Cases7 cases

1 to 5 of 7

1. IL-0110 A Grafana Agent pod's high memory use and crash-looping Hangfire pods drove a Kubernetes node into system OOM and NotReady, twice in one day

   DFDS2024

   Symptoms

   At 10:01 UTC on 2024-03-13 a Kubernetes node entered NotReady state, with CPU requests at 78% and memory requests at 82%. An alert fired in Slack at 10:03 and was picked up at 10:05. An attempt to SSH into the node at 10:13 failed because it was unresponsive; it started responding again at 10:19.

   Node NotReadyContainer crash loopOOMKilledMonitoring outage

   Trigger

   Pods of a dev container that used Hangfire to trigger jobs failed with OOM and crash-looped on a node where a Grafana Agent pod was already using a lot of memory.

   Root cause

   Capacity exhaustion

   Component

   Telemetry agentContainer memory limitApplication database

   Contributing factor

   Excessive blast radiusNo resource requests or limitsHarmful manual actionMonitoring blind spot

   Detection

   A Slack alert fired two minutes after the node went NotReady and was picked up two minutes later; the second node's NotReady at 15:03 also raised a Slack alert.

   Remediation

   • marked the EC2 instance unhealthy so a new node started
   • cordoned and force-drained the NotReady node and terminated its EC2 instance
   • removed the new LimitRange from the Grafana Agent namespace and restarted the Grafana Agent pod
   • scaled the dev container to 0 replicas, after which EC2 network traffic returned to normal
   • after the second NotReady, scaled the dev container to 0 replicas again and added a new node
   • emailed the team that owns the dev container, which confirmed it was working on a fix

   Action items

   • Move grafana-agent to the monitoring node group
   • Add alerts for when bandwidth across the cluster reaches a certain threshold
   • Investigate whether memory limits can be set on the grafana-agent Helm chart
   • Investigate grafana-agent memory usage
   • Ask Grafana support whether grafana-agent should use a PVC
   • Consider pushing node logs to Loki with limited retention
   • Create a wiki page with common metrics and log queries to check when investigating issues with Kubernetes nodes

   Lessons

   Dev workloads mixed with production let one crash-looping dev container take down nodes that production also used, and a monitoring agent outside its dedicated node group added to the memory pressure. Scaling the suspect container back up before its owners had fixed it brought the failure back on the replacement node. The team also noted that action items from earlier post-mortems need follow-up, and that knowledge of useful CloudWatch metrics had not been shared, which made the diagnosis harder.

   View case
2. IL-0070 Critical pods on core nodes evicted when Prometheus began scraping about 200 nodes after a dask-gateway scale-up

   2i2c2023

   Symptoms

   The hub pod of the prod JupyterHub on the leap cluster (leap.2i2c.org) restarted unexpectedly during a large node scale-up, and a user opened a support ticket. The ingress-nginx and proxy pods kept running.

   Pod evictionPods Pending

   Trigger

   A user's dask-gateway workload added about 100 dask-worker nodes within a minute, and Prometheus started scraping the metrics exporters on about 200 nodes.

   Root cause

   Capacity exhaustion

   Component

   PrometheusNode pool

   Contributing factor

   No headroomExcessive blast radiusMonitoring blind spot

   Detection

   A user support ticket (2i2c Freshdesk ticket 414) about the leap hub; the engineer then looked at Grafana and the cluster's nodes and events.

   Action items

   • Configure CPU and memory requests for the hub and proxy pods (#2127; at least 100m CPU was proposed)
   • Make the Grafana OOMKiller dashboard work (#2213)
   • Move LEAP cloud infrastructure to shared nodes (#2209)
   • Update resource requests and limits, mainly for ingress-nginx and Prometheus (#2324)
   • Decide whether Prometheus should scrape dask worker pods (#2366)

   Lessons

   Prometheus load grows with the number of nodes, so a burst of autoscaled nodes can push a nearly full core node over the edge and evict the pods that matter most. Core pods that request 10m of CPU get a tenth of the CPU share of busy neighbours that request 100m. Kubernetes events expire after an hour, so evidence of OOM kills needs a dashboard that keeps it.

   View case
3. IL-0094 Student pods filled the shared nodes of a JupyterHub cluster and starved the hub's core pods, freezing the hub

   2i2c2020

   Symptoms

   At 08:52 PM IST a report came in from WER that many students could not access the JupyterHub and that it was frozen; pages were stuck and nothing was usable. A rise in activity was visible by 09:02 PM, but the usual fixes, such as opening an incognito window and restarting servers, did not help.

   Service outageSustained high node CPU

   Trigger

   WER students' pods used a good chunk of their memory limit (tests had shown they almost always use just under 1G of their 2G limit, against a 512M guarantee) on nodes shared with the hub's core pods.

   Root cause

   Capacity exhaustion

   Component

   Node poolContainer memory limit

   Contributing factor

   No resource requests or limitsUnverified assumptionExcessive blast radius

   Detection

   WER reported stuck pages and students unable to reach the hub in a GitHub issue (2i2c-org/docs#27).

   Remediation

   • removed memory overcommit for the WER students
   • raised resource guarantees for all core pods, which restarted them and moved some to a new node

   Action items

   • Put user pods in a separate pool so they do not create pressure on the core pods (infrastructure#89)
   • Set limits on the support infrastructure (Prometheus, Grafana, ingress) as well (infrastructure#90)
   • Document and think about overcommit ratios for memory usage (infrastructure#91)
   • Set up better Grafana dashboards to monitor resource usage (infrastructure#92)
   • Document how people can get kubectl access to the cluster so others can look into issues too (infrastructure#87)

   Lessons

   Core pods without resource guarantees get whatever is left on a node, so when user pods on the same nodes fill the CPU and memory, the hub that serves everyone freezes. The memory overcommit ratio has to come from measured use: WER students used just under 1G against a 512M guarantee, which a 4x overcommit could not hold.

   View case
4. IL-0037 Image registry rate-limited a whole region after a crash-looping DaemonSet with imagePullPolicy Always pulled through three NAT instances

   Datadog2019

   Symptoms

   Users reported that their jobs were not starting, with some sign that image pulls were involved. Many pods across the cluster were in error states related to image pulls, while applications that were already running were not affected.

   Image pull failuresService outage

   Trigger

   A change to the permissions on a storage bucket that one application needed to read. The application could no longer start, and its DaemonSet, running on roughly a thousand nodes of the cluster, went into a crash loop with imagePullPolicy: Always, so every restart pulled the image again although it was already on the node.

   Root cause

   Capacity exhaustion

   Component

   Container registry and its credentialsNAT gatewayApplication databaseAdmission webhook

   Contributing factor

   Automation amplificationSingle point of failureUnknown limitHarmful manual actionExcessive blast radius

   Detection

   Users reported that their jobs were not starting; monitoring had not caught it first.

   Remediation

   • replaced the affected NAT instances so registry traffic came from new source IPs
   • reconfigured the static IPs and firewall rules so applications could reach the Cloud SQL database again

   Action items

   • Add an admission webhook that rejects floating image tags, starting with latest
   • Apply the image tag webhook to workload objects only, not to pods, after it blocked pods created by in-cluster controllers

   Lessons

   The speakers' takeaway is to be very careful with DaemonSets in large clusters: they say they had broken everything DaemonSets depend on, including DNS, Vault and the image repository, and that it is very easy to break things when managing them by the thousand. imagePullPolicy: Always made every crash-loop restart pull the image again. Sending all registry traffic through three NAT instances put the whole region behind three source IPs, which the registry rate-limited, and changing those IPs cut the connections to a critical database reached over the internet through them. An admission webhook on pods rejects the pods that controllers in the cluster create, where no user sees the error.

   View case
5. IL-0001 Cluster-wide DNS outage after CoreDNS pods were OOM-killed again and again under a burst of DNS queries

   Zalando2019

   Symptoms

   Customers of the Zalando Fashion Store got a high rate of errors on all web product pages and outfit pages for more than an hour. The errors came from the main data aggregation layer service, which runs in one of Zalando's Kubernetes clusters.

   High error rateDNS resolution failuresOOMKilledMonitoring outage

   Trigger

   Calls from the aggregation layer to a single, not very important downstream service started timing out. The aggregation layer returned 404s for them, clients retried, and the resulting spike in requests became a spike in DNS queries to CoreDNS.

   Root cause

   Capacity exhaustion

   Component

   CoreDNSContainer memory limitClient-side DNS resolver and cache

   Contributing factor

   Unknown limitNo cachingRetry stormUnreviewed defaultsExcessive blast radiusMonitoring blind spot

   Detection

   The on-call engineer for the aggregation layer phoned the on-call Kubernetes engineer. Automatic paging did not happen because the cluster's monitoring and alerting ran inside the cluster and failed along with DNS. The Kubernetes engineer then saw that the CoreDNS pods were being OOM-killed.

   Remediation

   • Raised the CoreDNS memory requests and limits by hand from 100Mi to 2000Mi

   Action items

   • Introduce a more resilient DNS setup: CoreDNS fronted by dnsmasq on every node
   • Improve high-level alerting from outside the clusters, so that a cluster problem is known before or at the same time as applications are affected
   • Improve incident response processes and tooling so that any on-call engineer can escalate directly to other teams when automatic paging fails, for example through a chat bot

   Lessons

   The Kubernetes DNS setup was far from resilient enough: a single application could take down DNS for everything in the cluster. The blast radius of one application sending more DNS queries should be limited to one node at most, ideally to single pods. Known Kubernetes DNS problems, such as Linux kernel races in conntrack handling and the ndots 5 problem, were familiar to the team and partly mitigated, but their combined effect on the DNS infrastructure was worse than the team had understood. Monitoring that runs inside the cluster was not robust enough: when the cluster's DNS broke, it could not page anyone, and recovery took longer than it should have.

   View case

By root cause1