Cases16 cases

6 to 10 of 16

1. IL-0302 Peak load on GitHub's mysql1 MySQL cluster maxed out its database proxy's connections and stopped writes in March 2022

   GitHub2022

   Symptoms

   On March 16, 2022 at 14:09 UTC, write operations across GitHub stopped working, including git operations, webhooks, pull requests, API requests, issues, GitHub Packages, GitHub Codespaces, GitHub Actions and GitHub Pages. Under peak-hour load, the database proxy in front of the shared mysql1 MySQL database had reached its maximum number of connections.

   Writes rejectedDatabase overloadHigh error rateFailover failure

   Trigger

   Increased load on mysql1 during peak hours, combined with poor query performance in specific circumstances, pushed the database proxy to its maximum number of connections.

   Root cause

   Capacity exhaustion

   Component

   DatabaseDatabase proxy and connection pooler

   Contributing factor

   Inefficient queryChange during peak hoursHarmful manual actionExcessive blast radius

   Remediation

   • Failed over mysql1 to a healthy replica on March 16
   • Reset the application connections to the new primary on March 17
   • Added an index that fixed the main query performance problem
   • Performed a primary failover on March 22
   • Performed a primary failover on March 23
   • Throttled webhook traffic to reduce load

   Action items

   • Keep throttling webhook traffic at peak load times
   • Audit the load patterns of mysql1 during peak hours and make performance fixes based on the audits
   • Move traffic to other databases to reduce load and speed up failover
   • Review change management, particularly monitoring and changes during high load in production
   • Shard the databases and scale up hardware

   View case
2. IL-0240 Cloudflare API requests failed and the dashboard slowed for hours after the authentication database lost its replicas

   Cloudflare2020

   Symptoms

   On 2 November 2020 the Cloudflare API and dashboard were degraded for six hours and 33 minutes. The success rate of API queries dropped at times to 75%, and the dashboard was up to 80 times slower than normal, while Cloudflare's edge network kept working.

   High error rateHigh latencyDatabase overloadWrites rejectedPacket loss

   Trigger

   At 14:43 UTC a network switch in a control plane data center partly failed: it kept LACP and BGP running but stopped forwarding some packets, and it recovered on its own six minutes later.

   Root cause

   DNS or network fault

   Component

   NIC, cable and switch port linkCoordination and key-value storeDatabase failover managerDatabaseDatabase replication

   Contributing factor

   Automation amplificationNo headroomHarmful manual action

   Detection

   At 14:43 UTC alerts fired because the misbehaving switch was unreachable to pings. Engineers then saw that the primary authentication database was overwhelmed.

   Remediation

   • Shed load from the primary authentication database by slowing SSL certificate pushes to the edge, emails and other features
   • Moved API traffic that could use read replicas to the secondary data center by hand
   • Sent authentication calls fully back to the primary data center when the dashboard got worse
   • Rebuilt the first database replica, which put itself back into service at 21:20 UTC and returned performance to normal
   • Ramped the turned-down services back up so asynchronous processing could catch up

   Action items

   • Remove the cluster management limitation that requires rebuilding all replicas after a primary is promoted
   • Redesign the user sessions system so dashboard traffic can be steered between data centers
   • Change the auto-remediation configuration so a database replica is not promoted so quickly
   • Tune each system involved to be more resilient to failures of its dependencies

   Lessons

   Every system in the chain had redundancy and none failed completely; each only degraded, which made the chain of events much harder to model and foresee. Automating replica promotion so that it could trigger on a minute's notice had been a point of pride, but for at least one database a fast promotion can do more harm than the failure it answers. Most general-purpose cluster managers use Raft or Paxos rather than Byzantine fault tolerant protocols, accepting a rare failure mode in exchange for a protocol that is simpler to implement correctly and debug.

   View case
3. IL-0323 A RAID battery backup unit failure crashed db1075, the MariaDB primary of section s3, and every s3 wiki went read-only

   Wikimedia Foundation2019

   Symptoms

   At 18:40 UTC db1075, the primary database of section s3, stopped answering, and all s3 wikis went read-only because no writes could reach it. Reads kept working from the replicas. At 18:42:45 Icinga reported "PROBLEM - Host db1075 is DOWN: PING CRITICAL - Packet loss = 100%".

   Writes rejectedReplication lagHigh latency

   Trigger

   The RAID battery backup unit (BBU) of db1075, the s3 primary database host, failed and the whole host crashed.

   Root cause

   Hardware failure

   Component

   DatabaseDatabase replication

   Contributing factor

   Pages not deliveredHarmful manual action

   Detection

   Icinga reported db1075 HOST DOWN on IRC at 18:42:45, but that alert does not page; replica Slave IO alerts followed, users reported problems on #wikimedia-operations, and the first SMS page went out at 18:56. Volunteers and staff noticed the failure before the alerts did.

   Remediation

   • Power-cycled db1075 from the iDRAC after finding the BBU problem
   • Let MySQL finish InnoDB recovery on db1075
   • Removed read_only=ON from db1075 by hand
   • Ran puppet by hand a second time so pt-heartbeat started

   Action items

   • Implement or refactor a script that moves replicas when the primary is unavailable
   • Fix the MediaWiki heartbeat model so pt-heartbeat does not use a super-user, avoids a single point of failure and follows the real primary without depending on puppet
   • Decide what to do with the batch of hosts that already had BBU issues
   • Buy a new BBU for db1075
   • Remove db1075 from the primary role
   • Address MediaWiki spam while the database is read-only or the primary is unavailable
   • Make primary database hosts page on HOST DOWN
   • Track hardware errors better in Netbox

   Lessons

   A BBU failure should not crash a whole host, yet it had happened before on HP hosts. HOST DOWN on a primary database should page instead of only alerting on IRC. Starting pt-heartbeat through puppet races with MySQL startup, and the unnoticed failure kept lag reported and made the outage 8 minutes longer.

   View case
4. IL-0241 A database shard could not elect a new primary, and the Stripe API failed most requests in two periods on one day

   Stripe2019

   Symptoms

   On 10 July 2019 the Stripe API failed a substantial majority of requests twice, from 16:35 to 17:02 UTC and from 21:14 to 22:47 UTC. In the first period automated monitoring detected within a minute that a database cluster had failed to elect a new primary.

   High error rateFailover failureWrites rejectedIntermittent timeoutsSustained high node CPU

   Trigger

   The primary node of a database cluster failed at 16:35 UTC while one shard had several stalled nodes. The second period was set off by rolling the election protocol back to the previous minor version at 20:42 UTC.

   Root cause

   Software defect

   Component

   DatabaseDatabase failover manager

   Contributing factor

   Change with a delayed effectMonitoring blind spotExcessive blast radiusHarmful manual actionUnverified assumptionOverlapping failures

   Detection

   Automated monitoring detected the failed election within a minute, and the team was alerted at 16:36 UTC. The second period was announced at 21:14 UTC by automated alerts that some shards in the cluster were unavailable.

   Remediation

   • Restarted all nodes of the database cluster, which forced a successful primary election
   • Updated the production configuration and restarted the database cluster's nodes
   • Ramped traffic back up, putting services for user-initiated API requests first

   Action items

   • Alert when nodes stop reporting their replication lag
   • Alert when a shard enters a state that could trigger the election fault
   • Work with the database maintainers on a fix for the underlying fault
   • Add circuit breaking on failed operations to particular database clusters
   • Use fault isolation to contain the impact of a single failed shard
   • Limit the resources used by clients that keep retrying failed requests
   • Add procedures and tooling that make rapid configuration changes during incident response safer

   View case
5. IL-0211 A Mandrill PostgreSQL shard shut down at transaction ID wraparound and email sending was impaired for about 40 hours

   Mailchimp2019

   Symptoms

   From 05:35 UTC on 4 February 2019 Mandrill, Mailchimp's transactional email service, sent only 80% of queued emails, because one of its PostgreSQL shards, shard4, stopped accepting writes. When Mandrill engineers opened an investigation at 11:58 UTC, they saw a sharply elevated load on shard4.

   Writes rejectedThroughput degradationLoad imbalanceNode disk full

   Trigger

   At 05:35 UTC on 4 February the transaction ID counter of shard4, the busiest Mandrill PostgreSQL shard, reached its upper limit and PostgreSQL shut the database down to protect against wraparound.

   Root cause

   Capacity exhaustion

   Component

   DatabasePostgreSQL vacuum

   Contributing factor

   Ignored early signalNo alert on limitSignal buried in noiseRetry stormMonitoring blind spot

   Detection

   The first exception was logged overnight but was buried by unrelated exceptions in the centralized error reporting. Mandrill engineers opened an investigation at 11:58 UTC and, while looking for the source of the rising load on shard4, found the wraparound at 12:56 UTC.

   Remediation

   • Put shard4 into standalone mode and started VACUUM at 14:16 UTC on 4 February
   • Stopped and restarted the vacuum with settings that made it run faster
   • Started a dump and restore of the database without the Search and Url tables while the vacuum ran
   • Replaced storage volumes on the Mandrill app servers whose disks were filling with queued jobs and logs
   • Moved the job-queue tables from shard4 to other live shards
   • Truncated the Search and Url tables on the locked database at 19:12 UTC on 5 February, after which the vacuum finished in about an hour
   • Started sending from the backlog at 21:36 UTC
   • Added alerting for XID wraparound by 22:40 UTC

   Lessons

   Mailchimp named the factors that slowed its response: knowledge of and access to Mandrill systems and monitoring rested with a few people, Mandrill logging needed a locally writable disk, logs of malformed API requests were hard to separate from real application errors, job health was hard to see, and the disk space problem made partial deployments for triage risky. What helped was trained incident commanders with clear roles (incident commanders in 3-hour rotations, scribes, technical liaisons and points of contact between teams), periodic summaries with a list of recent and open decisions, and taking time in a video meeting to reassess, which led to the truncation. Running in the cloud let the team expand storage quickly, and the team was lucky that the largest table holding up the vacuum held data it could delete.

   View case

By root cause7