diff --git a/k8s/infra/cluster-maintenance/etcd-defrag-cronjob.yaml b/k8s/infra/cluster-maintenance/etcd-defrag-cronjob.yaml index 99a0ad1..c75fb3d 100644 --- a/k8s/infra/cluster-maintenance/etcd-defrag-cronjob.yaml +++ b/k8s/infra/cluster-maintenance/etcd-defrag-cronjob.yaml @@ -1,23 +1,58 @@ -# etcd defrag maintenance. +# etcd backend maintenance: compact, defrag, disarm NOSPACE. # -# Why this exists: the apiserver compacts etcd every 5m, but compaction only marks -# superseded revisions free INSIDE the backend file -- the file never shrinks. -# Only `etcdctl defrag` returns space to the filesystem, and nothing runs it -# automatically. On 2026-10-07 the 2 GiB quota was reached after ~73 days -# (backend 2.1 GiB) -> etcd raised the NOSPACE alarm -> etcd refused ALL writes -# -> kubelets could not post node status -> 3 nodes went NotReady and the tunnel -# origin pods on them vanished (502s). Recovery = compact + defrag + alarm disarm. +# Why this exists +# --------------- +# etcd's backend file only grows. The apiserver compacts every 5m, but +# compaction marks superseded revisions free *inside* the file; only `defrag` +# returns that space to the filesystem. Nothing ran defrag, so the file grew +# until it crossed the 2 GiB quota: # -# This CronJob keeps the backend well under quota: compact to the current -# revision, defrag each member sequentially, then disarm any NOSPACE alarm. +# 2026-10-07 backend 2,148,843,520 B (2.1 GB) on talos-cp-1 and talos-cp-3 +# -> etcd raised NOSPACE on those two members +# -> etcd rejected ALL writes cluster-wide +# -> kubelets could not post node status: 3 nodes NotReady +# -> apiserver writes returned 500, the tunnel API path 502 +# +# The live data was tiny: 15,943 keys, 69 MB after compaction. The rest was +# dead pages. Recovery was `compact ` then `defrag` per +# member then `alarm disarm`. Compaction had also stalled while the alarm was +# up, so `dbSizeInUse` read 100% of the file - defrag alone would NOT have +# worked. Order matters: compact first, then defrag. +# +# The earlier revision of this file never ran, for two independent reasons: +# 1. it existed only on branch fix/etcd-defrag-cron; the ArgoCD application +# `cluster-maintenance` tracks `main` (targetRevision: main), so the +# cluster never had the CronJob or the Secret. +# 2. the image was quay.io/coreos/etcd, which has NO /bin/sh (verified: +# `exec: "/bin/sh": no such file or directory`). Any container that runs +# a shell script needs an image that ships one. +# This revision fixes both: image bitnamilegacy/etcd (ships bash + etcdctl +# 3.6.4, matching the 3.6.11 servers) pinned by digest. +# +# Cadence: every 15 days. Measured growth is ~29 MB/day, so a 15-day cycle +# peaks near 500 MB - comfortably under the 2 GiB quota. The schedule is daily +# and the script exits unless the UTC epoch day is a multiple of 15. That gives +# an exact 15-day interval; `*/15` in the day-of-month field does not (it fires +# on the 1st, 16th and 31st, which puts two runs one day apart). +# +# Safety +# ------ +# 1. Compaction uses the MINIMUM revision across members. Compacting to a +# revision a member has not reached wedges that member - measured on +# 2026-10-07, when talos-cp-2 froze ~1.2M entries behind the leader and +# needed a reboot to rejoin. +# 2. A member whose raft applied index lags the leader by more than 100000 is +# skipped and reported. Defragging a frozen member reclaims nothing. +# 3. Members are defragged one at a time. A defrag pauses the member's apply +# loop for the duration of the file copy. +# +# Credentials: Secret etcd-defrag-creds in kube-system, SOPS-managed in +# k8s/argocd/secrets/etcd-defrag-creds.enc.yaml (ksops generator 00-secrets). +# Its client certificate is signed by the cluster's etcd CA and expires +# 2036-10; rotate it before then by re-running the mint and re-encrypting. # # Companion alerts (monitoring): etcd_mvcc_db_total_size_in_bytes / -# etcd_server_quota_in_bytes > 0.8, and a NOSPACE alarm alert. -# -# Credentials: secret etcd-defrag-creds (kube-system), SOPS-managed in -# k8s/argocd/secrets/etcd-defrag-creds.enc.yaml. Its client cert is signed by the -# cluster's etcd CA and expires 2036-10 -- rotate it before then by re-running the -# mint + re-encrypt (see the repo's sops workflow). +# etcd_server_quota_backend_bytes > 0.8, and an etcd NOSPACE alarm alert. apiVersion: batch/v1 kind: CronJob metadata: @@ -27,7 +62,7 @@ metadata: app.kubernetes.io/name: etcd-defrag app.kubernetes.io/part-of: cluster-maintenance spec: - schedule: "0 3 * * 0" # Sundays 03:00, low traffic + schedule: "0 3 * * *" # daily; the script acts only every 15th day concurrencyPolicy: Forbid startingDeadlineSeconds: 600 successfulJobsHistoryLimit: 3 @@ -44,7 +79,7 @@ spec: effect: NoSchedule containers: - name: defrag - image: quay.io/coreos/etcd:v3.5.17 + image: bitnamilegacy/etcd:3.6.4@sha256:c86c06f1ce6a08b6df21eb7a9655b1818778b64c85b5cbb8413ebf7534789730 env: - name: ETCDCTL_API value: "3" @@ -56,36 +91,77 @@ spec: value: /etc/etcd/client.key - name: EPS value: "https://192.168.1.166:2379 https://192.168.1.214:2379 https://192.168.1.162:2379" - command: ["/bin/sh", "-c"] + command: ["/bin/bash", "-c"] args: - | set -u - PRIMARY=${EPS%% *} - echo "== before ==" - etcdctl --endpoints=$EPS endpoint status -w table || true - REV=$(etcdctl --endpoints=$PRIMARY endpoint status -w json \ - | sed -n 's/.*"revision":\([0-9]*\).*/\1/p' | head -1) - if [ -n "$REV" ]; then - echo "== compact to revision $REV ==" - etcdctl --endpoints=$PRIMARY compact "$REV" || true + DAY=$(( $(date -u +%s) / 86400 )) + if [ $(( DAY % 15 )) -ne 0 ]; then + echo "skip: UTC epoch day $DAY is not a 15-day boundary" + exit 0 fi + echo "== before ==" + for ep in $EPS; do + etcdctl --endpoints="$ep" endpoint status -w table || true + done + + MINREV="" + MAXAPPLIED=0 + for ep in $EPS; do + json=$(etcdctl --endpoints="$ep" endpoint status -w json 2>/dev/null) || continue + rev=$(printf '%s' "$json" | sed -n 's/.*"revision":\([0-9]*\).*/\1/p' | head -1) + app=$(printf '%s' "$json" | sed -n 's/.*"raftAppliedIndex":\([0-9]*\).*/\1/p' | head -1) + echo "member $ep revision=${rev:-?} raftAppliedIndex=${app:-?}" + if [ -n "$rev" ] && { [ -z "$MINREV" ] || [ "$rev" -lt "$MINREV" ]; }; then + MINREV="$rev" + fi + if [ -n "$app" ] && [ "$app" -gt "$MAXAPPLIED" ]; then + MAXAPPLIED="$app" + fi + done + + if [ -z "$MINREV" ]; then + echo "FATAL: no member returned a revision; nothing attempted" + exit 1 + fi + + echo "== compact to revision $MINREV ==" + etcdctl --endpoints="$(echo "$EPS" | awk '{print $1}')" compact "$MINREV" || echo "COMPACT-FAILED (continuing: defrag still reclaims free pages)" + + # Physical deletion of superseded keys runs in the background + # after the compaction commit; give it a moment to drain. + sleep 20 + echo "== defrag each member (sequential, one at a time) ==" rc=0 for ep in $EPS; do + json=$(etcdctl --endpoints="$ep" endpoint status -w json 2>/dev/null) || { echo "SKIP $ep (unreachable)"; rc=1; continue; } + app=$(printf '%s' "$json" | sed -n 's/.*"raftAppliedIndex":\([0-9]*\).*/\1/p' | head -1) + if [ -n "$app" ] && [ "$app" -lt $(( MAXAPPLIED - 100000 )) ]; then + echo "SKIP $ep (applied index $app lags leader $MAXAPPLIED; defrag would reclaim nothing)" + rc=1 + continue + fi echo "-- $ep" - etcdctl --endpoints="$ep" defrag || { echo "DEFRAG-FAILED $ep"; rc=1; } + if ! etcdctl --endpoints="$ep" defrag; then + echo "DEFRAG-FAILED $ep" + rc=1 + fi done echo "== disarm NOSPACE ==" for ep in $EPS; do + etcdctl --endpoints="$ep" alarm list 2>/dev/null || true etcdctl --endpoints="$ep" alarm disarm 2>/dev/null || true done echo "== after ==" - etcdctl --endpoints=$EPS endpoint status -w table || true - etcdctl --endpoints=$PRIMARY alarm list || true + for ep in $EPS; do + etcdctl --endpoints="$ep" endpoint status -w table || true + done + etcdctl --endpoints="$(echo "$EPS" | awk '{print $1}')" alarm list || true exit $rc resources: requests: { cpu: 10m, memory: 32Mi }