Cases3 cases

1 to 3 of 3

1. IL-0534 Amazon S3 in US-EAST-1 could not serve GET, LIST, PUT or DELETE requests for hours while its index subsystem restarted

   Amazon Web Services2017

   Symptoms

   From 9:37AM PST on February 28th, 2017, Amazon S3 in the Northern Virginia (US-EAST-1) Region could not serve requests. AWS services in the region that store data in S3 failed with it, including the S3 console, new Amazon EC2 instance launches, Amazon EBS volumes that needed data from an S3 snapshot, and AWS Lambda.

   Service outage

   Trigger

   While debugging an S3 billing system that was progressing more slowly than expected, an authorized S3 team member followed an established playbook to remove a small number of servers from one S3 subsystem used by the billing process, and entered one input of the command incorrectly.

   Root cause

   Operator error

   Component

   Object storageCloud block storageServerless function platform

   Contributing factor

   No safeguard on destructive changeExcessive blast radiusCircular dependency

   Remediation

   • Restarted the index subsystem, which served GET, LIST and DELETE again from 12:26PM PST
   • Restarted the placement subsystem after the index subsystem worked, restoring PUT by 1:54PM PST

   Action items

   • Change the capacity removal tool to remove capacity more slowly
   • Add safeguards that stop capacity removal when it would take a subsystem below its minimum required capacity
   • Audit other operational tools for similar safety checks
   • Improve the recovery time of key S3 subsystems and start the planned further partitioning of the index subsystem into cells now
   • Run the SHD administration console across multiple AWS regions

   View case
2. IL-0224 ELB control plane APIs failed in US-East, and load balancers it then changed broke, after ELB state data was deleted

   Amazon Web Services2012

   Symptoms

   From 12:24 PM PST on 24 December 2012, the Amazon Elastic Load Balancing (ELB) control plane in the US-East Region showed high latency and error rates for API calls that manage load balancers. Running load balancers kept handling requests normally at first.

   Control plane lagHigh error rateHigh latency

   Trigger

   One of the very few developers with access to the production ELB environment inadvertently ran a maintenance process against the production ELB state data, and it logically deleted part of that data.

   Root cause

   Operator error

   Component

   Cloud load balancer

   Contributing factor

   No safeguard on destructive changeUntested backupAutomation amplification

   Detection

   The ELB team noticed the control plane API errors first; the missing state data was found only after the team investigated load balancers that had become degraded.

   Remediation

   • Disabled several ELB control plane workflows, including scaling and descaling
   • Recovered some of the affected running load balancers by hand
   • Restored a snapshot of the ELB state data from just before the deletion, using an alternate recovery process
   • Merged the restored data with the state changes since the snapshot and verified it
   • Re-enabled the ELB workflows and APIs slowly while recovering each affected load balancer

   Action items

   • Require per-incident Change Management approval for all access to production ELB state data
   • Change the data recovery process so ELB state data can be recovered much faster
   • Reprogram the ELB control plane workflows to reconcile central service data with current load balancer state

   View case
3. IL-0337 EBS volumes in one US East Availability Zone got stuck after a network change cut EBS nodes off from their replicas

   Amazon Web Services2011

   Symptoms

   From 12:47 AM PDT on 21 April 2011, a subset of Amazon EBS volumes in one Availability Zone of the US East Region could no longer serve reads or writes, and EC2 instances that tried to use them got stuck as well. AWS called these "stuck" volumes. EBS API calls across the whole US East Region also returned high error rates and latencies during two periods on the first day.

   Storage disconnected or stale mountsNetwork unreachableControl plane lagHigh error rateFailover failureData loss

   Trigger

   During a routine network change to upgrade the capacity of the primary EBS network in one Availability Zone, traffic was to be shifted off one of the redundant routers. The shift was executed incorrectly and sent the traffic onto the lower-capacity replication network instead of the other primary router, which could not carry it.

   Root cause

   Operator error

   Component

   Cloud block storageDatabase

   Contributing factor

   Automation amplificationRetry stormNo headroomExcessive blast radiusSignal buried in noise

   Remediation

   • Rolled back the incorrect traffic shift, which restored network connectivity
   • Disabled all new Create Volume requests in the affected Availability Zone at 2:40 AM PDT
   • Disabled all communication between the degraded EBS cluster and the EBS control plane from 8:20 AM PDT
   • Stopped EBS servers in the degraded cluster from futilely contacting other servers for free space
   • Changed the EBS control plane so new EBS-backed instance launches stopped failing
   • Moved spare server capacity physically from across the US East Region into the degraded cluster
   • Adjusted the negotiation throttles so the new servers could join without flooding the old ones
   • Built a separate EBS control plane partitioned to the affected zone and finer-grained throttles, then processed the backlog
   • Restored the remaining volumes from S3 snapshots taken early in the event
   • Restored volumes on failed machines that had no snapshot after forensic work
   • Intervened by hand on the RDS multi-AZ instances that did not fail over automatically

   Action items

   • Audit the change process and add automation to prevent the traffic shift mistake
   • Change capacity planning and alarming to keep the extra safety capacity needed for large recovery events
   • Change the retry logic in EBS nodes to back off harder and reconnect to previous replicas instead of searching for new nodes
   • Test and deploy the fix for the race condition that crashed EBS nodes
   • Fix the RDS bug that kept multi-AZ instances from failing over automatically
   • Improve the EBS control plane timeout logic to prevent thread exhaustion when one zone's cluster is slow
   • Make the EBS control plane aware of Availability Zones so it sheds load when over capacity
   • Move more EBS control plane functions into per-cluster services that run in the same zone as the cluster
   • Offer multiple Availability Zones to Amazon VPC customers
   • Provide better tools for building multi-AZ applications that survive the loss of a zone
   • Host free webinars and publish whitepapers on fault-tolerant architecture
   • Build the fine-grained control and throttling used in recovery into the EBS nodes and automate the recovery models
   • Look at changes that keep volumes working while a cluster is degraded, including the ability to take a snapshot of a stuck volume
   • Send more frequent and detailed customer updates and staff developer support more widely during events
   • Develop tools that show through the APIs whether instances are impaired

   Lessons

   AWS writes that with more spare capacity the cluster would have absorbed the re-mirroring requests without a storm, and that it now understands how much capacity large recovery events need. The event also showed that the EBS control plane let a failure in one Availability Zone affect the others, so more work is needed to make zones behave as if completely independent. AWS adds that some customers had critical components in a single zone, and that multi-AZ deployments need to become easier to design and run.

   View case

By root cause1