_check in new_loc:
-            new_level = int(new_loc[level_to_check])  # type: Optional[int]
+            new_level: Optional[int] = int(new_loc[level_to_check])
         else:
             new_level = None
 
diff --git a/synapse/events/__init__.py b/synapse/events/__init__.py
index 6286ad999a..65dc7a4ed0 100644
--- a/synapse/events/__init__.py
+++ b/synapse/events/__init__.py
@@ -105,28 +105,28 @@ class _EventInternalMetadata:
         self._dict = dict(internal_metadata_dict)
 
         # the stream ordering of this event. None, until it has been persisted.
-        self.stream_ordering = None  # type: Optional[int]
+        self.stream_ordering: Optional[int] = None
 
         # whether this event is an outlier (ie, whether we have the state at that point
         # in the DAG)
         self.outlier = False
 
-    out_of_band_membership = DictProperty("out_of_band_membership")  # type: bool
-    send_on_behalf_of = DictProperty("send_on_behalf_of")  # type: str
-    recheck_redaction = DictProperty("recheck_redaction")  # type: bool
-    soft_failed = DictProperty("soft_failed")  # type: bool
-    proactively_send = DictProperty("proactively_send")  # type: bool
-    redacted = DictProperty("redacted")  # type: bool
-    txn_id = DictProperty("txn_id")  # type: str
-    token_id = DictProperty("token_id")  # type: int
-    historical = DictProperty("historical")  # type: bool
+    out_of_band_membership: bool = DictProperty("out_of_band_membership")
+    send_on_behalf_of: str = DictProperty("send_on_behalf_of")
+    recheck_redaction: bool = DictProperty("recheck_redaction")
+    soft_failed: bool = DictProperty("soft_failed")
+    proactively_send: bool = DictProperty("proactively_send")
+    redacted: bool = DictProperty("redacted")
+    txn_id: str = DictProperty("txn_id")
+    token_id: int = DictProperty("token_id")
+    historical: bool = DictProperty("historical")
 
     # XXX: These are set by StreamWorkerStore._set_before_and_after.
     # I'm pretty sure that these are never persisted to the database, so shouldn't
     # be here
-    before = DictProperty("before")  # type: RoomStreamToken
-    after = DictProperty("after")  # type: RoomStreamToken
-    order = DictProperty("order")  # type: Tuple[int, int]
+    before: RoomStreamToken = DictProperty("before")
+    after: RoomStreamToken = DictProperty("after")
+    order: Tuple[int, int] = DictProperty("order")
 
     def get_dict(self) -> JsonDict:
         return dict(self._dict)
diff --git a/synapse/events/builder.py b/synapse/events/builder.py
index 26e3950859..87e2bb123b 100644
--- a/synapse/events/builder.py
+++ b/synapse/events/builder.py
@@ -132,12 +132,12 @@ class EventBuilder:
         format_version = self.room_version.event_format
         if format_version == EventFormatVersions.V1:
             # The types of auth/prev events changes between event versions.
-            auth_events = await self._store.add_event_hashes(
-                auth_event_ids
-            )  # type: Union[List[str], List[Tuple[str, Dict[str, str]]]]
-            prev_events = await self._store.add_event_hashes(
-                prev_event_ids
-            )  # type: Union[List[str], List[Tuple[str, Dict[str, str]]]]
+            auth_events: Union[
+                List[str], List[Tuple[str, Dict[str, str]]]
+            ] = await self._store.add_event_hashes(auth_event_ids)
+            prev_events: Union[
+                List[str], List[Tuple[str, Dict[str, str]]]
+            ] = await self._store.add_event_hashes(prev_event_ids)
         else:
             auth_events = auth_event_ids
             prev_events = prev_event_ids
@@ -156,7 +156,7 @@ class EventBuilder:
         # the db)
         depth = min(depth, MAX_DEPTH)
 
-        event_dict = {
+        event_dict: Dict[str, Any] = {
             "auth_events": auth_events,
             "prev_events": prev_events,
             "type": self.type,
@@ -166,7 +166,7 @@ class EventBuilder:
             "unsigned": self.unsigned,
             "depth": depth,
             "prev_state": [],
-        }  # type: Dict[str, Any]
+        }
 
         if self.is_state():
             event_dict["state_key"] = self._state_key
diff --git a/synapse/events/spamcheck.py b/synapse/events/spamcheck.py
index efec16c226..57f1d53fa8 100644
--- a/synapse/events/spamcheck.py
+++ b/synapse/events/spamcheck.py
@@ -76,7 +76,7 @@ def load_legacy_spam_checkers(hs: "synapse.server.HomeServer"):
     """Wrapper that loads spam checkers configured using the old configuration, and
     registers the spam checker hooks they implement.
     """
-    spam_checkers = []  # type: List[Any]
+    spam_checkers: List[Any] = []
     api = hs.get_module_api()
     for module, config in hs.config.spam_checkers:
         # Older spam checkers don't accept the `api` argument, so we
@@ -239,7 +239,7 @@ class SpamChecker:
             will be used as the error message returned to the user.
         """
         for callback in self._check_event_for_spam_callbacks:
-            res = await callback(event)  # type: Union[bool, str]
+            res: Union[bool, str] = await callback(event)
             if res:
                 return res
 
diff --git a/synapse/federation/federation_client.py b/synapse/federation/federation_client.py
index ed09c6af1f..c767d30627 100644
--- a/synapse/federation/federation_client.py
+++ b/synapse/federation/federation_client.py
@@ -86,7 +86,7 @@ class FederationClient(FederationBase):
     def __init__(self, hs: "HomeServer"):
         super().__init__(hs)
 
-        self.pdu_destination_tried = {}  # type: Dict[str, Dict[str, int]]
+        self.pdu_destination_tried: Dict[str, Dict[str, int]] = {}
         self._clock.looping_call(self._clear_tried_cache, 60 * 1000)
         self.state = hs.get_state_handler()
         self.transport_layer = hs.get_federation_transport_client()
@@ -94,13 +94,13 @@ class FederationClient(FederationBase):
         self.hostname = hs.hostname
         self.signing_key = hs.signing_key
 
-        self._get_pdu_cache = ExpiringCache(
+        self._get_pdu_cache: ExpiringCache[str, EventBase] = ExpiringCache(
             cache_name="get_pdu_cache",
             clock=self._clock,
             max_len=1000,
             expiry_ms=120 * 1000,
             reset_expiry_on_get=False,
-        )  # type: ExpiringCache[str, EventBase]
+        )
 
     def _clear_tried_cache(self):
         """Clear pdu_destination_tried cache"""
@@ -293,10 +293,10 @@ class FederationClient(FederationBase):
                     transaction_data,
                 )
 
-                pdu_list = [
+                pdu_list: List[EventBase] = [
                     event_from_pdu_json(p, room_version, outlier=outlier)
                     for p in transaction_data["pdus"]
-                ]  # type: List[EventBase]
+                ]
 
                 if pdu_list and pdu_list[0]:
                     pdu = pdu_list[0]
diff --git a/synapse/federation/federation_server.py b/synapse/federation/federation_server.py
index ac0f2ccfb3..d91f0ff32f 100644
--- a/synapse/federation/federation_server.py
+++ b/synapse/federation/federation_server.py
@@ -122,12 +122,12 @@ class FederationServer(FederationBase):
 
         # origins that we are currently processing a transaction from.
         # a dict from origin to txn id.
-        self._active_transactions = {}  # type: Dict[str, str]
+        self._active_transactions: Dict[str, str] = {}
 
         # We cache results for transaction with the same ID
-        self._transaction_resp_cache = ResponseCache(
+        self._transaction_resp_cache: ResponseCache[Tuple[str, str]] = ResponseCache(
             hs.get_clock(), "fed_txn_handler", timeout_ms=30000
-        )  # type: ResponseCache[Tuple[str, str]]
+        )
 
         self.transaction_actions = TransactionActions(self.store)
 
@@ -135,12 +135,12 @@ class FederationServer(FederationBase):
 
         # We cache responses to state queries, as they take a while and often
         # come in waves.
-        self._state_resp_cache = ResponseCache(
-            hs.get_clock(), "state_resp", timeout_ms=30000
-        )  # type: ResponseCache[Tuple[str, Optional[str]]]
-        self._state_ids_resp_cache = ResponseCache(
+        self._state_resp_cache: ResponseCache[
+            Tuple[str, Optional[str]]
+        ] = ResponseCache(hs.get_clock(), "state_resp", timeout_ms=30000)
+        self._state_ids_resp_cache: ResponseCache[Tuple[str, str]] = ResponseCache(
             hs.get_clock(), "state_ids_resp", timeout_ms=30000
-        )  # type: ResponseCache[Tuple[str, str]]
+        )
 
         self._federation_metrics_domains = (
             hs.config.federation.federation_metrics_domains
@@ -337,7 +337,7 @@ class FederationServer(FederationBase):
 
         origin_host, _ = parse_server_name(origin)
 
-        pdus_by_room = {}  # type: Dict[str, List[EventBase]]
+        pdus_by_room: Dict[str, List[EventBase]] = {}
 
         newest_pdu_ts = 0
 
@@ -516,9 +516,9 @@ class FederationServer(FederationBase):
         self, room_id: str, event_id: Optional[str]
     ) -> Dict[str, list]:
         if event_id:
-            pdus = await self.handler.get_state_for_pdu(
+            pdus: Iterable[EventBase] = await self.handler.get_state_for_pdu(
                 room_id, event_id
-            )  # type: Iterable[EventBase]
+            )
         else:
             pdus = (await self.state.get_current_state(room_id)).values()
 
@@ -791,7 +791,7 @@ class FederationServer(FederationBase):
         log_kv({"message": "Claiming one time keys.", "user, device pairs": query})
         results = await self.store.claim_e2e_one_time_keys(query)
 
-        json_result = {}  # type: Dict[str, Dict[str, dict]]
+        json_result: Dict[str, Dict[str, dict]] = {}
         for user_id, device_keys in results.items():
             for device_id, keys in device_keys.items():
                 for key_id, json_str in keys.items():
@@ -1119,17 +1119,13 @@ class FederationHandlerRegistry:
         self._get_query_client = ReplicationGetQueryRestServlet.make_client(hs)
         self._send_edu = ReplicationFederationSendEduRestServlet.make_client(hs)
 
-        self.edu_handlers = (
-            {}
-        )  # type: Dict[str, Callable[[str, dict], Awaitable[None]]]
-        self.query_handlers = (
-            {}
-        )  # type: Dict[str, Callable[[dict], Awaitable[JsonDict]]]
+        self.edu_handlers: Dict[str, Callable[[str, dict], Awaitable[None]]] = {}
+        self.query_handlers: Dict[str, Callable[[dict], Awaitable[JsonDict]]] = {}
 
         # Map from type to instance names that we should route EDU handling to.
         # We randomly choose one instance from the list to route to for each new
         # EDU received.
-        self._edu_type_to_instance = {}  # type: Dict[str, List[str]]
+        self._edu_type_to_instance: Dict[str, List[str]] = {}
 
     def register_edu_handler(
         self, edu_type: str, handler: Callable[[str, JsonDict], Awaitable[None]]
diff --git a/synapse/federation/send_queue.py b/synapse/federation/send_queue.py
index 65d76ea974..1fbf325fdc 100644
--- a/synapse/federation/send_queue.py
+++ b/synapse/federation/send_queue.py
@@ -71,34 +71,32 @@ class FederationRemoteSendQueue(AbstractFederationSender):
         # We may have multiple federation sender instances, so we need to track
         # their positions separately.
         self._sender_instances = hs.config.worker.federation_shard_config.instances
-        self._sender_positions = {}  # type: Dict[str, int]
+        self._sender_positions: Dict[str, int] = {}
 
         # Pending presence map user_id -> UserPresenceState
-        self.presence_map = {}  # type: Dict[str, UserPresenceState]
+        self.presence_map: Dict[str, UserPresenceState] = {}
 
         # Stores the destinations we need to explicitly send presence to about a
         # given user.
         # Stream position -> (user_id, destinations)
-        self.presence_destinations = (
-            SortedDict()
-        )  # type: SortedDict[int, Tuple[str, Iterable[str]]]
+        self.presence_destinations: SortedDict[
+            int, Tuple[str, Iterable[str]]
+        ] = SortedDict()
 
         # (destination, key) -> EDU
-        self.keyed_edu = {}  # type: Dict[Tuple[str, tuple], Edu]
+        self.keyed_edu: Dict[Tuple[str, tuple], Edu] = {}
 
         # stream position -> (destination, key)
-        self.keyed_edu_changed = (
-            SortedDict()
-        )  # type: SortedDict[int, Tuple[str, tuple]]
+        self.keyed_edu_changed: SortedDict[int, Tuple[str, tuple]] = SortedDict()
 
-        self.edus = SortedDict()  # type: SortedDict[int, Edu]
+        self.edus: SortedDict[int, Edu] = SortedDict()
 
         # stream ID for the next entry into keyed_edu_changed/edus.
         self.pos = 1
 
         # map from stream ID to the time that stream entry was generated, so that we
         # can clear out entries after a while
-        self.pos_time = SortedDict()  # type: SortedDict[int, int]
+        self.pos_time: SortedDict[int, int] = SortedDict()
 
         # EVERYTHING IS SAD. In particular, python only makes new scopes when
         # we make a new function, so we need to make a new function so the inner
@@ -291,7 +289,7 @@ class FederationRemoteSendQueue(AbstractFederationSender):
 
         # list of tuple(int, BaseFederationRow), where the first is the position
         # of the federation stream.
-        rows = []  # type: List[Tuple[int, BaseFederationRow]]
+        rows: List[Tuple[int, BaseFederationRow]] = []
 
         # Fetch presence to send to destinations
         i = self.presence_destinations.bisect_right(from_token)
@@ -445,11 +443,11 @@ class EduRow(BaseFederationRow, namedtuple("EduRow", ("edu",))):  # Edu
         buff.edus.setdefault(self.edu.destination, []).append(self.edu)
 
 
-_rowtypes = (
+_rowtypes: Tuple[Type[BaseFederationRow], ...] = (
     PresenceDestinationsRow,
     KeyedEduRow,
     EduRow,
-)  # type: Tuple[Type[BaseFederationRow], ...]
+)
 
 TypeToRow = {Row.TypeId: Row for Row in _rowtypes}
 
diff --git a/synapse/federation/sender/__init__.py b/synapse/federation/sender/__init__.py
index deb40f4610..d980e0d986 100644
--- a/synapse/federation/sender/__init__.py
+++ b/synapse/federation/sender/__init__.py
@@ -14,9 +14,12 @@
 
 import abc
 import logging
+from collections import OrderedDict
 from typing import TYPE_CHECKING, Dict, Hashable, Iterable, List, Optional, Set, Tuple
 
+import attr
 from prometheus_client import Counter
+from typing_extensions import Literal
 
 from twisted.internet import defer
 
@@ -33,8 +36,12 @@ from synapse.metrics import (
     event_processing_loop_room_count,
     events_processed_counter,
 )
-from synapse.metrics.background_process_metrics import run_as_background_process
+from synapse.metrics.background_process_metrics import (
+    run_as_background_process,
+    wrap_as_background_process,
+)
 from synapse.types import JsonDict, ReadReceipt, RoomStreamToken
+from synapse.util import Clock
 from synapse.util.metrics import Measure
 
 if TYPE_CHECKING:
@@ -137,6 +144,84 @@ class AbstractFederationSender(metaclass=abc.ABCMeta):
         raise NotImplementedError()
 
 
+@attr.s
+class _PresenceQueue:
+    """A queue of destinations that need to be woken up due to new presence
+    updates.
+
+    Staggers waking up of per destination queues to ensure that we don't attempt
+    to start TLS connections with many hosts all at once, leading to pinned CPU.
+    """
+
+    # The maximum duration in seconds between queuing up a destination and it
+    # being woken up.
+    _MAX_TIME_IN_QUEUE = 30.0
+
+    # The maximum duration in seconds between waking up consecutive destination
+    # queues.
+    _MAX_DELAY = 0.1
+
+    sender: "FederationSender" = attr.ib()
+    clock: Clock = attr.ib()
+    queue: "OrderedDict[str, Literal[None]]" = attr.ib(factory=OrderedDict)
+    processing: bool = attr.ib(default=False)
+
+    def add_to_queue(self, destination: str) -> None:
+        """Add a destination to the queue to be woken up."""
+
+        self.queue[destination] = None
+
+        if not self.processing:
+            self._handle()
+
+    @wrap_as_background_process("_PresenceQueue.handle")
+    async def _handle(self) -> None:
+        """Background process to drain the queue."""
+
+        if not self.queue:
+            return
+
+        assert not self.processing
+        self.processing = True
+
+        try:
+            # We start with a delay that should drain the queue quickly enough that
+            # we process all destinations in the queue in _MAX_TIME_IN_QUEUE
+            # seconds.
+            #
+            # We also add an upper bound to the delay, to gracefully handle the
+            # case where the queue only has a few entries in it.
+            current_sleep_seconds = min(
+                self._MAX_DELAY, self._MAX_TIME_IN_QUEUE / len(self.queue)
+            )
+
+            while self.queue:
+                destination, _ = self.queue.popitem(last=False)
+
+                queue = self.sender._get_per_destination_queue(destination)
+
+                if not queue._new_data_to_send:
+                    # The per destination queue has already been woken up.
+                    continue
+
+                queue.attempt_new_transaction()
+
+                await self.clock.sleep(current_sleep_seconds)
+
+                if not self.queue:
+                    break
+
+                # More destinations may have been added to the queue, so we may
+                # need to reduce the delay to ensure everything gets processed
+                # within _MAX_TIME_IN_QUEUE seconds.
+                current_sleep_seconds = min(
+                    current_sleep_seconds, self._MAX_TIME_IN_QUEUE / len(self.queue)
+                )
+
+        finally:
+            self.processing = False
+
+
 class FederationSender(AbstractFederationSender):
     def __init__(self, hs: "HomeServer"):
         self.hs = hs
@@ -148,14 +233,14 @@ class FederationSender(AbstractFederationSender):
         self.clock = hs.get_clock()
         self.is_mine_id = hs.is_mine_id
 
-        self._presence_router = None  # type: Optional[PresenceRouter]
+        self._presence_router: Optional["PresenceRouter"] = None
         self._transaction_manager = TransactionManager(hs)
 
         self._instance_name = hs.get_instance_name()
         self._federation_shard_config = hs.config.worker.federation_shard_config
 
         # map from destination to PerDestinationQueue
-        self._per_destination_queues = {}  # type: Dict[str, PerDestinationQueue]
+        self._per_destination_queues: Dict[str, PerDestinationQueue] = {}
 
         LaterGauge(
             "synapse_federation_transaction_queue_pending_destinations",
@@ -192,9 +277,7 @@ class FederationSender(AbstractFederationSender):
         # awaiting a call to flush_read_receipts_for_room. The presence of an entry
         # here for a given room means that we are rate-limiting RR flushes to that room,
         # and that there is a pending call to _flush_rrs_for_room in the system.
-        self._queues_awaiting_rr_flush_by_room = (
-            {}
-        )  # type: Dict[str, Set[PerDestinationQueue]]
+        self._queues_awaiting_rr_flush_by_room: Dict[str, Set[PerDestinationQueue]] = {}
 
         self._rr_txn_interval_per_room_ms = (
             1000.0 / hs.config.federation_rr_transactions_per_room_per_second
@@ -210,6 +293,8 @@ class FederationSender(AbstractFederationSender):
 
         self._external_cache = hs.get_external_cache()
 
+        self._presence_queue = _PresenceQueue(self, self.clock)
+
     def _get_per_destination_queue(self, destination: str) -> PerDestinationQueue:
         """Get or create a PerDestinationQueue for the given destination
 
@@ -265,7 +350,7 @@ class FederationSender(AbstractFederationSender):
                     if not event.internal_metadata.should_proactively_send():
                         return
 
-                    destinations = None  # type: Optional[Set[str]]
+                    destinations: Optional[Set[str]] = None
                     if not event.prev_event_ids():
                         # If there are no prev event IDs then the state is empty
                         # and so no remote servers in the room
@@ -331,7 +416,7 @@ class FederationSender(AbstractFederationSender):
                         for event in events:
                             await handle_event(event)
 
-                events_by_room = {}  # type: Dict[str, List[EventBase]]
+                events_by_room: Dict[str, List[EventBase]] = {}
                 for event in events:
                     events_by_room.setdefault(event.room_id, []).append(event)
 
@@ -519,7 +604,12 @@ class FederationSender(AbstractFederationSender):
                 self._instance_name, destination
             ):
                 continue
-            self._get_per_destination_queue(destination).send_presence(states)
+
+            self._get_per_destination_queue(destination).send_presence(
+                states, start_loop=False
+            )
+
+            self._presence_queue.add_to_queue(destination)
 
     def build_and_send_edu(
         self,
@@ -628,7 +718,7 @@ class FederationSender(AbstractFederationSender):
         In order to reduce load spikes, adds a delay between each destination.
         """
 
-        last_processed = None  # type: Optional[str]
+        last_processed: Optional[str] = None
 
         while True:
             destinations_to_wake = (
diff --git a/synapse/federation/sender/per_destination_queue.py b/synapse/federation/sender/per_destination_queue.py
index 3a2efd56ee..c11d1f6d31 100644
--- a/synapse/federation/sender/per_destination_queue.py
+++ b/synapse/federation/sender/per_destination_queue.py
@@ -105,34 +105,34 @@ class PerDestinationQueue:
         # catch-up at startup.
         # New events will only be sent once this is finished, at which point
         # _catching_up is flipped to False.
-        self._catching_up = True  # type: bool
+        self._catching_up: bool = True
 
         # The stream_ordering of the most recent PDU that was discarded due to
         # being in catch-up mode.
-        self._catchup_last_skipped = 0  # type: int
+        self._catchup_last_skipped: int = 0
 
         # Cache of the last successfully-transmitted stream ordering for this
         # destination (we are the only updater so this is safe)
-        self._last_successful_stream_ordering = None  # type: Optional[int]
+        self._last_successful_stream_ordering: Optional[int] = None
 
         # a queue of pending PDUs
-        self._pending_pdus = []  # type: List[EventBase]
+        self._pending_pdus: List[EventBase] = []
 
         # XXX this is never actually used: see
         # https://github.com/matrix-org/synapse/issues/7549
-        self._pending_edus = []  # type: List[Edu]
+        self._pending_edus: List[Edu] = []
 
         # Pending EDUs by their "key". Keyed EDUs are EDUs that get clobbered
         # based on their key (e.g. typing events by room_id)
         # Map of (edu_type, key) -> Edu
-        self._pending_edus_keyed = {}  # type: Dict[Tuple[str, Hashable], Edu]
+        self._pending_edus_keyed: Dict[Tuple[str, Hashable], Edu] = {}
 
         # Map of user_id -> UserPresenceState of pending presence to be sent to this
         # destination
-        self._pending_presence = {}  # type: Dict[str, UserPresenceState]
+        self._pending_presence: Dict[str, UserPresenceState] = {}
 
         # room_id -> receipt_type -> user_id -> receipt_dict
-        self._pending_rrs = {}  # type: Dict[str, Dict[str, Dict[str, dict]]]
+        self._pending_rrs: Dict[str, Dict[str, Dict[str, dict]]] = {}
         self._rrs_pending_flush = False
 
         # stream_id of last successfully sent to-device message.
@@ -171,14 +171,24 @@ class PerDestinationQueue:
 
         self.attempt_new_transaction()
 
-    def send_presence(self, states: Iterable[UserPresenceState]) -> None:
-        """Add presence updates to the queue. Start the transmission loop if necessary.
+    def send_presence(
+        self, states: Iterable[UserPresenceState], start_loop: bool = True
+    ) -> None:
+        """Add presence updates to the queue.
+
+        Args:
+            states: Presence updates to send
+            start_loop: Whether to start the transmission loop if not already
+                running.
 
         Args:
             states: presence to send
         """
         self._pending_presence.update({state.user_id: state for state in states})
-        self.attempt_new_transaction()
+        self._new_data_to_send = True
+
+        if start_loop:
+            self.attempt_new_transaction()
 
     def queue_read_receipt(self, receipt: ReadReceipt) -> None:
         """Add a RR to the list to be sent. Doesn't start the transmission loop yet
@@ -243,7 +253,7 @@ class PerDestinationQueue:
         )
 
     async def _transaction_transmission_loop(self) -> None:
-        pending_pdus = []  # type: List[EventBase]
+        pending_pdus: List[EventBase] = []
         try:
             self.transmission_loop_running = True
 
diff --git a/synapse/federation/transport/client.py b/synapse/federation/transport/client.py
index c9e7c57461..98b1bf77fd 100644
--- a/synapse/federation/transport/client.py
+++ b/synapse/federation/transport/client.py
@@ -395,9 +395,9 @@ class TransportLayerClient:
             # this uses MSC2197 (Search Filtering over Federation)
             path = _create_v1_path("/publicRooms")
 
-            data = {
+            data: Dict[str, Any] = {
                 "include_all_networks": "true" if include_all_networks else "false"
-            }  # type: Dict[str, Any]
+            }
             if third_party_instance_id:
                 data["third_party_instance_id"] = third_party_instance_id
             if limit:
@@ -423,9 +423,9 @@ class TransportLayerClient:
         else:
             path = _create_v1_path("/publicRooms")
 
-            args = {
+            args: Dict[str, Any] = {
                 "include_all_networks": "true" if include_all_networks else "false"
-            }  # type: Dict[str, Any]
+            }
             if third_party_instance_id:
                 args["third_party_instance_id"] = (third_party_instance_id,)
             if limit:
diff --git a/synapse/federation/transport/server.py b/synapse/federation/transport/server.py
index d37d9565fc..2974d4d0cc 100644
--- a/synapse/federation/transport/server.py
+++ b/synapse/federation/transport/server.py
@@ -1013,7 +1013,7 @@ class PublicRoomList(BaseFederationServlet):
         if not self.allow_access:
             raise FederationDeniedError(origin)
 
-        limit = int(content.get("limit", 100))  # type: Optional[int]
+        limit: Optional[int] = int(content.get("limit", 100))
         since_token = content.get("since", None)
         search_filter = content.get("filter", None)
 
@@ -1095,7 +1095,9 @@ class FederationGroupsProfileServlet(BaseGroupsServerServlet):
         query: Dict[bytes, List[bytes]],
         group_id: str,
     ) -> Tuple[int, JsonDict]:
-        requester_user_id = parse_string_from_args(query, "requester_user_id")
+        requester_user_id = parse_string_from_args(
+            query, "requester_user_id", required=True
+        )
         if get_domain_from_id(requester_user_id) != origin:
             raise SynapseError(403, "requester_user_id doesn't match origin")
 
@@ -1110,7 +1112,9 @@ class FederationGroupsProfileServlet(BaseGroupsServerServlet):
         query: Dict[bytes, List[bytes]],
         group_id: str,
     ) -> Tuple[int, JsonDict]:
-        requester_user_id = parse_string_from_args(query, "requester_user_id")
+        requester_user_id = parse_string_from_args(
+            query, "requester_user_id", required=True
+        )
         if get_domain_from_id(requester_user_id) != origin:
             raise SynapseError(403, "requester_user_id doesn't match origin")
 
@@ -1131,7 +1135,9 @@ class FederationGroupsSummaryServlet(BaseGroupsServerServlet):
         query: Dict[bytes, List[bytes]],
         group_id: str,
     ) -> Tuple[int, JsonDict]:
-        requester_user_id = parse_string_from_args(query, "requester_user_id")
+        requester_user_id = parse_string_from_args(
+            query, "requester_user_id", required=True
+        )
         if get_domain_from_id(requester_user_id) != origin:
             raise SynapseError(403, "requester_user_id doesn't match origin")
 
@@ -1152,7 +1158,9 @@ class FederationGroupsRoomsServlet(BaseGroupsServerServlet):
         query: Dict[bytes, List[bytes]],
         group_id: str,
     ) -> Tuple[int, JsonDict]:
-        requester_user_id = parse_string_from_args(query, "requester_user_id")
+        requester_user_id = parse_string_from_args(
+            query, "requester_user_id", required=True
+        )
         if get_domain_from_id(requester_user_id) != origin:
             raise SynapseError(403, "requester_user_id doesn't match origin")
 
@@ -1174,7 +1182,9 @@ class FederationGroupsAddRoomsServlet(BaseGroupsServerServlet):
         group_id: str,
         room_id: str,
     ) -> Tuple[int, JsonDict]:
-        requester_user_id = parse_string_from_args(query, "requester_user_id")
+        requester_user_id = parse_string_from_args(
+            query, "requester_user_id", required=True
+        )
         if get_domain_from_id(requester_user_id) != origin:
             raise SynapseError(403, "requester_user_id doesn't match origin")
 
@@ -1192,7 +1202,9 @@ class FederationGroupsAddRoomsServlet(BaseGroupsServerServlet):
         group_id: str,
         room_id: str,
     ) -> Tuple[int, JsonDict]:
-        requester_user_id = parse_string_from_args(query, "requester_user_id")
+        requester_user_id = parse_string_from_args(
+            query, "requester_user_id", required=True
+        )
         if get_domain_from_id(requester_user_id) != origin:
             raise SynapseError(403, "requester_user_id doesn't match origin")
 
@@ -1220,7 +1232,9 @@ class FederationGroupsAddRoomsConfigServlet(BaseGroupsServerServlet):
         room_id: str,
         config_key: str,
     ) -> Tuple[int, JsonDict]:
-        requester_user_id = parse_string_from_args(query, "requester_user_id")
+        requester_user_id = parse_string_from_args(
+            query, "requester_user_id", required=True
+        )
         if get_domain_from_id(requester_user_id) != origin:
             raise SynapseError(403, "requester_user_id doesn't match origin")
 
@@ -1243,7 +1257,9 @@ class FederationGroupsUsersServlet(BaseGroupsServerServlet):
         query: Dict[bytes, List[bytes]],
         group_id: str,
     ) -> Tuple[int, JsonDict]:
-        requester_user_id = parse_string_from_args(query, "requester_user_id")
+        requester_user_id = parse_string_from_args(
+            query, "requester_user_id", required=True
+        )
         if get_domain_from_id(requester_user_id) != origin:
             raise SynapseError(403, "requester_user_id doesn't match origin")
 
@@ -1264,7 +1280,9 @@ class FederationGroupsInvitedUsersServlet(BaseGroupsServerServlet):
         query: Dict[bytes, List[bytes]],
         group_id: str,
     ) -> Tuple[int, JsonDict]:
-        requester_user_id = parse_string_from_args(query, "requester_user_id")
+        requester_user_id = parse_string_from_args(
+            query, "requester_user_id", required=True
+        )
         if get_domain_from_id(requester_user_id) != origin:
             raise SynapseError(403, "requester_user_id doesn't match origin")
 
@@ -1288,7 +1306,9 @@ class FederationGroupsInviteServlet(BaseGroupsServerServlet):
         group_id: str,
         user_id: str,
     ) -> Tuple[int, JsonDict]:
-        requester_user_id = parse_string_from_args(query, "requester_user_id")
+        requester_user_id = parse_string_from_args(
+            query, "requester_user_id", required=True
+        )
         if get_domain_from_id(requester_user_id) != origin:
             raise SynapseError(403, "requester_user_id doesn't match origin")
 
@@ -1354,7 +1374,9 @@ class FederationGroupsRemoveUserServlet(BaseGroupsServerServlet):
         group_id: str,
         user_id: str,
     ) -> Tuple[int, JsonDict]:
-        requester_user_id = parse_string_from_args(query, "requester_user_id")
+        requester_user_id = parse_string_from_args(
+            query, "requester_user_id", required=True
+        )
         if get_domain_from_id(requester_user_id) != origin:
             raise SynapseError(403, "requester_user_id doesn't match origin")
 
@@ -1487,7 +1509,9 @@ class FederationGroupsSummaryRoomsServlet(BaseGroupsServerServlet):
         category_id: str,
         room_id: str,
     ) -> Tuple[int, JsonDict]:
-        requester_user_id = parse_string_from_args(query, "requester_user_id")
+        requester_user_id = parse_string_from_args(
+            query, "requester_user_id", required=True
+        )
         if get_domain_from_id(requester_user_id) != origin:
             raise SynapseError(403, "requester_user_id doesn't match origin")
 
@@ -1523,7 +1547,9 @@ class FederationGroupsSummaryRoomsServlet(BaseGroupsServerServlet):
         category_id: str,
         room_id: str,
     ) -> Tuple[int, JsonDict]:
-        requester_user_id = parse_string_from_args(query, "requester_user_id")
+        requester_user_id = parse_string_from_args(
+            query, "requester_user_id", required=True
+        )
         if get_domain_from_id(requester_user_id) != origin:
             raise SynapseError(403, "requester_user_id doesn't match origin")
 
@@ -1549,7 +1575,9 @@ class FederationGroupsCategoriesServlet(BaseGroupsServerServlet):
         query: Dict[bytes, List[bytes]],
         group_id: str,
     ) -> Tuple[int, JsonDict]:
-        requester_user_id = parse_string_from_args(query, "requester_user_id")
+        requester_user_id = parse_string_from_args(
+            query, "requester_user_id", required=True
+        )
         if get_domain_from_id(requester_user_id) != origin:
             raise SynapseError(403, "requester_user_id doesn't match origin")
 
@@ -1571,7 +1599,9 @@ class FederationGroupsCategoryServlet(BaseGroupsServerServlet):
         group_id: str,
         category_id: str,
     ) -> Tuple[int, JsonDict]:
-        requester_user_id = parse_string_from_args(query, "requester_user_id")
+        requester_user_id = parse_string_from_args(
+            query, "requester_user_id", required=True
+        )
         if get_domain_from_id(requester_user_id) != origin:
             raise SynapseError(403, "requester_user_id doesn't match origin")
 
@@ -1589,7 +1619,9 @@ class FederationGroupsCategoryServlet(BaseGroupsServerServlet):
         group_id: str,
         category_id: str,
     ) -> Tuple[int, JsonDict]:
-        requester_user_id = parse_string_from_args(query, "requester_user_id")
+        requester_user_id = parse_string_from_args(
+            query, "requester_user_id", required=True
+        )
         if get_domain_from_id(requester_user_id) != origin:
             raise SynapseError(403, "requester_user_id doesn't match origin")
 
@@ -1618,7 +1650,9 @@ class FederationGroupsCategoryServlet(BaseGroupsServerServlet):
         group_id: str,
         category_id: str,
     ) -> Tuple[int, JsonDict]:
-        requester_user_id = parse_string_from_args(query, "requester_user_id")
+        requester_user_id = parse_string_from_args(
+            query, "requester_user_id", required=True
+        )
         if get_domain_from_id(requester_user_id) != origin:
             raise SynapseError(403, "requester_user_id doesn't match origin")
 
@@ -1644,7 +1678,9 @@ class FederationGroupsRolesServlet(BaseGroupsServerServlet):
         query: Dict[bytes, List[bytes]],
         group_id: str,
     ) -> Tuple[int, JsonDict]:
-        requester_user_id = parse_string_from_args(query, "requester_user_id")
+        requester_user_id = parse_string_from_args(
+            query, "requester_user_id", required=True
+        )
         if get_domain_from_id(requester_user_id) != origin:
             raise SynapseError(403, "requester_user_id doesn't match origin")
 
@@ -1666,7 +1702,9 @@ class FederationGroupsRoleServlet(BaseGroupsServerServlet):
         group_id: str,
         role_id: str,
     ) -> Tuple[int, JsonDict]:
-        requester_user_id = parse_string_from_args(query, "requester_user_id")
+        requester_user_id = parse_string_from_args(
+            query, "requester_user_id", required=True
+        )
         if get_domain_from_id(requester_user_id) != origin:
             raise SynapseError(403, "requester_user_id doesn't match origin")
 
@@ -1682,7 +1720,9 @@ class FederationGroupsRoleServlet(BaseGroupsServerServlet):
         group_id: str,
         role_id: str,
     ) -> Tuple[int, JsonDict]:
-        requester_user_id = parse_string_from_args(query, "requester_user_id")
+        requester_user_id = parse_string_from_args(
+            query, "requester_user_id", required=True
+        )
         if get_domain_from_id(requester_user_id) != origin:
             raise SynapseError(403, "requester_user_id doesn't match origin")
 
@@ -1713,7 +1753,9 @@ class FederationGroupsRoleServlet(BaseGroupsServerServlet):
         group_id: str,
         role_id: str,
     ) -> Tuple[int, JsonDict]:
-        requester_user_id = parse_string_from_args(query, "requester_user_id")
+        requester_user_id = parse_string_from_args(
+            query, "requester_user_id", required=True
+        )
         if get_domain_from_id(requester_user_id) != origin:
             raise SynapseError(403, "requester_user_id doesn't match origin")
 
@@ -1750,7 +1792,9 @@ class FederationGroupsSummaryUsersServlet(BaseGroupsServerServlet):
         role_id: str,
         user_id: str,
     ) -> Tuple[int, JsonDict]:
-        requester_user_id = parse_string_from_args(query, "requester_user_id")
+        requester_user_id = parse_string_from_args(
+            query, "requester_user_id", required=True
+        )
         if get_domain_from_id(requester_user_id) != origin:
             raise SynapseError(403, "requester_user_id doesn't match origin")
 
@@ -1784,7 +1828,9 @@ class FederationGroupsSummaryUsersServlet(BaseGroupsServerServlet):
         role_id: str,
         user_id: str,
     ) -> Tuple[int, JsonDict]:
-        requester_user_id = parse_string_from_args(query, "requester_user_id")
+        requester_user_id = parse_string_from_args(
+            query, "requester_user_id", required=True
+        )
         if get_domain_from_id(requester_user_id) != origin:
             raise SynapseError(403, "requester_user_id doesn't match origin")
 
@@ -1825,7 +1871,9 @@ class FederationGroupsSettingJoinPolicyServlet(BaseGroupsServerServlet):
         query: Dict[bytes, List[bytes]],
         group_id: str,
     ) -> Tuple[int, JsonDict]:
-        requester_user_id = parse_string_from_args(query, "requester_user_id")
+        requester_user_id = parse_string_from_args(
+            query, "requester_user_id", required=True
+        )
         if get_domain_from_id(requester_user_id) != origin:
             raise SynapseError(403, "requester_user_id doesn't match origin")
 
@@ -1943,7 +1991,7 @@ class RoomComplexityServlet(BaseFederationServlet):
         return 200, complexity
 
 
-FEDERATION_SERVLET_CLASSES = (
+FEDERATION_SERVLET_CLASSES: Tuple[Type[BaseFederationServlet], ...] = (
     FederationSendServlet,
     FederationEventServlet,
     FederationStateV1Servlet,
@@ -1971,15 +2019,13 @@ FEDERATION_SERVLET_CLASSES = (
     FederationSpaceSummaryServlet,
     FederationV1SendKnockServlet,
     FederationMakeKnockServlet,
-)  # type: Tuple[Type[BaseFederationServlet], ...]
+)
 
-OPENID_SERVLET_CLASSES = (
-    OpenIdUserInfo,
-)  # type: Tuple[Type[BaseFederationServlet], ...]
+OPENID_SERVLET_CLASSES: Tuple[Type[BaseFederationServlet], ...] = (OpenIdUserInfo,)
 
-ROOM_LIST_CLASSES = (PublicRoomList,)  # type: Tuple[Type[PublicRoomList], ...]
+ROOM_LIST_CLASSES: Tuple[Type[PublicRoomList], ...] = (PublicRoomList,)
 
-GROUP_SERVER_SERVLET_CLASSES = (
+GROUP_SERVER_SERVLET_CLASSES: Tuple[Type[BaseFederationServlet], ...] = (
     FederationGroupsProfileServlet,
     FederationGroupsSummaryServlet,
     FederationGroupsRoomsServlet,
@@ -1998,19 +2044,19 @@ GROUP_SERVER_SERVLET_CLASSES = (
     FederationGroupsAddRoomsServlet,
     FederationGroupsAddRoomsConfigServlet,
     FederationGroupsSettingJoinPolicyServlet,
-)  # type: Tuple[Type[BaseFederationServlet], ...]
+)
 
 
-GROUP_LOCAL_SERVLET_CLASSES = (
+GROUP_LOCAL_SERVLET_CLASSES: Tuple[Type[BaseFederationServlet], ...] = (
     FederationGroupsLocalInviteServlet,
     FederationGroupsRemoveLocalUserServlet,
     FederationGroupsBulkPublicisedServlet,
-)  # type: Tuple[Type[BaseFederationServlet], ...]
+)
 
 
-GROUP_ATTESTATION_SERVLET_CLASSES = (
+GROUP_ATTESTATION_SERVLET_CLASSES: Tuple[Type[BaseFederationServlet], ...] = (
     FederationGroupsRenewAttestaionServlet,
-)  # type: Tuple[Type[BaseFederationServlet], ...]
+)
 
 
 DEFAULT_SERVLET_GROUPS = (
diff --git a/synapse/groups/groups_server.py b/synapse/groups/groups_server.py
index a06d060ebf..3dc55ab861 100644
--- a/synapse/groups/groups_server.py
+++ b/synapse/groups/groups_server.py
@@ -707,9 +707,9 @@ class GroupsServerHandler(GroupsServerWorkerHandler):
         See accept_invite, join_group.
         """
         if not self.hs.is_mine_id(user_id):
-            local_attestation = self.attestations.create_attestation(
-                group_id, user_id
-            )  # type: Optional[JsonDict]
+            local_attestation: Optional[
+                JsonDict
+            ] = self.attestations.create_attestation(group_id, user_id)
 
             remote_attestation = content["attestation"]
 
@@ -868,9 +868,9 @@ class GroupsServerHandler(GroupsServerWorkerHandler):
                 remote_attestation, user_id=requester_user_id, group_id=group_id
             )
 
-            local_attestation = self.attestations.create_attestation(
-                group_id, requester_user_id
-            )  # type: Optional[JsonDict]
+            local_attestation: Optional[
+                JsonDict
+            ] = self.attestations.create_attestation(group_id, requester_user_id)
         else:
             local_attestation = None
             remote_attestation = None
diff --git a/synapse/handlers/directory.py b/synapse/handlers/directory.py
index 4064a2b859..06d7012bac 100644
--- a/synapse/handlers/directory.py
+++ b/synapse/handlers/directory.py
@@ -22,6 +22,7 @@ from synapse.api.errors import (
     CodeMessageException,
     Codes,
     NotFoundError,
+    RequestSendFailed,
     ShadowBanError,
     StoreError,
     SynapseError,
@@ -252,12 +253,14 @@ class DirectoryHandler(BaseHandler):
                     retry_on_dns_fail=False,
                     ignore_backoff=True,
                 )
+            except RequestSendFailed:
+                raise SynapseError(502, "Failed to fetch alias")
             except CodeMessageException as e:
                 logging.warning("Error retrieving alias")
                 if e.code == 404:
                     fed_result = None
                 else:
-                    raise
+                    raise SynapseError(502, "Failed to fetch alias")
 
             if fed_result and "room_id" in fed_result and "servers" in fed_result:
                 room_id = fed_result["room_id"]
diff --git a/synapse/handlers/federation.py b/synapse/handlers/federation.py
index 991ec9919a..0209aee186 100644
--- a/synapse/handlers/federation.py
+++ b/synapse/handlers/federation.py
@@ -1414,12 +1414,15 @@ class FederationHandler(BaseHandler):
 
         Invites must be signed by the invitee's server before distribution.
         """
-        pdu = await self.federation_client.send_invite(
-            destination=target_host,
-            room_id=event.room_id,
-            event_id=event.event_id,
-            pdu=event,
-        )
+        try:
+            pdu = await self.federation_client.send_invite(
+                destination=target_host,
+                room_id=event.room_id,
+                event_id=event.event_id,
+                pdu=event,
+            )
+        except RequestSendFailed:
+            raise SynapseError(502, f"Can't connect to server {target_host}")
 
         return pdu
 
@@ -3031,9 +3034,13 @@ class FederationHandler(BaseHandler):
             await member_handler.send_membership_event(None, event, context)
         else:
             destinations = {x.split(":", 1)[-1] for x in (sender_user_id, room_id)}
-            await self.federation_client.forward_third_party_invite(
-                destinations, room_id, event_dict
-            )
+
+            try:
+                await self.federation_client.forward_third_party_invite(
+                    destinations, room_id, event_dict
+                )
+            except (RequestSendFailed, HttpResponseException):
+                raise SynapseError(502, "Failed to forward third party invite")
 
     async def on_exchange_third_party_invite_request(
         self, event_dict: JsonDict
diff --git a/synapse/handlers/message.py b/synapse/handlers/message.py
index 66e40a915d..e06655f3d4 100644
--- a/synapse/handlers/message.py
+++ b/synapse/handlers/message.py
@@ -518,6 +518,9 @@ class EventCreationHandler:
             outlier: Indicates whether the event is an `outlier`, i.e. if
                 it's from an arbitrary point and floating in the DAG as
                 opposed to being inline with the current DAG.
+            historical: Indicates whether the message is being inserted
+                back in time around some existing events. This is used to skip
+                a few checks and mark the event as backfilled.
             depth: Override the depth used to order the event in the DAG.
                 Should normally be set to None, which will cause the depth to be calculated
                 based on the prev_events.
@@ -772,6 +775,7 @@ class EventCreationHandler:
         txn_id: Optional[str] = None,
         ignore_shadow_ban: bool = False,
         outlier: bool = False,
+        historical: bool = False,
         depth: Optional[int] = None,
     ) -> Tuple[EventBase, int]:
         """
@@ -799,6 +803,9 @@ class EventCreationHandler:
             outlier: Indicates whether the event is an `outlier`, i.e. if
                 it's from an arbitrary point and floating in the DAG as
                 opposed to being inline with the current DAG.
+            historical: Indicates whether the message is being inserted
+                back in time around some existing events. This is used to skip
+                a few checks and mark the event as backfilled.
             depth: Override the depth used to order the event in the DAG.
                 Should normally be set to None, which will cause the depth to be calculated
                 based on the prev_events.
@@ -847,6 +854,7 @@ class EventCreationHandler:
                 prev_event_ids=prev_event_ids,
                 auth_event_ids=auth_event_ids,
                 outlier=outlier,
+                historical=historical,
                 depth=depth,
             )
 
@@ -1594,11 +1602,13 @@ class EventCreationHandler:
         for k, v in original_event.internal_metadata.get_dict().items():
             setattr(builder.internal_metadata, k, v)
 
-        # the event type hasn't changed, so there's no point in re-calculating the
-        # auth events.
+        # modules can send new state events, so we re-calculate the auth events just in
+        # case.
+        prev_event_ids = await self.store.get_prev_events_for_room(builder.room_id)
+
         event = await builder.build(
-            prev_event_ids=original_event.prev_event_ids(),
-            auth_event_ids=original_event.auth_event_ids(),
+            prev_event_ids=prev_event_ids,
+            auth_event_ids=None,
         )
 
         # we rebuild the event context, to be on the safe side. If nothing else,
diff --git a/synapse/handlers/receipts.py b/synapse/handlers/receipts.py
index f782d9db32..0059ad0f56 100644
--- a/synapse/handlers/receipts.py
+++ b/synapse/handlers/receipts.py
@@ -30,6 +30,8 @@ class ReceiptsHandler(BaseHandler):
 
         self.server_name = hs.config.server_name
         self.store = hs.get_datastore()
+        self.event_auth_handler = hs.get_event_auth_handler()
+
         self.hs = hs
 
         # We only need to poke the federation sender explicitly if its on the
@@ -59,6 +61,19 @@ class ReceiptsHandler(BaseHandler):
         """Called when we receive an EDU of type m.receipt from a remote HS."""
         receipts = []
         for room_id, room_values in content.items():
+            # If we're not in the room just ditch the event entirely. This is
+            # probably an old server that has come back and thinks we're still in
+            # the room (or we've been rejoined to the room by a state reset).
+            is_in_room = await self.event_auth_handler.check_host_in_room(
+                room_id, self.server_name
+            )
+            if not is_in_room:
+                logger.info(
+                    "Ignoring receipt from %s as we're not in the room",
+                    origin,
+                )
+                continue
+
             for receipt_type, users in room_values.items():
                 for user_id, user_values in users.items():
                     if get_domain_from_id(user_id) != origin:
diff --git a/synapse/handlers/room_list.py b/synapse/handlers/room_list.py
index 5e3ef7ce3a..c6bfa5451f 100644
--- a/synapse/handlers/room_list.py
+++ b/synapse/handlers/room_list.py
@@ -20,7 +20,12 @@ import msgpack
 from unpaddedbase64 import decode_base64, encode_base64
 
 from synapse.api.constants import EventTypes, HistoryVisibility, JoinRules
-from synapse.api.errors import Codes, HttpResponseException
+from synapse.api.errors import (
+    Codes,
+    HttpResponseException,
+    RequestSendFailed,
+    SynapseError,
+)
 from synapse.types import JsonDict, ThirdPartyInstanceID
 from synapse.util.caches.descriptors import cached
 from synapse.util.caches.response_cache import ResponseCache
@@ -417,14 +422,17 @@ class RoomListHandler(BaseHandler):
         repl_layer = self.hs.get_federation_client()
         if search_filter:
             # We can't cache when asking for search
-            return await repl_layer.get_public_rooms(
-                server_name,
-                limit=limit,
-                since_token=since_token,
-                search_filter=search_filter,
-                include_all_networks=include_all_networks,
-                third_party_instance_id=third_party_instance_id,
-            )
+            try:
+                return await repl_layer.get_public_rooms(
+                    server_name,
+                    limit=limit,
+                    since_token=since_token,
+                    search_filter=search_filter,
+                    include_all_networks=include_all_networks,
+                    third_party_instance_id=third_party_instance_id,
+                )
+            except (RequestSendFailed, HttpResponseException):
+                raise SynapseError(502, "Failed to fetch room list")
 
         key = (
             server_name,
diff --git a/synapse/handlers/space_summary.py b/synapse/handlers/space_summary.py
index b585057ec3..366e6211e5 100644
--- a/synapse/handlers/space_summary.py
+++ b/synapse/handlers/space_summary.py
@@ -24,6 +24,7 @@ from synapse.api.constants import (
     EventContentFields,
     EventTypes,
     HistoryVisibility,
+    JoinRules,
     Membership,
     RoomTypes,
 )
@@ -150,14 +151,21 @@ class SpaceSummaryHandler:
                     # The room should only be included in the summary if:
                     #     a. the user is in the room;
                     #     b. the room is world readable; or
-                    #     c. the user is in a space that has been granted access to
-                    #        the room.
+                    #     c. the user could join the room, e.g. the join rules
+                    #        are set to public or the user is in a space that
+                    #        has been granted access to the room.
                     #
                     # Note that we know the user is not in the root room (which is
                     # why the remote call was made in the first place), but the user
                     # could be in one of the children rooms and we just didn't know
                     # about the link.
-                    include_room = room.get("world_readable") is True
+
+                    # The API doesn't return the room version so assume that a
+                    # join rule of knock is valid.
+                    include_room = (
+                        room.get("join_rules") in (JoinRules.PUBLIC, JoinRules.KNOCK)
+                        or room.get("world_readable") is True
+                    )
 
                     # Check if the user is a member of any of the allowed spaces
                     # from the response.
@@ -420,9 +428,8 @@ class SpaceSummaryHandler:
 
         It should be included if:
 
-        * The requester is joined or invited to the room.
-        * The requester can join without an invite (per MSC3083).
-        * The origin server has any user that is joined or invited to the room.
+        * The requester is joined or can join the room (per MSC3173).
+        * The origin server has any user that is joined or can join the room.
         * The history visibility is set to world readable.
 
         Args:
@@ -441,13 +448,39 @@ class SpaceSummaryHandler:
 
         # If there's no state for the room, it isn't known.
         if not state_ids:
+            # The user might have a pending invite for the room.
+            if requester and await self._store.get_invite_for_local_user_in_room(
+                requester, room_id
+            ):
+                return True
+
             logger.info("room %s is unknown, omitting from summary", room_id)
             return False
 
         room_version = await self._store.get_room_version(room_id)
 
-        # if we have an authenticated requesting user, first check if they are able to view
-        # stripped state in the room.
+        # Include the room if it has join rules of public or knock.
+        join_rules_event_id = state_ids.get((EventTypes.JoinRules, ""))
+        if join_rules_event_id:
+            join_rules_event = await self._store.get_event(join_rules_event_id)
+            join_rule = join_rules_event.content.get("join_rule")
+            if join_rule == JoinRules.PUBLIC or (
+                room_version.msc2403_knocking and join_rule == JoinRules.KNOCK
+            ):
+                return True
+
+        # Include the room if it is peekable.
+        hist_vis_event_id = state_ids.get((EventTypes.RoomHistoryVisibility, ""))
+        if hist_vis_event_id:
+            hist_vis_ev = await self._store.get_event(hist_vis_event_id)
+            hist_vis = hist_vis_ev.content.get("history_visibility")
+            if hist_vis == HistoryVisibility.WORLD_READABLE:
+                return True
+
+        # Otherwise we need to check information specific to the user or server.
+
+        # If we have an authenticated requesting user, check if they are a member
+        # of the room (or can join the room).
         if requester:
             member_event_id = state_ids.get((EventTypes.Member, requester), None)
 
@@ -470,9 +503,11 @@ class SpaceSummaryHandler:
                     return True
 
         # If this is a request over federation, check if the host is in the room or
-        # is in one of the spaces specified via the join rules.
+        # has a user who could join the room.
         elif origin:
-            if await self._event_auth_handler.check_host_in_room(room_id, origin):
+            if await self._event_auth_handler.check_host_in_room(
+                room_id, origin
+            ) or await self._store.is_host_invited(room_id, origin):
                 return True
 
             # Alternately, if the host has a user in any of the spaces specified
@@ -490,18 +525,10 @@ class SpaceSummaryHandler:
                     ):
                         return True
 
-        # otherwise, check if the room is peekable
-        hist_vis_event_id = state_ids.get((EventTypes.RoomHistoryVisibility, ""), None)
-        if hist_vis_event_id:
-            hist_vis_ev = await self._store.get_event(hist_vis_event_id)
-            hist_vis = hist_vis_ev.content.get("history_visibility")
-            if hist_vis == HistoryVisibility.WORLD_READABLE:
-                return True
-
         logger.info(
-            "room %s is unpeekable and user %s is not a member / not allowed to join, omitting from summary",
+            "room %s is unpeekable and requester %s is not a member / not allowed to join, omitting from summary",
             room_id,
-            requester,
+            requester or origin,
         )
         return False
 
@@ -535,6 +562,7 @@ class SpaceSummaryHandler:
             "canonical_alias": stats["canonical_alias"],
             "num_joined_members": stats["joined_members"],
             "avatar_url": stats["avatar"],
+            "join_rules": stats["join_rules"],
             "world_readable": (
                 stats["history_visibility"] == HistoryVisibility.WORLD_READABLE
             ),
diff --git a/synapse/handlers/stats.py b/synapse/handlers/stats.py
index 4e45d1da57..814d08efcb 100644
--- a/synapse/handlers/stats.py
+++ b/synapse/handlers/stats.py
@@ -45,7 +45,6 @@ class StatsHandler:
         self.clock = hs.get_clock()
         self.notifier = hs.get_notifier()
         self.is_mine_id = hs.is_mine_id
-        self.stats_bucket_size = hs.config.stats_bucket_size
 
         self.stats_enabled = hs.config.stats_enabled
 
@@ -106,20 +105,6 @@ class StatsHandler:
                 room_deltas = {}
                 user_deltas = {}
 
-            # Then count deltas for total_events and total_event_bytes.
-            (
-                room_count,
-                user_count,
-            ) = await self.store.get_changes_room_total_events_and_bytes(
-                self.pos, max_pos
-            )
-
-            for room_id, fields in room_count.items():
-                room_deltas.setdefault(room_id, Counter()).update(fields)
-
-            for user_id, fields in user_count.items():
-                user_deltas.setdefault(user_id, Counter()).update(fields)
-
             logger.debug("room_deltas: %s", room_deltas)
             logger.debug("user_deltas: %s", user_deltas)
 
@@ -181,12 +166,10 @@ class StatsHandler:
 
             event_content = {}  # type: JsonDict
 
-            sender = None
             if event_id is not None:
                 event = await self.store.get_event(event_id, allow_none=True)
                 if event:
                     event_content = event.content or {}
-                    sender = event.sender
 
             # All the values in this dict are deltas (RELATIVE changes)
             room_stats_delta = room_to_stats_deltas.setdefault(room_id, Counter())
@@ -244,12 +227,6 @@ class StatsHandler:
                     room_stats_delta["joined_members"] += 1
                 elif membership == Membership.INVITE:
                     room_stats_delta["invited_members"] += 1
-
-                    if sender and self.is_mine_id(sender):
-                        user_to_stats_deltas.setdefault(sender, Counter())[
-                            "invites_sent"
-                        ] += 1
-
                 elif membership == Membership.LEAVE:
                     room_stats_delta["left_members"] += 1
                 elif membership == Membership.BAN:
@@ -279,10 +256,6 @@ class StatsHandler:
                 room_state["is_federatable"] = (
                     event_content.get("m.federate", True) is True
                 )
-                if sender and self.is_mine_id(sender):
-                    user_to_stats_deltas.setdefault(sender, Counter())[
-                        "rooms_created"
-                    ] += 1
             elif typ == EventTypes.JoinRules:
                 room_state["join_rules"] = event_content.get("join_rule")
             elif typ == EventTypes.RoomHistoryVisibility:
diff --git a/synapse/handlers/typing.py b/synapse/handlers/typing.py
index e22393adc4..c0a8364755 100644
--- a/synapse/handlers/typing.py
+++ b/synapse/handlers/typing.py
@@ -208,6 +208,7 @@ class TypingWriterHandler(FollowerTypingHandler):
 
         self.auth = hs.get_auth()
         self.notifier = hs.get_notifier()
+        self.event_auth_handler = hs.get_event_auth_handler()
 
         self.hs = hs
 
@@ -326,6 +327,19 @@ class TypingWriterHandler(FollowerTypingHandler):
         room_id = content["room_id"]
         user_id = content["user_id"]
 
+        # If we're not in the room just ditch the event entirely. This is
+        # probably an old server that has come back and thinks we're still in
+        # the room (or we've been rejoined to the room by a state reset).
+        is_in_room = await self.event_auth_handler.check_host_in_room(
+            room_id, self.server_name
+        )
+        if not is_in_room:
+            logger.info(
+                "Ignoring typing update from %s as we're not in the room",
+                origin,
+            )
+            return
+
         member = RoomMember(user_id=user_id, room_id=room_id)
 
         # Check that the string is a valid user id
diff --git a/synapse/http/__init__.py b/synapse/http/__init__.py
index ed4671b7de..578fc48ef4 100644
--- a/synapse/http/__init__.py
+++ b/synapse/http/__init__.py
@@ -69,7 +69,7 @@ def _get_requested_host(request: IRequest) -> bytes:
         return hostname
 
     # no Host header, use the address/port that the request arrived on
-    host = request.getHost()  # type: Union[address.IPv4Address, address.IPv6Address]
+    host: Union[address.IPv4Address, address.IPv6Address] = request.getHost()
 
     hostname = host.host.encode("ascii")
 
diff --git a/synapse/http/client.py b/synapse/http/client.py
index 1ca6624fd5..2ac76b15c2 100644
--- a/synapse/http/client.py
+++ b/synapse/http/client.py
@@ -160,7 +160,7 @@ class _IPBlacklistingResolver:
     def resolveHostName(
         self, recv: IResolutionReceiver, hostname: str, portNumber: int = 0
     ) -> IResolutionReceiver:
-        addresses = []  # type: List[IAddress]
+        addresses: List[IAddress] = []
 
         def _callback() -> None:
             has_bad_ip = False
@@ -333,9 +333,9 @@ class SimpleHttpClient:
         if self._ip_blacklist:
             # If we have an IP blacklist, we need to use a DNS resolver which
             # filters out blacklisted IP addresses, to prevent DNS rebinding.
-            self.reactor = BlacklistingReactorWrapper(
+            self.reactor: ISynapseReactor = BlacklistingReactorWrapper(
                 hs.get_reactor(), self._ip_whitelist, self._ip_blacklist
-            )  # type: ISynapseReactor
+            )
         else:
             self.reactor = hs.get_reactor()
 
@@ -349,14 +349,14 @@ class SimpleHttpClient:
         pool.maxPersistentPerHost = max((100 * hs.config.caches.global_factor, 5))
         pool.cachedConnectionTimeout = 2 * 60
 
-        self.agent = ProxyAgent(
+        self.agent: IAgent = ProxyAgent(
             self.reactor,
             hs.get_reactor(),
             connectTimeout=15,
             contextFactory=self.hs.get_http_client_context_factory(),
             pool=pool,
             use_proxy=use_proxy,
-        )  # type: IAgent
+        )
 
         if self._ip_blacklist:
             # If we have an IP blacklist, we then install the blacklisting Agent
@@ -411,7 +411,7 @@ class SimpleHttpClient:
                         cooperator=self._cooperator,
                     )
 
-                request_deferred = treq.request(
+                request_deferred: defer.Deferred = treq.request(
                     method,
                     uri,
                     agent=self.agent,
@@ -421,7 +421,7 @@ class SimpleHttpClient:
                     # response bodies.
                     unbuffered=True,
                     **self._extra_treq_args,
-                )  # type: defer.Deferred
+                )
 
                 # we use our own timeout mechanism rather than treq's as a workaround
                 # for https://twistedmatrix.com/trac/ticket/9534.
@@ -772,7 +772,7 @@ class BodyExceededMaxSize(Exception):
 class _DiscardBodyWithMaxSizeProtocol(protocol.Protocol):
     """A protocol which immediately errors upon receiving data."""
 
-    transport = None  # type: Optional[ITCPTransport]
+    transport: Optional[ITCPTransport] = None
 
     def __init__(self, deferred: defer.Deferred):
         self.deferred = deferred
@@ -798,7 +798,7 @@ class _DiscardBodyWithMaxSizeProtocol(protocol.Protocol):
 class _ReadBodyWithMaxSizeProtocol(protocol.Protocol):
     """A protocol which reads body to a stream, erroring if the body exceeds a maximum size."""
 
-    transport = None  # type: Optional[ITCPTransport]
+    transport: Optional[ITCPTransport] = None
 
     def __init__(
         self, stream: ByteWriteable, deferred: defer.Deferred, max_size: Optional[int]
diff --git a/synapse/http/matrixfederationclient.py b/synapse/http/matrixfederationclient.py
index b8849c0150..2efa15bf04 100644
--- a/synapse/http/matrixfederationclient.py
+++ b/synapse/http/matrixfederationclient.py
@@ -43,6 +43,7 @@ from twisted.internet import defer
 from twisted.internet.error import DNSLookupError
 from twisted.internet.interfaces import IReactorTime
 from twisted.internet.task import _EPSILON, Cooperator
+from twisted.web.client import ResponseFailed
 from twisted.web.http_headers import Headers
 from twisted.web.iweb import IBodyProducer, IResponse
 
@@ -105,7 +106,7 @@ class ByteParser(ByteWriteable, Generic[T], abc.ABC):
     the parsed data.
     """
 
-    CONTENT_TYPE = abc.abstractproperty()  # type: str  # type: ignore
+    CONTENT_TYPE: str = abc.abstractproperty()  # type: ignore
     """The expected content type of the response, e.g. `application/json`. If
     the content type doesn't match we fail the request.
     """
@@ -262,6 +263,15 @@ async def _handle_response(
             request.uri.decode("ascii"),
         )
         raise RequestSendFailed(e, can_retry=True) from e
+    except ResponseFailed as e:
+        logger.warning(
+            "{%s} [%s] Failed to read response - %s %s",
+            request.txn_id,
+            request.destination,
+            request.method,
+            request.uri.decode("ascii"),
+        )
+        raise RequestSendFailed(e, can_retry=True) from e
     except Exception as e:
         logger.warning(
             "{%s} [%s] Error reading response %s %s: %s",
@@ -317,11 +327,11 @@ class MatrixFederationHttpClient:
 
         # We need to use a DNS resolver which filters out blacklisted IP
         # addresses, to prevent DNS rebinding.
-        self.reactor = BlacklistingReactorWrapper(
+        self.reactor: ISynapseReactor = BlacklistingReactorWrapper(
             hs.get_reactor(),
             hs.config.federation_ip_range_whitelist,
             hs.config.federation_ip_range_blacklist,
-        )  # type: ISynapseReactor
+        )
 
         user_agent = hs.version_string
         if hs.config.user_agent_suffix:
@@ -494,7 +504,7 @@ class MatrixFederationHttpClient:
         )
 
         # Inject the span into the headers
-        headers_dict = {}  # type: Dict[bytes, List[bytes]]
+        headers_dict: Dict[bytes, List[bytes]] = {}
         opentracing.inject_header_dict(headers_dict, request.destination)
 
         headers_dict[b"User-Agent"] = [self.version_string_bytes]
@@ -523,9 +533,9 @@ class MatrixFederationHttpClient:
                             destination_bytes, method_bytes, url_to_sign_bytes, json
                         )
                         data = encode_canonical_json(json)
-                        producer = QuieterFileBodyProducer(
+                        producer: Optional[IBodyProducer] = QuieterFileBodyProducer(
                             BytesIO(data), cooperator=self._cooperator
-                        )  # type: Optional[IBodyProducer]
+                        )
                     else:
                         producer = None
                         auth_headers = self.build_auth_headers(
@@ -1137,6 +1147,24 @@ class MatrixFederationHttpClient:
                 msg,
             )
             raise SynapseError(502, msg, Codes.TOO_LARGE)
+        except defer.TimeoutError as e:
+            logger.warning(
+                "{%s} [%s] Timed out reading response - %s %s",
+                request.txn_id,
+                request.destination,
+                request.method,
+                request.uri.decode("ascii"),
+            )
+            raise RequestSendFailed(e, can_retry=True) from e
+        except ResponseFailed as e:
+            logger.warning(
+                "{%s} [%s] Failed to read response - %s %s",
+                request.txn_id,
+                request.destination,
+                request.method,
+                request.uri.decode("ascii"),
+            )
+            raise RequestSendFailed(e, can_retry=True) from e
         except Exception as e:
             logger.warning(
                 "{%s} [%s] Error reading response: %s",
diff --git a/synapse/http/proxyagent.py b/synapse/http/proxyagent.py
index 7dfae8b786..7a6a1717de 100644
--- a/synapse/http/proxyagent.py
+++ b/synapse/http/proxyagent.py
@@ -117,7 +117,8 @@ class ProxyAgent(_AgentBase):
             https_proxy = proxies["https"].encode() if "https" in proxies else None
             no_proxy = proxies["no"] if "no" in proxies else None
 
-        # Parse credentials from https proxy connection string if present
+        # Parse credentials from http and https proxy connection string if present
+        self.http_proxy_creds, http_proxy = parse_username_password(http_proxy)
         self.https_proxy_creds, https_proxy = parse_username_password(https_proxy)
 
         self.http_proxy_endpoint = _http_proxy_endpoint(
@@ -189,6 +190,15 @@ class ProxyAgent(_AgentBase):
             and self.http_proxy_endpoint
             and not should_skip_proxy
         ):
+            # Determine whether we need to set Proxy-Authorization headers
+            if self.http_proxy_creds:
+                # Set a Proxy-Authorization header
+                if headers is None:
+                    headers = Headers()
+                headers.addRawHeader(
+                    b"Proxy-Authorization",
+                    self.http_proxy_creds.as_proxy_authorization_value(),
+                )
             # Cache *all* connections under the same key, since we are only
             # connecting to a single destination, the proxy:
             pool_key = ("http-proxy", self.http_proxy_endpoint)
diff --git a/synapse/http/server.py b/synapse/http/server.py
index efbc6d5b25..b79fa722e9 100644
--- a/synapse/http/server.py
+++ b/synapse/http/server.py
@@ -81,7 +81,7 @@ def return_json_error(f: failure.Failure, request: SynapseRequest) -> None:
 
     if f.check(SynapseError):
         # mypy doesn't understand that f.check asserts the type.
-        exc = f.value  # type: SynapseError  # type: ignore
+        exc: SynapseError = f.value  # type: ignore
         error_code = exc.code
         error_dict = exc.error_dict()
 
@@ -132,7 +132,7 @@ def return_html_error(
     """
     if f.check(CodeMessageException):
         # mypy doesn't understand that f.check asserts the type.
-        cme = f.value  # type: CodeMessageException  # type: ignore
+        cme: CodeMessageException = f.value  # type: ignore
         code = cme.code
         msg = cme.msg
 
@@ -404,7 +404,7 @@ class JsonResource(DirectServeJsonResource):
             key word arguments to pass to the callback
         """
         # At this point the path must be bytes.
-        request_path_bytes = request.path  # type: bytes  # type: ignore
+        request_path_bytes: bytes = request.path  # type: ignore
         request_path = request_path_bytes.decode("ascii")
         # Treat HEAD requests as GET requests.
         request_method = request.method
@@ -557,7 +557,7 @@ class _ByteProducer:
         request: Request,
         iterator: Iterator[bytes],
     ):
-        self._request = request  # type: Optional[Request]
+        self._request: Optional[Request] = request
         self._iterator = iterator
         self._paused = False
 
diff --git a/synapse/http/servlet.py b/synapse/http/servlet.py
index 6ba2ce1e53..04560fb589 100644
--- a/synapse/http/servlet.py
+++ b/synapse/http/servlet.py
@@ -205,7 +205,7 @@ def parse_string(
             parameter is present, must be one of a list of allowed values and
             is not one of those allowed values.
     """
-    args = request.args  # type: Dict[bytes, List[bytes]]  # type: ignore
+    args: Dict[bytes, List[bytes]] = request.args  # type: ignore
     return parse_string_from_args(
         args,
         name,
diff --git a/synapse/http/site.py b/synapse/http/site.py
index 40754b7bea..3b0a38124e 100644
--- a/synapse/http/site.py
+++ b/synapse/http/site.py
@@ -64,16 +64,16 @@ class SynapseRequest(Request):
     def __init__(self, channel, *args, max_request_body_size=1024, **kw):
         Request.__init__(self, channel, *args, **kw)
         self._max_request_body_size = max_request_body_size
-        self.site = channel.site  # type: SynapseSite
+        self.site: SynapseSite = channel.site
         self._channel = channel  # this is used by the tests
         self.start_time = 0.0
 
         # The requester, if authenticated. For federation requests this is the
         # server name, for client requests this is the Requester object.
-        self._requester = None  # type: Optional[Union[Requester, str]]
+        self._requester: Optional[Union[Requester, str]] = None
 
         # we can't yet create the logcontext, as we don't know the method.
-        self.logcontext = None  # type: Optional[LoggingContext]
+        self.logcontext: Optional[LoggingContext] = None
 
         global _next_request_seq
         self.request_seq = _next_request_seq
@@ -152,7 +152,7 @@ class SynapseRequest(Request):
         Returns:
             The redacted URI as a string.
         """
-        uri = self.uri  # type: Union[bytes, str]
+        uri: Union[bytes, str] = self.uri
         if isinstance(uri, bytes):
             uri = uri.decode("ascii", errors="replace")
         return redact_uri(uri)
@@ -167,7 +167,7 @@ class SynapseRequest(Request):
         Returns:
             The request method as a string.
         """
-        method = self.method  # type: Union[bytes, str]
+        method: Union[bytes, str] = self.method
         if isinstance(method, bytes):
             return self.method.decode("ascii")
         return method
@@ -434,8 +434,8 @@ class XForwardedForRequest(SynapseRequest):
     """
 
     # the client IP and ssl flag, as extracted from the headers.
-    _forwarded_for = None  # type: Optional[_XForwardedForAddress]
-    _forwarded_https = False  # type: bool
+    _forwarded_for: "Optional[_XForwardedForAddress]" = None
+    _forwarded_https: bool = False
 
     def requestReceived(self, command, path, version):
         # this method is called by the Channel once the full request has been
diff --git a/synapse/logging/_remote.py b/synapse/logging/_remote.py
index c515690b38..8202d0494d 100644
--- a/synapse/logging/_remote.py
+++ b/synapse/logging/_remote.py
@@ -110,9 +110,9 @@ class RemoteHandler(logging.Handler):
         self.port = port
         self.maximum_buffer = maximum_buffer
 
-        self._buffer = deque()  # type: Deque[logging.LogRecord]
-        self._connection_waiter = None  # type: Optional[Deferred]
-        self._producer = None  # type: Optional[LogProducer]
+        self._buffer: Deque[logging.LogRecord] = deque()
+        self._connection_waiter: Optional[Deferred] = None
+        self._producer: Optional[LogProducer] = None
 
         # Connect without DNS lookups if it's a direct IP.
         if _reactor is None:
@@ -123,9 +123,9 @@ class RemoteHandler(logging.Handler):
         try:
             ip = ip_address(self.host)
             if isinstance(ip, IPv4Address):
-                endpoint = TCP4ClientEndpoint(
+                endpoint: IStreamClientEndpoint = TCP4ClientEndpoint(
                     _reactor, self.host, self.port
-                )  # type: IStreamClientEndpoint
+                )
             elif isinstance(ip, IPv6Address):
                 endpoint = TCP6ClientEndpoint(_reactor, self.host, self.port)
             else:
@@ -165,7 +165,7 @@ class RemoteHandler(logging.Handler):
         def writer(result: Protocol) -> None:
             # Force recognising transport as a Connection and not the more
             # generic ITransport.
-            transport = result.transport  # type: Connection  # type: ignore
+            transport: Connection = result.transport  # type: ignore
 
             # We have a connection. If we already have a producer, and its
             # transport is the same, just trigger a resumeProducing.
@@ -188,7 +188,7 @@ class RemoteHandler(logging.Handler):
             self._producer.resumeProducing()
             self._connection_waiter = None
 
-        deferred = self._service.whenConnected(failAfterFailures=1)  # type: Deferred
+        deferred: Deferred = self._service.whenConnected(failAfterFailures=1)
         deferred.addCallbacks(writer, fail)
         self._connection_waiter = deferred
 
diff --git a/synapse/logging/_structured.py b/synapse/logging/_structured.py
index c7a971a9d6..b9933a1528 100644
--- a/synapse/logging/_structured.py
+++ b/synapse/logging/_structured.py
@@ -63,7 +63,7 @@ def parse_drain_configs(
             DrainType.CONSOLE_JSON,
             DrainType.FILE_JSON,
         ):
-            formatter = "json"  # type: Optional[str]
+            formatter: Optional[str] = "json"
         elif logging_type in (
             DrainType.CONSOLE_JSON_TERSE,
             DrainType.NETWORK_JSON_TERSE,
diff --git a/synapse/logging/context.py b/synapse/logging/context.py
index 7fc11a9ac2..18ac507802 100644
--- a/synapse/logging/context.py
+++ b/synapse/logging/context.py
@@ -113,13 +113,13 @@ class ContextResourceUsage:
             self.reset()
         else:
             # FIXME: mypy can't infer the types set via reset() above, so specify explicitly for now
-            self.ru_utime = copy_from.ru_utime  # type: float
-            self.ru_stime = copy_from.ru_stime  # type: float
-            self.db_txn_count = copy_from.db_txn_count  # type: int
+            self.ru_utime: float = copy_from.ru_utime
+            self.ru_stime: float = copy_from.ru_stime
+            self.db_txn_count: int = copy_from.db_txn_count
 
-            self.db_txn_duration_sec = copy_from.db_txn_duration_sec  # type: float
-            self.db_sched_duration_sec = copy_from.db_sched_duration_sec  # type: float
-            self.evt_db_fetch_count = copy_from.evt_db_fetch_count  # type: int
+            self.db_txn_duration_sec: float = copy_from.db_txn_duration_sec
+            self.db_sched_duration_sec: float = copy_from.db_sched_duration_sec
+            self.evt_db_fetch_count: int = copy_from.evt_db_fetch_count
 
     def copy(self) -> "ContextResourceUsage":
         return ContextResourceUsage(copy_from=self)
@@ -289,12 +289,12 @@ class LoggingContext:
 
         # The thread resource usage when the logcontext became active. None
         # if the context is not currently active.
-        self.usage_start = None  # type: Optional[resource._RUsage]
+        self.usage_start: Optional[resource._RUsage] = None
 
         self.main_thread = get_thread_id()
         self.request = None
         self.tag = ""
-        self.scope = None  # type: Optional[_LogContextScope]
+        self.scope: Optional["_LogContextScope"] = None
 
         # keep track of whether we have hit the __exit__ block for this context
         # (suggesting that the the thing that created the context thinks it should
diff --git a/synapse/logging/opentracing.py b/synapse/logging/opentracing.py
index 140ed711e3..185844f188 100644
--- a/synapse/logging/opentracing.py
+++ b/synapse/logging/opentracing.py
@@ -251,7 +251,7 @@ try:
             except Exception:
                 logger.exception("Failed to report span")
 
-    RustReporter = _WrappedRustReporter  # type: Optional[Type[_WrappedRustReporter]]
+    RustReporter: Optional[Type[_WrappedRustReporter]] = _WrappedRustReporter
 except ImportError:
     RustReporter = None
 
@@ -286,7 +286,7 @@ class SynapseBaggage:
 # Block everything by default
 # A regex which matches the server_names to expose traces for.
 # None means 'block everything'.
-_homeserver_whitelist = None  # type: Optional[Pattern[str]]
+_homeserver_whitelist: Optional[Pattern[str]] = None
 
 # Util methods
 
@@ -662,7 +662,7 @@ def inject_header_dict(
 
     span = opentracing.tracer.active_span
 
-    carrier = {}  # type: Dict[str, str]
+    carrier: Dict[str, str] = {}
     opentracing.tracer.inject(span.context, opentracing.Format.HTTP_HEADERS, carrier)
 
     for key, value in carrier.items():
@@ -704,7 +704,7 @@ def get_active_span_text_map(destination=None):
     if destination and not whitelisted_homeserver(destination):
         return {}
 
-    carrier = {}  # type: Dict[str, str]
+    carrier: Dict[str, str] = {}
     opentracing.tracer.inject(
         opentracing.tracer.active_span.context, opentracing.Format.TEXT_MAP, carrier
     )
@@ -718,7 +718,7 @@ def active_span_context_as_string():
     Returns:
         The active span context encoded as a string.
     """
-    carrier = {}  # type: Dict[str, str]
+    carrier: Dict[str, str] = {}
     if opentracing:
         opentracing.tracer.inject(
             opentracing.tracer.active_span.context, opentracing.Format.TEXT_MAP, carrier
diff --git a/synapse/metrics/__init__.py b/synapse/metrics/__init__.py
index fef2846669..f237b8a236 100644
--- a/synapse/metrics/__init__.py
+++ b/synapse/metrics/__init__.py
@@ -46,7 +46,7 @@ logger = logging.getLogger(__name__)
 METRICS_PREFIX = "/_synapse/metrics"
 
 running_on_pypy = platform.python_implementation() == "PyPy"
-all_gauges = {}  # type: Dict[str, Union[LaterGauge, InFlightGauge]]
+all_gauges: "Dict[str, Union[LaterGauge, InFlightGauge]]" = {}
 
 HAVE_PROC_SELF_STAT = os.path.exists("/proc/self/stat")
 
@@ -130,7 +130,7 @@ class InFlightGauge:
         )
 
         # Counts number of in flight blocks for a given set of label values
-        self._registrations = {}  # type: Dict
+        self._registrations: Dict = {}
 
         # Protects access to _registrations
         self._lock = threading.Lock()
@@ -248,7 +248,7 @@ class GaugeBucketCollector:
 
         # We initially set this to None. We won't report metrics until
         # this has been initialised after a successful data update
-        self._metric = None  # type: Optional[GaugeHistogramMetricFamily]
+        self._metric: Optional[GaugeHistogramMetricFamily] = None
 
         registry.register(self)
 
diff --git a/synapse/metrics/_exposition.py b/synapse/metrics/_exposition.py
index 8002be56e0..7e49d0d02c 100644
--- a/synapse/metrics/_exposition.py
+++ b/synapse/metrics/_exposition.py
@@ -125,7 +125,7 @@ def generate_latest(registry, emit_help=False):
             )
         output.append("# TYPE {0} {1}\n".format(mname, mtype))
 
-        om_samples = {}  # type: Dict[str, List[str]]
+        om_samples: Dict[str, List[str]] = {}
         for s in metric.samples:
             for suffix in ["_created", "_gsum", "_gcount"]:
                 if s.name == metric.name + suffix:
diff --git a/synapse/metrics/background_process_metrics.py b/synapse/metrics/background_process_metrics.py
index de96ca0821..4455fa71a8 100644
--- a/synapse/metrics/background_process_metrics.py
+++ b/synapse/metrics/background_process_metrics.py
@@ -93,7 +93,7 @@ _background_process_db_sched_duration = Counter(
 # map from description to a counter, so that we can name our logcontexts
 # incrementally. (It actually duplicates _background_process_start_count, but
 # it's much simpler to do so than to try to combine them.)
-_background_process_counts = {}  # type: Dict[str, int]
+_background_process_counts: Dict[str, int] = {}
 
 # Set of all running background processes that became active active since the
 # last time metrics were scraped (i.e. background processes that performed some
@@ -103,7 +103,7 @@ _background_process_counts = {}  # type: Dict[str, int]
 # background processes stacking up behind a lock or linearizer, where we then
 # only need to iterate over and update metrics for the process that have
 # actually been active and can ignore the idle ones.
-_background_processes_active_since_last_scrape = set()  # type: Set[_BackgroundProcess]
+_background_processes_active_since_last_scrape: "Set[_BackgroundProcess]" = set()
 
 # A lock that covers the above set and dict
 _bg_metrics_lock = threading.Lock()
diff --git a/synapse/module_api/__init__.py b/synapse/module_api/__init__.py
index 721c45abac..308f045700 100644
--- a/synapse/module_api/__init__.py
+++ b/synapse/module_api/__init__.py
@@ -54,7 +54,7 @@ class ModuleApi:
         self._state = hs.get_state_handler()
 
         # We expose these as properties below in order to attach a helpful docstring.
-        self._http_client = hs.get_simple_http_client()  # type: SimpleHttpClient
+        self._http_client: SimpleHttpClient = hs.get_simple_http_client()
         self._public_room_list_manager = PublicRoomListManager(hs)
 
         self._spam_checker = hs.get_spam_checker()
diff --git a/synapse/notifier.py b/synapse/notifier.py
index 3c3cc47631..c5fbebc17d 100644
--- a/synapse/notifier.py
+++ b/synapse/notifier.py
@@ -203,21 +203,21 @@ class Notifier:
     UNUSED_STREAM_EXPIRY_MS = 10 * 60 * 1000
 
     def __init__(self, hs: "synapse.server.HomeServer"):
-        self.user_to_user_stream = {}  # type: Dict[str, _NotifierUserStream]
-        self.room_to_user_streams = {}  # type: Dict[str, Set[_NotifierUserStream]]
+        self.user_to_user_stream: Dict[str, _NotifierUserStream] = {}
+        self.room_to_user_streams: Dict[str, Set[_NotifierUserStream]] = {}
 
         self.hs = hs
         self.storage = hs.get_storage()
         self.event_sources = hs.get_event_sources()
         self.store = hs.get_datastore()
-        self.pending_new_room_events = []  # type: List[_PendingRoomEventEntry]
+        self.pending_new_room_events: List[_PendingRoomEventEntry] = []
 
         # Called when there are new things to stream over replication
-        self.replication_callbacks = []  # type: List[Callable[[], None]]
+        self.replication_callbacks: List[Callable[[], None]] = []
 
         # Called when remote servers have come back online after having been
         # down.
-        self.remote_server_up_callbacks = []  # type: List[Callable[[str], None]]
+        self.remote_server_up_callbacks: List[Callable[[str], None]] = []
 
         self.clock = hs.get_clock()
         self.appservice_handler = hs.get_application_service_handler()
@@ -237,7 +237,7 @@ class Notifier:
         # when rendering the metrics page, which is likely once per minute at
         # most when scraping it.
         def count_listeners():
-            all_user_streams = set()  # type: Set[_NotifierUserStream]
+            all_user_streams: Set[_NotifierUserStream] = set()
 
             for streams in list(self.room_to_user_streams.values()):
                 all_user_streams |= streams
@@ -329,8 +329,8 @@ class Notifier:
         pending = self.pending_new_room_events
         self.pending_new_room_events = []
 
-        users = set()  # type: Set[UserID]
-        rooms = set()  # type: Set[str]
+        users: Set[UserID] = set()
+        rooms: Set[str] = set()
 
         for entry in pending:
             if entry.event_pos.persisted_after(max_room_stream_token):
@@ -580,7 +580,7 @@ class Notifier:
             if after_token == before_token:
                 return EventStreamResult([], (from_token, from_token))
 
-            events = []  # type: List[EventBase]
+            events: List[EventBase] = []
             end_token = from_token
 
             for name, source in self.event_sources.sources.items():
diff --git a/synapse/push/bulk_push_rule_evaluator.py b/synapse/push/bulk_push_rule_evaluator.py
index 669ea462e2..c337e530d3 100644
--- a/synapse/push/bulk_push_rule_evaluator.py
+++ b/synapse/push/bulk_push_rule_evaluator.py
@@ -194,7 +194,7 @@ class BulkPushRuleEvaluator:
         count_as_unread = _should_count_as_unread(event, context)
 
         rules_by_user = await self._get_rules_for_event(event, context)
-        actions_by_user = {}  # type: Dict[str, List[Union[dict, str]]]
+        actions_by_user: Dict[str, List[Union[dict, str]]] = {}
 
         room_members = await self.store.get_joined_users_from_context(event, context)
 
@@ -207,7 +207,7 @@ class BulkPushRuleEvaluator:
             event, len(room_members), sender_power_level, power_levels
         )
 
-        condition_cache = {}  # type: Dict[str, bool]
+        condition_cache: Dict[str, bool] = {}
 
         # If the event is not a state event check if any users ignore the sender.
         if not event.is_state():
diff --git a/synapse/push/clientformat.py b/synapse/push/clientformat.py
index 2ee0ccd58a..1fc9716a34 100644
--- a/synapse/push/clientformat.py
+++ b/synapse/push/clientformat.py
@@ -26,10 +26,10 @@ def format_push_rules_for_user(user: UserID, ruleslist) -> Dict[str, Dict[str, l
     # We're going to be mutating this a lot, so do a deep copy
     ruleslist = copy.deepcopy(ruleslist)
 
-    rules = {
+    rules: Dict[str, Dict[str, List[Dict[str, Any]]]] = {
         "global": {},
         "device": {},
-    }  # type: Dict[str, Dict[str, List[Dict[str, Any]]]]
+    }
 
     rules["global"] = _add_empty_priority_class_arrays(rules["global"])
 
diff --git a/synapse/push/emailpusher.py b/synapse/push/emailpusher.py
index 99a18874d1..e08e125cb8 100644
--- a/synapse/push/emailpusher.py
+++ b/synapse/push/emailpusher.py
@@ -66,8 +66,8 @@ class EmailPusher(Pusher):
 
         self.store = self.hs.get_datastore()
         self.email = pusher_config.pushkey
-        self.timed_call = None  # type: Optional[IDelayedCall]
-        self.throttle_params = {}  # type: Dict[str, ThrottleParams]
+        self.timed_call: Optional[IDelayedCall] = None
+        self.throttle_params: Dict[str, ThrottleParams] = {}
         self._inited = False
 
         self._is_processing = False
@@ -168,7 +168,7 @@ class EmailPusher(Pusher):
             )
         )
 
-        soonest_due_at = None  # type: Optional[int]
+        soonest_due_at: Optional[int] = None
 
         if not unprocessed:
             await self.save_last_stream_ordering_and_success(self.max_stream_ordering)
diff --git a/synapse/push/httppusher.py b/synapse/push/httppusher.py
index 06bf5f8ada..36aabd8422 100644
--- a/synapse/push/httppusher.py
+++ b/synapse/push/httppusher.py
@@ -71,7 +71,7 @@ class HttpPusher(Pusher):
         self.data = pusher_config.data
         self.backoff_delay = HttpPusher.INITIAL_BACKOFF_SEC
         self.failing_since = pusher_config.failing_since
-        self.timed_call = None  # type: Optional[IDelayedCall]
+        self.timed_call: Optional[IDelayedCall] = None
         self._is_processing = False
         self._group_unread_count_by_room = hs.config.push_group_unread_count_by_room
         self._pusherpool = hs.get_pusherpool()
diff --git a/synapse/push/mailer.py b/synapse/push/mailer.py
index 5f9ea5003a..7be5fe1e9b 100644
--- a/synapse/push/mailer.py
+++ b/synapse/push/mailer.py
@@ -110,7 +110,7 @@ class Mailer:
         self.state_handler = self.hs.get_state_handler()
         self.storage = hs.get_storage()
         self.app_name = app_name
-        self.email_subjects = hs.config.email_subjects  # type: EmailSubjectConfig
+        self.email_subjects: EmailSubjectConfig = hs.config.email_subjects
 
         logger.info("Created Mailer for app_name %s" % app_name)
 
@@ -230,7 +230,7 @@ class Mailer:
             [pa["event_id"] for pa in push_actions]
         )
 
-        notifs_by_room = {}  # type: Dict[str, List[Dict[str, Any]]]
+        notifs_by_room: Dict[str, List[Dict[str, Any]]] = {}
         for pa in push_actions:
             notifs_by_room.setdefault(pa["room_id"], []).append(pa)
 
@@ -356,13 +356,13 @@ class Mailer:
 
         room_name = await calculate_room_name(self.store, room_state_ids, user_id)
 
-        room_vars = {
+        room_vars: Dict[str, Any] = {
             "title": room_name,
             "hash": string_ordinal_total(room_id),  # See sender avatar hash
             "notifs": [],
             "invite": is_invite,
             "link": self._make_room_link(room_id),
-        }  # type: Dict[str, Any]
+        }
 
         if not is_invite:
             for n in notifs:
@@ -460,9 +460,9 @@ class Mailer:
         type_state_key = ("m.room.member", event.sender)
         sender_state_event_id = room_state_ids.get(type_state_key)
         if sender_state_event_id:
-            sender_state_event = await self.store.get_event(
+            sender_state_event: Optional[EventBase] = await self.store.get_event(
                 sender_state_event_id
-            )  # type: Optional[EventBase]
+            )
         else:
             # Attempt to check the historical state for the room.
             historical_state = await self.state_store.get_state_for_event(
diff --git a/synapse/push/presentable_names.py b/synapse/push/presentable_names.py
index 412941393f..0510c1cbd5 100644
--- a/synapse/push/presentable_names.py
+++ b/synapse/push/presentable_names.py
@@ -199,7 +199,7 @@ def name_from_member_event(member_event: EventBase) -> str:
 
 
 def _state_as_two_level_dict(state: StateMap[str]) -> Dict[str, Dict[str, str]]:
-    ret = {}  # type: Dict[str, Dict[str, str]]
+    ret: Dict[str, Dict[str, str]] = {}
     for k, v in state.items():
         ret.setdefault(k[0], {})[k[1]] = v
     return ret
diff --git a/synapse/push/push_rule_evaluator.py b/synapse/push/push_rule_evaluator.py
index 98b90a4f51..7a8dc63976 100644
--- a/synapse/push/push_rule_evaluator.py
+++ b/synapse/push/push_rule_evaluator.py
@@ -195,9 +195,9 @@ class PushRuleEvaluatorForEvent:
 
 
 # Caches (string, is_glob, word_boundary) -> regex for push. See _glob_matches
-regex_cache = LruCache(
+regex_cache: LruCache[Tuple[str, bool, bool], Pattern] = LruCache(
     50000, "regex_push_cache"
-)  # type: LruCache[Tuple[str, bool, bool], Pattern]
+)
 
 
 def _glob_matches(glob: str, value: str, word_boundary: bool = False) -> bool:
diff --git a/synapse/push/pusher.py b/synapse/push/pusher.py
index c51938b8cf..021275437c 100644
--- a/synapse/push/pusher.py
+++ b/synapse/push/pusher.py
@@ -31,13 +31,13 @@ class PusherFactory:
         self.hs = hs
         self.config = hs.config
 
-        self.pusher_types = {
+        self.pusher_types: Dict[str, Callable[[HomeServer, PusherConfig], Pusher]] = {
             "http": HttpPusher
-        }  # type: Dict[str, Callable[[HomeServer, PusherConfig], Pusher]]
+        }
 
         logger.info("email enable notifs: %r", hs.config.email_enable_notifs)
         if hs.config.email_enable_notifs:
-            self.mailers = {}  # type: Dict[str, Mailer]
+            self.mailers: Dict[str, Mailer] = {}
 
             self._notif_template_html = hs.config.email_notif_template_html
             self._notif_template_text = hs.config.email_notif_template_text
diff --git a/synapse/push/pusherpool.py b/synapse/push/pusherpool.py
index 579fcdf472..2519ad76db 100644
--- a/synapse/push/pusherpool.py
+++ b/synapse/push/pusherpool.py
@@ -87,7 +87,7 @@ class PusherPool:
         self._last_room_stream_id_seen = self.store.get_room_max_stream_ordering()
 
         # map from user id to app_id:pushkey to pusher
-        self.pushers = {}  # type: Dict[str, Dict[str, Pusher]]
+        self.pushers: Dict[str, Dict[str, Pusher]] = {}
 
     def start(self) -> None:
         """Starts the pushers off in a background process."""
diff --git a/synapse/python_dependencies.py b/synapse/python_dependencies.py
index 271c17c226..cdcbdd772b 100644
--- a/synapse/python_dependencies.py
+++ b/synapse/python_dependencies.py
@@ -115,7 +115,7 @@ CONDITIONAL_REQUIREMENTS = {
     "cache_memory": ["pympler"],
 }
 
-ALL_OPTIONAL_REQUIREMENTS = set()  # type: Set[str]
+ALL_OPTIONAL_REQUIREMENTS: Set[str] = set()
 
 for name, optional_deps in CONDITIONAL_REQUIREMENTS.items():
     # Exclude systemd as it's a system-based requirement.
@@ -193,7 +193,7 @@ def check_requirements(for_feature=None):
     if not for_feature:
         # Check the optional dependencies are up to date. We allow them to not be
         # installed.
-        OPTS = sum(CONDITIONAL_REQUIREMENTS.values(), [])  # type: List[str]
+        OPTS: List[str] = sum(CONDITIONAL_REQUIREMENTS.values(), [])
 
         for dependency in OPTS:
             try:
diff --git a/synapse/replication/http/_base.py b/synapse/replication/http/_base.py
index f13a7c23b4..25589b0042 100644
--- a/synapse/replication/http/_base.py
+++ b/synapse/replication/http/_base.py
@@ -85,17 +85,17 @@ class ReplicationEndpoint(metaclass=abc.ABCMeta):
             is received.
     """
 
-    NAME = abc.abstractproperty()  # type: str  # type: ignore
-    PATH_ARGS = abc.abstractproperty()  # type: Tuple[str, ...]  # type: ignore
+    NAME: str = abc.abstractproperty()  # type: ignore
+    PATH_ARGS: Tuple[str, ...] = abc.abstractproperty()  # type: ignore
     METHOD = "POST"
     CACHE = True
     RETRY_ON_TIMEOUT = True
 
     def __init__(self, hs: "HomeServer"):
         if self.CACHE:
-            self.response_cache = ResponseCache(
+            self.response_cache: ResponseCache[str] = ResponseCache(
                 hs.get_clock(), "repl." + self.NAME, timeout_ms=30 * 60 * 1000
-            )  # type: ResponseCache[str]
+            )
 
         # We reserve `instance_name` as a parameter to sending requests, so we
         # assert here that sub classes don't try and use the name.
@@ -232,7 +232,7 @@ class ReplicationEndpoint(metaclass=abc.ABCMeta):
                 # have a good idea that the request has either succeeded or failed on
                 # the master, and so whether we should clean up or not.
                 while True:
-                    headers = {}  # type: Dict[bytes, List[bytes]]
+                    headers: Dict[bytes, List[bytes]] = {}
                     # Add an authorization header, if configured.
                     if replication_secret:
                         headers[b"Authorization"] = [b"Bearer " + replication_secret]
diff --git a/synapse/replication/slave/storage/_base.py b/synapse/replication/slave/storage/_base.py
index faa99387a7..e460dd85cd 100644
--- a/synapse/replication/slave/storage/_base.py
+++ b/synapse/replication/slave/storage/_base.py
@@ -27,7 +27,9 @@ class BaseSlavedStore(CacheInvalidationWorkerStore):
     def __init__(self, database: DatabasePool, db_conn, hs):
         super().__init__(database, db_conn, hs)
         if isinstance(self.database_engine, PostgresEngine):
-            self._cache_id_gen = MultiWriterIdGenerator(
+            self._cache_id_gen: Optional[
+                MultiWriterIdGenerator
+            ] = MultiWriterIdGenerator(
                 db_conn,
                 database,
                 stream_name="caches",
@@ -41,7 +43,7 @@ class BaseSlavedStore(CacheInvalidationWorkerStore):
                 ],
                 sequence_name="cache_invalidation_stream_seq",
                 writers=[],
-            )  # type: Optional[MultiWriterIdGenerator]
+            )
         else:
             self._cache_id_gen = None
 
diff --git a/synapse/replication/slave/storage/client_ips.py b/synapse/replication/slave/storage/client_ips.py
index 13ed87adc4..436d39c320 100644
--- a/synapse/replication/slave/storage/client_ips.py
+++ b/synapse/replication/slave/storage/client_ips.py
@@ -23,9 +23,9 @@ class SlavedClientIpStore(BaseSlavedStore):
     def __init__(self, database: DatabasePool, db_conn, hs):
         super().__init__(database, db_conn, hs)
 
-        self.client_ip_last_seen = LruCache(
+        self.client_ip_last_seen: LruCache[tuple, int] = LruCache(
             cache_name="client_ip_last_seen", max_size=50000
-        )  # type: LruCache[tuple, int]
+        )
 
     async def insert_client_ip(self, user_id, access_token, ip, user_agent, device_id):
         now = int(self._clock.time_msec())
diff --git a/synapse/replication/tcp/client.py b/synapse/replication/tcp/client.py
index 62d7809175..9d4859798b 100644
--- a/synapse/replication/tcp/client.py
+++ b/synapse/replication/tcp/client.py
@@ -121,13 +121,13 @@ class ReplicationDataHandler:
         self._pusher_pool = hs.get_pusherpool()
         self._presence_handler = hs.get_presence_handler()
 
-        self.send_handler = None  # type: Optional[FederationSenderHandler]
+        self.send_handler: Optional[FederationSenderHandler] = None
         if hs.should_send_federation():
             self.send_handler = FederationSenderHandler(hs)
 
         # Map from stream to list of deferreds waiting for the stream to
         # arrive at a particular position. The lists are sorted by stream position.
-        self._streams_to_waiters = {}  # type: Dict[str, List[Tuple[int, Deferred]]]
+        self._streams_to_waiters: Dict[str, List[Tuple[int, Deferred]]] = {}
 
     async def on_rdata(
         self, stream_name: str, instance_name: str, token: int, rows: list
@@ -173,7 +173,7 @@ class ReplicationDataHandler:
             if entities:
                 self.notifier.on_new_event("to_device_key", token, users=entities)
         elif stream_name == DeviceListsStream.NAME:
-            all_room_ids = set()  # type: Set[str]
+            all_room_ids: Set[str] = set()
             for row in rows:
                 if row.entity.startswith("@"):
                     room_ids = await self.store.get_rooms_for_user(row.entity)
@@ -201,7 +201,7 @@ class ReplicationDataHandler:
                 if row.data.rejected:
                     continue
 
-                extra_users = ()  # type: Tuple[UserID, ...]
+                extra_users: Tuple[UserID, ...] = ()
                 if row.data.type == EventTypes.Member and row.data.state_key:
                     extra_users = (UserID.from_string(row.data.state_key),)
 
@@ -348,7 +348,7 @@ class FederationSenderHandler:
 
         # Stores the latest position in the federation stream we've gotten up
         # to. This is always set before we use it.
-        self.federation_position = None  # type: Optional[int]
+        self.federation_position: Optional[int] = None
 
         self._fed_position_linearizer = Linearizer(name="_fed_position_linearizer")
 
diff --git a/synapse/replication/tcp/commands.py b/synapse/replication/tcp/commands.py
index 505d450e19..1311b013da 100644
--- a/synapse/replication/tcp/commands.py
+++ b/synapse/replication/tcp/commands.py
@@ -34,7 +34,7 @@ class Command(metaclass=abc.ABCMeta):
     A full command line on the wire is constructed from `NAME + " " + to_line()`
     """
 
-    NAME = None  # type: str
+    NAME: str
 
     @classmethod
     @abc.abstractmethod
@@ -380,7 +380,7 @@ class RemoteServerUpCommand(_SimpleCommand):
     NAME = "REMOTE_SERVER_UP"
 
 
-_COMMANDS = (
+_COMMANDS: Tuple[Type[Command], ...] = (
     ServerCommand,
     RdataCommand,
     PositionCommand,
@@ -393,7 +393,7 @@ _COMMANDS = (
     UserIpCommand,
     RemoteServerUpCommand,
     ClearUserSyncsCommand,
-)  # type: Tuple[Type[Command], ...]
+)
 
 # Map of command name to command type.
 COMMAND_MAP = {cmd.NAME: cmd for cmd in _COMMANDS}
diff --git a/synapse/replication/tcp/handler.py b/synapse/replication/tcp/handler.py
index 2ad7a200bb..eae4515363 100644
--- a/synapse/replication/tcp/handler.py
+++ b/synapse/replication/tcp/handler.py
@@ -105,12 +105,12 @@ class ReplicationCommandHandler:
             hs.get_instance_name() in hs.config.worker.writers.presence
         )
 
-        self._streams = {
+        self._streams: Dict[str, Stream] = {
             stream.NAME: stream(hs) for stream in STREAMS_MAP.values()
-        }  # type: Dict[str, Stream]
+        }
 
         # List of streams that this instance is the source of
-        self._streams_to_replicate = []  # type: List[Stream]
+        self._streams_to_replicate: List[Stream] = []
 
         for stream in self._streams.values():
             if hs.config.redis.redis_enabled and stream.NAME == CachesStream.NAME:
@@ -180,14 +180,14 @@ class ReplicationCommandHandler:
 
         # Map of stream name to batched updates. See RdataCommand for info on
         # how batching works.
-        self._pending_batches = {}  # type: Dict[str, List[Any]]
+        self._pending_batches: Dict[str, List[Any]] = {}
 
         # The factory used to create connections.
-        self._factory = None  # type: Optional[ReconnectingClientFactory]
+        self._factory: Optional[ReconnectingClientFactory] = None
 
         # The currently connected connections. (The list of places we need to send
         # outgoing replication commands to.)
-        self._connections = []  # type: List[IReplicationConnection]
+        self._connections: List[IReplicationConnection] = []
 
         LaterGauge(
             "synapse_replication_tcp_resource_total_connections",
@@ -200,7 +200,7 @@ class ReplicationCommandHandler:
         # them in order in a separate background process.
 
         # the streams which are currently being processed by _unsafe_process_queue
-        self._processing_streams = set()  # type: Set[str]
+        self._processing_streams: Set[str] = set()
 
         # for each stream, a queue of commands that are awaiting processing, and the
         # connection that they arrived on.
@@ -210,7 +210,7 @@ class ReplicationCommandHandler:
 
         # For each connection, the incoming stream names that have received a POSITION
         # from that connection.
-        self._streams_by_connection = {}  # type: Dict[IReplicationConnection, Set[str]]
+        self._streams_by_connection: Dict[IReplicationConnection, Set[str]] = {}
 
         LaterGauge(
             "synapse_replication_tcp_command_queue",
diff --git a/synapse/replication/tcp/protocol.py b/synapse/replication/tcp/protocol.py
index 6e3705364f..8c80153ab6 100644
--- a/synapse/replication/tcp/protocol.py
+++ b/synapse/replication/tcp/protocol.py
@@ -102,7 +102,7 @@ tcp_outbound_commands_counter = Counter(
 
 # A list of all connected protocols. This allows us to send metrics about the
 # connections.
-connected_connections = []  # type: List[BaseReplicationStreamProtocol]
+connected_connections: "List[BaseReplicationStreamProtocol]" = []
 
 
 logger = logging.getLogger(__name__)
@@ -146,15 +146,15 @@ class BaseReplicationStreamProtocol(LineOnlyReceiver):
 
     # The transport is going to be an ITCPTransport, but that doesn't have the
     # (un)registerProducer methods, those are only on the implementation.
-    transport = None  # type: Connection
+    transport: Connection
 
     delimiter = b"\n"
 
     # Valid commands we expect to receive
-    VALID_INBOUND_COMMANDS = []  # type: Collection[str]
+    VALID_INBOUND_COMMANDS: Collection[str] = []
 
     # Valid commands we can send
-    VALID_OUTBOUND_COMMANDS = []  # type: Collection[str]
+    VALID_OUTBOUND_COMMANDS: Collection[str] = []
 
     max_line_buffer = 10000
 
@@ -165,7 +165,7 @@ class BaseReplicationStreamProtocol(LineOnlyReceiver):
         self.last_received_command = self.clock.time_msec()
         self.last_sent_command = 0
         # When we requested the connection be closed
-        self.time_we_closed = None  # type: Optional[int]
+        self.time_we_closed: Optional[int] = None
 
         self.received_ping = False  # Have we received a ping from the other side
 
@@ -175,10 +175,10 @@ class BaseReplicationStreamProtocol(LineOnlyReceiver):
         self.conn_id = random_string(5)  # To dedupe in case of name clashes.
 
         # List of pending commands to send once we've established the connection
-        self.pending_commands = []  # type: List[Command]
+        self.pending_commands: List[Command] = []
 
         # The LoopingCall for sending pings.
-        self._send_ping_loop = None  # type: Optional[task.LoopingCall]
+        self._send_ping_loop: Optional[task.LoopingCall] = None
 
         # a logcontext which we use for processing incoming commands. We declare it as a
         # background process so that the CPU stats get reported to prometheus.
diff --git a/synapse/replication/tcp/redis.py b/synapse/replication/tcp/redis.py
index 6a2c2655e4..8c0df627c8 100644
--- a/synapse/replication/tcp/redis.py
+++ b/synapse/replication/tcp/redis.py
@@ -57,7 +57,7 @@ class ConstantProperty(Generic[T, V]):
     it.
     """
 
-    constant = attr.ib()  # type: V
+    constant: V = attr.ib()
 
     def __get__(self, obj: Optional[T], objtype: Optional[Type[T]] = None) -> V:
         return self.constant
@@ -91,9 +91,9 @@ class RedisSubscriber(txredisapi.SubscriberProtocol):
             commands.
     """
 
-    synapse_handler = None  # type: ReplicationCommandHandler
-    synapse_stream_name = None  # type: str
-    synapse_outbound_redis_connection = None  # type: txredisapi.RedisProtocol
+    synapse_handler: "ReplicationCommandHandler"
+    synapse_stream_name: str
+    synapse_outbound_redis_connection: txredisapi.RedisProtocol
 
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
diff --git a/synapse/replication/tcp/streams/_base.py b/synapse/replication/tcp/streams/_base.py
index b03824925a..3716c41bea 100644
--- a/synapse/replication/tcp/streams/_base.py
+++ b/synapse/replication/tcp/streams/_base.py
@@ -85,9 +85,9 @@ class Stream:
     time it was called.
     """
 
-    NAME = None  # type: str  # The name of the stream
+    NAME: str  # The name of the stream
     # The type of the row. Used by the default impl of parse_row.
-    ROW_TYPE = None  # type: Any
+    ROW_TYPE: Any = None
 
     @classmethod
     def parse_row(cls, row: StreamRow):
@@ -283,9 +283,7 @@ class PresenceStream(Stream):
 
             assert isinstance(presence_handler, PresenceHandler)
 
-            update_function = (
-                presence_handler.get_all_presence_updates
-            )  # type: UpdateFunction
+            update_function: UpdateFunction = presence_handler.get_all_presence_updates
         else:
             # Query presence writer process
             update_function = make_http_update_function(hs, self.NAME)
@@ -334,9 +332,9 @@ class TypingStream(Stream):
         if writer_instance == hs.get_instance_name():
             # On the writer, query the typing handler
             typing_writer_handler = hs.get_typing_writer_handler()
-            update_function = (
-                typing_writer_handler.get_all_typing_updates
-            )  # type: Callable[[str, int, int, int], Awaitable[Tuple[List[Tuple[int, Any]], int, bool]]]
+            update_function: Callable[
+                [str, int, int, int], Awaitable[Tuple[List[Tuple[int, Any]], int, bool]]
+            ] = typing_writer_handler.get_all_typing_updates
             current_token_function = typing_writer_handler.get_current_token
         else:
             # Query the typing writer process
diff --git a/synapse/replication/tcp/streams/events.py b/synapse/replication/tcp/streams/events.py
index e7e87bac92..a030e9299e 100644
--- a/synapse/replication/tcp/streams/events.py
+++ b/synapse/replication/tcp/streams/events.py
@@ -65,7 +65,7 @@ class BaseEventsStreamRow:
     """
 
     # Unique string that ids the type. Must be overridden in sub classes.
-    TypeId = None  # type: str
+    TypeId: str
 
     @classmethod
     def from_data(cls, data):
@@ -103,10 +103,10 @@ class EventsStreamCurrentStateRow(BaseEventsStreamRow):
     event_id = attr.ib()  # str, optional
 
 
-_EventRows = (
+_EventRows: Tuple[Type[BaseEventsStreamRow], ...] = (
     EventsStreamEventRow,
     EventsStreamCurrentStateRow,
-)  # type: Tuple[Type[BaseEventsStreamRow], ...]
+)
 
 TypeToRow = {Row.TypeId: Row for Row in _EventRows}
 
@@ -157,9 +157,9 @@ class EventsStream(Stream):
 
         # now we fetch up to that many rows from the events table
 
-        event_rows = await self._store.get_all_new_forward_event_rows(
+        event_rows: List[Tuple] = await self._store.get_all_new_forward_event_rows(
             instance_name, from_token, current_token, target_row_count
-        )  # type: List[Tuple]
+        )
 
         # we rely on get_all_new_forward_event_rows strictly honouring the limit, so
         # that we know it is safe to just take upper_limit = event_rows[-1][0].
@@ -172,7 +172,7 @@ class EventsStream(Stream):
 
         if len(event_rows) == target_row_count:
             limited = True
-            upper_limit = event_rows[-1][0]  # type: int
+            upper_limit: int = event_rows[-1][0]
         else:
             limited = False
             upper_limit = current_token
@@ -191,30 +191,30 @@ class EventsStream(Stream):
         # finally, fetch the ex-outliers rows. We assume there are few enough of these
         # not to bother with the limit.
 
-        ex_outliers_rows = await self._store.get_ex_outlier_stream_rows(
+        ex_outliers_rows: List[Tuple] = await self._store.get_ex_outlier_stream_rows(
             instance_name, from_token, upper_limit
-        )  # type: List[Tuple]
+        )
 
         # we now need to turn the raw database rows returned into tuples suitable
         # for the replication protocol (basically, we add an identifier to
         # distinguish the row type). At the same time, we can limit the event_rows
         # to the max stream_id from state_rows.
 
-        event_updates = (
+        event_updates: Iterable[Tuple[int, Tuple]] = (
             (stream_id, (EventsStreamEventRow.TypeId, rest))
             for (stream_id, *rest) in event_rows
             if stream_id <= upper_limit
-        )  # type: Iterable[Tuple[int, Tuple]]
+        )
 
-        state_updates = (
+        state_updates: Iterable[Tuple[int, Tuple]] = (
             (stream_id, (EventsStreamCurrentStateRow.TypeId, rest))
             for (stream_id, *rest) in state_rows
-        )  # type: Iterable[Tuple[int, Tuple]]
+        )
 
-        ex_outliers_updates = (
+        ex_outliers_updates: Iterable[Tuple[int, Tuple]] = (
             (stream_id, (EventsStreamEventRow.TypeId, rest))
             for (stream_id, *rest) in ex_outliers_rows
-        )  # type: Iterable[Tuple[int, Tuple]]
+        )
 
         # we need to return a sorted list, so merge them together.
         updates = list(heapq.merge(event_updates, state_updates, ex_outliers_updates))
diff --git a/synapse/replication/tcp/streams/federation.py b/synapse/replication/tcp/streams/federation.py
index 096a85d363..c445af9bd9 100644
--- a/synapse/replication/tcp/streams/federation.py
+++ b/synapse/replication/tcp/streams/federation.py
@@ -51,9 +51,9 @@ class FederationStream(Stream):
             current_token = current_token_without_instance(
                 federation_sender.get_current_token
             )
-            update_function = (
-                federation_sender.get_replication_rows
-            )  # type: Callable[[str, int, int, int], Awaitable[Tuple[List[Tuple[int, Any]], int, bool]]]
+            update_function: Callable[
+                [str, int, int, int], Awaitable[Tuple[List[Tuple[int, Any]], int, bool]]
+            ] = federation_sender.get_replication_rows
 
         elif hs.should_send_federation():
             # federation sender: Query master process
diff --git a/synapse/rest/admin/rooms.py b/synapse/rest/admin/rooms.py
index f0cddd2d2c..3c51a742bf 100644
--- a/synapse/rest/admin/rooms.py
+++ b/synapse/rest/admin/rooms.py
@@ -462,6 +462,7 @@ class MakeRoomAdminRestServlet(ResolveRoomIdMixin, RestServlet):
         super().__init__(hs)
         self.hs = hs
         self.auth = hs.get_auth()
+        self.store = hs.get_datastore()
         self.event_creation_handler = hs.get_event_creation_handler()
         self.state_handler = hs.get_state_handler()
         self.is_mine_id = hs.is_mine_id
@@ -500,7 +501,13 @@ class MakeRoomAdminRestServlet(ResolveRoomIdMixin, RestServlet):
             admin_user_id = None
 
             for admin_user in reversed(admin_users):
-                if room_state.get((EventTypes.Member, admin_user)):
+                (
+                    current_membership_type,
+                    _,
+                ) = await self.store.get_local_current_membership_for_user_in_room(
+                    admin_user, room_id
+                )
+                if current_membership_type == "join":
                     admin_user_id = admin_user
                     break
 
diff --git a/synapse/rest/client/v1/room.py b/synapse/rest/client/v1/room.py
index 92ebe838fd..ebf4e32230 100644
--- a/synapse/rest/client/v1/room.py
+++ b/synapse/rest/client/v1/room.py
@@ -29,6 +29,7 @@ from synapse.api.errors import (
     SynapseError,
 )
 from synapse.api.filtering import Filter
+from synapse.appservice import ApplicationService
 from synapse.events.utils import format_event_for_client_v2
 from synapse.http.servlet import (
     RestServlet,
@@ -47,11 +48,13 @@ from synapse.storage.state import StateFilter
 from synapse.streams.config import PaginationConfig
 from synapse.types import (
     JsonDict,
+    Requester,
     RoomAlias,
     RoomID,
     StreamToken,
     ThirdPartyInstanceID,
     UserID,
+    create_requester,
 )
 from synapse.util import json_decoder
 from synapse.util.stringutils import parse_and_validate_server_name, random_string
@@ -309,7 +312,7 @@ class RoomBatchSendEventRestServlet(TransactionRestServlet):
         self.room_member_handler = hs.get_room_member_handler()
         self.auth = hs.get_auth()
 
-    async def inherit_depth_from_prev_ids(self, prev_event_ids) -> int:
+    async def _inherit_depth_from_prev_ids(self, prev_event_ids) -> int:
         (
             most_recent_prev_event_id,
             most_recent_prev_event_depth,
@@ -349,6 +352,54 @@ class RoomBatchSendEventRestServlet(TransactionRestServlet):
 
         return depth
 
+    def _create_insertion_event_dict(
+        self, sender: str, room_id: str, origin_server_ts: int
+    ):
+        """Creates an event dict for an "insertion" event with the proper fields
+        and a random chunk ID.
+
+        Args:
+            sender: The event author MXID
+            room_id: The room ID that the event belongs to
+            origin_server_ts: Timestamp when the event was sent
+
+        Returns:
+            Tuple of event ID and stream ordering position
+        """
+
+        next_chunk_id = random_string(8)
+        insertion_event = {
+            "type": EventTypes.MSC2716_INSERTION,
+            "sender": sender,
+            "room_id": room_id,
+            "content": {
+                EventContentFields.MSC2716_NEXT_CHUNK_ID: next_chunk_id,
+                EventContentFields.MSC2716_HISTORICAL: True,
+            },
+            "origin_server_ts": origin_server_ts,
+        }
+
+        return insertion_event
+
+    async def _create_requester_for_user_id_from_app_service(
+        self, user_id: str, app_service: ApplicationService
+    ) -> Requester:
+        """Creates a new requester for the given user_id
+        and validates that the app service is allowed to control
+        the given user.
+
+        Args:
+            user_id: The author MXID that the app service is controlling
+            app_service: The app service that controls the user
+
+        Returns:
+            Requester object
+        """
+
+        await self.auth.validate_appservice_can_control_user_id(app_service, user_id)
+
+        return create_requester(user_id, app_service=app_service)
+
     async def on_POST(self, request, room_id):
         requester = await self.auth.get_user_by_req(request, allow_guest=False)
 
@@ -414,7 +465,9 @@ class RoomBatchSendEventRestServlet(TransactionRestServlet):
             if event_dict["type"] == EventTypes.Member:
                 membership = event_dict["content"].get("membership", None)
                 event_id, _ = await self.room_member_handler.update_membership(
-                    requester,
+                    await self._create_requester_for_user_id_from_app_service(
+                        state_event["sender"], requester.app_service
+                    ),
                     target=UserID.from_string(event_dict["state_key"]),
                     room_id=room_id,
                     action=membership,
@@ -434,7 +487,9 @@ class RoomBatchSendEventRestServlet(TransactionRestServlet):
                     event,
                     _,
                 ) = await self.event_creation_handler.create_and_send_nonmember_event(
-                    requester,
+                    await self._create_requester_for_user_id_from_app_service(
+                        state_event["sender"], requester.app_service
+                    ),
                     event_dict,
                     outlier=True,
                     prev_event_ids=[fake_prev_event_id],
@@ -449,37 +504,73 @@ class RoomBatchSendEventRestServlet(TransactionRestServlet):
 
         events_to_create = body["events"]
 
-        # If provided, connect the chunk to the last insertion point
-        # The chunk ID passed in comes from the chunk_id in the
-        # "insertion" event from the previous chunk.
+        prev_event_ids = prev_events_from_query
+        inherited_depth = await self._inherit_depth_from_prev_ids(
+            prev_events_from_query
+        )
+
+        # Figure out which chunk to connect to. If they passed in
+        # chunk_id_from_query let's use it. The chunk ID passed in comes
+        # from the chunk_id in the "insertion" event from the previous chunk.
+        last_event_in_chunk = events_to_create[-1]
+        chunk_id_to_connect_to = chunk_id_from_query
+        base_insertion_event = None
         if chunk_id_from_query:
-            last_event_in_chunk = events_to_create[-1]
-            last_event_in_chunk["content"][
-                EventContentFields.MSC2716_CHUNK_ID
-            ] = chunk_id_from_query
+            # TODO: Verify the chunk_id_from_query corresponds to an insertion event
+            pass
+        # Otherwise, create an insertion event to act as a starting point.
+        #
+        # We don't always have an insertion event to start hanging more history
+        # off of (ideally there would be one in the main DAG, but that's not the
+        # case if we're wanting to add history to e.g. existing rooms without
+        # an insertion event), in which case we just create a new insertion event
+        # that can then get pointed to by a "marker" event later.
+        else:
+            base_insertion_event_dict = self._create_insertion_event_dict(
+                sender=requester.user.to_string(),
+                room_id=room_id,
+                origin_server_ts=last_event_in_chunk["origin_server_ts"],
+            )
+            base_insertion_event_dict["prev_events"] = prev_event_ids.copy()
+
+            (
+                base_insertion_event,
+                _,
+            ) = await self.event_creation_handler.create_and_send_nonmember_event(
+                await self._create_requester_for_user_id_from_app_service(
+                    base_insertion_event_dict["sender"],
+                    requester.app_service,
+                ),
+                base_insertion_event_dict,
+                prev_event_ids=base_insertion_event_dict.get("prev_events"),
+                auth_event_ids=auth_event_ids,
+                historical=True,
+                depth=inherited_depth,
+            )
+
+            chunk_id_to_connect_to = base_insertion_event["content"][
+                EventContentFields.MSC2716_NEXT_CHUNK_ID
+            ]
 
-        # Add an "insertion" event to the start of each chunk (next to the oldest
+        # Connect this current chunk to the insertion event from the previous chunk
+        last_event_in_chunk["content"][
+            EventContentFields.MSC2716_CHUNK_ID
+        ] = chunk_id_to_connect_to
+
+        # Add an "insertion" event to the start of each chunk (next to the oldest-in-time
         # event in the chunk) so the next chunk can be connected to this one.
-        next_chunk_id = random_string(64)
-        insertion_event = {
-            "type": EventTypes.MSC2716_INSERTION,
-            "sender": requester.user.to_string(),
-            "content": {
-                EventContentFields.MSC2716_NEXT_CHUNK_ID: next_chunk_id,
-                EventContentFields.MSC2716_HISTORICAL: True,
-            },
+        insertion_event = self._create_insertion_event_dict(
+            sender=requester.user.to_string(),
+            room_id=room_id,
             # Since the insertion event is put at the start of the chunk,
-            # where the oldest event is, copy the origin_server_ts from
+            # where the oldest-in-time event is, copy the origin_server_ts from
             # the first event we're inserting
-            "origin_server_ts": events_to_create[0]["origin_server_ts"],
-        }
+            origin_server_ts=events_to_create[0]["origin_server_ts"],
+        )
         # Prepend the insertion event to the start of the chunk
         events_to_create = [insertion_event] + events_to_create
 
-        inherited_depth = await self.inherit_depth_from_prev_ids(prev_events_from_query)
-
         event_ids = []
-        prev_event_ids = prev_events_from_query
         events_to_persist = []
         for ev in events_to_create:
             assert_params_in_dict(ev, ["type", "origin_server_ts", "content", "sender"])
@@ -498,7 +589,9 @@ class RoomBatchSendEventRestServlet(TransactionRestServlet):
             }
 
             event, context = await self.event_creation_handler.create_event(
-                requester,
+                await self._create_requester_for_user_id_from_app_service(
+                    ev["sender"], requester.app_service
+                ),
                 event_dict,
                 prev_event_ids=event_dict.get("prev_events"),
                 auth_event_ids=auth_event_ids,
@@ -528,15 +621,23 @@ class RoomBatchSendEventRestServlet(TransactionRestServlet):
         # where topological_ordering is just depth.
         for (event, context) in reversed(events_to_persist):
             ev = await self.event_creation_handler.handle_new_client_event(
-                requester=requester,
+                await self._create_requester_for_user_id_from_app_service(
+                    event["sender"], requester.app_service
+                ),
                 event=event,
                 context=context,
             )
 
+        # Add the base_insertion_event to the bottom of the list we return
+        if base_insertion_event is not None:
+            event_ids.append(base_insertion_event.event_id)
+
         return 200, {
             "state_events": auth_event_ids,
             "events": event_ids,
-            "next_chunk_id": next_chunk_id,
+            "next_chunk_id": insertion_event["content"][
+                EventContentFields.MSC2716_NEXT_CHUNK_ID
+            ],
         }
 
     def on_GET(self, request, room_id):
diff --git a/synapse/server.py b/synapse/server.py
index 2c27d2a7e8..095dba9ad0 100644
--- a/synapse/server.py
+++ b/synapse/server.py
@@ -247,15 +247,15 @@ class HomeServer(metaclass=abc.ABCMeta):
         # the key we use to sign events and requests
         self.signing_key = config.key.signing_key[0]
         self.config = config
-        self._listening_services = []  # type: List[twisted.internet.tcp.Port]
-        self.start_time = None  # type: Optional[int]
+        self._listening_services: List[twisted.internet.tcp.Port] = []
+        self.start_time: Optional[int] = None
 
         self._instance_id = random_string(5)
         self._instance_name = config.worker.instance_name
 
         self.version_string = version_string
 
-        self.datastores = None  # type: Optional[Databases]
+        self.datastores: Optional[Databases] = None
 
         self._module_web_resources: Dict[str, IResource] = {}
         self._module_web_resources_consumed = False
diff --git a/synapse/server_notices/consent_server_notices.py b/synapse/server_notices/consent_server_notices.py
index e65f6f88fe..4e0f814035 100644
--- a/synapse/server_notices/consent_server_notices.py
+++ b/synapse/server_notices/consent_server_notices.py
@@ -34,7 +34,7 @@ class ConsentServerNotices:
         self._server_notices_manager = hs.get_server_notices_manager()
         self._store = hs.get_datastore()
 
-        self._users_in_progress = set()  # type: Set[str]
+        self._users_in_progress: Set[str] = set()
 
         self._current_consent_version = hs.config.user_consent_version
         self._server_notice_content = hs.config.user_consent_server_notice_content
diff --git a/synapse/server_notices/resource_limits_server_notices.py b/synapse/server_notices/resource_limits_server_notices.py
index e4b0bc5c72..073b0d754f 100644
--- a/synapse/server_notices/resource_limits_server_notices.py
+++ b/synapse/server_notices/resource_limits_server_notices.py
@@ -205,7 +205,7 @@ class ResourceLimitsServerNotices:
             # The user has yet to join the server notices room
             pass
 
-        referenced_events = []  # type: List[str]
+        referenced_events: List[str] = []
         if pinned_state_event is not None:
             referenced_events = list(pinned_state_event.content.get("pinned", []))
 
diff --git a/synapse/server_notices/server_notices_sender.py b/synapse/server_notices/server_notices_sender.py
index c875b15b32..cdf0973d05 100644
--- a/synapse/server_notices/server_notices_sender.py
+++ b/synapse/server_notices/server_notices_sender.py
@@ -32,10 +32,12 @@ class ServerNoticesSender(WorkerServerNoticesSender):
 
     def __init__(self, hs: "HomeServer"):
         super().__init__(hs)
-        self._server_notices = (
+        self._server_notices: Iterable[
+            Union[ConsentServerNotices, ResourceLimitsServerNotices]
+        ] = (
             ConsentServerNotices(hs),
             ResourceLimitsServerNotices(hs),
-        )  # type: Iterable[Union[ConsentServerNotices, ResourceLimitsServerNotices]]
+        )
 
     async def on_user_syncing(self, user_id: str) -> None:
         """Called when the user performs a sync operation.
diff --git a/synapse/state/__init__.py b/synapse/state/__init__.py
index a1770f620e..6223daf522 100644
--- a/synapse/state/__init__.py
+++ b/synapse/state/__init__.py
@@ -309,9 +309,9 @@ class StateHandler:
 
         if old_state:
             # if we're given the state before the event, then we use that
-            state_ids_before_event = {
+            state_ids_before_event: StateMap[str] = {
                 (s.type, s.state_key): s.event_id for s in old_state
-            }  # type: StateMap[str]
+            }
             state_group_before_event = None
             state_group_before_event_prev_group = None
             deltas_to_state_group_before_event = None
@@ -513,23 +513,25 @@ class StateResolutionHandler:
         self.resolve_linearizer = Linearizer(name="state_resolve_lock")
 
         # dict of set of event_ids -> _StateCacheEntry.
-        self._state_cache = ExpiringCache(
+        self._state_cache: ExpiringCache[
+            FrozenSet[int], _StateCacheEntry
+        ] = ExpiringCache(
             cache_name="state_cache",
             clock=self.clock,
             max_len=100000,
             expiry_ms=EVICTION_TIMEOUT_SECONDS * 1000,
             iterable=True,
             reset_expiry_on_get=True,
-        )  # type: ExpiringCache[FrozenSet[int], _StateCacheEntry]
+        )
 
         #
         # stuff for tracking time spent on state-res by room
         #
 
         # tracks the amount of work done on state res per room
-        self._state_res_metrics = defaultdict(
+        self._state_res_metrics: DefaultDict[str, _StateResMetrics] = defaultdict(
             _StateResMetrics
-        )  # type: DefaultDict[str, _StateResMetrics]
+        )
 
         self.clock.looping_call(self._report_metrics, 120 * 1000)
 
@@ -700,9 +702,9 @@ class StateResolutionHandler:
         items = self._state_res_metrics.items()
 
         # log the N biggest rooms
-        biggest = heapq.nlargest(
+        biggest: List[Tuple[str, _StateResMetrics]] = heapq.nlargest(
             n_to_log, items, key=lambda i: extract_key(i[1])
-        )  # type: List[Tuple[str, _StateResMetrics]]
+        )
         metrics_logger.debug(
             "%i biggest rooms for state-res by %s: %s",
             len(biggest),
@@ -754,7 +756,7 @@ def _make_state_cache_entry(
 
     # failing that, look for the closest match.
     prev_group = None
-    delta_ids = None  # type: Optional[StateMap[str]]
+    delta_ids: Optional[StateMap[str]] = None
 
     for old_group, old_state in state_groups_ids.items():
         n_delta_ids = {k: v for k, v in new_state.items() if old_state.get(k) != v}
diff --git a/synapse/state/v1.py b/synapse/state/v1.py
index 318e998813..267193cedf 100644
--- a/synapse/state/v1.py
+++ b/synapse/state/v1.py
@@ -159,7 +159,7 @@ def _seperate(
     """
     state_set_iterator = iter(state_sets)
     unconflicted_state = dict(next(state_set_iterator))
-    conflicted_state = {}  # type: MutableStateMap[Set[str]]
+    conflicted_state: MutableStateMap[Set[str]] = {}
 
     for state_set in state_set_iterator:
         for key, value in state_set.items():
diff --git a/synapse/state/v2.py b/synapse/state/v2.py
index 008644cd98..e66e6571c8 100644
--- a/synapse/state/v2.py
+++ b/synapse/state/v2.py
@@ -276,7 +276,7 @@ async def _get_auth_chain_difference(
     # event IDs if they appear in the `event_map`. This is the intersection of
     # the event's auth chain with the events in the `event_map` *plus* their
     # auth event IDs.
-    events_to_auth_chain = {}  # type: Dict[str, Set[str]]
+    events_to_auth_chain: Dict[str, Set[str]] = {}
     for event in event_map.values():
         chain = {event.event_id}
         events_to_auth_chain[event.event_id] = chain
@@ -301,17 +301,17 @@ async def _get_auth_chain_difference(
         # ((type, state_key)->event_id) mappings; and (b) we have stripped out
         # unpersisted events and replaced them with the persisted events in
         # their auth chain.
-        state_sets_ids = []  # type: List[Set[str]]
+        state_sets_ids: List[Set[str]] = []
 
         # For each state set, the unpersisted event IDs reachable (by their auth
         # chain) from the events in that set.
-        unpersisted_set_ids = []  # type: List[Set[str]]
+        unpersisted_set_ids: List[Set[str]] = []
 
         for state_set in state_sets:
-            set_ids = set()  # type: Set[str]
+            set_ids: Set[str] = set()
             state_sets_ids.append(set_ids)
 
-            unpersisted_ids = set()  # type: Set[str]
+            unpersisted_ids: Set[str] = set()
             unpersisted_set_ids.append(unpersisted_ids)
 
             for event_id in state_set.values():
@@ -334,7 +334,7 @@ async def _get_auth_chain_difference(
         union = unpersisted_set_ids[0].union(*unpersisted_set_ids[1:])
         intersection = unpersisted_set_ids[0].intersection(*unpersisted_set_ids[1:])
 
-        difference_from_event_map = union - intersection  # type: Collection[str]
+        difference_from_event_map: Collection[str] = union - intersection
     else:
         difference_from_event_map = ()
         state_sets_ids = [set(state_set.values()) for state_set in state_sets]
@@ -458,7 +458,7 @@ async def _reverse_topological_power_sort(
         The sorted list
     """
 
-    graph = {}  # type: Dict[str, Set[str]]
+    graph: Dict[str, Set[str]] = {}
     for idx, event_id in enumerate(event_ids, start=1):
         await _add_event_and_auth_chain_to_graph(
             graph, room_id, event_id, event_map, state_res_store, auth_diff
@@ -657,7 +657,7 @@ async def _get_mainline_depth_for_event(
     """
 
     room_id = event.room_id
-    tmp_event = event  # type: Optional[EventBase]
+    tmp_event: Optional[EventBase] = event
 
     # We do an iterative search, replacing `event with the power level in its
     # auth events (if any)
@@ -767,7 +767,7 @@ def lexicographical_topological_sort(
     # outgoing edges, c.f.
     # https://en.wikipedia.org/wiki/Topological_sorting#Kahn's_algorithm
     outdegree_map = graph
-    reverse_graph = {}  # type: Dict[str, Set[str]]
+    reverse_graph: Dict[str, Set[str]] = {}
 
     # Lists of nodes with zero out degree. Is actually a tuple of
     # `(key(node), node)` so that sorting does the right thing
diff --git a/synapse/storage/databases/main/event_federation.py b/synapse/storage/databases/main/event_federation.py
index c4474df975..4e06938849 100644
--- a/synapse/storage/databases/main/event_federation.py
+++ b/synapse/storage/databases/main/event_federation.py
@@ -1230,7 +1230,9 @@ class EventFederationWorkerStore(EventsWorkerStore, SignatureWorkerStore, SQLBas
                 "SELECT coalesce(min(received_ts), 0) FROM federation_inbound_events_staging"
             )
 
-            (age,) = txn.fetchone()
+            (received_ts,) = txn.fetchone()
+
+            age = self._clock.time_msec() - received_ts
 
             return count, age
 
diff --git a/synapse/storage/databases/main/events.py b/synapse/storage/databases/main/events.py
index 897fa06639..08c580b0dc 100644
--- a/synapse/storage/databases/main/events.py
+++ b/synapse/storage/databases/main/events.py
@@ -1580,11 +1580,11 @@ class PersistEventsStore:
         # invalidate the cache for the redacted event
         txn.call_after(self.store._invalidate_get_event_cache, event.redacts)
 
-        self.db_pool.simple_insert_txn(
+        self.db_pool.simple_upsert_txn(
             txn,
             table="redactions",
+            keyvalues={"event_id": event.event_id},
             values={
-                "event_id": event.event_id,
                 "redacts": event.redacts,
                 "received_ts": self._clock.time_msec(),
             },
diff --git a/synapse/storage/databases/main/metrics.py b/synapse/storage/databases/main/metrics.py
index c3f551d377..e3a544d9b2 100644
--- a/synapse/storage/databases/main/metrics.py
+++ b/synapse/storage/databases/main/metrics.py
@@ -320,7 +320,7 @@ class ServerMetricsStore(EventPushActionsWorkerStore, SQLBaseStore):
         """
         Returns millisecond unixtime for start of UTC day.
         """
-        now = time.gmtime()
+        now = time.gmtime(self._clock.time())
         today_start = calendar.timegm((now.tm_year, now.tm_mon, now.tm_mday, 0, 0, 0))
         return today_start * 1000
 
@@ -352,7 +352,7 @@ class ServerMetricsStore(EventPushActionsWorkerStore, SQLBaseStore):
                     ) udv
                     ON u.user_id = udv.user_id AND u.device_id=udv.device_id
                     INNER JOIN users ON users.name=u.user_id
-                    WHERE last_seen > ? AND last_seen <= ?
+                    WHERE ? <= last_seen AND last_seen < ?
                     AND udv.timestamp IS NULL AND users.is_guest=0
                     AND users.appservice_id IS NULL
                     GROUP BY u.user_id, u.device_id
diff --git a/synapse/storage/databases/main/purge_events.py b/synapse/storage/databases/main/purge_events.py
index 7fb7780d0f..eb4841830d 100644
--- a/synapse/storage/databases/main/purge_events.py
+++ b/synapse/storage/databases/main/purge_events.py
@@ -215,6 +215,7 @@ class PurgeEventsStore(StateGroupWorkerStore, CacheInvalidationWorkerStore):
             "event_relations",
             "event_search",
             "rejections",
+            "redactions",
         ):
             logger.info("[purge] removing events from %s", table)
 
@@ -392,7 +393,6 @@ class PurgeEventsStore(StateGroupWorkerStore, CacheInvalidationWorkerStore):
             "room_memberships",
             "room_stats_state",
             "room_stats_current",
-            "room_stats_historical",
             "room_stats_earliest_token",
             "rooms",
             "stream_ordering_to_exterm",
diff --git a/synapse/storage/databases/main/room.py b/synapse/storage/databases/main/room.py
index 9f0d64a325..6ddafe5434 100644
--- a/synapse/storage/databases/main/room.py
+++ b/synapse/storage/databases/main/room.py
@@ -25,6 +25,7 @@ from synapse.api.room_versions import RoomVersion, RoomVersions
 from synapse.storage._base import SQLBaseStore, db_to_json
 from synapse.storage.database import DatabasePool, LoggingTransaction
 from synapse.storage.databases.main.search import SearchStore
+from synapse.storage.types import Cursor
 from synapse.types import JsonDict, ThirdPartyInstanceID
 from synapse.util import json_encoder
 from synapse.util.caches.descriptors import cached
@@ -1022,10 +1023,22 @@ class RoomWorkerStore(SQLBaseStore):
         )
 
 
-class RoomBackgroundUpdateStore(SQLBaseStore):
+class _BackgroundUpdates:
     REMOVE_TOMESTONED_ROOMS_BG_UPDATE = "remove_tombstoned_rooms_from_directory"
     ADD_ROOMS_ROOM_VERSION_COLUMN = "add_rooms_room_version_column"
+    POPULATE_ROOM_DEPTH_MIN_DEPTH2 = "populate_room_depth_min_depth2"
+    REPLACE_ROOM_DEPTH_MIN_DEPTH = "replace_room_depth_min_depth"
+
+
+_REPLACE_ROOM_DEPTH_SQL_COMMANDS = (
+    "DROP TRIGGER populate_min_depth2_trigger ON room_depth",
+    "DROP FUNCTION populate_min_depth2()",
+    "ALTER TABLE room_depth DROP COLUMN min_depth",
+    "ALTER TABLE room_depth RENAME COLUMN min_depth2 TO min_depth",
+)
+
 
+class RoomBackgroundUpdateStore(SQLBaseStore):
     def __init__(self, database: DatabasePool, db_conn, hs):
         super().__init__(database, db_conn, hs)
 
@@ -1037,15 +1050,25 @@ class RoomBackgroundUpdateStore(SQLBaseStore):
         )
 
         self.db_pool.updates.register_background_update_handler(
-            self.REMOVE_TOMESTONED_ROOMS_BG_UPDATE,
+            _BackgroundUpdates.REMOVE_TOMESTONED_ROOMS_BG_UPDATE,
             self._remove_tombstoned_rooms_from_directory,
         )
 
         self.db_pool.updates.register_background_update_handler(
-            self.ADD_ROOMS_ROOM_VERSION_COLUMN,
+            _BackgroundUpdates.ADD_ROOMS_ROOM_VERSION_COLUMN,
             self._background_add_rooms_room_version_column,
         )
 
+        # BG updates to change the type of room_depth.min_depth
+        self.db_pool.updates.register_background_update_handler(
+            _BackgroundUpdates.POPULATE_ROOM_DEPTH_MIN_DEPTH2,
+            self._background_populate_room_depth_min_depth2,
+        )
+        self.db_pool.updates.register_background_update_handler(
+            _BackgroundUpdates.REPLACE_ROOM_DEPTH_MIN_DEPTH,
+            self._background_replace_room_depth_min_depth,
+        )
+
     async def _background_insert_retention(self, progress, batch_size):
         """Retrieves a list of all rooms within a range and inserts an entry for each of
         them into the room_retention table.
@@ -1164,7 +1187,9 @@ class RoomBackgroundUpdateStore(SQLBaseStore):
                 new_last_room_id = room_id
 
             self.db_pool.updates._background_update_progress_txn(
-                txn, self.ADD_ROOMS_ROOM_VERSION_COLUMN, {"room_id": new_last_room_id}
+                txn,
+                _BackgroundUpdates.ADD_ROOMS_ROOM_VERSION_COLUMN,
+                {"room_id": new_last_room_id},
             )
 
             return False
@@ -1176,7 +1201,7 @@ class RoomBackgroundUpdateStore(SQLBaseStore):
 
         if end:
             await self.db_pool.updates._end_background_update(
-                self.ADD_ROOMS_ROOM_VERSION_COLUMN
+                _BackgroundUpdates.ADD_ROOMS_ROOM_VERSION_COLUMN
             )
 
         return batch_size
@@ -1215,7 +1240,7 @@ class RoomBackgroundUpdateStore(SQLBaseStore):
 
         if not rooms:
             await self.db_pool.updates._end_background_update(
-                self.REMOVE_TOMESTONED_ROOMS_BG_UPDATE
+                _BackgroundUpdates.REMOVE_TOMESTONED_ROOMS_BG_UPDATE
             )
             return 0
 
@@ -1224,7 +1249,7 @@ class RoomBackgroundUpdateStore(SQLBaseStore):
             await self.set_room_is_public(room_id, False)
 
         await self.db_pool.updates._background_update_progress(
-            self.REMOVE_TOMESTONED_ROOMS_BG_UPDATE, {"room_id": rooms[-1]}
+            _BackgroundUpdates.REMOVE_TOMESTONED_ROOMS_BG_UPDATE, {"room_id": rooms[-1]}
         )
 
         return len(rooms)
@@ -1268,6 +1293,71 @@ class RoomBackgroundUpdateStore(SQLBaseStore):
 
         return max_ordering is None
 
+    async def _background_populate_room_depth_min_depth2(
+        self, progress: JsonDict, batch_size: int
+    ) -> int:
+        """Populate room_depth.min_depth2
+
+        This is to deal with the fact that min_depth was initially created as a
+        32-bit integer field.
+        """
+
+        def process(txn: Cursor) -> int:
+            last_room = progress.get("last_room", "")
+            txn.execute(
+                """
+                UPDATE room_depth SET min_depth2=min_depth
+                WHERE room_id IN (
+                   SELECT room_id FROM room_depth WHERE room_id > ?
+                   ORDER BY room_id LIMIT ?
+                )
+                RETURNING room_id;
+                """,
+                (last_room, batch_size),
+            )
+            row_count = txn.rowcount
+            if row_count == 0:
+                return 0
+            last_room = max(row[0] for row in txn)
+            logger.info("populated room_depth up to %s", last_room)
+
+            self.db_pool.updates._background_update_progress_txn(
+                txn,
+                _BackgroundUpdates.POPULATE_ROOM_DEPTH_MIN_DEPTH2,
+                {"last_room": last_room},
+            )
+            return row_count
+
+        result = await self.db_pool.runInteraction(
+            "_background_populate_min_depth2", process
+        )
+
+        if result != 0:
+            return result
+
+        await self.db_pool.updates._end_background_update(
+            _BackgroundUpdates.POPULATE_ROOM_DEPTH_MIN_DEPTH2
+        )
+        return 0
+
+    async def _background_replace_room_depth_min_depth(
+        self, progress: JsonDict, batch_size: int
+    ) -> int:
+        """Drop the old 'min_depth' column and rename 'min_depth2' into its place."""
+
+        def process(txn: Cursor) -> None:
+            for sql in _REPLACE_ROOM_DEPTH_SQL_COMMANDS:
+                logger.info("completing room_depth migration: %s", sql)
+                txn.execute(sql)
+
+        await self.db_pool.runInteraction("_background_replace_room_depth", process)
+
+        await self.db_pool.updates._end_background_update(
+            _BackgroundUpdates.REPLACE_ROOM_DEPTH_MIN_DEPTH,
+        )
+
+        return 0
+
 
 class RoomStore(RoomBackgroundUpdateStore, RoomWorkerStore, SearchStore):
     def __init__(self, database: DatabasePool, db_conn, hs):
diff --git a/synapse/storage/databases/main/roommember.py b/synapse/storage/databases/main/roommember.py
index 2796354a1f..4d82c4c26d 100644
--- a/synapse/storage/databases/main/roommember.py
+++ b/synapse/storage/databases/main/roommember.py
@@ -703,13 +703,22 @@ class RoomMemberWorkerStore(EventsWorkerStore):
 
     @cached(max_entries=10000)
     async def is_host_joined(self, room_id: str, host: str) -> bool:
+        return await self._check_host_room_membership(room_id, host, Membership.JOIN)
+
+    @cached(max_entries=10000)
+    async def is_host_invited(self, room_id: str, host: str) -> bool:
+        return await self._check_host_room_membership(room_id, host, Membership.INVITE)
+
+    async def _check_host_room_membership(
+        self, room_id: str, host: str, membership: str
+    ) -> bool:
         if "%" in host or "_" in host:
             raise Exception("Invalid host name")
 
         sql = """
             SELECT state_key FROM current_state_events AS c
             INNER JOIN room_memberships AS m USING (event_id)
-            WHERE m.membership = 'join'
+            WHERE m.membership = ?
                 AND type = 'm.room.member'
                 AND c.room_id = ?
                 AND state_key LIKE ?
@@ -722,7 +731,7 @@ class RoomMemberWorkerStore(EventsWorkerStore):
         like_clause = "%:" + host
 
         rows = await self.db_pool.execute(
-            "is_host_joined", None, sql, room_id, like_clause
+            "is_host_joined", None, sql, membership, room_id, like_clause
         )
 
         if not rows:
diff --git a/synapse/storage/databases/main/stats.py b/synapse/storage/databases/main/stats.py
index 82a1833509..59d67c255b 100644
--- a/synapse/storage/databases/main/stats.py
+++ b/synapse/storage/databases/main/stats.py
@@ -26,7 +26,6 @@ from synapse.api.constants import EventTypes, Membership
 from synapse.api.errors import StoreError
 from synapse.storage.database import DatabasePool
 from synapse.storage.databases.main.state_deltas import StateDeltasStore
-from synapse.storage.engines import PostgresEngine
 from synapse.types import JsonDict
 from synapse.util.caches.descriptors import cached
 
@@ -49,14 +48,6 @@ ABSOLUTE_STATS_FIELDS = {
     "user": ("joined_rooms",),
 }
 
-# these fields are per-timeslice and so should be reset to 0 upon a new slice
-# You can draw these stats on a histogram.
-# Example: number of events sent locally during a time slice
-PER_SLICE_FIELDS = {
-    "room": ("total_events", "total_event_bytes"),
-    "user": ("invites_sent", "rooms_created", "total_events", "total_event_bytes"),
-}
-
 TYPE_TO_TABLE = {"room": ("room_stats", "room_id"), "user": ("user_stats", "user_id")}
 
 # these are the tables (& ID columns) which contain our actual subjects
@@ -106,7 +97,6 @@ class StatsStore(StateDeltasStore):
         self.server_name = hs.hostname
         self.clock = self.hs.get_clock()
         self.stats_enabled = hs.config.stats_enabled
-        self.stats_bucket_size = hs.config.stats_bucket_size
 
         self.stats_delta_processing_lock = DeferredLock()
 
@@ -122,22 +112,6 @@ class StatsStore(StateDeltasStore):
         self.db_pool.updates.register_noop_background_update("populate_stats_cleanup")
         self.db_pool.updates.register_noop_background_update("populate_stats_prepare")
 
-    def quantise_stats_time(self, ts):
-        """
-        Quantises a timestamp to be a multiple of the bucket size.
-
-        Args:
-            ts (int): the timestamp to quantise, in milliseconds since the Unix
-                Epoch
-
-        Returns:
-            int: a timestamp which
-              - is divisible by the bucket size;
-              - is no later than `ts`; and
-              - is the largest such timestamp.
-        """
-        return (ts // self.stats_bucket_size) * self.stats_bucket_size
-
     async def _populate_stats_process_users(self, progress, batch_size):
         """
         This is a background update which regenerates statistics for users.
@@ -288,56 +262,6 @@ class StatsStore(StateDeltasStore):
             desc="update_room_state",
         )
 
-    async def get_statistics_for_subject(
-        self, stats_type: str, stats_id: str, start: str, size: int = 100
-    ) -> List[dict]:
-        """
-        Get statistics for a given subject.
-
-        Args:
-            stats_type: The type of subject
-            stats_id: The ID of the subject (e.g. room_id or user_id)
-            start: Pagination start. Number of entries, not timestamp.
-            size: How many entries to return.
-
-        Returns:
-            A list of dicts, where the dict has the keys of
-            ABSOLUTE_STATS_FIELDS[stats_type],  and "bucket_size" and "end_ts".
-        """
-        return await self.db_pool.runInteraction(
-            "get_statistics_for_subject",
-            self._get_statistics_for_subject_txn,
-            stats_type,
-            stats_id,
-            start,
-            size,
-        )
-
-    def _get_statistics_for_subject_txn(
-        self, txn, stats_type, stats_id, start, size=100
-    ):
-        """
-        Transaction-bound version of L{get_statistics_for_subject}.
-        """
-
-        table, id_col = TYPE_TO_TABLE[stats_type]
-        selected_columns = list(
-            ABSOLUTE_STATS_FIELDS[stats_type] + PER_SLICE_FIELDS[stats_type]
-        )
-
-        slice_list = self.db_pool.simple_select_list_paginate_txn(
-            txn,
-            table + "_historical",
-            "end_ts",
-            start,
-            size,
-            retcols=selected_columns + ["bucket_size", "end_ts"],
-            keyvalues={id_col: stats_id},
-            order_direction="DESC",
-        )
-
-        return slice_list
-
     @cached()
     async def get_earliest_token_for_stats(
         self, stats_type: str, id: str
@@ -451,14 +375,10 @@ class StatsStore(StateDeltasStore):
 
         table, id_col = TYPE_TO_TABLE[stats_type]
 
-        quantised_ts = self.quantise_stats_time(int(ts))
-        end_ts = quantised_ts + self.stats_bucket_size
-
         # Lets be paranoid and check that all the given field names are known
         abs_field_names = ABSOLUTE_STATS_FIELDS[stats_type]
-        slice_field_names = PER_SLICE_FIELDS[stats_type]
         for field in chain(fields.keys(), absolute_field_overrides.keys()):
-            if field not in abs_field_names and field not in slice_field_names:
+            if field not in abs_field_names:
                 # guard against potential SQL injection dodginess
                 raise ValueError(
                     "%s is not a recognised field"
@@ -491,20 +411,6 @@ class StatsStore(StateDeltasStore):
             additive_relatives=deltas_of_absolute_fields,
         )
 
-        per_slice_additive_relatives = {
-            key: fields.get(key, 0) for key in slice_field_names
-        }
-        self._upsert_copy_from_table_with_additive_relatives_txn(
-            txn=txn,
-            into_table=table + "_historical",
-            keyvalues={id_col: stats_id},
-            extra_dst_insvalues={"bucket_size": self.stats_bucket_size},
-            extra_dst_keyvalues={"end_ts": end_ts},
-            additive_relatives=per_slice_additive_relatives,
-            src_table=table + "_current",
-            copy_columns=abs_field_names,
-        )
-
     def _upsert_with_additive_relatives_txn(
         self, txn, table, keyvalues, absolutes, additive_relatives
     ):
@@ -528,7 +434,7 @@ class StatsStore(StateDeltasStore):
             ]
 
             relative_updates = [
-                "%(field)s = EXCLUDED.%(field)s + %(table)s.%(field)s"
+                "%(field)s = EXCLUDED.%(field)s + COALESCE(%(table)s.%(field)s, 0)"
                 % {"table": table, "field": field}
                 for field in additive_relatives.keys()
             ]
@@ -568,205 +474,13 @@ class StatsStore(StateDeltasStore):
                 self.db_pool.simple_insert_txn(txn, table, merged_dict)
             else:
                 for (key, val) in additive_relatives.items():
-                    current_row[key] += val
+                    if current_row[key] is None:
+                        current_row[key] = val
+                    else:
+                        current_row[key] += val
                 current_row.update(absolutes)
                 self.db_pool.simple_update_one_txn(txn, table, keyvalues, current_row)
 
-    def _upsert_copy_from_table_with_additive_relatives_txn(
-        self,
-        txn,
-        into_table,
-        keyvalues,
-        extra_dst_keyvalues,
-        extra_dst_insvalues,
-        additive_relatives,
-        src_table,
-        copy_columns,
-    ):
-        """Updates the historic stats table with latest updates.
-
-        This involves copying "absolute" fields from the `_current` table, and
-        adding relative fields to any existing values.
-
-        Args:
-             txn: Transaction
-             into_table (str): The destination table to UPSERT the row into
-             keyvalues (dict[str, any]): Row-identifying key values
-             extra_dst_keyvalues (dict[str, any]): Additional keyvalues
-                for `into_table`.
-             extra_dst_insvalues (dict[str, any]): Additional values to insert
-                on new row creation for `into_table`.
-             additive_relatives (dict[str, any]): Fields that will be added onto
-                if existing row present. (Must be disjoint from copy_columns.)
-             src_table (str): The source table to copy from
-             copy_columns (iterable[str]): The list of columns to copy
-        """
-        if self.database_engine.can_native_upsert:
-            ins_columns = chain(
-                keyvalues,
-                copy_columns,
-                additive_relatives,
-                extra_dst_keyvalues,
-                extra_dst_insvalues,
-            )
-            sel_exprs = chain(
-                keyvalues,
-                copy_columns,
-                (
-                    "?"
-                    for _ in chain(
-                        additive_relatives, extra_dst_keyvalues, extra_dst_insvalues
-                    )
-                ),
-            )
-            keyvalues_where = ("%s = ?" % f for f in keyvalues)
-
-            sets_cc = ("%s = EXCLUDED.%s" % (f, f) for f in copy_columns)
-            sets_ar = (
-                "%s = EXCLUDED.%s + %s.%s" % (f, f, into_table, f)
-                for f in additive_relatives
-            )
-
-            sql = """
-                INSERT INTO %(into_table)s (%(ins_columns)s)
-                SELECT %(sel_exprs)s
-                FROM %(src_table)s
-                WHERE %(keyvalues_where)s
-                ON CONFLICT (%(keyvalues)s)
-                DO UPDATE SET %(sets)s
-            """ % {
-                "into_table": into_table,
-                "ins_columns": ", ".join(ins_columns),
-                "sel_exprs": ", ".join(sel_exprs),
-                "keyvalues_where": " AND ".join(keyvalues_where),
-                "src_table": src_table,
-                "keyvalues": ", ".join(
-                    chain(keyvalues.keys(), extra_dst_keyvalues.keys())
-                ),
-                "sets": ", ".join(chain(sets_cc, sets_ar)),
-            }
-
-            qargs = list(
-                chain(
-                    additive_relatives.values(),
-                    extra_dst_keyvalues.values(),
-                    extra_dst_insvalues.values(),
-                    keyvalues.values(),
-                )
-            )
-            txn.execute(sql, qargs)
-        else:
-            self.database_engine.lock_table(txn, into_table)
-            src_row = self.db_pool.simple_select_one_txn(
-                txn, src_table, keyvalues, copy_columns
-            )
-            all_dest_keyvalues = {**keyvalues, **extra_dst_keyvalues}
-            dest_current_row = self.db_pool.simple_select_one_txn(
-                txn,
-                into_table,
-                keyvalues=all_dest_keyvalues,
-                retcols=list(chain(additive_relatives.keys(), copy_columns)),
-                allow_none=True,
-            )
-
-            if dest_current_row is None:
-                merged_dict = {
-                    **keyvalues,
-                    **extra_dst_keyvalues,
-                    **extra_dst_insvalues,
-                    **src_row,
-                    **additive_relatives,
-                }
-                self.db_pool.simple_insert_txn(txn, into_table, merged_dict)
-            else:
-                for (key, val) in additive_relatives.items():
-                    src_row[key] = dest_current_row[key] + val
-                self.db_pool.simple_update_txn(
-                    txn, into_table, all_dest_keyvalues, src_row
-                )
-
-    async def get_changes_room_total_events_and_bytes(
-        self, min_pos: int, max_pos: int
-    ) -> Tuple[Dict[str, Dict[str, int]], Dict[str, Dict[str, int]]]:
-        """Fetches the counts of events in the given range of stream IDs.
-
-        Args:
-            min_pos
-            max_pos
-
-        Returns:
-            Mapping of room ID to field changes.
-        """
-
-        return await self.db_pool.runInteraction(
-            "stats_incremental_total_events_and_bytes",
-            self.get_changes_room_total_events_and_bytes_txn,
-            min_pos,
-            max_pos,
-        )
-
-    def get_changes_room_total_events_and_bytes_txn(
-        self, txn, low_pos: int, high_pos: int
-    ) -> Tuple[Dict[str, Dict[str, int]], Dict[str, Dict[str, int]]]:
-        """Gets the total_events and total_event_bytes counts for rooms and
-        senders, in a range of stream_orderings (including backfilled events).
-
-        Args:
-            txn
-            low_pos: Low stream ordering
-            high_pos: High stream ordering
-
-        Returns:
-            The room and user deltas for total_events/total_event_bytes in the
-            format of `stats_id` -> fields
-        """
-
-        if low_pos >= high_pos:
-            # nothing to do here.
-            return {}, {}
-
-        if isinstance(self.database_engine, PostgresEngine):
-            new_bytes_expression = "OCTET_LENGTH(json)"
-        else:
-            new_bytes_expression = "LENGTH(CAST(json AS BLOB))"
-
-        sql = """
-            SELECT events.room_id, COUNT(*) AS new_events, SUM(%s) AS new_bytes
-            FROM events INNER JOIN event_json USING (event_id)
-            WHERE (? < stream_ordering AND stream_ordering <= ?)
-                OR (? <= stream_ordering AND stream_ordering <= ?)
-            GROUP BY events.room_id
-        """ % (
-            new_bytes_expression,
-        )
-
-        txn.execute(sql, (low_pos, high_pos, -high_pos, -low_pos))
-
-        room_deltas = {
-            room_id: {"total_events": new_events, "total_event_bytes": new_bytes}
-            for room_id, new_events, new_bytes in txn
-        }
-
-        sql = """
-            SELECT events.sender, COUNT(*) AS new_events, SUM(%s) AS new_bytes
-            FROM events INNER JOIN event_json USING (event_id)
-            WHERE (? < stream_ordering AND stream_ordering <= ?)
-                OR (? <= stream_ordering AND stream_ordering <= ?)
-            GROUP BY events.sender
-        """ % (
-            new_bytes_expression,
-        )
-
-        txn.execute(sql, (low_pos, high_pos, -high_pos, -low_pos))
-
-        user_deltas = {
-            user_id: {"total_events": new_events, "total_event_bytes": new_bytes}
-            for user_id, new_events, new_bytes in txn
-            if self.hs.is_mine_id(user_id)
-        }
-
-        return room_deltas, user_deltas
-
     async def _calculate_and_set_initial_state_for_room(
         self, room_id: str
     ) -> Tuple[dict, dict, int]:
@@ -893,6 +607,7 @@ class StatsStore(StateDeltasStore):
                 "invited_members": membership_counts.get(Membership.INVITE, 0),
                 "left_members": membership_counts.get(Membership.LEAVE, 0),
                 "banned_members": membership_counts.get(Membership.BAN, 0),
+                "knocked_members": membership_counts.get(Membership.KNOCK, 0),
                 "local_users_in_room": len(local_users_in_room),
             },
         )
diff --git a/synapse/storage/schema/__init__.py b/synapse/storage/schema/__init__.py
index 0a53b73ccc..36340a652a 100644
--- a/synapse/storage/schema/__init__.py
+++ b/synapse/storage/schema/__init__.py
@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-SCHEMA_VERSION = 60
+SCHEMA_VERSION = 61
 """Represents the expectations made by the codebase about the database schema
 
 This should be incremented whenever the codebase changes its requirements on the
@@ -21,6 +21,10 @@ older versions of Synapse).
 
 See `README.md <synapse/storage/schema/README.md>`_  for more information on how this
 works.
+
+Changes in SCHEMA_VERSION = 61:
+    - The `user_stats_historical` and `room_stats_historical` tables are not written and
+      are not read (previously, they were written but not read).
 """
 
 
diff --git a/synapse/storage/schema/main/delta/61/01change_appservices_txns.sql.postgres b/synapse/storage/schema/main/delta/61/01change_appservices_txns.sql.postgres
new file mode 100644
index 0000000000..c8aec78e60
--- /dev/null
+++ b/synapse/storage/schema/main/delta/61/01change_appservices_txns.sql.postgres
@@ -0,0 +1,23 @@
+/* Copyright 2021 The Matrix.org Foundation C.I.C
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *    http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+-- we use bigint elsewhere in the database for appservice txn ids (notably,
+-- application_services_state.last_txn), and generally we use bigints everywhere else
+-- we have monotonic counters, so let's bring this one in line.
+--
+-- assuming there aren't thousands of rows for decommisioned/non-functional ASes, this
+-- table should be pretty small, so safe to do a synchronous ALTER TABLE.
+
+ALTER TABLE application_services_txns ALTER COLUMN txn_id SET DATA TYPE BIGINT;
diff --git a/synapse/storage/schema/main/delta/61/02drop_redundant_room_depth_index.sql b/synapse/storage/schema/main/delta/61/02drop_redundant_room_depth_index.sql
new file mode 100644
index 0000000000..35ca7a40c0
--- /dev/null
+++ b/synapse/storage/schema/main/delta/61/02drop_redundant_room_depth_index.sql
@@ -0,0 +1,18 @@
+/* Copyright 2021 The Matrix.org Foundation C.I.C
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *    http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+-- this index is redundant; there is another UNIQUE index on this table.
+DROP INDEX IF EXISTS room_depth_room;
+
diff --git a/synapse/storage/schema/main/delta/61/03recreate_min_depth.py b/synapse/storage/schema/main/delta/61/03recreate_min_depth.py
new file mode 100644
index 0000000000..f8d7db9f2e
--- /dev/null
+++ b/synapse/storage/schema/main/delta/61/03recreate_min_depth.py
@@ -0,0 +1,70 @@
+# Copyright 2021 The Matrix.org Foundation C.I.C.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+"""
+This migration handles the process of changing the type of `room_depth.min_depth` to
+a BIGINT.
+"""
+from synapse.storage.engines import BaseDatabaseEngine, PostgresEngine
+from synapse.storage.types import Cursor
+
+
+def run_create(cur: Cursor, database_engine: BaseDatabaseEngine, *args, **kwargs):
+    if not isinstance(database_engine, PostgresEngine):
+        # this only applies to postgres - sqlite does not distinguish between big and
+        # little ints.
+        return
+
+    # First add a new column to contain the bigger min_depth
+    cur.execute("ALTER TABLE room_depth ADD COLUMN min_depth2 BIGINT")
+
+    # Create a trigger which will keep it populated.
+    cur.execute(
+        """
+        CREATE OR REPLACE FUNCTION populate_min_depth2() RETURNS trigger AS $BODY$
+            BEGIN
+                new.min_depth2 := new.min_depth;
+                RETURN NEW;
+            END;
+        $BODY$ LANGUAGE plpgsql
+        """
+    )
+
+    cur.execute(
+        """
+        CREATE TRIGGER populate_min_depth2_trigger BEFORE INSERT OR UPDATE ON room_depth
+        FOR EACH ROW
+        EXECUTE PROCEDURE populate_min_depth2()
+        """
+    )
+
+    # Start a bg process to populate it for old rooms
+    cur.execute(
+        """
+       INSERT INTO background_updates (ordering, update_name, progress_json) VALUES
+            (6103, 'populate_room_depth_min_depth2', '{}')
+       """
+    )
+
+    # and another to switch them over once it completes.
+    cur.execute(
+        """
+        INSERT INTO background_updates (ordering, update_name, progress_json, depends_on) VALUES
+            (6103, 'replace_room_depth_min_depth', '{}', 'populate_room_depth2')
+        """
+    )
+
+
+def run_upgrade(cur: Cursor, database_engine: BaseDatabaseEngine, *args, **kwargs):
+    pass
diff --git a/synapse/streams/events.py b/synapse/streams/events.py
index 20fceaa935..99b0aac2fb 100644
--- a/synapse/streams/events.py
+++ b/synapse/streams/events.py
@@ -32,9 +32,9 @@ class EventSources:
     }
 
     def __init__(self, hs):
-        self.sources = {
+        self.sources: Dict[str, Any] = {
             name: cls(hs) for name, cls in EventSources.SOURCE_TYPES.items()
-        }  # type: Dict[str, Any]
+        }
         self.store = hs.get_datastore()
 
     def get_current_token(self) -> StreamToken:
diff --git a/synapse/types.py b/synapse/types.py
index 8d2fa00f71..fad23c8700 100644
--- a/synapse/types.py
+++ b/synapse/types.py
@@ -182,14 +182,14 @@ def create_requester(
     )
 
 
-def get_domain_from_id(string):
+def get_domain_from_id(string: str) -> str:
     idx = string.find(":")
     if idx == -1:
         raise SynapseError(400, "Invalid ID: %r" % (string,))
     return string[idx + 1 :]
 
 
-def get_localpart_from_id(string):
+def get_localpart_from_id(string: str) -> str:
     idx = string.find(":")
     if idx == -1:
         raise SynapseError(400, "Invalid ID: %r" % (string,))
@@ -210,7 +210,7 @@ class DomainSpecificString(metaclass=abc.ABCMeta):
         'domain' : The domain part of the name
     """
 
-    SIGIL = abc.abstractproperty()  # type: str  # type: ignore
+    SIGIL: str = abc.abstractproperty()  # type: ignore
 
     localpart = attr.ib(type=str)
     domain = attr.ib(type=str)
@@ -304,7 +304,7 @@ class GroupID(DomainSpecificString):
 
     @classmethod
     def from_string(cls: Type[DS], s: str) -> DS:
-        group_id = super().from_string(s)  # type: DS # type: ignore
+        group_id: DS = super().from_string(s)  # type: ignore
 
         if not group_id.localpart:
             raise SynapseError(400, "Group ID cannot be empty", Codes.INVALID_PARAM)
@@ -600,7 +600,7 @@ class StreamToken:
     groups_key = attr.ib(type=int)
 
     _SEPARATOR = "_"
-    START = None  # type: StreamToken
+    START: "StreamToken"
 
     @classmethod
     async def from_string(cls, store: "DataStore", string: str) -> "StreamToken":
diff --git a/synapse/visibility.py b/synapse/visibility.py
index 490fb26e81..1dc6b90275 100644
--- a/synapse/visibility.py
+++ b/synapse/visibility.py
@@ -90,7 +90,7 @@ async def filter_events_for_client(
         AccountDataTypes.IGNORED_USER_LIST, user_id
     )
 
-    ignore_list = frozenset()  # type: FrozenSet[str]
+    ignore_list: FrozenSet[str] = frozenset()
     if ignore_dict_content:
         ignored_users_dict = ignore_dict_content.get("ignored_users", {})
         if isinstance(ignored_users_dict, dict):
diff --git a/sytest-blacklist b/sytest-blacklist
index 566ef96711..de9986357b 100644
--- a/sytest-blacklist
+++ b/sytest-blacklist
@@ -41,8 +41,3 @@ We can't peek into rooms with invited history_visibility
 We can't peek into rooms with joined history_visibility
 Local users can peek by room alias
 Peeked rooms only turn up in the sync for the device who peeked them
-
-
-# Blacklisted due to changes made in #10272
-Outbound federation will ignore a missing event with bad JSON for room version 6
-Federation rejects inbound events where the prev_events cannot be found
diff --git a/tests/app/test_phone_stats_home.py b/tests/app/test_phone_stats_home.py
new file mode 100644
index 0000000000..2da6ba4dde
--- /dev/null
+++ b/tests/app/test_phone_stats_home.py
@@ -0,0 +1,153 @@
+import synapse
+from synapse.rest.client.v1 import login, room
+
+from tests import unittest
+from tests.unittest import HomeserverTestCase
+
+ONE_DAY_IN_SECONDS = 86400
+
+
+class PhoneHomeTestCase(HomeserverTestCase):
+    servlets = [
+        synapse.rest.admin.register_servlets_for_client_rest_resource,
+        room.register_servlets,
+        login.register_servlets,
+    ]
+
+    # Override the retention time for the user_ips table because otherwise it
+    # gets pruned too aggressively for our R30 test.
+    @unittest.override_config({"user_ips_max_age": "365d"})
+    def test_r30_minimum_usage(self):
+        """
+        Tests the minimum amount of interaction necessary for the R30 metric
+        to consider a user 'retained'.
+        """
+
+        # Register a user, log it in, create a room and send a message
+        user_id = self.register_user("u1", "secret!")
+        access_token = self.login("u1", "secret!")
+        room_id = self.helper.create_room_as(room_creator=user_id, tok=access_token)
+        self.helper.send(room_id, "message", tok=access_token)
+
+        # Check the R30 results do not count that user.
+        r30_results = self.get_success(self.hs.get_datastore().count_r30_users())
+        self.assertEqual(r30_results, {"all": 0})
+
+        # Advance 30 days (+ 1 second, because strict inequality causes issues if we are
+        # bang on 30 days later).
+        self.reactor.advance(30 * ONE_DAY_IN_SECONDS + 1)
+
+        # (Make sure the user isn't somehow counted by this point.)
+        r30_results = self.get_success(self.hs.get_datastore().count_r30_users())
+        self.assertEqual(r30_results, {"all": 0})
+
+        # Send a message (this counts as activity)
+        self.helper.send(room_id, "message2", tok=access_token)
+
+        # We have to wait some time for _update_client_ips_batch to get
+        # called and update the user_ips table.
+        self.reactor.advance(2 * 60 * 60)
+
+        # *Now* the user is counted.
+        r30_results = self.get_success(self.hs.get_datastore().count_r30_users())
+        self.assertEqual(r30_results, {"all": 1, "unknown": 1})
+
+        # Advance 29 days. The user has now not posted for 29 days.
+        self.reactor.advance(29 * ONE_DAY_IN_SECONDS)
+
+        # The user is still counted.
+        r30_results = self.get_success(self.hs.get_datastore().count_r30_users())
+        self.assertEqual(r30_results, {"all": 1, "unknown": 1})
+
+        # Advance another day. The user has now not posted for 30 days.
+        self.reactor.advance(ONE_DAY_IN_SECONDS)
+
+        # The user is now no longer counted in R30.
+        r30_results = self.get_success(self.hs.get_datastore().count_r30_users())
+        self.assertEqual(r30_results, {"all": 0})
+
+    def test_r30_minimum_usage_using_default_config(self):
+        """
+        Tests the minimum amount of interaction necessary for the R30 metric
+        to consider a user 'retained'.
+
+        N.B. This test does not override the `user_ips_max_age` config setting,
+        which defaults to 28 days.
+        """
+
+        # Register a user, log it in, create a room and send a message
+        user_id = self.register_user("u1", "secret!")
+        access_token = self.login("u1", "secret!")
+        room_id = self.helper.create_room_as(room_creator=user_id, tok=access_token)
+        self.helper.send(room_id, "message", tok=access_token)
+
+        # Check the R30 results do not count that user.
+        r30_results = self.get_success(self.hs.get_datastore().count_r30_users())
+        self.assertEqual(r30_results, {"all": 0})
+
+        # Advance 30 days (+ 1 second, because strict inequality causes issues if we are
+        # bang on 30 days later).
+        self.reactor.advance(30 * ONE_DAY_IN_SECONDS + 1)
+
+        # (Make sure the user isn't somehow counted by this point.)
+        r30_results = self.get_success(self.hs.get_datastore().count_r30_users())
+        self.assertEqual(r30_results, {"all": 0})
+
+        # Send a message (this counts as activity)
+        self.helper.send(room_id, "message2", tok=access_token)
+
+        # We have to wait some time for _update_client_ips_batch to get
+        # called and update the user_ips table.
+        self.reactor.advance(2 * 60 * 60)
+
+        # *Now* the user is counted.
+        r30_results = self.get_success(self.hs.get_datastore().count_r30_users())
+        self.assertEqual(r30_results, {"all": 1, "unknown": 1})
+
+        # Advance 27 days. The user has now not posted for 27 days.
+        self.reactor.advance(27 * ONE_DAY_IN_SECONDS)
+
+        # The user is still counted.
+        r30_results = self.get_success(self.hs.get_datastore().count_r30_users())
+        self.assertEqual(r30_results, {"all": 1, "unknown": 1})
+
+        # Advance another day. The user has now not posted for 28 days.
+        self.reactor.advance(ONE_DAY_IN_SECONDS)
+
+        # The user is now no longer counted in R30.
+        # (This is because the user_ips table has been pruned, which by default
+        # only preserves the last 28 days of entries.)
+        r30_results = self.get_success(self.hs.get_datastore().count_r30_users())
+        self.assertEqual(r30_results, {"all": 0})
+
+    def test_r30_user_must_be_retained_for_at_least_a_month(self):
+        """
+        Tests that a newly-registered user must be retained for a whole month
+        before appearing in the R30 statistic, even if they post every day
+        during that time!
+        """
+        # Register a user and send a message
+        user_id = self.register_user("u1", "secret!")
+        access_token = self.login("u1", "secret!")
+        room_id = self.helper.create_room_as(room_creator=user_id, tok=access_token)
+        self.helper.send(room_id, "message", tok=access_token)
+
+        # Check the user does not contribute to R30 yet.
+        r30_results = self.get_success(self.hs.get_datastore().count_r30_users())
+        self.assertEqual(r30_results, {"all": 0})
+
+        for _ in range(30):
+            # This loop posts a message every day for 30 days
+            self.reactor.advance(ONE_DAY_IN_SECONDS)
+            self.helper.send(room_id, "I'm still here", tok=access_token)
+
+            # Notice that the user *still* does not contribute to R30!
+            r30_results = self.get_success(self.hs.get_datastore().count_r30_users())
+            self.assertEqual(r30_results, {"all": 0})
+
+        self.reactor.advance(ONE_DAY_IN_SECONDS)
+        self.helper.send(room_id, "Still here!", tok=access_token)
+
+        # *Now* the user appears in R30.
+        r30_results = self.get_success(self.hs.get_datastore().count_r30_users())
+        self.assertEqual(r30_results, {"all": 1, "unknown": 1})
diff --git a/tests/config/test_load.py b/tests/config/test_load.py
index ebe2c05165..903c69127d 100644
--- a/tests/config/test_load.py
+++ b/tests/config/test_load.py
@@ -43,7 +43,7 @@ class ConfigLoadingTestCase(unittest.TestCase):
     def test_generates_and_loads_macaroon_secret_key(self):
         self.generate_config()
 
-        with open(self.file, "r") as f:
+        with open(self.file) as f:
             raw = yaml.safe_load(f)
         self.assertIn("macaroon_secret_key", raw)
 
@@ -120,7 +120,7 @@ class ConfigLoadingTestCase(unittest.TestCase):
     def generate_config_and_remove_lines_containing(self, needle):
         self.generate_config()
 
-        with open(self.file, "r") as f:
+        with open(self.file) as f:
             contents = f.readlines()
         contents = [line for line in contents if needle not in line]
         with open(self.file, "w") as f:
diff --git a/tests/events/test_presence_router.py b/tests/events/test_presence_router.py
index 875b0d0a11..3f41e99950 100644
--- a/tests/events/test_presence_router.py
+++ b/tests/events/test_presence_router.py
@@ -152,7 +152,7 @@ class PresenceRouterTestCase(FederatingHomeserverTestCase):
         )
         self.assertEqual(len(presence_updates), 1)
 
-        presence_update = presence_updates[0]  # type: UserPresenceState
+        presence_update: UserPresenceState = presence_updates[0]
         self.assertEqual(presence_update.user_id, self.other_user_one_id)
         self.assertEqual(presence_update.state, "online")
         self.assertEqual(presence_update.status_msg, "boop")
@@ -274,7 +274,7 @@ class PresenceRouterTestCase(FederatingHomeserverTestCase):
         presence_updates, _ = sync_presence(self, self.other_user_id)
         self.assertEqual(len(presence_updates), 1)
 
-        presence_update = presence_updates[0]  # type: UserPresenceState
+        presence_update: UserPresenceState = presence_updates[0]
         self.assertEqual(presence_update.user_id, self.other_user_id)
         self.assertEqual(presence_update.state, "online")
         self.assertEqual(presence_update.status_msg, "I'm online!")
@@ -285,6 +285,10 @@ class PresenceRouterTestCase(FederatingHomeserverTestCase):
         presence_updates, _ = sync_presence(self, self.presence_receiving_user_two_id)
         self.assertEqual(len(presence_updates), 3)
 
+        # We stagger sending of presence, so we need to wait a bit for them to
+        # get sent out.
+        self.reactor.advance(60)
+
         # Test that sending to a remote user works
         remote_user_id = "@far_away_person:island"
 
@@ -301,6 +305,10 @@ class PresenceRouterTestCase(FederatingHomeserverTestCase):
             self.module_api.send_local_online_presence_to([remote_user_id])
         )
 
+        # We stagger sending of presence, so we need to wait a bit for them to
+        # get sent out.
+        self.reactor.advance(60)
+
         # Check that the expected presence updates were sent
         # We explicitly compare using sets as we expect that calling
         # module_api.send_local_online_presence_to will create a presence
@@ -320,7 +328,7 @@ class PresenceRouterTestCase(FederatingHomeserverTestCase):
         )
         for call in calls:
             call_args = call[0]
-            federation_transaction = call_args[0]  # type: Transaction
+            federation_transaction: Transaction = call_args[0]
 
             # Get the sent EDUs in this transaction
             edus = federation_transaction.get_dict()["edus"]
diff --git a/tests/handlers/test_profile.py b/tests/handlers/test_profile.py
index cdb41101b3..2928c4f48c 100644
--- a/tests/handlers/test_profile.py
+++ b/tests/handlers/test_profile.py
@@ -103,7 +103,7 @@ class ProfileTestCase(unittest.HomeserverTestCase):
         )
 
         self.assertIsNone(
-            (self.get_success(self.store.get_profile_displayname(self.frank.localpart)))
+            self.get_success(self.store.get_profile_displayname(self.frank.localpart))
         )
 
     def test_set_my_name_if_disabled(self):
diff --git a/tests/handlers/test_space_summary.py b/tests/handlers/test_space_summary.py
index 9771d3fb3b..3f73ad7f94 100644
--- a/tests/handlers/test_space_summary.py
+++ b/tests/handlers/test_space_summary.py
@@ -14,8 +14,18 @@
 from typing import Any, Iterable, Optional, Tuple
 from unittest import mock
 
-from synapse.api.constants import EventContentFields, RoomTypes
+from synapse.api.constants import (
+    EventContentFields,
+    EventTypes,
+    HistoryVisibility,
+    JoinRules,
+    Membership,
+    RestrictedJoinRuleTypes,
+    RoomTypes,
+)
 from synapse.api.errors import AuthError
+from synapse.api.room_versions import RoomVersions
+from synapse.events import make_event_from_dict
 from synapse.handlers.space_summary import _child_events_comparison_key
 from synapse.rest import admin
 from synapse.rest.client.v1 import login, room
@@ -117,7 +127,7 @@ class SpaceSummaryTestCase(unittest.HomeserverTestCase):
         """Add a child room to a space."""
         self.helper.send_state(
             space_id,
-            event_type="m.space.child",
+            event_type=EventTypes.SpaceChild,
             body={"via": [self.hs.hostname]},
             tok=token,
             state_key=room_id,
@@ -155,26 +165,379 @@ class SpaceSummaryTestCase(unittest.HomeserverTestCase):
         # The user cannot see the space.
         self.get_failure(self.handler.get_space_summary(user2, self.space), AuthError)
 
-        # Joining the room causes it to be visible.
-        self.helper.join(self.space, user2, tok=token2)
+        # If the space is made world-readable it should return a result.
+        self.helper.send_state(
+            self.space,
+            event_type=EventTypes.RoomHistoryVisibility,
+            body={"history_visibility": HistoryVisibility.WORLD_READABLE},
+            tok=self.token,
+        )
         result = self.get_success(self.handler.get_space_summary(user2, self.space))
-
-        # The result should only have the space, but includes the link to the room.
-        self._assert_rooms(result, [self.space])
+        self._assert_rooms(result, [self.space, self.room])
         self._assert_events(result, [(self.space, self.room)])
 
-    def test_world_readable(self):
-        """A world-readable room is visible to everyone."""
+        # Make it not world-readable again and confirm it results in an error.
         self.helper.send_state(
             self.space,
-            event_type="m.room.history_visibility",
-            body={"history_visibility": "world_readable"},
+            event_type=EventTypes.RoomHistoryVisibility,
+            body={"history_visibility": HistoryVisibility.JOINED},
+            tok=self.token,
+        )
+        self.get_failure(self.handler.get_space_summary(user2, self.space), AuthError)
+
+        # Join the space and results should be returned.
+        self.helper.join(self.space, user2, tok=token2)
+        result = self.get_success(self.handler.get_space_summary(user2, self.space))
+        self._assert_rooms(result, [self.space, self.room])
+        self._assert_events(result, [(self.space, self.room)])
+
+    def _create_room_with_join_rule(
+        self, join_rule: str, room_version: Optional[str] = None, **extra_content
+    ) -> str:
+        """Create a room with the given join rule and add it to the space."""
+        room_id = self.helper.create_room_as(
+            self.user,
+            room_version=room_version,
             tok=self.token,
+            extra_content={
+                "initial_state": [
+                    {
+                        "type": EventTypes.JoinRules,
+                        "state_key": "",
+                        "content": {
+                            "join_rule": join_rule,
+                            **extra_content,
+                        },
+                    }
+                ]
+            },
         )
+        self._add_child(self.space, room_id, self.token)
+        return room_id
 
+    def test_filtering(self):
+        """
+        Rooms should be properly filtered to only include rooms the user has access to.
+        """
         user2 = self.register_user("user2", "pass")
+        token2 = self.login("user2", "pass")
 
-        # The space should be visible, as well as the link to the room.
+        # Create a few rooms which will have different properties.
+        public_room = self._create_room_with_join_rule(JoinRules.PUBLIC)
+        knock_room = self._create_room_with_join_rule(
+            JoinRules.KNOCK, room_version=RoomVersions.V7.identifier
+        )
+        not_invited_room = self._create_room_with_join_rule(JoinRules.INVITE)
+        invited_room = self._create_room_with_join_rule(JoinRules.INVITE)
+        self.helper.invite(invited_room, targ=user2, tok=self.token)
+        restricted_room = self._create_room_with_join_rule(
+            JoinRules.MSC3083_RESTRICTED,
+            room_version=RoomVersions.MSC3083.identifier,
+            allow=[],
+        )
+        restricted_accessible_room = self._create_room_with_join_rule(
+            JoinRules.MSC3083_RESTRICTED,
+            room_version=RoomVersions.MSC3083.identifier,
+            allow=[
+                {
+                    "type": RestrictedJoinRuleTypes.ROOM_MEMBERSHIP,
+                    "room_id": self.space,
+                    "via": [self.hs.hostname],
+                }
+            ],
+        )
+        world_readable_room = self._create_room_with_join_rule(JoinRules.INVITE)
+        self.helper.send_state(
+            world_readable_room,
+            event_type=EventTypes.RoomHistoryVisibility,
+            body={"history_visibility": HistoryVisibility.WORLD_READABLE},
+            tok=self.token,
+        )
+        joined_room = self._create_room_with_join_rule(JoinRules.INVITE)
+        self.helper.invite(joined_room, targ=user2, tok=self.token)
+        self.helper.join(joined_room, user2, tok=token2)
+
+        # Join the space.
+        self.helper.join(self.space, user2, tok=token2)
         result = self.get_success(self.handler.get_space_summary(user2, self.space))
-        self._assert_rooms(result, [self.space])
-        self._assert_events(result, [(self.space, self.room)])
+
+        self._assert_rooms(
+            result,
+            [
+                self.space,
+                self.room,
+                public_room,
+                knock_room,
+                invited_room,
+                restricted_accessible_room,
+                world_readable_room,
+                joined_room,
+            ],
+        )
+        self._assert_events(
+            result,
+            [
+                (self.space, self.room),
+                (self.space, public_room),
+                (self.space, knock_room),
+                (self.space, not_invited_room),
+                (self.space, invited_room),
+                (self.space, restricted_room),
+                (self.space, restricted_accessible_room),
+                (self.space, world_readable_room),
+                (self.space, joined_room),
+            ],
+        )
+
+    def test_complex_space(self):
+        """
+        Create a "complex" space to see how it handles things like loops and subspaces.
+        """
+        # Create an inaccessible room.
+        user2 = self.register_user("user2", "pass")
+        token2 = self.login("user2", "pass")
+        room2 = self.helper.create_room_as(user2, is_public=False, tok=token2)
+        # This is a bit odd as "user" is adding a room they don't know about, but
+        # it works for the tests.
+        self._add_child(self.space, room2, self.token)
+
+        # Create a subspace under the space with an additional room in it.
+        subspace = self.helper.create_room_as(
+            self.user,
+            tok=self.token,
+            extra_content={
+                "creation_content": {EventContentFields.ROOM_TYPE: RoomTypes.SPACE}
+            },
+        )
+        subroom = self.helper.create_room_as(self.user, tok=self.token)
+        self._add_child(self.space, subspace, token=self.token)
+        self._add_child(subspace, subroom, token=self.token)
+        # Also add the two rooms from the space into this subspace (causing loops).
+        self._add_child(subspace, self.room, token=self.token)
+        self._add_child(subspace, room2, self.token)
+
+        result = self.get_success(self.handler.get_space_summary(self.user, self.space))
+
+        # The result should include each room a single time and each link.
+        self._assert_rooms(result, [self.space, self.room, subspace, subroom])
+        self._assert_events(
+            result,
+            [
+                (self.space, self.room),
+                (self.space, room2),
+                (self.space, subspace),
+                (subspace, subroom),
+                (subspace, self.room),
+                (subspace, room2),
+            ],
+        )
+
+    def test_fed_complex(self):
+        """
+        Return data over federation and ensure that it is handled properly.
+        """
+        fed_hostname = self.hs.hostname + "2"
+        subspace = "#subspace:" + fed_hostname
+        subroom = "#subroom:" + fed_hostname
+
+        async def summarize_remote_room(
+            _self, room, suggested_only, max_children, exclude_rooms
+        ):
+            # Return some good data, and some bad data:
+            #
+            # * Event *back* to the root room.
+            # * Unrelated events / rooms
+            # * Multiple levels of events (in a not-useful order, e.g. grandchild
+            #   events before child events).
+
+            # Note that these entries are brief, but should contain enough info.
+            rooms = [
+                {
+                    "room_id": subspace,
+                    "world_readable": True,
+                    "room_type": RoomTypes.SPACE,
+                },
+                {
+                    "room_id": subroom,
+                    "world_readable": True,
+                },
+            ]
+            event_content = {"via": [fed_hostname]}
+            events = [
+                {
+                    "room_id": subspace,
+                    "state_key": subroom,
+                    "content": event_content,
+                },
+            ]
+            return rooms, events
+
+        # Add a room to the space which is on another server.
+        self._add_child(self.space, subspace, self.token)
+
+        with mock.patch(
+            "synapse.handlers.space_summary.SpaceSummaryHandler._summarize_remote_room",
+            new=summarize_remote_room,
+        ):
+            result = self.get_success(
+                self.handler.get_space_summary(self.user, self.space)
+            )
+
+        self._assert_rooms(result, [self.space, self.room, subspace, subroom])
+        self._assert_events(
+            result,
+            [
+                (self.space, self.room),
+                (self.space, subspace),
+                (subspace, subroom),
+            ],
+        )
+
+    def test_fed_filtering(self):
+        """
+        Rooms returned over federation should be properly filtered to only include
+        rooms the user has access to.
+        """
+        fed_hostname = self.hs.hostname + "2"
+        subspace = "#subspace:" + fed_hostname
+
+        # Create a few rooms which will have different properties.
+        public_room = "#public:" + fed_hostname
+        knock_room = "#knock:" + fed_hostname
+        not_invited_room = "#not_invited:" + fed_hostname
+        invited_room = "#invited:" + fed_hostname
+        restricted_room = "#restricted:" + fed_hostname
+        restricted_accessible_room = "#restricted_accessible:" + fed_hostname
+        world_readable_room = "#world_readable:" + fed_hostname
+        joined_room = self.helper.create_room_as(self.user, tok=self.token)
+
+        # Poke an invite over federation into the database.
+        fed_handler = self.hs.get_federation_handler()
+        event = make_event_from_dict(
+            {
+                "room_id": invited_room,
+                "event_id": "!abcd:" + fed_hostname,
+                "type": EventTypes.Member,
+                "sender": "@remote:" + fed_hostname,
+                "state_key": self.user,
+                "content": {"membership": Membership.INVITE},
+                "prev_events": [],
+                "auth_events": [],
+                "depth": 1,
+                "origin_server_ts": 1234,
+            }
+        )
+        self.get_success(
+            fed_handler.on_invite_request(fed_hostname, event, RoomVersions.V6)
+        )
+
+        async def summarize_remote_room(
+            _self, room, suggested_only, max_children, exclude_rooms
+        ):
+            # Note that these entries are brief, but should contain enough info.
+            rooms = [
+                {
+                    "room_id": public_room,
+                    "world_readable": False,
+                    "join_rules": JoinRules.PUBLIC,
+                },
+                {
+                    "room_id": knock_room,
+                    "world_readable": False,
+                    "join_rules": JoinRules.KNOCK,
+                },
+                {
+                    "room_id": not_invited_room,
+                    "world_readable": False,
+                    "join_rules": JoinRules.INVITE,
+                },
+                {
+                    "room_id": invited_room,
+                    "world_readable": False,
+                    "join_rules": JoinRules.INVITE,
+                },
+                {
+                    "room_id": restricted_room,
+                    "world_readable": False,
+                    "join_rules": JoinRules.MSC3083_RESTRICTED,
+                    "allowed_spaces": [],
+                },
+                {
+                    "room_id": restricted_accessible_room,
+                    "world_readable": False,
+                    "join_rules": JoinRules.MSC3083_RESTRICTED,
+                    "allowed_spaces": [self.room],
+                },
+                {
+                    "room_id": world_readable_room,
+                    "world_readable": True,
+                    "join_rules": JoinRules.INVITE,
+                },
+                {
+                    "room_id": joined_room,
+                    "world_readable": False,
+                    "join_rules": JoinRules.INVITE,
+                },
+            ]
+
+            # Place each room in the sub-space.
+            event_content = {"via": [fed_hostname]}
+            events = [
+                {
+                    "room_id": subspace,
+                    "state_key": room["room_id"],
+                    "content": event_content,
+                }
+                for room in rooms
+            ]
+
+            # Also include the subspace.
+            rooms.insert(
+                0,
+                {
+                    "room_id": subspace,
+                    "world_readable": True,
+                },
+            )
+            return rooms, events
+
+        # Add a room to the space which is on another server.
+        self._add_child(self.space, subspace, self.token)
+
+        with mock.patch(
+            "synapse.handlers.space_summary.SpaceSummaryHandler._summarize_remote_room",
+            new=summarize_remote_room,
+        ):
+            result = self.get_success(
+                self.handler.get_space_summary(self.user, self.space)
+            )
+
+        self._assert_rooms(
+            result,
+            [
+                self.space,
+                self.room,
+                subspace,
+                public_room,
+                knock_room,
+                invited_room,
+                restricted_accessible_room,
+                world_readable_room,
+                joined_room,
+            ],
+        )
+        self._assert_events(
+            result,
+            [
+                (self.space, self.room),
+                (self.space, subspace),
+                (subspace, public_room),
+                (subspace, knock_room),
+                (subspace, not_invited_room),
+                (subspace, invited_room),
+                (subspace, restricted_room),
+                (subspace, restricted_accessible_room),
+                (subspace, world_readable_room),
+                (subspace, joined_room),
+            ],
+        )
diff --git a/tests/handlers/test_stats.py b/tests/handlers/test_stats.py
index c9d4fd9336..e4059acda3 100644
--- a/tests/handlers/test_stats.py
+++ b/tests/handlers/test_stats.py
@@ -88,16 +88,12 @@ class StatsRoomTests(unittest.HomeserverTestCase):
     def _get_current_stats(self, stats_type, stat_id):
         table, id_col = stats.TYPE_TO_TABLE[stats_type]
 
-        cols = list(stats.ABSOLUTE_STATS_FIELDS[stats_type]) + list(
-            stats.PER_SLICE_FIELDS[stats_type]
-        )
-
-        end_ts = self.store.quantise_stats_time(self.reactor.seconds() * 1000)
+        cols = list(stats.ABSOLUTE_STATS_FIELDS[stats_type])
 
         return self.get_success(
             self.store.db_pool.simple_select_one(
-                table + "_historical",
-                {id_col: stat_id, end_ts: end_ts},
+                table + "_current",
+                {id_col: stat_id},
                 cols,
                 allow_none=True,
             )
@@ -156,115 +152,6 @@ class StatsRoomTests(unittest.HomeserverTestCase):
         self.assertEqual(len(r), 1)
         self.assertEqual(r[0]["topic"], "foo")
 
-    def test_initial_earliest_token(self):
-        """
-        Ingestion via notify_new_event will ignore tokens that the background
-        update have already processed.
-        """
-
-        self.reactor.advance(86401)
-
-        self.hs.config.stats_enabled = False
-        self.handler.stats_enabled = False
-
-        u1 = self.register_user("u1", "pass")
-        u1_token = self.login("u1", "pass")
-
-        u2 = self.register_user("u2", "pass")
-        u2_token = self.login("u2", "pass")
-
-        u3 = self.register_user("u3", "pass")
-        u3_token = self.login("u3", "pass")
-
-        room_1 = self.helper.create_room_as(u1, tok=u1_token)
-        self.helper.send_state(
-            room_1, event_type="m.room.topic", body={"topic": "foo"}, tok=u1_token
-        )
-
-        # Begin the ingestion by creating the temp tables. This will also store
-        # the position that the deltas should begin at, once they take over.
-        self.hs.config.stats_enabled = True
-        self.handler.stats_enabled = True
-        self.store.db_pool.updates._all_done = False
-        self.get_success(
-            self.store.db_pool.simple_update_one(
-                table="stats_incremental_position",
-                keyvalues={},
-                updatevalues={"stream_id": 0},
-            )
-        )
-
-        self.get_success(
-            self.store.db_pool.simple_insert(
-                "background_updates",
-                {"update_name": "populate_stats_prepare", "progress_json": "{}"},
-            )
-        )
-
-        while not self.get_success(
-            self.store.db_pool.updates.has_completed_background_updates()
-        ):
-            self.get_success(
-                self.store.db_pool.updates.do_next_background_update(100), by=0.1
-            )
-
-        # Now, before the table is actually ingested, add some more events.
-        self.helper.invite(room=room_1, src=u1, targ=u2, tok=u1_token)
-        self.helper.join(room=room_1, user=u2, tok=u2_token)
-
-        # orig_delta_processor = self.store.
-
-        # Now do the initial ingestion.
-        self.get_success(
-            self.store.db_pool.simple_insert(
-                "background_updates",
-                {"update_name": "populate_stats_process_rooms", "progress_json": "{}"},
-            )
-        )
-        self.get_success(
-            self.store.db_pool.simple_insert(
-                "background_updates",
-                {
-                    "update_name": "populate_stats_cleanup",
-                    "progress_json": "{}",
-                    "depends_on": "populate_stats_process_rooms",
-                },
-            )
-        )
-
-        self.store.db_pool.updates._all_done = False
-        while not self.get_success(
-            self.store.db_pool.updates.has_completed_background_updates()
-        ):
-            self.get_success(
-                self.store.db_pool.updates.do_next_background_update(100), by=0.1
-            )
-
-        self.reactor.advance(86401)
-
-        # Now add some more events, triggering ingestion. Because of the stream
-        # position being set to before the events sent in the middle, a simpler
-        # implementation would reprocess those events, and say there were four
-        # users, not three.
-        self.helper.invite(room=room_1, src=u1, targ=u3, tok=u1_token)
-        self.helper.join(room=room_1, user=u3, tok=u3_token)
-
-        # self.handler.notify_new_event()
-
-        # We need to let the delta processor advance

-        self.reactor.advance(10 * 60)
-
-        # Get the slices! There should be two -- day 1, and day 2.
-        r = self.get_success(self.store.get_statistics_for_subject("room", room_1, 0))
-
-        self.assertEqual(len(r), 2)
-
-        # The oldest has 2 joined members
-        self.assertEqual(r[-1]["joined_members"], 2)
-
-        # The newest has 3
-        self.assertEqual(r[0]["joined_members"], 3)
-
     def test_create_user(self):
         """
         When we create a user, it should have statistics already ready.
@@ -296,22 +183,6 @@ class StatsRoomTests(unittest.HomeserverTestCase):
         self.assertIsNotNone(r1stats)
         self.assertIsNotNone(r2stats)
 
-        # contains the default things you'd expect in a fresh room
-        self.assertEqual(
-            r1stats["total_events"],
-            EXPT_NUM_STATE_EVTS_IN_FRESH_PUBLIC_ROOM,
-            "Wrong number of total_events in new room's stats!"
-            " You may need to update this if more state events are added to"
-            " the room creation process.",
-        )
-        self.assertEqual(
-            r2stats["total_events"],
-            EXPT_NUM_STATE_EVTS_IN_FRESH_PRIVATE_ROOM,
-            "Wrong number of total_events in new room's stats!"
-            " You may need to update this if more state events are added to"
-            " the room creation process.",
-        )
-
         self.assertEqual(
             r1stats["current_state_events"], EXPT_NUM_STATE_EVTS_IN_FRESH_PUBLIC_ROOM
         )
@@ -327,24 +198,6 @@ class StatsRoomTests(unittest.HomeserverTestCase):
         self.assertEqual(r2stats["invited_members"], 0)
         self.assertEqual(r2stats["banned_members"], 0)
 
-    def test_send_message_increments_total_events(self):
-        """
-        When we send a message, it increments total_events.
-        """
-
-        self._perform_background_initial_update()
-
-        u1 = self.register_user("u1", "pass")
-        u1token = self.login("u1", "pass")
-        r1 = self.helper.create_room_as(u1, tok=u1token)
-        r1stats_ante = self._get_current_stats("room", r1)
-
-        self.helper.send(r1, "hiss", tok=u1token)
-
-        r1stats_post = self._get_current_stats("room", r1)
-
-        self.assertEqual(r1stats_post["total_events"] - r1stats_ante["total_events"], 1)
-
     def test_updating_profile_information_does_not_increase_joined_members_count(self):
         """
         Check that the joined_members count does not increase when a user changes their
@@ -378,7 +231,7 @@ class StatsRoomTests(unittest.HomeserverTestCase):
 
     def test_send_state_event_nonoverwriting(self):
         """
-        When we send a non-overwriting state event, it increments total_events AND current_state_events
+        When we send a non-overwriting state event, it increments current_state_events
         """
 
         self._perform_background_initial_update()
@@ -399,44 +252,14 @@ class StatsRoomTests(unittest.HomeserverTestCase):
 
         r1stats_post = self._get_current_stats("room", r1)
 
-        self.assertEqual(r1stats_post["total_events"] - r1stats_ante["total_events"], 1)
         self.assertEqual(
             r1stats_post["current_state_events"] - r1stats_ante["current_state_events"],
             1,
         )
 
-    def test_send_state_event_overwriting(self):
-        """
-        When we send an overwriting state event, it increments total_events ONLY
-        """
-
-        self._perform_background_initial_update()
-
-        u1 = self.register_user("u1", "pass")
-        u1token = self.login("u1", "pass")
-        r1 = self.helper.create_room_as(u1, tok=u1token)
-
-        self.helper.send_state(
-            r1, "cat.hissing", {"value": True}, tok=u1token, state_key="tabby"
-        )
-
-        r1stats_ante = self._get_current_stats("room", r1)
-
-        self.helper.send_state(
-            r1, "cat.hissing", {"value": False}, tok=u1token, state_key="tabby"
-        )
-
-        r1stats_post = self._get_current_stats("room", r1)
-
-        self.assertEqual(r1stats_post["total_events"] - r1stats_ante["total_events"], 1)
-        self.assertEqual(
-            r1stats_post["current_state_events"] - r1stats_ante["current_state_events"],
-            0,
-        )
-
     def test_join_first_time(self):
         """
-        When a user joins a room for the first time, total_events, current_state_events and
+        When a user joins a room for the first time, current_state_events and
         joined_members should increase by exactly 1.
         """
 
@@ -455,7 +278,6 @@ class StatsRoomTests(unittest.HomeserverTestCase):
 
         r1stats_post = self._get_current_stats("room", r1)
 
-        self.assertEqual(r1stats_post["total_events"] - r1stats_ante["total_events"], 1)
         self.assertEqual(
             r1stats_post["current_state_events"] - r1stats_ante["current_state_events"],
             1,
@@ -466,7 +288,7 @@ class StatsRoomTests(unittest.HomeserverTestCase):
 
     def test_join_after_leave(self):
         """
-        When a user joins a room after being previously left, total_events and
+        When a user joins a room after being previously left,
         joined_members should increase by exactly 1.
         current_state_events should not increase.
         left_members should decrease by exactly 1.
@@ -490,7 +312,6 @@ class StatsRoomTests(unittest.HomeserverTestCase):
 
         r1stats_post = self._get_current_stats("room", r1)
 
-        self.assertEqual(r1stats_post["total_events"] - r1stats_ante["total_events"], 1)
         self.assertEqual(
             r1stats_post["current_state_events"] - r1stats_ante["current_state_events"],
             0,
@@ -504,7 +325,7 @@ class StatsRoomTests(unittest.HomeserverTestCase):
 
     def test_invited(self):
         """
-        When a user invites another user, current_state_events, total_events and
+        When a user invites another user, current_state_events and
         invited_members should increase by exactly 1.
         """
 
@@ -522,7 +343,6 @@ class StatsRoomTests(unittest.HomeserverTestCase):
 
         r1stats_post = self._get_current_stats("room", r1)
 
-        self.assertEqual(r1stats_post["total_events"] - r1stats_ante["total_events"], 1)
         self.assertEqual(
             r1stats_post["current_state_events"] - r1stats_ante["current_state_events"],
             1,
@@ -533,7 +353,7 @@ class StatsRoomTests(unittest.HomeserverTestCase):
 
     def test_join_after_invite(self):
         """
-        When a user joins a room after being invited, total_events and
+        When a user joins a room after being invited and
         joined_members should increase by exactly 1.
         current_state_events should not increase.
         invited_members should decrease by exactly 1.
@@ -556,7 +376,6 @@ class StatsRoomTests(unittest.HomeserverTestCase):
 
         r1stats_post = self._get_current_stats("room", r1)
 
-        self.assertEqual(r1stats_post["total_events"] - r1stats_ante["total_events"], 1)
         self.assertEqual(
             r1stats_post["current_state_events"] - r1stats_ante["current_state_events"],
             0,
@@ -570,7 +389,7 @@ class StatsRoomTests(unittest.HomeserverTestCase):
 
     def test_left(self):
         """
-        When a user leaves a room after joining, total_events and
+        When a user leaves a room after joining and
         left_members should increase by exactly 1.
         current_state_events should not increase.
         joined_members should decrease by exactly 1.
@@ -593,7 +412,6 @@ class StatsRoomTests(unittest.HomeserverTestCase):
 
         r1stats_post = self._get_current_stats("room", r1)
 
-        self.assertEqual(r1stats_post["total_events"] - r1stats_ante["total_events"], 1)
         self.assertEqual(
             r1stats_post["current_state_events"] - r1stats_ante["current_state_events"],
             0,
@@ -607,7 +425,7 @@ class StatsRoomTests(unittest.HomeserverTestCase):
 
     def test_banned(self):
         """
-        When a user is banned from a room after joining, total_events and
+        When a user is banned from a room after joining and
         left_members should increase by exactly 1.
         current_state_events should not increase.
         banned_members should decrease by exactly 1.
@@ -630,7 +448,6 @@ class StatsRoomTests(unittest.HomeserverTestCase):
 
         r1stats_post = self._get_current_stats("room", r1)
 
-        self.assertEqual(r1stats_post["total_events"] - r1stats_ante["total_events"], 1)
         self.assertEqual(
             r1stats_post["current_state_events"] - r1stats_ante["current_state_events"],
             0,
diff --git a/tests/handlers/test_typing.py b/tests/handlers/test_typing.py
index f58afbc244..fa3cff598e 100644
--- a/tests/handlers/test_typing.py
+++ b/tests/handlers/test_typing.py
@@ -38,6 +38,9 @@ U_ONION = UserID.from_string("@onion:farm")
 # Test room id
 ROOM_ID = "a-room"
 
+# Room we're not in
+OTHER_ROOM_ID = "another-room"
+
 
 def _expect_edu_transaction(edu_type, content, origin="test"):
     return {
@@ -115,6 +118,11 @@ class TypingNotificationsTestCase(unittest.HomeserverTestCase):
 
         hs.get_auth().check_user_in_room = check_user_in_room
 
+        async def check_host_in_room(room_id, server_name):
+            return room_id == ROOM_ID
+
+        hs.get_event_auth_handler().check_host_in_room = check_host_in_room
+
         def get_joined_hosts_for_room(room_id):
             return {member.domain for member in self.room_members}
 
@@ -244,6 +252,35 @@ class TypingNotificationsTestCase(unittest.HomeserverTestCase):
             ],
         )
 
+    def test_started_typing_remote_recv_not_in_room(self):
+        self.room_members = [U_APPLE, U_ONION]
+
+        self.assertEquals(self.event_source.get_current_key(), 0)
+
+        channel = self.make_request(
+            "PUT",
+            "/_matrix/federation/v1/send/1000000",
+            _make_edu_transaction_json(
+                "m.typing",
+                content={
+                    "room_id": OTHER_ROOM_ID,
+                    "user_id": U_ONION.to_string(),
+                    "typing": True,
+                },
+            ),
+            federation_auth_origin=b"farm",
+        )
+        self.assertEqual(channel.code, 200)
+
+        self.on_new_event.assert_not_called()
+
+        self.assertEquals(self.event_source.get_current_key(), 0)
+        events = self.get_success(
+            self.event_source.get_new_events(room_ids=[OTHER_ROOM_ID], from_key=0)
+        )
+        self.assertEquals(events[0], [])
+        self.assertEquals(events[1], 0)
+
     @override_config({"send_federation": True})
     def test_stopped_typing(self):
         self.room_members = [U_APPLE, U_BANANA, U_ONION]
diff --git a/tests/http/federation/test_matrix_federation_agent.py b/tests/http/federation/test_matrix_federation_agent.py
index e45980316b..a37bce08c3 100644
--- a/tests/http/federation/test_matrix_federation_agent.py
+++ b/tests/http/federation/test_matrix_federation_agent.py
@@ -273,7 +273,7 @@ class MatrixFederationAgentTests(unittest.TestCase):
         self.assertEqual(response.code, 200)
 
         # Send the body
-        request.write('{ "a": 1 }'.encode("ascii"))
+        request.write(b'{ "a": 1 }')
         request.finish()
 
         self.reactor.pump((0.1,))
diff --git a/tests/http/test_fedclient.py b/tests/http/test_fedclient.py
index ed9a884d76..d9a8b077d3 100644
--- a/tests/http/test_fedclient.py
+++ b/tests/http/test_fedclient.py
@@ -102,7 +102,7 @@ class FederationClientTests(HomeserverTestCase):
         self.assertNoResult(test_d)
 
         # Send it the HTTP response
-        res_json = '{ "a": 1 }'.encode("ascii")
+        res_json = b'{ "a": 1 }'
         protocol.dataReceived(
             b"HTTP/1.1 200 OK\r\n"
             b"Server: Fake\r\n"
@@ -339,10 +339,8 @@ class FederationClientTests(HomeserverTestCase):
 
         # Send it the HTTP response
         client.dataReceived(
-            (
-                b"HTTP/1.1 200 OK\r\nContent-Type: application/json\r\n"
-                b"Server: Fake\r\n\r\n"
-            )
+            b"HTTP/1.1 200 OK\r\nContent-Type: application/json\r\n"
+            b"Server: Fake\r\n\r\n"
         )
 
         # Push by enough to time it out
diff --git a/tests/http/test_proxyagent.py b/tests/http/test_proxyagent.py
index fefc8099c9..437113929a 100644
--- a/tests/http/test_proxyagent.py
+++ b/tests/http/test_proxyagent.py
@@ -205,6 +205,41 @@ class MatrixFederationAgentTests(TestCase):
 
     @patch.dict(os.environ, {"http_proxy": "proxy.com:8888", "no_proxy": "unused.com"})
     def test_http_request_via_proxy(self):
+        """
+        Tests that requests can be made through a proxy.
+        """
+        self._do_http_request_via_proxy(auth_credentials=None)
+
+    @patch.dict(
+        os.environ,
+        {"http_proxy": "bob:pinkponies@proxy.com:8888", "no_proxy": "unused.com"},
+    )
+    def test_http_request_via_proxy_with_auth(self):
+        """
+        Tests that authenticated requests can be made through a proxy.
+        """
+        self._do_http_request_via_proxy(auth_credentials="bob:pinkponies")
+
+    @patch.dict(os.environ, {"https_proxy": "proxy.com", "no_proxy": "unused.com"})
+    def test_https_request_via_proxy(self):
+        """Tests that TLS-encrypted requests can be made through a proxy"""
+        self._do_https_request_via_proxy(auth_credentials=None)
+
+    @patch.dict(
+        os.environ,
+        {"https_proxy": "bob:pinkponies@proxy.com", "no_proxy": "unused.com"},
+    )
+    def test_https_request_via_proxy_with_auth(self):
+        """Tests that authenticated, TLS-encrypted requests can be made through a proxy"""
+        self._do_https_request_via_proxy(auth_credentials="bob:pinkponies")
+
+    def _do_http_request_via_proxy(
+        self,
+        auth_credentials: Optional[str] = None,
+    ):
+        """
+        Tests that requests can be made through a proxy.
+        """
         agent = ProxyAgent(self.reactor, use_proxy=True)
 
         self.reactor.lookups["proxy.com"] = "1.2.3.5"
@@ -229,6 +264,23 @@ class MatrixFederationAgentTests(TestCase):
         self.assertEqual(len(http_server.requests), 1)
 
         request = http_server.requests[0]
+
+        # Check whether auth credentials have been supplied to the proxy
+        proxy_auth_header_values = request.requestHeaders.getRawHeaders(
+            b"Proxy-Authorization"
+        )
+
+        if auth_credentials is not None:
+            # Compute the correct header value for Proxy-Authorization
+            encoded_credentials = base64.b64encode(b"bob:pinkponies")
+            expected_header_value = b"Basic " + encoded_credentials
+
+            # Validate the header's value
+            self.assertIn(expected_header_value, proxy_auth_header_values)
+        else:
+            # Check that the Proxy-Authorization header has not been supplied to the proxy
+            self.assertIsNone(proxy_auth_header_values)
+
         self.assertEqual(request.method, b"GET")
         self.assertEqual(request.path, b"http://test.com")
         self.assertEqual(request.requestHeaders.getRawHeaders(b"host"), [b"test.com"])
@@ -241,19 +293,6 @@ class MatrixFederationAgentTests(TestCase):
         body = self.successResultOf(treq.content(resp))
         self.assertEqual(body, b"result")
 
-    @patch.dict(os.environ, {"https_proxy": "proxy.com", "no_proxy": "unused.com"})
-    def test_https_request_via_proxy(self):
-        """Tests that TLS-encrypted requests can be made through a proxy"""
-        self._do_https_request_via_proxy(auth_credentials=None)
-
-    @patch.dict(
-        os.environ,
-        {"https_proxy": "bob:pinkponies@proxy.com", "no_proxy": "unused.com"},
-    )
-    def test_https_request_via_proxy_with_auth(self):
-        """Tests that authenticated, TLS-encrypted requests can be made through a proxy"""
-        self._do_https_request_via_proxy(auth_credentials="bob:pinkponies")
-
     def _do_https_request_via_proxy(
         self,
         auth_credentials: Optional[str] = None,
diff --git a/tests/module_api/test_api.py b/tests/module_api/test_api.py
index 2c68b9a13c..81d9e2f484 100644
--- a/tests/module_api/test_api.py
+++ b/tests/module_api/test_api.py
@@ -100,9 +100,9 @@ class ModuleApiTestCase(HomeserverTestCase):
             "content": content,
             "sender": user_id,
         }
-        event = self.get_success(
+        event: EventBase = self.get_success(
             self.module_api.create_and_send_event_into_room(event_dict)
-        )  # type: EventBase
+        )
         self.assertEqual(event.sender, user_id)
         self.assertEqual(event.type, "m.room.message")
         self.assertEqual(event.room_id, room_id)
@@ -136,9 +136,9 @@ class ModuleApiTestCase(HomeserverTestCase):
             "sender": user_id,
             "state_key": "",
         }
-        event = self.get_success(
+        event: EventBase = self.get_success(
             self.module_api.create_and_send_event_into_room(event_dict)
-        )  # type: EventBase
+        )
         self.assertEqual(event.sender, user_id)
         self.assertEqual(event.type, "m.room.power_levels")
         self.assertEqual(event.room_id, room_id)
@@ -281,7 +281,7 @@ class ModuleApiTestCase(HomeserverTestCase):
         )
         for call in calls:
             call_args = call[0]
-            federation_transaction = call_args[0]  # type: Transaction
+            federation_transaction: Transaction = call_args[0]
 
             # Get the sent EDUs in this transaction
             edus = federation_transaction.get_dict()["edus"]
@@ -390,7 +390,7 @@ def _test_sending_local_online_presence_to_local_user(
     )
     test_case.assertEqual(len(presence_updates), 1)
 
-    presence_update = presence_updates[0]  # type: UserPresenceState
+    presence_update: UserPresenceState = presence_updates[0]
     test_case.assertEqual(presence_update.user_id, test_case.presence_sender_id)
     test_case.assertEqual(presence_update.state, "online")
 
@@ -443,7 +443,7 @@ def _test_sending_local_online_presence_to_local_user(
     )
     test_case.assertEqual(len(presence_updates), 1)
 
-    presence_update = presence_updates[0]  # type: UserPresenceState
+    presence_update: UserPresenceState = presence_updates[0]
     test_case.assertEqual(presence_update.user_id, test_case.presence_sender_id)
     test_case.assertEqual(presence_update.state, "online")
 
@@ -454,7 +454,7 @@ def _test_sending_local_online_presence_to_local_user(
     )
     test_case.assertEqual(len(presence_updates), 1)
 
-    presence_update = presence_updates[0]  # type: UserPresenceState
+    presence_update: UserPresenceState = presence_updates[0]
     test_case.assertEqual(presence_update.user_id, test_case.presence_sender_id)
     test_case.assertEqual(presence_update.state, "online")
 
diff --git a/tests/replication/_base.py b/tests/replication/_base.py
index 624bd1b927..e9fd991718 100644
--- a/tests/replication/_base.py
+++ b/tests/replication/_base.py
@@ -53,9 +53,9 @@ class BaseStreamTestCase(unittest.HomeserverTestCase):
         # build a replication server
         server_factory = ReplicationStreamProtocolFactory(hs)
         self.streamer = hs.get_replication_streamer()
-        self.server = server_factory.buildProtocol(
+        self.server: ServerReplicationStreamProtocol = server_factory.buildProtocol(
             None
-        )  # type: ServerReplicationStreamProtocol
+        )
 
         # Make a new HomeServer object for the worker
         self.reactor.lookups["testserv"] = "1.2.3.4"
@@ -195,7 +195,7 @@ class BaseStreamTestCase(unittest.HomeserverTestCase):
         fetching updates for given stream.
         """
 
-        path = request.path  # type: bytes  # type: ignore
+        path: bytes = request.path  # type: ignore
         self.assertRegex(
             path,
             br"^/_synapse/replication/get_repl_stream_updates/%s/[^/]+$"
@@ -212,7 +212,7 @@ class BaseMultiWorkerStreamTestCase(unittest.HomeserverTestCase):
     unlike `BaseStreamTestCase`.
     """
 
-    servlets = []  # type: List[Callable[[HomeServer, JsonResource], None]]
+    servlets: List[Callable[[HomeServer, JsonResource], None]] = []
 
     def setUp(self):
         super().setUp()
@@ -448,7 +448,7 @@ class TestReplicationDataHandler(ReplicationDataHandler):
         super().__init__(hs)
 
         # list of received (stream_name, token, row) tuples
-        self.received_rdata_rows = []  # type: List[Tuple[str, int, Any]]
+        self.received_rdata_rows: List[Tuple[str, int, Any]] = []
 
     async def on_rdata(self, stream_name, instance_name, token, rows):
         await super().on_rdata(stream_name, instance_name, token, rows)
@@ -484,7 +484,7 @@ class FakeRedisPubSubServer:
 class FakeRedisPubSubProtocol(Protocol):
     """A connection from a client talking to the fake Redis server."""
 
-    transport = None  # type: Optional[FakeTransport]
+    transport: Optional[FakeTransport] = None
 
     def __init__(self, server: FakeRedisPubSubServer):
         self._server = server
@@ -550,12 +550,12 @@ class FakeRedisPubSubProtocol(Protocol):
         if obj is None:
             return "$-1\r\n"
         if isinstance(obj, str):
-            return "${len}\r\n{str}\r\n".format(len=len(obj), str=obj)
+            return f"${len(obj)}\r\n{obj}\r\n"
         if isinstance(obj, int):
-            return ":{val}\r\n".format(val=obj)
+            return f":{obj}\r\n"
         if isinstance(obj, (list, tuple)):
             items = "".join(self.encode(a) for a in obj)
-            return "*{len}\r\n{items}".format(len=len(obj), items=items)
+            return f"*{len(obj)}\r\n{items}"
 
         raise Exception("Unrecognized type for encoding redis: %r: %r", type(obj), obj)
 
diff --git a/tests/replication/tcp/streams/test_events.py b/tests/replication/tcp/streams/test_events.py
index f51fa0a79e..666008425a 100644
--- a/tests/replication/tcp/streams/test_events.py
+++ b/tests/replication/tcp/streams/test_events.py
@@ -135,9 +135,9 @@ class EventsStreamTestCase(BaseStreamTestCase):
         )
 
         # this is the point in the DAG where we make a fork
-        fork_point = self.get_success(
+        fork_point: List[str] = self.get_success(
             self.hs.get_datastore().get_latest_event_ids_in_room(self.room_id)
-        )  # type: List[str]
+        )
 
         events = [
             self._inject_state_event(sender=OTHER_USER)
@@ -238,7 +238,7 @@ class EventsStreamTestCase(BaseStreamTestCase):
         self.assertEqual(row.data.event_id, pl_event.event_id)
 
         # the state rows are unsorted
-        state_rows = []  # type: List[EventsStreamCurrentStateRow]
+        state_rows: List[EventsStreamCurrentStateRow] = []
         for stream_name, _, row in received_rows:
             self.assertEqual("events", stream_name)
             self.assertIsInstance(row, EventsStreamRow)
@@ -290,11 +290,11 @@ class EventsStreamTestCase(BaseStreamTestCase):
         )
 
         # this is the point in the DAG where we make a fork
-        fork_point = self.get_success(
+        fork_point: List[str] = self.get_success(
             self.hs.get_datastore().get_latest_event_ids_in_room(self.room_id)
-        )  # type: List[str]
+        )
 
-        events = []  # type: List[EventBase]
+        events: List[EventBase] = []
         for user in user_ids:
             events.extend(
                 self._inject_state_event(sender=user) for _ in range(STATES_PER_USER)
@@ -355,7 +355,7 @@ class EventsStreamTestCase(BaseStreamTestCase):
             self.assertEqual(row.data.event_id, pl_events[i].event_id)
 
             # the state rows are unsorted
-            state_rows = []  # type: List[EventsStreamCurrentStateRow]
+            state_rows: List[EventsStreamCurrentStateRow] = []
             for _ in range(STATES_PER_USER + 1):
                 stream_name, token, row = received_rows.pop(0)
                 self.assertEqual("events", stream_name)
diff --git a/tests/replication/tcp/streams/test_receipts.py b/tests/replication/tcp/streams/test_receipts.py
index 7f5d932f0b..38e292c1ab 100644
--- a/tests/replication/tcp/streams/test_receipts.py
+++ b/tests/replication/tcp/streams/test_receipts.py
@@ -43,7 +43,7 @@ class ReceiptsStreamTestCase(BaseStreamTestCase):
         stream_name, _, token, rdata_rows = self.test_handler.on_rdata.call_args[0]
         self.assertEqual(stream_name, "receipts")
         self.assertEqual(1, len(rdata_rows))
-        row = rdata_rows[0]  # type: ReceiptsStream.ReceiptsStreamRow
+        row: ReceiptsStream.ReceiptsStreamRow = rdata_rows[0]
         self.assertEqual("!room:blue", row.room_id)
         self.assertEqual("m.read", row.receipt_type)
         self.assertEqual(USER_ID, row.user_id)
@@ -75,7 +75,7 @@ class ReceiptsStreamTestCase(BaseStreamTestCase):
         self.assertEqual(token, 3)
         self.assertEqual(1, len(rdata_rows))
 
-        row = rdata_rows[0]  # type: ReceiptsStream.ReceiptsStreamRow
+        row: ReceiptsStream.ReceiptsStreamRow = rdata_rows[0]
         self.assertEqual("!room2:blue", row.room_id)
         self.assertEqual("m.read", row.receipt_type)
         self.assertEqual(USER_ID, row.user_id)
diff --git a/tests/replication/tcp/streams/test_typing.py b/tests/replication/tcp/streams/test_typing.py
index ecd360c2d0..3ff5afc6e5 100644
--- a/tests/replication/tcp/streams/test_typing.py
+++ b/tests/replication/tcp/streams/test_typing.py
@@ -47,7 +47,7 @@ class TypingStreamTestCase(BaseStreamTestCase):
         stream_name, _, token, rdata_rows = self.test_handler.on_rdata.call_args[0]
         self.assertEqual(stream_name, "typing")
         self.assertEqual(1, len(rdata_rows))
-        row = rdata_rows[0]  # type: TypingStream.TypingStreamRow
+        row: TypingStream.TypingStreamRow = rdata_rows[0]
         self.assertEqual(ROOM_ID, row.room_id)
         self.assertEqual([USER_ID], row.user_ids)
 
@@ -102,7 +102,7 @@ class TypingStreamTestCase(BaseStreamTestCase):
         stream_name, _, token, rdata_rows = self.test_handler.on_rdata.call_args[0]
         self.assertEqual(stream_name, "typing")
         self.assertEqual(1, len(rdata_rows))
-        row = rdata_rows[0]  # type: TypingStream.TypingStreamRow
+        row: TypingStream.TypingStreamRow = rdata_rows[0]
         self.assertEqual(ROOM_ID, row.room_id)
         self.assertEqual([USER_ID], row.user_ids)
 
diff --git a/tests/replication/test_multi_media_repo.py b/tests/replication/test_multi_media_repo.py
index 76e6644353..ffa425328f 100644
--- a/tests/replication/test_multi_media_repo.py
+++ b/tests/replication/test_multi_media_repo.py
@@ -31,7 +31,7 @@ from tests.server import FakeChannel, FakeSite, FakeTransport, make_request
 
 logger = logging.getLogger(__name__)
 
-test_server_connection_factory = None  # type: Optional[TestServerTLSConnectionFactory]
+test_server_connection_factory: Optional[TestServerTLSConnectionFactory] = None
 
 
 class MediaRepoShardTestCase(BaseMultiWorkerStreamTestCase):
@@ -70,7 +70,7 @@ class MediaRepoShardTestCase(BaseMultiWorkerStreamTestCase):
             self.reactor,
             FakeSite(resource),
             "GET",
-            "/{}/{}".format(target, media_id),
+            f"/{target}/{media_id}",
             shorthand=False,
             access_token=self.access_token,
             await_result=False,
@@ -113,7 +113,7 @@ class MediaRepoShardTestCase(BaseMultiWorkerStreamTestCase):
         self.assertEqual(request.method, b"GET")
         self.assertEqual(
             request.path,
-            "/_matrix/media/r0/download/{}/{}".format(target, media_id).encode("utf-8"),
+            f"/_matrix/media/r0/download/{target}/{media_id}".encode("utf-8"),
         )
         self.assertEqual(
             request.requestHeaders.getRawHeaders(b"host"), [target.encode("utf-8")]
diff --git a/tests/replication/test_sharded_event_persister.py b/tests/replication/test_sharded_event_persister.py
index 5eca5c165d..f3615af97e 100644
--- a/tests/replication/test_sharded_event_persister.py
+++ b/tests/replication/test_sharded_event_persister.py
@@ -211,7 +211,7 @@ class EventPersisterShardTestCase(BaseMultiWorkerStreamTestCase):
             self.reactor,
             sync_hs_site,
             "GET",
-            "/sync?since={}".format(next_batch),
+            f"/sync?since={next_batch}",
             access_token=access_token,
         )
 
@@ -241,7 +241,7 @@ class EventPersisterShardTestCase(BaseMultiWorkerStreamTestCase):
             self.reactor,
             sync_hs_site,
             "GET",
-            "/sync?since={}".format(vector_clock_token),
+            f"/sync?since={vector_clock_token}",
             access_token=access_token,
         )
 
@@ -266,7 +266,7 @@ class EventPersisterShardTestCase(BaseMultiWorkerStreamTestCase):
             self.reactor,
             sync_hs_site,
             "GET",
-            "/sync?since={}".format(next_batch),
+            f"/sync?since={next_batch}",
             access_token=access_token,
         )
 
diff --git a/tests/rest/admin/test_admin.py b/tests/rest/admin/test_admin.py
index 2f7090e554..a7c6e595b9 100644
--- a/tests/rest/admin/test_admin.py
+++ b/tests/rest/admin/test_admin.py
@@ -66,7 +66,7 @@ class DeleteGroupTestCase(unittest.HomeserverTestCase):
         # Create a new group
         channel = self.make_request(
             "POST",
-            "/create_group".encode("ascii"),
+            b"/create_group",
             access_token=self.admin_user_tok,
             content={"localpart": "test"},
         )
@@ -129,9 +129,7 @@ class DeleteGroupTestCase(unittest.HomeserverTestCase):
 
     def _get_groups_user_is_in(self, access_token):
         """Returns the list of groups the user is in (given their access token)"""
-        channel = self.make_request(
-            "GET", "/joined_groups".encode("ascii"), access_token=access_token
-        )
+        channel = self.make_request("GET", b"/joined_groups", access_token=access_token)
 
         self.assertEqual(200, int(channel.result["code"]), msg=channel.result["body"])
 
diff --git a/tests/rest/admin/test_room.py b/tests/rest/admin/test_room.py
index ee071c2477..17ec8bfd3b 100644
--- a/tests/rest/admin/test_room.py
+++ b/tests/rest/admin/test_room.py
@@ -535,7 +535,7 @@ class DeleteRoomTestCase(unittest.HomeserverTestCase):
                 )
             )
 
-            self.assertEqual(count, 0, msg="Rows not purged in {}".format(table))
+            self.assertEqual(count, 0, msg=f"Rows not purged in {table}")
 
     def _assert_peek(self, room_id, expect_code):
         """Assert that the admin user can (or cannot) peek into the room."""
@@ -599,7 +599,7 @@ class PurgeRoomTestCase(unittest.HomeserverTestCase):
                 )
             )
 
-            self.assertEqual(count, 0, msg="Rows not purged in {}".format(table))
+            self.assertEqual(count, 0, msg=f"Rows not purged in {table}")
 
 
 class RoomTestCase(unittest.HomeserverTestCase):
@@ -1280,7 +1280,7 @@ class JoinAliasRoomTestCase(unittest.HomeserverTestCase):
         self.public_room_id = self.helper.create_room_as(
             self.creator, tok=self.creator_tok, is_public=True
         )
-        self.url = "/_synapse/admin/v1/join/{}".format(self.public_room_id)
+        self.url = f"/_synapse/admin/v1/join/{self.public_room_id}"
 
     def test_requester_is_no_admin(self):
         """
@@ -1420,7 +1420,7 @@ class JoinAliasRoomTestCase(unittest.HomeserverTestCase):
         private_room_id = self.helper.create_room_as(
             self.creator, tok=self.creator_tok, is_public=False
         )
-        url = "/_synapse/admin/v1/join/{}".format(private_room_id)
+        url = f"/_synapse/admin/v1/join/{private_room_id}"
         body = json.dumps({"user_id": self.second_user_id})
 
         channel = self.make_request(
@@ -1463,7 +1463,7 @@ class JoinAliasRoomTestCase(unittest.HomeserverTestCase):
 
         # Join user to room.
 
-        url = "/_synapse/admin/v1/join/{}".format(private_room_id)
+        url = f"/_synapse/admin/v1/join/{private_room_id}"
         body = json.dumps({"user_id": self.second_user_id})
 
         channel = self.make_request(
@@ -1493,7 +1493,7 @@ class JoinAliasRoomTestCase(unittest.HomeserverTestCase):
         private_room_id = self.helper.create_room_as(
             self.admin_user, tok=self.admin_user_tok, is_public=False
         )
-        url = "/_synapse/admin/v1/join/{}".format(private_room_id)
+        url = f"/_synapse/admin/v1/join/{private_room_id}"
         body = json.dumps({"user_id": self.second_user_id})
 
         channel = self.make_request(
@@ -1633,7 +1633,7 @@ class MakeRoomAdminTestCase(unittest.HomeserverTestCase):
 
         channel = self.make_request(
             "POST",
-            "/_synapse/admin/v1/rooms/{}/make_room_admin".format(room_id),
+            f"/_synapse/admin/v1/rooms/{room_id}/make_room_admin",
             content={},
             access_token=self.admin_user_tok,
         )
@@ -1660,7 +1660,7 @@ class MakeRoomAdminTestCase(unittest.HomeserverTestCase):
 
         channel = self.make_request(
             "POST",
-            "/_synapse/admin/v1/rooms/{}/make_room_admin".format(room_id),
+            f"/_synapse/admin/v1/rooms/{room_id}/make_room_admin",
             content={},
             access_token=self.admin_user_tok,
         )
@@ -1686,7 +1686,7 @@ class MakeRoomAdminTestCase(unittest.HomeserverTestCase):
 
         channel = self.make_request(
             "POST",
-            "/_synapse/admin/v1/rooms/{}/make_room_admin".format(room_id),
+            f"/_synapse/admin/v1/rooms/{room_id}/make_room_admin",
             content={"user_id": self.second_user_id},
             access_token=self.admin_user_tok,
         )
@@ -1720,7 +1720,7 @@ class MakeRoomAdminTestCase(unittest.HomeserverTestCase):
 
         channel = self.make_request(
             "POST",
-            "/_synapse/admin/v1/rooms/{}/make_room_admin".format(room_id),
+            f"/_synapse/admin/v1/rooms/{room_id}/make_room_admin",
             content={},
             access_token=self.admin_user_tok,
         )
@@ -1753,7 +1753,6 @@ PURGE_TABLES = [
     "room_memberships",
     "room_stats_state",
     "room_stats_current",
-    "room_stats_historical",
     "room_stats_earliest_token",
     "rooms",
     "stream_ordering_to_exterm",
diff --git a/tests/rest/client/test_third_party_rules.py b/tests/rest/client/test_third_party_rules.py
index e1fe72fc5d..c5e1c5458b 100644
--- a/tests/rest/client/test_third_party_rules.py
+++ b/tests/rest/client/test_third_party_rules.py
@@ -233,11 +233,11 @@ class ThirdPartyRulesTestCase(unittest.HomeserverTestCase):
             "content": content,
             "sender": self.user_id,
         }
-        event = self.get_success(
+        event: EventBase = self.get_success(
             current_rules_module().module_api.create_and_send_event_into_room(
                 event_dict
             )
-        )  # type: EventBase
+        )
 
         self.assertEquals(event.sender, self.user_id)
         self.assertEquals(event.room_id, self.room_id)
diff --git a/tests/rest/client/v1/test_login.py b/tests/rest/client/v1/test_login.py
index 605b952316..7eba69642a 100644
--- a/tests/rest/client/v1/test_login.py
+++ b/tests/rest/client/v1/test_login.py
@@ -453,7 +453,7 @@ class MultiSSOTestCase(unittest.HomeserverTestCase):
         self.assertEqual(channel.code, 200, channel.result)
 
         # stick the flows results in a dict by type
-        flow_results = {}  # type: Dict[str, Any]
+        flow_results: Dict[str, Any] = {}
         for f in channel.json_body["flows"]:
             flow_type = f["type"]
             self.assertNotIn(
@@ -501,7 +501,7 @@ class MultiSSOTestCase(unittest.HomeserverTestCase):
         p.close()
 
         # there should be a link for each href
-        returned_idps = []  # type: List[str]
+        returned_idps: List[str] = []
         for link in p.links:
             path, query = link.split("?", 1)
             self.assertEqual(path, "pick_idp")
@@ -582,7 +582,7 @@ class MultiSSOTestCase(unittest.HomeserverTestCase):
         # ... and should have set a cookie including the redirect url
         cookie_headers = channel.headers.getRawHeaders("Set-Cookie")
         assert cookie_headers
-        cookies = {}  # type: Dict[str, str]
+        cookies: Dict[str, str] = {}
         for h in cookie_headers:
             key, value = h.split(";")[0].split("=", maxsplit=1)
             cookies[key] = value
@@ -874,9 +874,7 @@ class JWTTestCase(unittest.HomeserverTestCase):
 
     def jwt_encode(self, payload: Dict[str, Any], secret: str = jwt_secret) -> str:
         # PyJWT 2.0.0 changed the return type of jwt.encode from bytes to str.
-        result = jwt.encode(
-            payload, secret, self.jwt_algorithm
-        )  # type: Union[str, bytes]
+        result: Union[str, bytes] = jwt.encode(payload, secret, self.jwt_algorithm)
         if isinstance(result, bytes):
             return result.decode("ascii")
         return result
@@ -1084,7 +1082,7 @@ class JWTPubKeyTestCase(unittest.HomeserverTestCase):
 
     def jwt_encode(self, payload: Dict[str, Any], secret: str = jwt_privatekey) -> str:
         # PyJWT 2.0.0 changed the return type of jwt.encode from bytes to str.
-        result = jwt.encode(payload, secret, "RS256")  # type: Union[bytes,str]
+        result: Union[bytes, str] = jwt.encode(payload, secret, "RS256")
         if isinstance(result, bytes):
             return result.decode("ascii")
         return result
@@ -1272,7 +1270,7 @@ class UsernamePickerTestCase(HomeserverTestCase):
         self.assertEqual(picker_url, "/_synapse/client/pick_username/account_details")
 
         # ... with a username_mapping_session cookie
-        cookies = {}  # type: Dict[str,str]
+        cookies: Dict[str, str] = {}
         channel.extract_cookies(cookies)
         self.assertIn("username_mapping_session", cookies)
         session_id = cookies["username_mapping_session"]
diff --git a/tests/rest/client/v1/test_rooms.py b/tests/rest/client/v1/test_rooms.py
index e94566ffd7..3df070c936 100644
--- a/tests/rest/client/v1/test_rooms.py
+++ b/tests/rest/client/v1/test_rooms.py
@@ -1206,7 +1206,7 @@ class RoomMembershipReasonTestCase(unittest.HomeserverTestCase):
         reason = "hello"
         channel = self.make_request(
             "POST",
-            "/_matrix/client/r0/rooms/{}/join".format(self.room_id),
+            f"/_matrix/client/r0/rooms/{self.room_id}/join",
             content={"reason": reason},
             access_token=self.second_tok,
         )
@@ -1220,7 +1220,7 @@ class RoomMembershipReasonTestCase(unittest.HomeserverTestCase):
         reason = "hello"
         channel = self.make_request(
             "POST",
-            "/_matrix/client/r0/rooms/{}/leave".format(self.room_id),
+            f"/_matrix/client/r0/rooms/{self.room_id}/leave",
             content={"reason": reason},
             access_token=self.second_tok,
         )
@@ -1234,7 +1234,7 @@ class RoomMembershipReasonTestCase(unittest.HomeserverTestCase):
         reason = "hello"
         channel = self.make_request(
             "POST",
-            "/_matrix/client/r0/rooms/{}/kick".format(self.room_id),
+            f"/_matrix/client/r0/rooms/{self.room_id}/kick",
             content={"reason": reason, "user_id": self.second_user_id},
             access_token=self.second_tok,
         )
@@ -1248,7 +1248,7 @@ class RoomMembershipReasonTestCase(unittest.HomeserverTestCase):
         reason = "hello"
         channel = self.make_request(
             "POST",
-            "/_matrix/client/r0/rooms/{}/ban".format(self.room_id),
+            f"/_matrix/client/r0/rooms/{self.room_id}/ban",
             content={"reason": reason, "user_id": self.second_user_id},
             access_token=self.creator_tok,
         )
@@ -1260,7 +1260,7 @@ class RoomMembershipReasonTestCase(unittest.HomeserverTestCase):
         reason = "hello"
         channel = self.make_request(
             "POST",
-            "/_matrix/client/r0/rooms/{}/unban".format(self.room_id),
+            f"/_matrix/client/r0/rooms/{self.room_id}/unban",
             content={"reason": reason, "user_id": self.second_user_id},
             access_token=self.creator_tok,
         )
@@ -1272,7 +1272,7 @@ class RoomMembershipReasonTestCase(unittest.HomeserverTestCase):
         reason = "hello"
         channel = self.make_request(
             "POST",
-            "/_matrix/client/r0/rooms/{}/invite".format(self.room_id),
+            f"/_matrix/client/r0/rooms/{self.room_id}/invite",
             content={"reason": reason, "user_id": self.second_user_id},
             access_token=self.creator_tok,
         )
@@ -1291,7 +1291,7 @@ class RoomMembershipReasonTestCase(unittest.HomeserverTestCase):
         reason = "hello"
         channel = self.make_request(
             "POST",
-            "/_matrix/client/r0/rooms/{}/leave".format(self.room_id),
+            f"/_matrix/client/r0/rooms/{self.room_id}/leave",
             content={"reason": reason},
             access_token=self.second_tok,
         )
diff --git a/tests/rest/client/v2_alpha/test_relations.py b/tests/rest/client/v2_alpha/test_relations.py
index 856aa8682f..2e2f94742e 100644
--- a/tests/rest/client/v2_alpha/test_relations.py
+++ b/tests/rest/client/v2_alpha/test_relations.py
@@ -273,7 +273,7 @@ class RelationsTestCase(unittest.HomeserverTestCase):
 
         prev_token = None
         found_event_ids = []
-        encoded_key = urllib.parse.quote_plus("👍".encode("utf-8"))
+        encoded_key = urllib.parse.quote_plus("👍".encode())
         for _ in range(20):
             from_token = ""
             if prev_token:
diff --git a/tests/rest/client/v2_alpha/test_report_event.py b/tests/rest/client/v2_alpha/test_report_event.py
index 1ec6b05e5b..a76a6fef1e 100644
--- a/tests/rest/client/v2_alpha/test_report_event.py
+++ b/tests/rest/client/v2_alpha/test_report_event.py
@@ -41,7 +41,7 @@ class ReportEventTestCase(unittest.HomeserverTestCase):
         self.helper.join(self.room_id, user=self.admin_user, tok=self.admin_user_tok)
         resp = self.helper.send(self.room_id, tok=self.admin_user_tok)
         self.event_id = resp["event_id"]
-        self.report_path = "rooms/{}/report/{}".format(self.room_id, self.event_id)
+        self.report_path = f"rooms/{self.room_id}/report/{self.event_id}"
 
     def test_reason_str_and_score_int(self):
         data = {"reason": "this makes me sad", "score": -100}
diff --git a/tests/rest/media/v1/test_media_storage.py b/tests/rest/media/v1/test_media_storage.py
index 95e7075841..2d6b49692e 100644
--- a/tests/rest/media/v1/test_media_storage.py
+++ b/tests/rest/media/v1/test_media_storage.py
@@ -310,7 +310,7 @@ class MediaRepoTests(unittest.HomeserverTestCase):
         correctly decode it as the UTF-8 string, and use filename* in the
         response.
         """
-        filename = parse.quote("\u2603".encode("utf8")).encode("ascii")
+        filename = parse.quote("\u2603".encode()).encode("ascii")
         channel = self._req(
             b"inline; filename*=utf-8''" + filename + self.test_image.extension
         )
diff --git a/tests/server.py b/tests/server.py
index f32d8dc375..6fddd3b305 100644
--- a/tests/server.py
+++ b/tests/server.py
@@ -52,7 +52,7 @@ class FakeChannel:
     _reactor = attr.ib()
     result = attr.ib(type=dict, default=attr.Factory(dict))
     _ip = attr.ib(type=str, default="127.0.0.1")
-    _producer = None  # type: Optional[Union[IPullProducer, IPushProducer]]
+    _producer: Optional[Union[IPullProducer, IPushProducer]] = None
 
     @property
     def json_body(self):
@@ -316,8 +316,10 @@ class ThreadedMemoryReactorClock(MemoryReactorClock):
 
         self._tcp_callbacks = {}
         self._udp = []
-        lookups = self.lookups = {}  # type: Dict[str, str]
-        self._thread_callbacks = deque()  # type: Deque[Callable[[], None]]
+        self.lookups: Dict[str, str] = {}
+        self._thread_callbacks: Deque[Callable[[], None]] = deque()
+
+        lookups = self.lookups
 
         @implementer(IResolverSimple)
         class FakeResolver:
diff --git a/tests/storage/test_background_update.py b/tests/storage/test_background_update.py
index 069db0edc4..0da42b5ac5 100644
--- a/tests/storage/test_background_update.py
+++ b/tests/storage/test_background_update.py
@@ -7,9 +7,7 @@ from tests import unittest
 
 class BackgroundUpdateTestCase(unittest.HomeserverTestCase):
     def prepare(self, reactor, clock, homeserver):
-        self.updates = (
-            self.hs.get_datastore().db_pool.updates
-        )  # type: BackgroundUpdater
+        self.updates: BackgroundUpdater = self.hs.get_datastore().db_pool.updates
         # the base test class should have run the real bg updates for us
         self.assertTrue(
             self.get_success(self.updates.has_completed_background_updates())
diff --git a/tests/storage/test_directory.py b/tests/storage/test_directory.py
index 41bef62ca8..43628ce44f 100644
--- a/tests/storage/test_directory.py
+++ b/tests/storage/test_directory.py
@@ -59,5 +59,5 @@ class DirectoryStoreTestCase(HomeserverTestCase):
         self.assertEqual(self.room.to_string(), room_id)
 
         self.assertIsNone(
-            (self.get_success(self.store.get_association_from_room_alias(self.alias)))
+            self.get_success(self.store.get_association_from_room_alias(self.alias))
         )
diff --git a/tests/storage/test_id_generators.py b/tests/storage/test_id_generators.py
index 792b1c44c1..7486078284 100644
--- a/tests/storage/test_id_generators.py
+++ b/tests/storage/test_id_generators.py
@@ -27,7 +27,7 @@ class MultiWriterIdGeneratorTestCase(HomeserverTestCase):
 
     def prepare(self, reactor, clock, hs):
         self.store = hs.get_datastore()
-        self.db_pool = self.store.db_pool  # type: DatabasePool
+        self.db_pool: DatabasePool = self.store.db_pool
 
         self.get_success(self.db_pool.runInteraction("_setup_db", self._setup_db))
 
@@ -460,7 +460,7 @@ class BackwardsMultiWriterIdGeneratorTestCase(HomeserverTestCase):
 
     def prepare(self, reactor, clock, hs):
         self.store = hs.get_datastore()
-        self.db_pool = self.store.db_pool  # type: DatabasePool
+        self.db_pool: DatabasePool = self.store.db_pool
 
         self.get_success(self.db_pool.runInteraction("_setup_db", self._setup_db))
 
@@ -586,7 +586,7 @@ class MultiTableMultiWriterIdGeneratorTestCase(HomeserverTestCase):
 
     def prepare(self, reactor, clock, hs):
         self.store = hs.get_datastore()
-        self.db_pool = self.store.db_pool  # type: DatabasePool
+        self.db_pool: DatabasePool = self.store.db_pool
 
         self.get_success(self.db_pool.runInteraction("_setup_db", self._setup_db))
 
diff --git a/tests/storage/test_profile.py b/tests/storage/test_profile.py
index 8a446da848..a1ba99ff14 100644
--- a/tests/storage/test_profile.py
+++ b/tests/storage/test_profile.py
@@ -45,11 +45,7 @@ class ProfileStoreTestCase(unittest.HomeserverTestCase):
         )
 
         self.assertIsNone(
-            (
-                self.get_success(
-                    self.store.get_profile_displayname(self.u_frank.localpart)
-                )
-            )
+            self.get_success(self.store.get_profile_displayname(self.u_frank.localpart))
         )
 
     def test_avatar_url(self):
@@ -76,9 +72,5 @@ class ProfileStoreTestCase(unittest.HomeserverTestCase):
         )
 
         self.assertIsNone(
-            (
-                self.get_success(
-                    self.store.get_profile_avatar_url(self.u_frank.localpart)
-                )
-            )
+            self.get_success(self.store.get_profile_avatar_url(self.u_frank.localpart))
         )
diff --git a/tests/storage/test_purge.py b/tests/storage/test_purge.py
index 54c5b470c7..e5574063f1 100644
--- a/tests/storage/test_purge.py
+++ b/tests/storage/test_purge.py
@@ -75,7 +75,7 @@ class PurgeTests(HomeserverTestCase):
         token = self.get_success(
             self.store.get_topological_token_for_event(last["event_id"])
         )
-        event = "t{}-{}".format(token.topological + 1, token.stream + 1)
+        event = f"t{token.topological + 1}-{token.stream + 1}"
 
         # Purge everything before this topological token
         f = self.get_failure(
diff --git a/tests/storage/test_room.py b/tests/storage/test_room.py
index 70257bf210..31ce7f6252 100644
--- a/tests/storage/test_room.py
+++ b/tests/storage/test_room.py
@@ -49,7 +49,7 @@ class RoomStoreTestCase(HomeserverTestCase):
         )
 
     def test_get_room_unknown_room(self):
-        self.assertIsNone((self.get_success(self.store.get_room("!uknown:test"))))
+        self.assertIsNone(self.get_success(self.store.get_room("!uknown:test")))
 
     def test_get_room_with_stats(self):
         self.assertDictContainsSubset(
diff --git a/tests/test_event_auth.py b/tests/test_event_auth.py
index 88888319cc..f73306ecc4 100644
--- a/tests/test_event_auth.py
+++ b/tests/test_event_auth.py
@@ -13,12 +13,13 @@
 # limitations under the License.
 
 import unittest
+from typing import Optional
 
 from synapse import event_auth
 from synapse.api.errors import AuthError
 from synapse.api.room_versions import RoomVersions
-from synapse.events import make_event_from_dict
-from synapse.types import get_domain_from_id
+from synapse.events import EventBase, make_event_from_dict
+from synapse.types import JsonDict, get_domain_from_id
 
 
 class EventAuthTestCase(unittest.TestCase):
@@ -432,7 +433,7 @@ class EventAuthTestCase(unittest.TestCase):
 TEST_ROOM_ID = "!test:room"
 
 
-def _create_event(user_id):
+def _create_event(user_id: str) -> EventBase:
     return make_event_from_dict(
         {
             "room_id": TEST_ROOM_ID,
@@ -444,7 +445,9 @@ def _create_event(user_id):
     )
 
 
-def _member_event(user_id, membership, sender=None):
+def _member_event(
+    user_id: str, membership: str, sender: Optional[str] = None
+) -> EventBase:
     return make_event_from_dict(
         {
             "room_id": TEST_ROOM_ID,
@@ -458,11 +461,11 @@ def _member_event(user_id, membership, sender=None):
     )
 
 
-def _join_event(user_id):
+def _join_event(user_id: str) -> EventBase:
     return _member_event(user_id, "join")
 
 
-def _power_levels_event(sender, content):
+def _power_levels_event(sender: str, content: JsonDict) -> EventBase:
     return make_event_from_dict(
         {
             "room_id": TEST_ROOM_ID,
@@ -475,7 +478,7 @@ def _power_levels_event(sender, content):
     )
 
 
-def _alias_event(sender, **kwargs):
+def _alias_event(sender: str, **kwargs) -> EventBase:
     data = {
         "room_id": TEST_ROOM_ID,
         "event_id": _get_event_id(),
@@ -488,7 +491,7 @@ def _alias_event(sender, **kwargs):
     return make_event_from_dict(data)
 
 
-def _random_state_event(sender):
+def _random_state_event(sender: str) -> EventBase:
     return make_event_from_dict(
         {
             "room_id": TEST_ROOM_ID,
@@ -501,7 +504,7 @@ def _random_state_event(sender):
     )
 
 
-def _join_rules_event(sender, join_rule):
+def _join_rules_event(sender: str, join_rule: str) -> EventBase:
     return make_event_from_dict(
         {
             "room_id": TEST_ROOM_ID,
@@ -519,7 +522,7 @@ def _join_rules_event(sender, join_rule):
 event_count = 0
 
 
-def _get_event_id():
+def _get_event_id() -> str:
     global event_count
     c = event_count
     event_count += 1
diff --git a/tests/test_state.py b/tests/test_state.py
index 62f7095873..780eba823c 100644
--- a/tests/test_state.py
+++ b/tests/test_state.py
@@ -199,7 +199,7 @@ class StateTestCase(unittest.TestCase):
 
         self.store.register_events(graph.walk())
 
-        context_store = {}  # type: dict[str, EventContext]
+        context_store: dict[str, EventContext] = {}
 
         for event in graph.walk():
             context = yield defer.ensureDeferred(
diff --git a/tests/test_types.py b/tests/test_types.py
index d7881021d3..0d0c00d97a 100644
--- a/tests/test_types.py
+++ b/tests/test_types.py
@@ -103,6 +103,4 @@ class MapUsernameTestCase(unittest.TestCase):
     def testNonAscii(self):
         # this should work with either a unicode or a bytes
         self.assertEqual(map_username_to_mxid_localpart("tĂȘst"), "t=c3=aast")
-        self.assertEqual(
-            map_username_to_mxid_localpart("tĂȘst".encode("utf-8")), "t=c3=aast"
-        )
+        self.assertEqual(map_username_to_mxid_localpart("tĂȘst".encode()), "t=c3=aast")
diff --git a/tests/test_utils/html_parsers.py b/tests/test_utils/html_parsers.py
index 1fbb38f4be..e878af5f12 100644
--- a/tests/test_utils/html_parsers.py
+++ b/tests/test_utils/html_parsers.py
@@ -23,13 +23,13 @@ class TestHtmlParser(HTMLParser):
         super().__init__()
 
         # a list of links found in the doc
-        self.links = []  # type: List[str]
+        self.links: List[str] = []
 
         # the values of any hidden <input>s: map from name to value
-        self.hiddens = {}  # type: Dict[str, Optional[str]]
+        self.hiddens: Dict[str, Optional[str]] = {}
 
         # the values of any radio buttons: map from name to list of values
-        self.radios = {}  # type: Dict[str, List[Optional[str]]]
+        self.radios: Dict[str, List[Optional[str]]] = {}
 
     def handle_starttag(
         self, tag: str, attrs: Iterable[Tuple[str, Optional[str]]]
diff --git a/tests/unittest.py b/tests/unittest.py
index 74db7c08f1..c6d9064423 100644
--- a/tests/unittest.py
+++ b/tests/unittest.py
@@ -140,7 +140,7 @@ class TestCase(unittest.TestCase):
             try:
                 self.assertEquals(attrs[key], getattr(obj, key))
             except AssertionError as e:
-                raise (type(e))("Assert error for '.{}':".format(key)) from e
+                raise (type(e))(f"Assert error for '.{key}':") from e
 
     def assert_dict(self, required, actual):
         """Does a partial assert of a dict.
@@ -520,7 +520,7 @@ class HomeserverTestCase(TestCase):
         if not isinstance(deferred, Deferred):
             return d
 
-        results = []  # type: list
+        results: list = []
         deferred.addBoth(results.append)
 
         self.pump(by=by)
diff --git a/tests/util/caches/test_descriptors.py b/tests/util/caches/test_descriptors.py
index 0277998cbe..39947a166b 100644
--- a/tests/util/caches/test_descriptors.py
+++ b/tests/util/caches/test_descriptors.py
@@ -174,7 +174,7 @@ class DescriptorTestCase(unittest.TestCase):
                 return self.result
 
         obj = Cls()
-        callbacks = set()  # type: Set[str]
+        callbacks: Set[str] = set()
 
         # set off an asynchronous request
         obj.result = origin_d = defer.Deferred()
diff --git a/tests/util/test_itertools.py b/tests/util/test_itertools.py
index e712eb42ea..3c0ddd4f18 100644
--- a/tests/util/test_itertools.py
+++ b/tests/util/test_itertools.py
@@ -44,7 +44,7 @@ class ChunkSeqTests(TestCase):
         )
 
     def test_empty_input(self):
-        parts = chunk_seq([], 5)  # type: Iterable[Sequence]
+        parts: Iterable[Sequence] = chunk_seq([], 5)
 
         self.assertEqual(
             list(parts),
@@ -56,13 +56,13 @@ class SortTopologically(TestCase):
     def test_empty(self):
         "Test that an empty graph works correctly"
 
-        graph = {}  # type: Dict[int, List[int]]
+        graph: Dict[int, List[int]] = {}
         self.assertEqual(list(sorted_topologically([], graph)), [])
 
     def test_handle_empty_graph(self):
         "Test that a graph where a node doesn't have an entry is treated as empty"
 
-        graph = {}  # type: Dict[int, List[int]]
+        graph: Dict[int, List[int]] = {}
 
         # For disconnected nodes the output is simply sorted.
         self.assertEqual(list(sorted_topologically([1, 2], graph)), [1, 2])
@@ -70,7 +70,7 @@ class SortTopologically(TestCase):
     def test_disconnected(self):
         "Test that a graph with no edges work"
 
-        graph = {1: [], 2: []}  # type: Dict[int, List[int]]
+        graph: Dict[int, List[int]] = {1: [], 2: []}
 
         # For disconnected nodes the output is simply sorted.
         self.assertEqual(list(sorted_topologically([1, 2], graph)), [1, 2])
@@ -78,19 +78,19 @@ class SortTopologically(TestCase):
     def test_linear(self):
         "Test that a simple `4 -> 3 -> 2 -> 1` graph works"
 
-        graph = {1: [], 2: [1], 3: [2], 4: [3]}  # type: Dict[int, List[int]]
+        graph: Dict[int, List[int]] = {1: [], 2: [1], 3: [2], 4: [3]}
 
         self.assertEqual(list(sorted_topologically([4, 3, 2, 1], graph)), [1, 2, 3, 4])
 
     def test_subset(self):
         "Test that only sorting a subset of the graph works"
-        graph = {1: [], 2: [1], 3: [2], 4: [3]}  # type: Dict[int, List[int]]
+        graph: Dict[int, List[int]] = {1: [], 2: [1], 3: [2], 4: [3]}
 
         self.assertEqual(list(sorted_topologically([4, 3], graph)), [3, 4])
 
     def test_fork(self):
         "Test that a forked graph works"
-        graph = {1: [], 2: [1], 3: [1], 4: [2, 3]}  # type: Dict[int, List[int]]
+        graph: Dict[int, List[int]] = {1: [], 2: [1], 3: [1], 4: [2, 3]}
 
         # Valid orderings are `[1, 3, 2, 4]` or `[1, 2, 3, 4]`, but we should
         # always get the same one.
@@ -98,12 +98,12 @@ class SortTopologically(TestCase):
 
     def test_duplicates(self):
         "Test that a graph with duplicate edges work"
-        graph = {1: [], 2: [1, 1], 3: [2, 2], 4: [3]}  # type: Dict[int, List[int]]
+        graph: Dict[int, List[int]] = {1: [], 2: [1, 1], 3: [2, 2], 4: [3]}
 
         self.assertEqual(list(sorted_topologically([4, 3, 2, 1], graph)), [1, 2, 3, 4])
 
     def test_multiple_paths(self):
         "Test that a graph with multiple paths between two nodes work"
-        graph = {1: [], 2: [1], 3: [2], 4: [3, 2, 1]}  # type: Dict[int, List[int]]
+        graph: Dict[int, List[int]] = {1: [], 2: [1], 3: [2], 4: [3, 2, 1]}
 
         self.assertEqual(list(sorted_topologically([4, 3, 2, 1], graph)), [1, 2, 3, 4])