Catalogue
- Cards
- 165
- Records
- 486
- Workloads
- 19
- Corpus version
- 74847648e25a
8 of 486 records match.
| Kind | Record | Organisation | Year | Setup |
|---|---|---|---|---|
| Failure | Users who follow hundreds of thousands of accounts made hot shards that slowed the timelines sharing them | Bluesky | 2025 | Sharded |
| Decision | Drop timeline writes with a probability set by how many accounts a user follows, accepting imperfect timelines | Bluesky | 2025 | Sharded |
| 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 | Sharded |
| Decision | Restrict Venice to asynchronous batch and stream writes with background version swaps, server-side partial updates, and hybrid replay | 2022 | Multi-region | |
| Decision | Push vector math onto Venice servers with Read Compute and embed Da Vinci as an eager local-state client library | 2022 | Multi-region | |
| Decision | Swap BDB-JE for pluggable RocksDB storage formats and operator-driven Zstandard shared-dictionary compression | 2022 | Multi-region | |
| Decision | Run active-active multi-region replication and rack-aware Apache Helix self-healing reusing the Full Push rebalance path | 2022 | Multi-region | |
| Decision | Enforce per-dataset storage and read quotas on multi-tenant clusters and group over-replicated partitions to bound fanout | 2022 | Multi-region |