Draft: Try to use use rust-jaeger-python-client

docker/Dockerfile

@@ -38,10 +38,10 @@ FROM docker.io/python:${PYTHON_VERSION}-slim as requirements
 # Here we use it to set up a cache for apt (and below for pip), to improve
 # rebuild speeds on slow connections.
 RUN \
-   --mount=type=cache,target=/var/cache/apt,sharing=locked \
-   --mount=type=cache,target=/var/lib/apt,sharing=locked \
- apt-get update -qq && apt-get install -yqq git \
-    && rm -rf /var/lib/apt/lists/*
+  --mount=type=cache,target=/var/cache/apt,sharing=locked \
+  --mount=type=cache,target=/var/lib/apt,sharing=locked \
+  apt-get update -qq && apt-get install -yqq git \
+  && rm -rf /var/lib/apt/lists/*
 
 # We install poetry in its own build stage to avoid its dependencies conflicting with
 # synapse's dependencies.
@@ -77,22 +77,31 @@ FROM docker.io/python:${PYTHON_VERSION}-slim as builder
 
 # install the OS build deps
 RUN \
-   --mount=type=cache,target=/var/cache/apt,sharing=locked \
-   --mount=type=cache,target=/var/lib/apt,sharing=locked \
- apt-get update -qq && apt-get install -yqq \
-    build-essential \
-    libffi-dev \
-    libjpeg-dev \
-    libpq-dev \
-    libssl-dev \
-    libwebp-dev \
-    libxml++2.6-dev \
-    libxslt1-dev \
-    openssl \
-    rustc \
-    zlib1g-dev \
-    git \
-    && rm -rf /var/lib/apt/lists/*
+  --mount=type=cache,target=/var/cache/apt,sharing=locked \
+  --mount=type=cache,target=/var/lib/apt,sharing=locked \
+  apt-get update -qq && apt-get install -yqq \
+  build-essential \
+  libffi-dev \
+  libjpeg-dev \
+  libpq-dev \
+  libssl-dev \
+  libwebp-dev \
+  libxml++2.6-dev \
+  libxslt1-dev \
+  openssl \
+  #rustc \
+  curl \
+  zlib1g-dev \
+  git \
+  && rm -rf /var/lib/apt/lists/*
+
+#RUN apt-cache policy rustc
+
+RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | bash -s -- -y
+# Add .cargo/bin to PATH
+ENV PATH="/root/.cargo/bin:${PATH}"
+# Check cargo is visible
+RUN cargo --help
 
 # To speed up rebuilds, install all of the dependencies before we copy over
 # the whole synapse project, so that this layer in the Docker cache can be
@@ -123,19 +132,19 @@ LABEL org.opencontainers.image.source='https://github.com/matrix-org/synapse.git
 LABEL org.opencontainers.image.licenses='Apache-2.0'
 
 RUN \
-   --mount=type=cache,target=/var/cache/apt,sharing=locked \
-   --mount=type=cache,target=/var/lib/apt,sharing=locked \
+  --mount=type=cache,target=/var/cache/apt,sharing=locked \
+  --mount=type=cache,target=/var/lib/apt,sharing=locked \
   apt-get update -qq && apt-get install -yqq \
-    curl \
-    gosu \
-    libjpeg62-turbo \
-    libpq5 \
-    libwebp6 \
-    xmlsec1 \
-    libjemalloc2 \
-    libssl-dev \
-    openssl \
-    && rm -rf /var/lib/apt/lists/*
+  curl \
+  gosu \
+  libjpeg62-turbo \
+  libpq5 \
+  libwebp6 \
+  xmlsec1 \
+  libjemalloc2 \
+  libssl-dev \
+  openssl \
+  && rm -rf /var/lib/apt/lists/*
 
 COPY --from=builder /install /usr/local
 COPY ./docker/start.py /start.py
@@ -146,4 +155,4 @@ EXPOSE 8008/tcp 8009/tcp 8448/tcp
 ENTRYPOINT ["/start.py"]
 
 HEALTHCHECK --start-period=5s --interval=15s --timeout=5s \
-    CMD curl -fSs http://localhost:8008/health || exit 1
+  CMD curl -fSs http://localhost:8008/health || exit 1

docker/conf/homeserver.yaml

@@ -184,3 +184,18 @@ trusted_key_servers:
 
 password_config:
    enabled: true
+
+opentracing:
+    enabled: true
+    jaeger_config:
+      # Sample everything
+      sampler:
+        type: const
+        param: 1
+      # via https://github.com/jaegertracing/jaeger-client-python/issues/47#issuecomment-493497439
+      local_agent:
+        reporting_host: "host.docker.internal"
+        reporting_port: 6831
+      #  Logging whether spans were started and reported
+      #
+      logging: true

pyproject.toml

@@ -182,6 +182,7 @@ hiredis = { version = "*", optional = true }
 Pympler = { version = "*", optional = true }
 parameterized = { version = ">=0.7.4", optional = true }
 idna = { version = ">=2.5", optional = true }
+rust-python-jaeger-reporter = {git = "https://github.com/erikjohnston/rust-jaeger-python-client.git"}
 
 [tool.poetry.extras]
 # NB: Packages that should be part of `pip install matrix-synapse[all]` need to be specified

scripts-dev/complement.sh

@@ -101,6 +101,7 @@ if [ -z "$skip_docker_build" ]; then
     echo_if_github "::group::Build Docker image: matrixdotorg/synapse"
     docker build -t matrixdotorg/synapse \
       --build-arg TEST_ONLY_SKIP_DEP_HASH_VERIFICATION \
+      --progress=plain \
       -f "docker/Dockerfile" .
     echo_if_github "::endgroup::"
 

synapse/api/auth.py

@@ -30,7 +30,12 @@
 from synapse.appservice import ApplicationService
 from synapse.http import get_request_user_agent
 from synapse.http.site import SynapseRequest
-from synapse.logging.opentracing import active_span, force_tracing, start_active_span
+from synapse.logging.opentracing import (
+    active_span,
+    force_tracing,
+    start_active_span,
+    trace,
+)
 from synapse.storage.databases.main.registration import TokenLookupResult
 from synapse.types import Requester, UserID, create_requester
 
@@ -563,6 +568,7 @@ def get_access_token_from_request(request: Request) -> str:
 
             return query_params[0].decode("ascii")
 
+    @trace
     async def check_user_in_room_or_world_readable(
         self, room_id: str, user_id: str, allow_departed_users: bool = False
     ) -> Tuple[str, Optional[str]]:

synapse/federation/federation_client.py

@@ -61,6 +61,7 @@
 )
 from synapse.federation.transport.client import SendJoinResponse
 from synapse.http.types import QueryParams
+from synapse.logging.opentracing import trace
 from synapse.types import JsonDict, UserID, get_domain_from_id
 from synapse.util.async_helpers import concurrently_execute
 from synapse.util.caches.expiringcache import ExpiringCache
@@ -233,6 +234,7 @@ async def claim_client_keys(
             destination, content, timeout
         )
 
+    @trace
     async def backfill(
         self, dest: str, room_id: str, limit: int, extremities: Collection[str]
     ) -> Optional[List[EventBase]]:

synapse/handlers/federation.py

@@ -59,6 +59,7 @@
 from synapse.federation.federation_client import InvalidResponseError
 from synapse.http.servlet import assert_params_in_dict
 from synapse.logging.context import nested_logging_context
+from synapse.logging.opentracing import trace
 from synapse.metrics.background_process_metrics import run_as_background_process
 from synapse.module_api import NOT_SPAM
 from synapse.replication.http.federation import (
@@ -180,6 +181,7 @@ def __init__(self, hs: "HomeServer"):
                 "resume_sync_partial_state_room", self._resume_sync_partial_state_room
             )
 
+    @trace
     async def maybe_backfill(
         self, room_id: str, current_depth: int, limit: int
     ) -> bool:

synapse/handlers/federation_event.py

@@ -59,6 +59,7 @@
 from synapse.events.snapshot import EventContext
 from synapse.federation.federation_client import InvalidResponseError
 from synapse.logging.context import nested_logging_context
+from synapse.logging.opentracing import trace
 from synapse.metrics.background_process_metrics import run_as_background_process
 from synapse.replication.http.devices import ReplicationUserDevicesResyncRestServlet
 from synapse.replication.http.federation import (
@@ -560,6 +561,7 @@ async def update_state_for_partial_state_event(
                 event.event_id
             )
 
+    @trace
     async def backfill(
         self, dest: str, room_id: str, limit: int, extremities: Collection[str]
     ) -> None:
@@ -604,6 +606,7 @@ async def backfill(
             backfilled=True,
         )
 
+    @trace
     async def _get_missing_events_for_pdu(
         self, origin: str, pdu: EventBase, prevs: Set[str], min_depth: int
     ) -> None:
@@ -704,6 +707,7 @@ async def _get_missing_events_for_pdu(
         logger.info("Got %d prev_events", len(missing_events))
         await self._process_pulled_events(origin, missing_events, backfilled=False)
 
+    @trace
     async def _process_pulled_events(
         self, origin: str, events: Iterable[EventBase], backfilled: bool
     ) -> None:
@@ -742,6 +746,7 @@ async def _process_pulled_events(
             with nested_logging_context(ev.event_id):
                 await self._process_pulled_event(origin, ev, backfilled=backfilled)
 
+    @trace
     async def _process_pulled_event(
         self, origin: str, event: EventBase, backfilled: bool
     ) -> None:

synapse/handlers/pagination.py

@@ -24,6 +24,7 @@
 from synapse.api.filtering import Filter
 from synapse.events.utils import SerializeEventConfig
 from synapse.handlers.room import ShutdownRoomResponse
+from synapse.logging.opentracing import trace
 from synapse.metrics.background_process_metrics import run_as_background_process
 from synapse.storage.state import StateFilter
 from synapse.streams.config import PaginationConfig
@@ -416,6 +417,7 @@ async def purge_room(self, room_id: str, force: bool = False) -> None:
 
             await self._storage_controllers.purge_events.purge_room(room_id)
 
+    @trace
     async def get_messages(
         self,
         requester: Requester,

synapse/handlers/relations.py

@@ -19,6 +19,7 @@
 from synapse.api.constants import RelationTypes
 from synapse.api.errors import SynapseError
 from synapse.events import EventBase, relation_from_event
+from synapse.logging.opentracing import trace
 from synapse.storage.databases.main.relations import _RelatedEvent
 from synapse.types import JsonDict, Requester, StreamToken, UserID
 from synapse.visibility import filter_events_for_client
@@ -364,6 +365,7 @@ async def _get_threads_for_events(
 
         return results
 
+    @trace
     async def get_bundled_aggregations(
         self, events: Iterable[EventBase], user_id: str
     ) -> Dict[str, BundledAggregations]:

synapse/storage/controllers/persist_events.py

@@ -778,7 +778,7 @@ async def _calculate_new_extremities(
             stale_forward_extremities_counter.observe(len(stale))
 
         return result
-
+    
     async def _get_new_state_after_events(
         self,
         room_id: str,