Cases36 cases

16 to 20 of 36

1. IL-0141 gke-metadata-server versions 0.4.272 to 0.4.280 flooded Cloud Logging with "Unable to sync sandbox" debug logs on GKE clusters with Workload Identity, using up logging quota and adding billable usage

   Google Cloud2023

   Symptoms

   Google Kubernetes Engine (GKE) customers with Workload Identity enabled saw a high logging rate. Debug log lines containing the string "Unable to sync sandbox" were ingested into Cloud Logging, used up the Cloud Logging ingestion quota and, beyond the free monthly allotment, produced extra billable usage. Workload Identity is opt-in on GKE Standard and always enabled on GKE Autopilot.

   Log floodHigh latency

   Trigger

   GKE clusters ran gke-metadata-server versions 0.4.272 to 0.4.280, which contained an incorrect configuration that wrote "Unable to sync sandbox" debug logs at a high rate.

   Root cause

   Software defect

   Component

   Credential broker for pods

   Contributing factor

   –

   Detection

   The first status update was posted at 13:32 US/Pacific on 2023-11-02, and the updates told customers how to check a cluster from the version annotation on the gke-metadata-server DaemonSet.

   Remediation

   • rolled out a fix across the GKE fleet so the excess logs were no longer ingested into Cloud Logging
   • offered GKE Rapid channel customers a control plane upgrade to 1.28.2-gke.1157000 or above, or 1.27.7-gke.1038000 or above, as a workaround

   View case
2. IL-0028 Temporal History service latency rose because its pods were CPU-throttled while CPU usage read below 60 percent

   Temporal2023

   Symptoms

   Request latency from the Temporal Server History service, the service that starts workflow executions and records their progress, was higher and less steady than it should be on a self-hosted Kubernetes deployment. The CPU dashboard showed the history pods using less than 60 percent of their CPU, yet the same pods were being throttled.

   CPU throttlingHigh latency

   Trigger

   Normal load on History pods that had a CPU limit of 2 cores on 8-core nodes, with the Go runtime's GOMAXPROCS left at its default of one per node core.

   Root cause

   Capacity exhaustion

   Component

   Container CPU limitLanguage runtime settingsPrometheus

   Contributing factor

   Unreviewed defaultsMonitoring blind spot

   Detection

   A Prometheus query for CPU throttling showed the history pods throttled although their CPU usage read under 60 percent.

   Remediation

   • set the GOMAXPROCS environment variable to 2 to match the 2-core CPU limit

   Action items

   • Set GOMAXPROCS automatically from the Kubernetes CPU limit, from Temporal release 1.21.0

   Lessons

   A CPU usage graph averaged over 15 seconds or more can sit far below 100 percent while a container is being throttled, so throttling needs its own metric. A Go program in a container should have GOMAXPROCS matched to its CPU limit, or to its CPU request when it has no limit. The author recommends not using CPU limits at all.

   View case
3. IL-0083 Intermittent 5xx errors in a multi-tenant Kubernetes cluster came from internal DNS: the node-local dnsmasq hit its 150 concurrent query limit, did not cache cluster.local answers, and ndots search lookups flooded CoreDNS

   Adevinta2023

   Symptoms

   On a Friday afternoon a tenant of SCHIP, Adevinta's multi-tenant Kubernetes runtime, reported a spike of HTTP 5xx errors in some of its services. The drops in quality of service came back periodically through the following days, each one short, and were reported mostly around midnight.

   High error rateDNS resolution failuresHigh latency

   Root cause

   DNS or network fault

   Component

   CoreDNSClient-side DNS resolver and cacheTelemetry agent

   Contributing factor

   Unreviewed defaultsUnknown limitIgnored early signalUnverified assumption

   Detection

   A tenant reported a spike of HTTP 5xx errors in some of its services; the DNS Latency SLI had already been degraded for some time without being acted on.

   Remediation

   • raised the dnsmasq concurrent query limit from 150 to 1500
   • added a CoreDNS header block that sets the ra and aa flags and clears rd, so dnsmasq caches cluster.local answers
   • configured dnsmasq on each node to answer NXDOMAIN for unresolvable search-domain names instead of forwarding them to CoreDNS
   • changed the fluent-bit log router hostname to a fully qualified name
   • asked the affected tenants to use fully qualified names for internal calls

   Lessons

   The DNS Latency SLI had shown the problem long before anyone looked at it. An SLO only protects you when its SLIs are trusted and a drop is investigated. The investigation took a month partly because several on-call groups worked on it separately, without one place for observations and hypotheses, and sometimes chased hypotheses already discarded. Disprove one hypothesis before starting the next, and collect data the metrics system lacks: DNStop showed the garbage lookups that no dashboard did. With ndots:5, short service names multiply DNS traffic; a node-local cache only helps if it can cache the cluster DNS answers at all.

   View case
4. IL-0151 A latent defect in the AWS Lambda Frontend, set off when one us-east-1 cell scaled past a size never reached before, raised errors for Lambda and for services that depend on it, including new EKS cluster provisioning

   Amazon Web Services2023

   Symptoms

   From 11:49 AM PDT on 13 June 2023, Lambda function invocations in the Northern Virginia (us-east-1) Region returned more errors and took longer. Customers that triggered functions from asynchronous or streaming event sources saw their event backlogs grow because the events were not being processed.

   High error rateHigh latencyCredentials unavailable

   Trigger

   At 11:49 AM PDT, while adding capacity for normal daily traffic growth, the Lambda Frontend fleet in one cell crossed a capacity threshold that no single cell had reached before.

   Root cause

   Software defect

   Component

   Serverless function platform

   Contributing factor

   Unknown limit

   Detection

   Engineering teams were engaged immediately and began investigating; by 12:26 PM PDT they had identified the latent defect and its effect on provisioning compute capacity.

   Remediation

   • scaled the Lambda Frontend fleet down to a size that no longer triggered the latent defect

   Action items

   • Disable the Lambda Frontend scaling activities that triggered the event
   • Fix the latent bug and deploy the fix to all Regions
   • Complete action items addressing the immediate concern with cellular scaling
   • Bound all cells to a well-tested size to avoid unexpected scaling issues

   Lessons

   A fleet that scales automatically can grow into a size that was never tested, and a defect that only appears at that size stays hidden until ordinary daily growth reaches it. AWS's answer is to cap every cell at a well-tested size. For EKS users, the event shows that provisioning new clusters in us-east-1 depended on Lambda, while clusters that were already running were not affected.

   View case
5. IL-0177 WebSocket connections to LINE's messaging-hub on Kubernetes dropped all at once whenever another service's change reloaded a shared HAProxy L7 load balancer, and the reconnect wave overloaded a token API and filled nf_conntrack on Nginx

   LINE+2022

   Symptoms

   The graph of WebSocket connections to messaging-hub, the messaging platform used by the Japanese food delivery service Demaecan, showed sudden deep drops even outside peak traffic. The drops kept coming back at irregular intervals. Messages still reached clients, because messaging-hub switches to Firebase Cloud Messaging when a WebSocket is gone.

   Connection resetsDatabase overloadIntermittent connection failuresHigh latency

   Trigger

   Another service that shared the same L7 load balancer deployed its own load balancer configuration in the Verda dashboard, which reloaded HAProxy; 30 minutes later, at the hard-stop-after limit, the old HAProxy process exited and closed every WebSocket connection it still held.

   Root cause

   Configuration change

   Component

   HAProxyCloud load balancerconntrack tableIngress controller

   Contributing factor

   Change with a delayed effectExcessive blast radiusRetry stormUnverified assumption

   Detection

   The developer noticed deep, sudden drops in the WebSocket connection graph that were not tied to peak traffic and kept recurring irregularly. The Nginx packet drops were found through network monitoring.

   Remediation

   • separated the Merchant system's token issuance API into its own deployment so reconnect traffic did not delay other Merchant APIs
   • scaled out Nginx with pod anti-affinity and a label selector so each pod ran on a different node, which stopped the nf_conntrack packet drops
   • raised Ingress Nginx proxy-read-timeout and proxy-send-timeout and the load balancer timeout to 3600s, which did not stop the drops
   • moved messaging-hub from the shared L7 load balancer to an L4 load balancer, which ended the WebSocket drops

   Lessons

   A reload of a shared load balancer by a different team can cut long-lived connections, and with hard-stop-after the cut comes 30 minutes later, far from the change that caused it. The author's lesson is not to narrow the scope of the search too early: trusting that the infrastructure was fine kept the investigation inside the team's own systems for days. A reconnect wave from many WebSocket clients can overload the systems that issue connection tokens and fill nf_conntrack on proxy nodes. Scaling Nginx out only helps for conntrack if the pods land on different nodes, and anti-affinity leaves extra replicas Pending once they outnumber the nodes. That messaging-hub problems can still load the connected systems remains an open problem.

   View case

By root cause7