fix(ci): Make integration tests on Linux arm64 not flaky

.github/workflows/test.yml

@@ -26,6 +26,7 @@ jobs:
   unit-test:
     if: github.repository_owner == 'getsentry'
     runs-on: ${{ matrix.os }}
+    timeout-minutes: 30
     strategy:
       matrix:
         os: [ubuntu-24.04, ubuntu-24.04-arm]
@@ -40,6 +41,7 @@ jobs:
   integration-test:
     if: github.repository_owner == 'getsentry'
     runs-on: ${{ matrix.os }}
+    timeout-minutes: 30
     strategy:
       fail-fast: false
       matrix:

action.yaml

@@ -264,3 +264,6 @@ runs:
         echo "::group::Inspect failure - docker compose logs"
         docker compose logs
         echo "::endgroup::"
+        echo "::group::Inspect failure - docker stats"
+        docker stats --no-stream
+        echo "::endgroup::"

docker-compose.yml

@@ -201,8 +201,8 @@ services:
       KAFKA_TOOLS_LOG4J_LOGLEVEL: "WARN"
     ulimits:
       nofile:
-        soft: 4096
-        hard: 4096
+        soft: 100000
+        hard: 100000
     volumes:
       - "sentry-kafka:/var/lib/kafka/data"
       - "sentry-kafka-log:/var/lib/kafka/log"

sentry/sentry.conf.example.py

@@ -221,7 +221,17 @@ def get_internal_network():
 DEFAULT_KAFKA_OPTIONS = {
     "bootstrap.servers": "kafka:9092",
     "message.max.bytes": 50000000,
-    "socket.timeout.ms": 1000,
+    "socket.timeout.ms": 10000,         # Timeout for individual socket operations (send/recv)
+    "request.timeout.ms": 30000,        # Max time to wait for a broker response before failing
+    "retries": 5,                       # Number of retries for transient/retriable request failures
+    "retry.backoff.ms": 1000,           # Wait time between retry attempts
+    "reconnect.backoff.ms": 1000,       # Initial wait before reconnecting after a lost connection
+    "reconnect.backoff.max.ms": 10000,  # Upper bound for exponential backoff on reconnect attempts
+    # Session & heartbeat — must satisfy:
+    # heartbeat.interval.ms < session.timeout.ms < max.poll.interval.ms
+    "session.timeout.ms": 60000,        # Grace period before broker evicts an unresponsive consumer (default: 45s)
+    "heartbeat.interval.ms": 20000,     # How often the consumer sends a heartbeat — must be 1/3 of session.timeout.ms
+    "max.poll.interval.ms": 600000,     # Max allowed time between poll() calls before the consumer is considered dead
 }
 
 SENTRY_EVENTSTREAM = "sentry.eventstream.kafka.KafkaEventStream"