ADR-0001 Phase 3: add cutover.sh (11-phase scripted cutover with auto-rollback)
ci/woodpecker/push/deploy Pipeline was successful
ci/woodpecker/push/deploy Pipeline was successful
This commit is contained in:
@@ -0,0 +1,452 @@
|
||||
#!/usr/bin/env bash
|
||||
# ADR-0001 Phase 3 Cutover — cutover.sh
|
||||
#
|
||||
# Run DIRECTLY on docker-2 via SSH (NOT via the LXC-exec MCP tool — several
|
||||
# phases here run well past its ~30s timeout):
|
||||
#
|
||||
# ssh root@192.168.4.32
|
||||
# bash /volume1/docker/compose-files/postgresql/cutover/cutover.sh
|
||||
#
|
||||
# Implements RUNBOOK.md's 11 phases. Any failed check triggers immediate,
|
||||
# automatic invocation of rollback.sh and the script exits nonzero — no
|
||||
# manual intervention should be required to reach a safe state. Designed
|
||||
# to be run unattended, but given the blast radius (production DB, this
|
||||
# chat's own dependency on it, ~13 consumers) watching it live the first
|
||||
# time is strongly recommended anyway.
|
||||
#
|
||||
# ── Design notes on HOW checks are implemented (read before editing) ──────
|
||||
#
|
||||
# Node locality: plain `docker exec` only works for containers whose task
|
||||
# is actually scheduled on the node you run it from — Swarm does NOT proxy
|
||||
# exec across nodes. patroni-0/1/haproxy/etcd-1/3 may land on docker-1 or
|
||||
# docker-3, not docker-2. Two techniques are used throughout to work
|
||||
# around this, both already validated in the ADR-0001 dry run:
|
||||
# 1. Legacy's own container IS pinned to docker-2 (see postgresql.yaml:
|
||||
# node.hostname == docker-2) and shares postgresql_db-backend with
|
||||
# every HA-stack container — so `docker exec <legacy_cid> ...` is
|
||||
# always available locally and can reach any HA container by its
|
||||
# Swarm-DNS hostname (patroni-0, patroni-1, haproxy, etcd-2, etc.).
|
||||
# This is the SAME proxy pattern documented in the ADR-0001 note
|
||||
# ("docker exec <legacy container> psql -h patroni-1 -p 5432 ...").
|
||||
# 2. `docker service ps <service>` and `docker service logs <service>`
|
||||
# work cluster-wide from any manager regardless of which node the
|
||||
# task landed on — used for stability/health signal checks that
|
||||
# don't need to reach inside the container.
|
||||
# Patroni REST calls (port 8008) are made via bash's `/dev/tcp` raw-socket
|
||||
# trick executed inside the legacy container, NOT via curl — this avoids
|
||||
# assuming curl is present in the (Debian-slim) postgres:17 legacy image.
|
||||
#
|
||||
# ⚠️ DEVIATION FLAGGED FOR OPERATOR REVIEW — Phase 5 (promotion):
|
||||
# The ADR-0001 dry run promoted by removing the standby_cluster key
|
||||
# directly via etcdctl (patronictl had an unrelated config-loader quirk
|
||||
# in that environment). This script instead uses Patroni's own official,
|
||||
# documented REST API mechanism: `PATCH /config` with `{"standby_cluster":
|
||||
# null}`, which is Patroni's sanctioned way to remove a dynamic-config
|
||||
# key (see Patroni docs, REST API section). This avoids needing jq/python
|
||||
# inside the minimal etcd image to hand-edit YAML, and avoids the
|
||||
# patronictl quirk entirely — but it was NOT the exact mechanism proven
|
||||
# in the dry run. A manual fallback (raw etcdctl, matching the dry-run
|
||||
# method) is documented below and in RUNBOOK.md in case this PATCH
|
||||
# doesn't behave as expected. Recommend a low-stakes smoke test (e.g. a
|
||||
# GET /config call, done automatically below before the real PATCH) and
|
||||
# operator attention specifically during this phase.
|
||||
#
|
||||
# Manual fallback for Phase 5 if the PATCH approach ever needs bypassing:
|
||||
# docker exec <etcd-2_cid> etcdctl --endpoints=http://etcd-1:2379,http://etcd-2:2379,http://etcd-3:2379 \
|
||||
# get /service/postgres-ha/config --print-value-only
|
||||
# (hand-edit the returned YAML to remove the standby_cluster block, then)
|
||||
# docker exec <etcd-2_cid> etcdctl --endpoints=... put /service/postgres-ha/config -- "<edited YAML>"
|
||||
# etcd-2 is guaranteed to be on docker-2 (node.hostname == docker-2
|
||||
# constraint in both staging/final yaml), so this exec always works
|
||||
# locally if needed.
|
||||
|
||||
set -uo pipefail # NOTE: deliberately not -e — every phase below checks
|
||||
# its own command's exit status explicitly so we can
|
||||
# invoke rollback with a specific, accurate reason
|
||||
# rather than an opaque `set -e` abort mid-phase.
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
REPO_ROOT="/volume1/docker/compose-files"
|
||||
CUTOVER_DIR="${REPO_ROOT}/postgresql/cutover"
|
||||
HA_STACK="postgresqlha"
|
||||
LEGACY_STACK="postgresql"
|
||||
LEGACY_SERVICE="postgresql_postgresql"
|
||||
NETWORK_NAME="postgresql_db-backend"
|
||||
PATRONI_SCOPE="postgres-ha"
|
||||
BACKUP_DIR="/volume1/docker/PostgreSQL/cutover-backups"
|
||||
|
||||
# Consumer services checked in Phase 9 — (service_name, external health URL
|
||||
# or empty if internal-only). Derived from the dependency map in
|
||||
# RUNBOOK.md section 1. Update this list if the dependency map changes.
|
||||
declare -A CONSUMER_HEALTH_URLS=(
|
||||
["auth_authentik-server"]="https://auth.bryanmail.net/-/health/live/"
|
||||
["git_gitea-server"]="https://git.bryanmail.net/api/healthz"
|
||||
["woodpecker_woodpecker-server"]="https://woodpecker.bryanmail.net/healthz"
|
||||
)
|
||||
# Services checked via Swarm task-stability only (no forwardAuth-free
|
||||
# external endpoint known / internal-only) — open-webui and litellm sit
|
||||
# behind Authentik forwardAuth on their public routes, so an external curl
|
||||
# would just hit a login redirect, not real app health.
|
||||
CONSUMER_STABILITY_ONLY=(
|
||||
"ai_open-webui"
|
||||
"ai_litellm"
|
||||
"auth_authentik-worker"
|
||||
)
|
||||
|
||||
log() { echo "[cutover $(date +%H:%M:%S)] $*"; }
|
||||
warn() { echo "[cutover WARN $(date +%H:%M:%S)] $*" >&2; }
|
||||
|
||||
# Any hard failure calls this — invokes rollback.sh, then exits nonzero.
|
||||
# No manual step should be required after this runs.
|
||||
trigger_rollback() {
|
||||
local reason="$1"
|
||||
echo "" >&2
|
||||
echo "[cutover FAIL $(date +%H:%M:%S)] ${reason}" >&2
|
||||
echo "[cutover] Invoking rollback.sh automatically — no manual action should be required." >&2
|
||||
bash "${CUTOVER_DIR}/rollback.sh" "${reason}"
|
||||
local rc=$?
|
||||
if [ $rc -ne 0 ]; then
|
||||
echo "" >&2
|
||||
echo "[cutover] ⚠️ rollback.sh ITSELF returned nonzero (${rc}). This is the one" >&2
|
||||
echo "[cutover] scenario requiring manual intervention — see RUNBOOK.md section 4," >&2
|
||||
echo "[cutover] 'If rollback.sh itself fails partway'. Do not blindly re-run scripts." >&2
|
||||
fi
|
||||
exit 1
|
||||
}
|
||||
|
||||
# Get the container ID for the (always docker-2-local) legacy container.
|
||||
legacy_cid() {
|
||||
docker ps -q --filter "name=${LEGACY_SERVICE}" | head -1
|
||||
}
|
||||
|
||||
# Raw-socket HTTP GET via /dev/tcp, executed inside the legacy container.
|
||||
# Avoids assuming curl exists in the legacy postgres:17 image.
|
||||
# Args: host port path
|
||||
http_get_via_legacy() {
|
||||
local host="$1" port="$2" path="$3" cid
|
||||
cid="$(legacy_cid)"
|
||||
docker exec "$cid" bash -c "
|
||||
exec 3<>/dev/tcp/${host}/${port} || exit 99
|
||||
printf 'GET ${path} HTTP/1.0\r\nHost: ${host}\r\nConnection: close\r\n\r\n' >&3
|
||||
cat <&3
|
||||
" 2>/dev/null
|
||||
}
|
||||
|
||||
# Raw-socket HTTP PATCH with basic auth + JSON body, via /dev/tcp inside
|
||||
# the legacy container. Args: host port path username password json_body
|
||||
http_patch_via_legacy() {
|
||||
local host="$1" port="$2" path="$3" user="$4" pass="$5" body="$6" cid auth
|
||||
cid="$(legacy_cid)"
|
||||
auth="$(docker exec "$cid" bash -c "printf '%s' '${user}:${pass}' | base64 -w0")"
|
||||
local body_len=${#body}
|
||||
docker exec "$cid" bash -c "
|
||||
exec 3<>/dev/tcp/${host}/${port} || exit 99
|
||||
printf 'PATCH ${path} HTTP/1.0\r\nHost: ${host}\r\nAuthorization: Basic ${auth}\r\nContent-Type: application/json\r\nContent-Length: ${body_len}\r\nConnection: close\r\n\r\n${body}' >&3
|
||||
cat <&3
|
||||
" 2>/dev/null
|
||||
}
|
||||
|
||||
# Poll a Patroni node's /patroni endpoint for its reported role.
|
||||
# Args: hostname (e.g. patroni-1) -> prints role string (leader/replica/standby_leader/etc)
|
||||
patroni_role() {
|
||||
local host="$1"
|
||||
http_get_via_legacy "$host" 8008 "/patroni" | grep -o '"role"[^,}]*' | sed 's/.*: *"//;s/"$//'
|
||||
}
|
||||
|
||||
# Poll a Patroni node's /patroni endpoint for streaming lag against
|
||||
# whichever host it's replicating from. Returns the numeric lag if found,
|
||||
# empty otherwise (some responses omit it when lag is genuinely 0/absent).
|
||||
patroni_lag() {
|
||||
local host="$1"
|
||||
http_get_via_legacy "$host" 8008 "/patroni" | grep -o '"replication_state"[^,}]*\|"lag"[^,}]*' | head -1
|
||||
}
|
||||
|
||||
wait_for_stack_running() {
|
||||
local stack="$1" expected_count="$2" max_wait="${3:-120}"
|
||||
local waited=0
|
||||
while [ "$waited" -lt "$max_wait" ]; do
|
||||
local running
|
||||
running=$(docker stack ps "$stack" --filter "desired-state=running" --format '{{.CurrentState}}' 2>/dev/null | grep -c '^Running')
|
||||
if [ "$running" -ge "$expected_count" ]; then
|
||||
return 0
|
||||
fi
|
||||
sleep 5
|
||||
waited=$((waited + 5))
|
||||
done
|
||||
return 1
|
||||
}
|
||||
|
||||
# ═══════════════════════════════════════════════════════════════════════
|
||||
log "=== ADR-0001 Phase 3 real cutover starting ==="
|
||||
log "Chat dependency reminder: this chat (ai_open-webui/litellm) is itself"
|
||||
log "a consumer of the DB being migrated. If this script exits nonzero"
|
||||
log "before completing rollback, follow RUNBOOK.md section 4 manually via"
|
||||
log "direct SSH — do not assume this chat will remain usable to help."
|
||||
|
||||
# ── Phase 0: preflight ────────────────────────────────────────────────
|
||||
log "--- Phase 0: preflight ---"
|
||||
if ! bash "${CUTOVER_DIR}/preflight.sh"; then
|
||||
echo "[cutover] preflight.sh failed. Nothing has been touched — safe to stop here, no rollback needed." >&2
|
||||
exit 1
|
||||
fi
|
||||
log "PASS: Phase 0 preflight"
|
||||
|
||||
# ── Phase 1: deploy postgresqlha staging stack ─────────────────────────
|
||||
log "--- Phase 1: deploy postgresqlha (staging) ---"
|
||||
|
||||
PRIMARY_LABELED=$(docker node ls --format '{{.Hostname}}' | xargs -I{} docker node inspect {} --format '{{.Spec.Labels.pg_role}}{{.Spec.Labels.pg-role}}' 2>/dev/null | grep -c primary || true)
|
||||
REPLICA_LABELED=$(docker node ls --format '{{.Hostname}}' | xargs -I{} docker node inspect {} --format '{{.Spec.Labels.pg_role}}{{.Spec.Labels.pg-role}}' 2>/dev/null | grep -c replica || true)
|
||||
if [ "$PRIMARY_LABELED" -lt 1 ] || [ "$REPLICA_LABELED" -lt 1 ]; then
|
||||
trigger_rollback "No node(s) found with pg-role=primary/replica labels — patroni-0/1 placement constraints cannot schedule. Set via: docker node update --label-add pg-role=primary <node> (and =replica on another). Nothing deployed yet, rollback is a no-op safety call."
|
||||
fi
|
||||
|
||||
docker stack deploy -c "${CUTOVER_DIR}/postgresql-ha-staging.yaml" "${HA_STACK}"
|
||||
if [ $? -ne 0 ]; then
|
||||
trigger_rollback "docker stack deploy of postgresql-ha-staging.yaml failed."
|
||||
fi
|
||||
|
||||
log "Waiting for postgresqlha services to be running (etcd-1/2/3, patroni-0/1, haproxy = 6)..."
|
||||
if ! wait_for_stack_running "${HA_STACK}" 6 180; then
|
||||
trigger_rollback "postgresqlha stack did not reach 6 running tasks within 180s."
|
||||
fi
|
||||
|
||||
log "Confirming patroni-1 reaches standby_leader..."
|
||||
ROLE=""
|
||||
for i in $(seq 1 24); do
|
||||
ROLE="$(patroni_role patroni-1)"
|
||||
[ "$ROLE" = "standby_leader" ] && break
|
||||
sleep 10
|
||||
done
|
||||
if [ "$ROLE" != "standby_leader" ]; then
|
||||
trigger_rollback "patroni-1 did not reach standby_leader role within 240s (last observed: '${ROLE}')."
|
||||
fi
|
||||
log "PASS: Phase 1 — patroni-1 is standby_leader"
|
||||
|
||||
# ── Phase 2: wait for streaming lag = 0 ────────────────────────────────
|
||||
log "--- Phase 2: confirm streaming lag = 0 ---"
|
||||
CONSECUTIVE_ZERO=0
|
||||
for i in $(seq 1 30); do
|
||||
P0_ROLE="$(patroni_role patroni-0)"
|
||||
LAG_INFO="$(patroni_lag patroni-0)"
|
||||
log "patroni-0 role=${P0_ROLE} lag_info=${LAG_INFO}"
|
||||
if [ "$P0_ROLE" = "replica" ] && { [ -z "$LAG_INFO" ] || echo "$LAG_INFO" | grep -q '"lag": *0\b\|streaming'; }; then
|
||||
CONSECUTIVE_ZERO=$((CONSECUTIVE_ZERO + 1))
|
||||
else
|
||||
CONSECUTIVE_ZERO=0
|
||||
fi
|
||||
[ "$CONSECUTIVE_ZERO" -ge 3 ] && break
|
||||
sleep 10
|
||||
done
|
||||
if [ "$CONSECUTIVE_ZERO" -lt 3 ]; then
|
||||
trigger_rollback "Streaming lag never reached 3 consecutive zero/streaming polls on patroni-0. Last state: role=${P0_ROLE} lag_info=${LAG_INFO}"
|
||||
fi
|
||||
log "PASS: Phase 2 — streaming confirmed, lag=0 for 3 consecutive polls"
|
||||
|
||||
# ── Phase 3: pre-promotion canary write/propagation check ─────────────
|
||||
log "--- Phase 3: pre-promotion canary (legacy -> patroni-0 cascade replica) ---"
|
||||
LEGACY_CID="$(legacy_cid)"
|
||||
if [ -z "$LEGACY_CID" ]; then
|
||||
trigger_rollback "Could not find legacy container for canary write."
|
||||
fi
|
||||
CANARY_VAL="cutover-$(date +%s)"
|
||||
docker exec "$LEGACY_CID" bash -c "psql -U \"\$POSTGRES_USER\" -c \"CREATE TABLE IF NOT EXISTS _cutover_canary (val text, ts timestamptz default now()); INSERT INTO _cutover_canary(val) VALUES ('${CANARY_VAL}');\"" >/dev/null 2>&1
|
||||
if [ $? -ne 0 ]; then
|
||||
trigger_rollback "Failed to write pre-promotion canary row to legacy."
|
||||
fi
|
||||
FOUND=0
|
||||
for i in $(seq 1 5); do
|
||||
RESULT=$(docker exec "$LEGACY_CID" bash -c "psql -h patroni-0 -U \"\$POSTGRES_USER\" -tAc \"SELECT 1 FROM _cutover_canary WHERE val = '${CANARY_VAL}';\"" 2>/dev/null)
|
||||
if [ "$RESULT" = "1" ]; then
|
||||
FOUND=1
|
||||
break
|
||||
fi
|
||||
sleep 1
|
||||
done
|
||||
if [ "$FOUND" -ne 1 ]; then
|
||||
trigger_rollback "Canary row did not propagate to patroni-0 within 5s. standby_cluster streaming is not working as expected."
|
||||
fi
|
||||
log "PASS: Phase 3 — canary write propagated to patroni-0 within 5s"
|
||||
|
||||
# ── Phase 4: flip legacy to read-only ───────────────────────────────────
|
||||
log "--- Phase 4: flip legacy read-only ---"
|
||||
docker exec "$LEGACY_CID" bash -c 'psql -U "$POSTGRES_USER" -c "ALTER SYSTEM SET default_transaction_read_only = on; SELECT pg_reload_conf();"' >/dev/null 2>&1
|
||||
if [ $? -ne 0 ]; then
|
||||
trigger_rollback "Failed to set default_transaction_read_only=on on legacy."
|
||||
fi
|
||||
RO_STATE=$(docker exec "$LEGACY_CID" bash -c 'psql -U "$POSTGRES_USER" -tAc "SHOW default_transaction_read_only;"' 2>/dev/null | tr -d '[:space:]')
|
||||
if [ "$RO_STATE" != "on" ]; then
|
||||
trigger_rollback "Verified read-only state is '${RO_STATE}', expected 'on'. Reversing immediately."
|
||||
fi
|
||||
log "Legacy confirmed read-only. Draining one more lag poll to confirm quiescence..."
|
||||
sleep 5
|
||||
LAG_INFO="$(patroni_lag patroni-0)"
|
||||
log "Post-read-only lag check: ${LAG_INFO}"
|
||||
log "PASS: Phase 4 — legacy is read-only, no further writes possible there"
|
||||
|
||||
# ── Phase 5: promote Patroni ─────────────────────────────────────────
|
||||
log "--- Phase 5: promote patroni-1 (remove standby_cluster from DCS config) ---"
|
||||
log "⚠️ Highest-scrutiny phase — see script header for the documented deviation from the dry-run's raw-etcdctl method (using Patroni's official REST PATCH /config instead). Manual etcdctl fallback documented above and in RUNBOOK.md if needed."
|
||||
|
||||
PATRONI_PASS=$(docker exec "$LEGACY_CID" cat /run/secrets/postgresql_patroni_password 2>/dev/null)
|
||||
if [ -z "$PATRONI_PASS" ]; then
|
||||
# legacy container may not have this secret mounted — fall back to reading via patroni-1 itself if reachable, else hard-fail before touching anything
|
||||
trigger_rollback "Could not read postgresql_patroni_password secret needed for the promotion PATCH call. Nothing promoted yet."
|
||||
fi
|
||||
|
||||
log "Smoke-test: GET /config on patroni-1 before attempting the PATCH..."
|
||||
CONFIG_CHECK=$(http_get_via_legacy patroni-1 8008 "/config")
|
||||
if ! echo "$CONFIG_CHECK" | grep -qi "standby_cluster"; then
|
||||
trigger_rollback "GET /config on patroni-1 did not show a standby_cluster key as expected before promotion — refusing to PATCH against an unexpected state. Raw response logged above for review."
|
||||
fi
|
||||
log "Smoke-test passed — standby_cluster key confirmed present pre-promotion."
|
||||
|
||||
PATCH_RESPONSE=$(http_patch_via_legacy patroni-1 8008 "/config" "patroni" "$PATRONI_PASS" '{"standby_cluster": null}')
|
||||
log "PATCH /config response: ${PATCH_RESPONSE}"
|
||||
|
||||
log "Waiting for patroni-1 to transition standby_leader -> leader (expect ~15-30s per dry-run drills)..."
|
||||
PROMOTED=0
|
||||
for i in $(seq 1 12); do
|
||||
ROLE="$(patroni_role patroni-1)"
|
||||
log "patroni-1 role: ${ROLE}"
|
||||
if [ "$ROLE" = "leader" ]; then
|
||||
PROMOTED=1
|
||||
break
|
||||
fi
|
||||
sleep 5
|
||||
done
|
||||
if [ "$PROMOTED" -ne 1 ]; then
|
||||
trigger_rollback "patroni-1 did not reach 'leader' role within 60s of the promotion PATCH. Last observed role: '${ROLE}'. Manual etcdctl fallback is documented in this script's header / RUNBOOK.md if the operator wants to investigate before accepting the automatic rollback."
|
||||
fi
|
||||
|
||||
IN_RECOVERY=$(docker exec "$LEGACY_CID" bash -c 'psql -h patroni-1 -U "$POSTGRES_USER" -tAc "SELECT pg_is_in_recovery();"' 2>/dev/null | tr -d '[:space:]')
|
||||
if [ "$IN_RECOVERY" != "f" ]; then
|
||||
trigger_rollback "patroni-1 reports role=leader but pg_is_in_recovery() = '${IN_RECOVERY}' (expected 'f'). Not trusting this as a genuine promotion."
|
||||
fi
|
||||
log "PASS: Phase 5 — patroni-1 is genuine writable leader, pg_is_in_recovery=f"
|
||||
|
||||
# ── Phase 6: confirm HAProxy would see a healthy backend ──────────────
|
||||
log "--- Phase 6: confirm healthy backend before touching DNS ---"
|
||||
PRIMARY_CHECK=$(http_get_via_legacy patroni-1 8008 "/primary")
|
||||
if ! echo "$PRIMARY_CHECK" | grep -q "200 OK"; then
|
||||
trigger_rollback "patroni-1 does not answer 200 on GET /primary post-promotion. Raw response: ${PRIMARY_CHECK}"
|
||||
fi
|
||||
log "PASS: Phase 6 — patroni-1 answers 200 on /primary, HAProxy's healthcheck will pass"
|
||||
|
||||
# ── Phase 7: deploy final HAProxy with postgresql/db aliases ──────────
|
||||
log "--- Phase 7: deploy postgresql-ha-final.yaml (adds postgresql/db aliases) ---"
|
||||
docker stack deploy -c "${CUTOVER_DIR}/postgresql-ha-final.yaml" "${HA_STACK}"
|
||||
if [ $? -ne 0 ]; then
|
||||
trigger_rollback "docker stack deploy of postgresql-ha-final.yaml failed."
|
||||
fi
|
||||
log "Waiting for haproxy service update to roll out..."
|
||||
sleep 15
|
||||
if ! wait_for_stack_running "${HA_STACK}" 6 90; then
|
||||
trigger_rollback "postgresqlha stack did not return to 6 running tasks after haproxy alias update."
|
||||
fi
|
||||
|
||||
log "Confirming DNS resolution of 'postgresql' now shows BOTH legacy and haproxy..."
|
||||
RESOLVE_OUTPUT=$(docker exec "$LEGACY_CID" bash -c "getent hosts postgresql" 2>/dev/null)
|
||||
log "Resolution: ${RESOLVE_OUTPUT}"
|
||||
NUM_IPS=$(echo "$RESOLVE_OUTPUT" | awk '{print $1}' | sort -u | wc -l)
|
||||
if [ "$NUM_IPS" -lt 2 ]; then
|
||||
trigger_rollback "Expected 2 distinct IPs for 'postgresql' (legacy + haproxy) after alias deploy, found ${NUM_IPS}. Resolution output: ${RESOLVE_OUTPUT}"
|
||||
fi
|
||||
log "PASS: Phase 7 — 'postgresql' resolves to ${NUM_IPS} IPs (legacy + haproxy), alias handoff live"
|
||||
|
||||
# ── Phase 8: canary write through the alias (retry-tolerant of legacy read-only hits) ──
|
||||
log "--- Phase 8: canary write/propagation THROUGH the shared alias ---"
|
||||
log "Note: during this window 'postgresql' round-robins between legacy (read-only)"
|
||||
log "and haproxy (writable). Write attempts landing on legacy will correctly fail"
|
||||
log "with a read-only error — that is EXPECTED, not a hard failure by itself."
|
||||
CANARY2_VAL="cutover-alias-$(date +%s)"
|
||||
ALIAS_WRITE_OK=0
|
||||
for i in $(seq 1 10); do
|
||||
docker exec "$LEGACY_CID" bash -c "psql -h postgresql -U \"\$POSTGRES_USER\" -c \"INSERT INTO _cutover_canary(val) VALUES ('${CANARY2_VAL}');\"" >/tmp/cutover_phase8_attempt_$i.log 2>&1
|
||||
if [ $? -eq 0 ]; then
|
||||
ALIAS_WRITE_OK=1
|
||||
break
|
||||
fi
|
||||
sleep 2
|
||||
done
|
||||
if [ "$ALIAS_WRITE_OK" -ne 1 ]; then
|
||||
trigger_rollback "Never succeeded writing through the 'postgresql' alias after 10 attempts (~20s). See /tmp/cutover_phase8_attempt_*.log on docker-2 for the read-only/connection errors encountered."
|
||||
fi
|
||||
log "Alias write succeeded on attempt ${i}. Confirming visibility on BOTH patroni-0 and patroni-1..."
|
||||
V0=$(docker exec "$LEGACY_CID" bash -c "psql -h patroni-0 -U \"\$POSTGRES_USER\" -tAc \"SELECT 1 FROM _cutover_canary WHERE val = '${CANARY2_VAL}';\"" 2>/dev/null)
|
||||
V1=$(docker exec "$LEGACY_CID" bash -c "psql -h patroni-1 -U \"\$POSTGRES_USER\" -tAc \"SELECT 1 FROM _cutover_canary WHERE val = '${CANARY2_VAL}';\"" 2>/dev/null)
|
||||
if [ "$V0" != "1" ] || [ "$V1" != "1" ]; then
|
||||
trigger_rollback "Alias-written canary row not visible on both nodes (patroni-0='${V0}' patroni-1='${V1}')."
|
||||
fi
|
||||
log "PASS: Phase 8 — real client-path write through the alias succeeded and is visible on both nodes"
|
||||
|
||||
# ── Phase 9: verify all known consumers ────────────────────────────────
|
||||
log "--- Phase 9: verify known consumers reconnect/function ---"
|
||||
CONSUMER_FAIL=0
|
||||
for svc in "${!CONSUMER_HEALTH_URLS[@]}"; do
|
||||
url="${CONSUMER_HEALTH_URLS[$svc]}"
|
||||
CODE=$(curl -sk -o /dev/null -w '%{http_code}' --max-time 10 "$url")
|
||||
log " ${svc} -> ${url} -> HTTP ${CODE}"
|
||||
if [ "$CODE" != "200" ]; then
|
||||
warn " ${svc} did not return 200 (got ${CODE})"
|
||||
CONSUMER_FAIL=1
|
||||
fi
|
||||
done
|
||||
for svc in "${CONSUMER_STABILITY_ONLY[@]}"; do
|
||||
RESTARTS=$(docker service ps "$svc" --filter "desired-state=running" --format '{{.CurrentState}}' 2>/dev/null | grep -c 'seconds ago\|Starting')
|
||||
log " ${svc} -> recent-restart signal count: ${RESTARTS} (0 expected if stable)"
|
||||
if [ "$RESTARTS" -gt 0 ]; then
|
||||
warn " ${svc} shows a recent restart — may just be catching up post-cutover, but flagging."
|
||||
CONSUMER_FAIL=1
|
||||
fi
|
||||
done
|
||||
if [ "$CONSUMER_FAIL" -ne 0 ]; then
|
||||
trigger_rollback "One or more consumers failed verification in Phase 9. See warnings above. Treating any consumer failure here as a cutover failure, not something to patch around live."
|
||||
fi
|
||||
log "PASS: Phase 9 — all known consumers verified"
|
||||
|
||||
# ── Phase 10: stop legacy ──────────────────────────────────────────────
|
||||
log "--- Phase 10: stop legacy service ---"
|
||||
docker service scale "${LEGACY_SERVICE}=0"
|
||||
if [ $? -ne 0 ]; then
|
||||
trigger_rollback "Failed to scale ${LEGACY_SERVICE} to 0."
|
||||
fi
|
||||
sleep 10
|
||||
log "Confirming HAProxy backend still healthy post-legacy-stop..."
|
||||
PRIMARY_CHECK2=$(http_get_via_legacy patroni-1 8008 "/primary" 2>/dev/null || true)
|
||||
# Note: legacy is now stopped, so http_get_via_legacy (which proxies via
|
||||
# the legacy container) will start failing itself shortly — this is
|
||||
# EXPECTED and is why this is the last check that uses that proxy method.
|
||||
log "Last legacy-proxied check (legacy is now down, this method retires after this call): ${PRIMARY_CHECK2}"
|
||||
|
||||
log "Confirming 'postgresql' now resolves ONLY to haproxy..."
|
||||
# Use a disposable probe container instead of the (now-stopping) legacy container.
|
||||
PROBE_OUT=$(docker run --rm --network "${NETWORK_NAME}" alpine:3 sh -c "getent hosts postgresql" 2>/dev/null)
|
||||
log "Resolution post-legacy-stop: ${PROBE_OUT}"
|
||||
NUM_IPS2=$(echo "$PROBE_OUT" | awk '{print $1}' | sort -u | wc -l)
|
||||
if [ "$NUM_IPS2" -ne 1 ]; then
|
||||
warn "Expected exactly 1 IP for 'postgresql' now that legacy is stopped, found ${NUM_IPS2}. This may just be DNS cache settling — re-check manually before treating as fatal, but NOT auto-rolling-back here since legacy has already been cleanly stopped (scale=1 would just resume it)."
|
||||
fi
|
||||
|
||||
log "Re-running Phase 9 consumer checks post-legacy-stop..."
|
||||
CONSUMER_FAIL2=0
|
||||
for svc in "${!CONSUMER_HEALTH_URLS[@]}"; do
|
||||
url="${CONSUMER_HEALTH_URLS[$svc]}"
|
||||
CODE=$(curl -sk -o /dev/null -w '%{http_code}' --max-time 10 "$url")
|
||||
log " ${svc} -> ${url} -> HTTP ${CODE}"
|
||||
[ "$CODE" != "200" ] && CONSUMER_FAIL2=1
|
||||
done
|
||||
if [ "$CONSUMER_FAIL2" -ne 0 ]; then
|
||||
trigger_rollback "Consumer check failed AFTER stopping legacy. Per RUNBOOK.md, rollback past this point is asymmetric (restores legacy as primary of record, not just a flag flip) — invoking rollback.sh now rather than leaving this in a broken state."
|
||||
fi
|
||||
log "PASS: Phase 10 — legacy stopped, consumers still healthy"
|
||||
|
||||
# ── Phase 11: final verification ────────────────────────────────────────
|
||||
log "--- Phase 11: final verification pass ---"
|
||||
docker stack ps "${HA_STACK}" --no-trunc | tail -n +1
|
||||
AVAIL_GB=$(df --output=avail -BG /volume1/docker/PostgreSQL 2>/dev/null | tail -1 | tr -dc '0-9')
|
||||
log "Disk space remaining at /volume1/docker/PostgreSQL: ${AVAIL_GB}GB"
|
||||
log "=== CUTOVER COMPLETE ==="
|
||||
log "Backup taken this run: $(cat ${BACKUP_DIR}/LATEST 2>/dev/null || echo 'unknown')"
|
||||
log "See RUNBOOK.md section 7 for manual post-cutover follow-up (legacy"
|
||||
log "decommission, external port 5430 / Traefik SNI handoff, burn-in period)."
|
||||
exit 0
|
||||
Reference in New Issue
Block a user