Catalogue

Cards
165
Records
486
Workloads
19
Corpus version
74847648e25a
Workload
Kind
Setup

24 of 486 records match; the first 20 are shown.

KindRecordOrganisationYearSetup
Failure

Users who follow hundreds of thousands of accounts made hot shards that slowed the timelines sharing them

bluesky-2025-lossy-timelines#f1peak of 100,000 requests/s or more

Bluesky2025Sharded
Decision

Drop timeline writes with a probability set by how many accounts a user follows, accepting imperfect timelines

bluesky-2025-lossy-timelines#d1peak of 100,000 requests/s or more

Bluesky2025Sharded
Decision

Cache high-follow accounts in a Redis sorted set loaded into memory every 30 seconds instead of reading follow counts per write

bluesky-2025-lossy-timelines#d2peak of 100,000 requests/s or more

Bluesky2025Sharded
Decision

Batch ping writes with COPY in one transaction instead of calling a stored procedure once per ping

healthchecks-2025-ping-ingest#d1peak under 100,000 requests/s

Healthchecks.io2025One database
Decision

Cache not-found results for UUID ping URLs so repeated pings to missing checks skip the database

healthchecks-2025-ping-ingest#d2peak under 100,000 requests/s

Healthchecks.io2025One database
Decision

Scale ZippyDB keyspaces online via logical-to-physical shard indirection and coordinator-worker resharding

meta-2023-threads#d1

Meta2023Sharded
Decision

Offload Instagram-to-Threads follow-graph mirroring and notifications to rate-limited Async workers

meta-2023-threads#d2

Meta2023Sharded
Failure

A viral customer's pageviews backlog the shared queue for all sites while the database runs out of disk IOPS

fathom-2020-viral-customer-backlog#f1

Fathom Analytics2020One database
Failure

Unindexed backlog tables and a text-typed site ID kept the database slow after the disk was fixed

fathom-2020-viral-customer-backlog#f2

Fathom Analytics2020One database
Decision

Cap concurrent queue workers on purpose to protect the database, accepting a bigger backlog

fathom-2020-viral-customer-backlog#d1

Fathom Analytics2020One database
Decision

Limit pageviews processed per site per minute so one viral site cannot block the rest, then drop it

fathom-2020-viral-customer-backlog#d2

Fathom Analytics2020One database
Decision

One reader per shard replaces one reader thread per customer webhook after delays reached 10 minutes

nylas-2018-webhooks#d1

Nylas2018Sharded
Decision

Kinesis chosen over the MySQL binlog and Kafka as the ordered source of changes, mainly for operational simplicity

nylas-2018-webhooks#d2

Nylas2018Sharded
Decision

New sender ran two months in a simulated mode that sent nothing, compared against the legacy sender, before cutover

nylas-2018-webhooks#d3

Nylas2018Sharded
Failure

Resuming from the last sent MySQL auto-increment id made the new webhook sender skip transactions in testing

nylas-2018-webhooks#f1

Nylas2018Sharded
Failure

Database contention filled Redis memory, and a full Redis could neither accept nor release jobs

slack-2017-job-queue#f1peak under 100,000 requests/s

Slack2017Sharded
Decision

Added Kafka in front of the Redis job queue instead of replacing Redis

slack-2017-job-queue#d1peak under 100,000 requests/s

Slack2017Sharded
Decision

Enqueue path acknowledges after the Kafka leader only, trading a small risk of lost jobs for latency

slack-2017-job-queue#d2peak under 100,000 requests/s

Slack2017Sharded
Decision

Serve every Q&A site from one multi-tenant application and keep web servers overprovisioned

stackoverflow-2016-architecture#d1peak under 10,000 requests/s

Stack Overflow2016Sharded
Decision

Use Elasticsearch for search instead of SQL Server full-text search, because SQL CPUs are expensive

stackoverflow-2016-architecture#d2peak under 10,000 requests/s

Stack Overflow2016Sharded

4 more records. Sign in to see all 24.