infra/docs/post-mortems
Viktor Barzin 0dd4a31eff docs(immich): cap server-side job concurrency to protect sdc + log recurrence
A library-wide Duplicate Detection run on 2026-06-01 fanned the ML/thumbnail
backfill out at thumbnailGeneration concurrency 8, saturating the shared sdc
HDD and starving etcd -> kube-apiserver down ~30 min (5th IO-pressure incident
on sdc). Capped server-side thumbnailGeneration/metadataExtraction/library to 2
in the Immich DB system-config; documented in the Immich row and recorded the
recurrence + still-TODO IO-isolation fixes in the 2026-05-25 post-mortem (this
also commits that previously-untracked post-mortem).

[ci skip]

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-06-01 15:15:26 +00:00
..
2026-03-16-kured-containerd-cascade-outage.html docs: consolidate all post-mortems under docs/post-mortems/ 2026-04-14 08:24:36 +00:00
2026-03-16-nfs-csi-cascade-failure.md docs: move post-mortems to docs/post-mortems/ 2026-04-14 08:20:09 +00:00
2026-04-14-nfs-fsid0-dns-vault-outage.md docs: update post-mortem follow-up implementation [PM-2026-04-14] [ci skip] 2026-04-14 18:09:11 +00:00
2026-04-14-postmortem-pipeline-test.md fix: use full path to claude CLI for non-interactive SSH 2026-04-14 17:44:50 +00:00
2026-04-18-authentik-outpost-shm-full.md docs/authentik: document postgres session backend + close out 2026-04-18 post-mortem items 2026-05-10 16:28:11 +00:00
2026-04-19-registry-orphan-index.md [registry] bulk-clean 34 orphan manifests + beads-server image bump 2026-04-19 23:16:34 +00:00
2026-04-22-vault-raft-leader-deadlock.md vault: complete Phase 2 NFS-hostile migration; remove nfs-proxmox SC 2026-04-25 17:10:00 +00:00
2026-05-09-io-pressure-stale-nfs.md mysql: bump to 4Gi limit / 3Gi request; grow /srv/nfs LV to 3 TiB 2026-05-09 17:01:57 +00:00
2026-05-16-kured-stalled-and-anubis-ha.md docs/pm: kured silently stalled 6 days + Anubis HA lift (2026-05-16) 2026-05-16 12:17:26 +00:00
2026-05-17-gpu-driver-ubuntu2604-mismatch.md nvidia: fix driver install deadlock + extend startup probe 2026-05-25 11:53:44 +00:00
2026-05-17-nfs-csi-keel-upgrade-master-port-conflict.md nfs-csi: pin chart v4.13.1 + controller affinity (post-mortem) 2026-05-17 09:11:09 +00:00
2026-05-25-immich-anca-elements-io-storm.md docs(immich): cap server-side job concurrency to protect sdc + log recurrence 2026-06-01 15:15:26 +00:00
2026-05-30-redis-split-brain.md redis: revert 3-node Sentinel HA to single standalone instance [ci skip] 2026-05-30 17:49:43 +00:00
2026-05-31-kured-sentinel-gate-oom.md kured: fix sentinel-gate OOM — 256Mi limit + self-restart leak guard 2026-05-31 14:49:04 +00:00
index.html docs: consolidate all post-mortems under docs/post-mortems/ 2026-04-14 08:24:36 +00:00