Cases39 cases

16 to 20 of 39

1. IL-0530 Virtual router controllers in us-central1 ran out of memory in a loop, cutting networking for new and migrated VMs

   Google Cloud2023

   Symptoms

   On 5 October 2023 in us-central1, newly created VMs waited a long time before their networking worked, and VMs that had been live migrated lost connectivity for a long time after the migration. Networking telemetry showed cross-region packet loss to and from us-central1 from 03:08 US/Pacific. Health check state of VMs reached load balancers late.

   Packet lossNetwork unreachableOOMKilledStale endpoint routingCluster or node provisioning stall

   Trigger

   A management plane behaviour change, meant to decouple the processing of API updates to Instance Groups and Network Endpoint Groups used as load balancer backends, was deployed in us-central1 after rolling out to several other regions without incident.

   Root cause

   Faulty deployment

   Component

   Network control plane (SDN)Cloud load balancer

   Contributing factor

   Excessive blast radiusNo alert on limit

   Detection

   Engineers were alerted to slowness in the virtual network control plane in us-central1 at 21:45 US/Pacific on 4 October, before the packet loss started, and to controller failures from memory exhaustion at 02:11 on 5 October. Networking telemetry showed cross-region packet loss from 03:08.

   Remediation

   • Increased the memory allocated to the virtual network router controllers
   • Rolled back the management plane change in us-central1
   • Restarted by hand the routers that were still not accepting updates

   Action items

   • Alert proactively on memory risks and unexpected memory increases
   • Refactor the deployment configuration so engineers can reallocate memory much faster
   • Re-evaluate existing practices and add safety mechanisms for API reconciliation
   • Make management plane changes more visible across teams so the changes can be correlated faster
   • Adjust the deployment footprint so a regional API change is less likely to exhaust memory across the region at once
   • Optimise memory use in the traffic routers and their controllers

   View case
2. IL-0342 DigitalOcean's AMS3, LON1 and SFO2 data centers lost Internet connectivity in repeated waves as edge routers failed

   DigitalOcean2023

   Symptoms

   From 09:55 UTC on 9 August 2023, DigitalOcean's AMS3, LON1 and SFO2 datacenters lost Internet access in waves of 10 to 15 minutes, about an hour apart. Users saw connectivity issues, latency and timeout errors on Droplets and on Droplet-based services such as Load Balancers, Kubernetes and Database clusters.

   Network unreachableIntermittent timeoutsHigh latency

   Trigger

   The edge routers received an RPKI-related routing update, and the operating system software on them crashed its routing process on that update.

   Root cause

   Software defect

   Component

   BGP routing

   Contributing factor

   Excessive blast radiusHarmful manual action

   Remediation

   • Rolled out a software update to the edge routers running the affected version, site by site
   • Rebalanced traffic on the congested routes between AMS3 and FRA1
   • Rolled out the fix to the redundant networking equipment so a failover would not hit the bug

   Action items

   • Upgrade all global edge routers to remove the bug
   • Bring the network upgrades already done in Asia to Europe and North America

   View case
3. IL-0473 Jenkins infrastructure went fully down after a pod IP range fix deleted every AKS node pool and could not recreate them

   Jenkins project2023

   Symptoms

   On 7 July 2023 from 11:05 to 15:25 UTC many public Jenkins infrastructure services were completely down, including get.jenkins.io, plugins.jenkins.io, accounts.jenkins.io, javadoc.jenkins.io and incrementals.jenkins.io, while ci.jenkins.io, issues.jenkins.io, repo.jenkins-ci.org and www.jenkins.io were partly or completely disrupted.

   Network unreachableResources deletedCluster or node provisioning stallService outage

   Trigger

   After the upgrade to Kubernetes 1.25 changed the range of the pods' originating IP and LDAP access was blocked, a fix (Azure PR 431) deployed at 10:55 UTC to set a proper set of pod IP ranges removed all node pools of the cluster.

   Root cause

   Configuration change

   Component

   Node poolCNI pluginCloud load balancer

   Contributing factor

   Unverified assumptionNo staged rolloutNo safeguard on destructive change

   Detection

   After the upgrade, at 10:30 UTC, the team noticed that services inside the cluster, such as accounts.jenkins.io, could not reach the LDAP service.

   Remediation

   • Created the cluster again from scratch with a fixed network setup
   • Set a custom pod CIDR in a range separate from the virtual network
   • Moved the services and their DNS records to new public IPs
   • Pushed a pull request that recorded the manual rebuild, including the IP setup, in code

   Action items

   • Protect the public IPs from deletion with a Management Lock
   • Keep the public IPs in a separate resource group and point the Kubernetes-managed load balancers to it with the service.beta.kubernetes.io/azure-load-balancer-resource-group annotation
   • Improve network diagrams and documentation so possible overlaps are visible when preparing operations
   • Avoid changing the configuration of all AKS node pools at once

   Lessons

   The team said that changing one node pool at a time would have shown the problem after the first pool and avoided a full outage, and that the public IPs should change as little as possible because users behind corporate firewalls with allow-lists depend on them. The team also noted that it could rebuild, in under 4 hours, the cluster that hosts almost all public services.

   View case
4. IL-0259 Outbound packets from Fastmail did not reach part of the internet for about 19 hours, cutting off 3-5% of customers

   Fastmail2023

   Symptoms

   From about 03:00 UTC on 30 June 2023, Fastmail and a fraction of the internet could not communicate with each other, and Fastmail first heard of it from customers through support tickets and social media. The problem lasted about 19 hours and affected an estimated 3-5% of customers as well as some email servers.

   Network unreachable

   Root cause

   Dependency failure

   Component

   ISP and transit networks

   Contributing factor

   Single point of failureMonitoring blind spot

   Detection

   Customers told Fastmail through support tickets and social media. Fastmail's own monitors in multiple locations and its staff were not on affected networks and saw nothing.

   Action items

   • Select a provider for a second transit connection directly into Fastmail's servers, via Megaport or a provider present in 365's New Jersey datacenter, so that Fastmail controls the outbound path and can route around a network with problems

   Lessons

   With a single path for outbound traffic, Fastmail could not route around a provider's network problem and could not fix it itself. Being able to choose between several outbound paths would let Fastmail get everyone back online faster.

   View case
5. IL-0541 Two Twingate Relay clusters were discoverable but unreachable, so Clients and Connectors could not attach to them

   Twingate2023

   Symptoms

   At 01:40 UTC on 14 February 2023, Twingate saw the number of connections drop in two of its Relay clusters, the one in us-east4 (Ashburn, Virginia) and the one in europe-west6 (Zurich, Switzerland).

   Network unreachable

   Trigger

   At 01:00 UTC on 14 February, Twingate started a Terraform change to all of its Relay clusters worldwide to add spot instance scaling; the rollout took about 45 minutes.

   Root cause

   Configuration change

   Component

   TerraformVPC route tables and firewall rules

   Contributing factor

   Unrepresentative stagingNo staged rollout

   Detection

   At 01:40 UTC Twingate noticed a decrease in the number of connections in the two clusters and started investigating.

   Remediation

   • Disabled the pods in the two affected Relay clusters at 02:04 UTC so Clients and Connectors reconnected to the next closest Relay cluster
   • Corrected the Terraform configuration error and redeployed the affected clusters at 03:30 UTC

   Action items

   • Make the staging environment reflect the sizing and configuration differences between Relay clusters
   • Create Terraform plans automatically for every environment and configuration variation on feature development branches
   • Extend Relay health checks so a cluster is not discoverable to Connectors and Clients when its network firewall tag is missing
   • Research and introduce staggered Terraform rollouts for the Relay cluster infrastructure
   • Add multi-cluster connectivity to Connectors so they handle regional Relay cluster problems automatically

   View case

By root cause10