From eef0205da35499f9586944629bf5ccea69e5330f Mon Sep 17 00:00:00 2001 From: Robert Autenrieth <31539813+rautenrieth-da@users.noreply.github.com> Date: Mon, 30 Jun 2025 10:07:39 +0200 Subject: [PATCH] [release-line-0.4.1] Suppress ACS mismatch warning on MainNet (#1246) Backport of #1246 [static] Signed-off-by: Robert Autenrieth --- cluster/expected/infra/expected.json | 2 +- cluster/pulumi/infra/src/gcpAlerts.ts | 13 ++++++++----- 2 files changed, 9 insertions(+), 6 deletions(-) diff --git a/cluster/expected/infra/expected.json b/cluster/expected/infra/expected.json index 63a97f8f78..68f2d1a6e0 100644 --- a/cluster/expected/infra/expected.json +++ b/cluster/expected/infra/expected.json @@ -1803,7 +1803,7 @@ "id": "", "inputs": { "description": "Logs with a severity level of warning or above", - "filter": "severity>=WARNING\nresource.type=\"k8s_container\"\nresource.labels.cluster_name=\"cn-mocknet\"\n-- Note that we ignore the validator runbook. This is because we reset it periodically, which sometimes produces noise.\nresource.labels.namespace_name=~\"sv|validator1|multi-validator|splitwell\"\n-(resource.labels.container_name=~\"participant\" AND jsonPayload.message=~\"Instrument .* has recorded multiple values for the same attributes.\")\n-- https://github.com/DACH-NY/canton-network-node/issues/10475\n-(resource.labels.container_name=\"cometbft\" AND\n ( jsonPayload.err=~\"\\Aerror adding vote\\z|\\Aalready stopped\\z|use of closed network connection\"\n OR jsonPayload._msg=~\"\\A(Stopping peer for error|Stopped accept routine, as transport is closed|Failed to write PacketMsg|Connection failed @ sendRoutine)\\z\"\n OR jsonPayload.error=\"already stopped\"\n OR textPayload=\"cp: not replacing '/cometbft/data/priv_validator_state.json'\"\n OR (jsonPayload._msg=\"Error stopping connection\" AND jsonPayload.err=\"already stopped\")\n OR jsonPayload._msg=\"Error adding peer to new bucket\"))\n-- execution context overload\n-jsonPayload.message=~\"Task runner canton-env-ec is .* overloaded\"\n-- on startup\n-textPayload=~\"Picked up JAVA_TOOL_OPTIONS:\"\n-- \\A and \\z anchor a search (=~) at beginning/end of string, respectively\n-- regex is significantly faster than OR; gcp docs themselves recommend\n-- regex-based factoring\n-resource.labels.container_name=~\"\\A(ans|wallet|scan|sv|splitwell)-web-ui\\z\"\n-- sequencer down\n-(resource.labels.namespace_name=~\"validator|splitwell\"\n AND resource.labels.container_name=~\"participant\"\n AND jsonPayload.message=~\"SEQUENCER_SUBSCRIPTION_LOST|Request failed for sequencer|Sequencer shutting down|Submission timed out|Response message for request .* timed out |periodic acknowledgement failed|Token refresh failed with Status{code=UNAVAILABLE\")\n-(resource.labels.container_name=\"postgres-exporter\" AND jsonPayload.msg=~\"Error loading config|Excluded databases\")\n-jsonPayload.message=~\"UnknownHostException\"\n-(resource.labels.container_name=~\"participant|mediator\" AND jsonPayload.message=~\"Late processing \\(or clock skew\\) of batch\")\n-(resource.labels.container_name=\"sequencer\" AND jsonPayload.stack_trace=~\"UnresolvedAddressException\")\n-(resource.labels.container_name=\"sequencer-pg\" AND\n (\"checkpoints are occurring too frequently\" OR \"Consider increasing the configuration parameter \\\"max_wal_size\\\".\"))\n-(resource.labels.container_name=~\"participant\" AND\n jsonPayload.message=~\"SYNC_SERVICE_ALARM.*Received a request.*where the view.*has (missing|extra) recipients|LOCAL_VERDICT_MALFORMED_PAYLOAD.*Rejected transaction due to malformed payload within views.*WrongRecipients|channel.*shutdown did not complete gracefully in allotted|LOCAL_VERDICT_FAILED_MODEL_CONFORMANCE_CHECK.*: UnvettedPackages\")\n-(resource.labels.container_name=\"mediator\" AND\n jsonPayload.message=~\"MEDIATOR_RECEIVED_MALFORMED_MESSAGE.*(Reason: (Missing root hash message for informee participants|Superfluous root hash message)|Received a (mediator|confirmation) response.*with an invalid root hash)\")\n-(jsonPayload.logger_name=~\"c.d.n.a.AdminAuthExtractor:\" AND jsonPayload.message=~\"Authorization Failed\")\n-(jsonPayload.level=\"error\" AND jsonPayload.msg=~\"/readyz\")\n-- The prometheus export server does not wait for any ongoing requests when shutting down https://github.com/prometheus/client_java/issues/938\n-jsonPayload.message=\"The Prometheus metrics HTTPServer caught an Exception while trying to send the metrics response.\"\n-- istio-proxy is spammy with warnings\n-(resource.labels.container_name=\"istio-proxy\" AND severity=WARNING\nresource.type=\"k8s_container\"\nresource.labels.cluster_name=\"cn-mocknet\"\n-- Note that we ignore the validator runbook. This is because we reset it periodically, which sometimes produces noise.\nresource.labels.namespace_name=~\"sv|validator1|multi-validator|splitwell\"\n-(resource.labels.container_name=~\"participant\" AND jsonPayload.message=~\"Instrument .* has recorded multiple values for the same attributes.\")\n-- https://github.com/DACH-NY/canton-network-node/issues/10475\n-(resource.labels.container_name=\"cometbft\" AND\n ( jsonPayload.err=~\"\\Aerror adding vote\\z|\\Aalready stopped\\z|use of closed network connection\"\n OR jsonPayload._msg=~\"\\A(Stopping peer for error|Stopped accept routine, as transport is closed|Failed to write PacketMsg|Connection failed @ sendRoutine)\\z\"\n OR jsonPayload.error=\"already stopped\"\n OR textPayload=\"cp: not replacing '/cometbft/data/priv_validator_state.json'\"\n OR (jsonPayload._msg=\"Error stopping connection\" AND jsonPayload.err=\"already stopped\")\n OR jsonPayload._msg=\"Error adding peer to new bucket\"))\n-- execution context overload\n-jsonPayload.message=~\"Task runner canton-env-ec is .* overloaded\"\n-- on startup\n-textPayload=~\"Picked up JAVA_TOOL_OPTIONS:\"\n-- \\A and \\z anchor a search (=~) at beginning/end of string, respectively\n-- regex is significantly faster than OR; gcp docs themselves recommend\n-- regex-based factoring\n-resource.labels.container_name=~\"\\A(ans|wallet|scan|sv|splitwell)-web-ui\\z\"\n-- sequencer down\n-(resource.labels.namespace_name=~\"validator|splitwell\"\n AND resource.labels.container_name=~\"participant\"\n AND jsonPayload.message=~\"SEQUENCER_SUBSCRIPTION_LOST|Request failed for sequencer|Sequencer shutting down|Submission timed out|Response message for request .* timed out |periodic acknowledgement failed|Token refresh failed with Status{code=UNAVAILABLE\")\n-(resource.labels.container_name=\"postgres-exporter\" AND jsonPayload.msg=~\"Error loading config|Excluded databases\")\n-jsonPayload.message=~\"UnknownHostException\"\n-(resource.labels.container_name=~\"participant|mediator\" AND jsonPayload.message=~\"Late processing \\(or clock skew\\) of batch\")\n-(resource.labels.container_name=\"sequencer\" AND jsonPayload.stack_trace=~\"UnresolvedAddressException\")\n-(resource.labels.container_name=\"sequencer-pg\" AND\n (\"checkpoints are occurring too frequently\" OR \"Consider increasing the configuration parameter \\\"max_wal_size\\\".\"))\n-(resource.labels.container_name=~\"participant\" AND\n jsonPayload.message=~\"SYNC_SERVICE_ALARM.*Received a request.*where the view.*has (missing|extra) recipients|LOCAL_VERDICT_MALFORMED_PAYLOAD.*Rejected transaction due to malformed payload within views.*WrongRecipients|channel.*shutdown did not complete gracefully in allotted|LOCAL_VERDICT_FAILED_MODEL_CONFORMANCE_CHECK.*: UnvettedPackages\")\n-(resource.labels.container_name=\"mediator\" AND\n jsonPayload.message=~\"MEDIATOR_RECEIVED_MALFORMED_MESSAGE.*(Reason: (Missing root hash message for informee participants|Superfluous root hash message)|Received a (mediator|confirmation) response.*with an invalid root hash)\")\n-(jsonPayload.logger_name=~\"c.d.n.a.AdminAuthExtractor:\" AND jsonPayload.message=~\"Authorization Failed\")\n-(jsonPayload.level=\"error\" AND jsonPayload.msg=~\"/readyz\")\n-- The prometheus export server does not wait for any ongoing requests when shutting down https://github.com/prometheus/client_java/issues/938\n-jsonPayload.message=\"The Prometheus metrics HTTPServer caught an Exception while trying to send the metrics response.\"\n-- istio-proxy is spammy with warnings\n-(resource.labels.container_name=\"istio-proxy\" AND severity