backlog(2): plausible Q4.7b scoped + ready (staged hardened entrypoint.clickhouse.sh; mirror+PR+run steps); queued behind Adversary Q4.6/F2-14c verifies
This commit is contained in:
64
machine-docs/plausible-entrypoint.clickhouse.sh.fixed
Normal file
64
machine-docs/plausible-entrypoint.clickhouse.sh.fixed
Normal file
@ -0,0 +1,64 @@
|
||||
#!/bin/bash
|
||||
# clickhouse entrypoint (cc-ci Q4.7b hardening — recipe-PR for recipe-maintainers/plausible).
|
||||
#
|
||||
# clickhouse-backup is the BACKUP tool (backupbot pre/post-hooks: `clickhouse-backup create/restore`).
|
||||
# It is NOT required for clickhouse-SERVER (`/entrypoint.sh`) to run. The published recipe fetched it
|
||||
# with `set -ex` + a single silenced no-retry wget to ephemeral /tmp, so ANY transient failure of the
|
||||
# 22 MB GitHub download (rate-limit / network) exited the container BEFORE the server started → swarm
|
||||
# restarted it → re-downloaded → amplified the throttle → crash-loop → deploy timeout (cc-ci Q4.7).
|
||||
#
|
||||
# Hardening (no behaviour change when the download succeeds first try):
|
||||
# - cache the binary on the PERSISTENT clickhouse data volume (/var/lib/clickhouse) so it is fetched
|
||||
# at most once and reused on every container restart (no re-download amplification);
|
||||
# - retry with backoff;
|
||||
# - NEVER let a download failure block the server start (best-effort: the server comes up, backup/
|
||||
# restore degrade until the next successful fetch);
|
||||
# - un-silenced so a failure is diagnosable in `docker service logs`.
|
||||
|
||||
set -e
|
||||
|
||||
CLICKHOUSE_BACKUP_VERSION=2.4.2
|
||||
|
||||
ARCH=$(uname -m)
|
||||
if [[ $ARCH =~ "aarch64" ]]; then
|
||||
ARCH="arm64"
|
||||
elif [[ $ARCH =~ "armv5l" ]]; then
|
||||
ARCH="armv5"
|
||||
elif [[ $ARCH =~ "armv6l" ]]; then
|
||||
ARCH="armv6"
|
||||
elif [[ $ARCH =~ "armv7l" ]]; then
|
||||
ARCH="armv7"
|
||||
elif [[ $ARCH =~ "x86_64" ]]; then
|
||||
ARCH="amd64"
|
||||
fi
|
||||
|
||||
CACHE_DIR=/var/lib/clickhouse/.ccci-bin
|
||||
CACHED="${CACHE_DIR}/clickhouse-backup"
|
||||
BIN=/usr/local/bin/clickhouse-backup
|
||||
URL="https://github.com/AlexAkulov/clickhouse-backup/releases/download/v${CLICKHOUSE_BACKUP_VERSION}/clickhouse-backup-linux-${ARCH}.tar.gz"
|
||||
|
||||
install_clickhouse_backup() {
|
||||
mkdir -p "$CACHE_DIR"
|
||||
if [ -x "$CACHED" ]; then
|
||||
cp -f "$CACHED" "$BIN"
|
||||
echo "clickhouse-backup: restored from persistent cache ($CACHED)"
|
||||
return 0
|
||||
fi
|
||||
for attempt in 1 2 3 4 5; do
|
||||
if wget --continue --output-document=/tmp/clickhouse-backup.tar.gz "$URL" \
|
||||
&& tar -xf /tmp/clickhouse-backup.tar.gz --directory=/usr/local/bin --strip-components=3; then
|
||||
cp -f "$BIN" "$CACHED" 2>/dev/null || true
|
||||
echo "clickhouse-backup: downloaded + cached (attempt ${attempt})"
|
||||
return 0
|
||||
fi
|
||||
echo "clickhouse-backup: fetch attempt ${attempt} failed; backing off $((attempt * 10))s" >&2
|
||||
sleep $((attempt * 10))
|
||||
done
|
||||
echo "clickhouse-backup: fetch FAILED after retries — starting clickhouse-server WITHOUT the backup tool (backup/restore unavailable until a later restart fetches it)" >&2
|
||||
return 1
|
||||
}
|
||||
|
||||
# Best-effort: the server MUST start even if the backup-tool fetch fails (it is not a server dependency).
|
||||
install_clickhouse_backup || true
|
||||
|
||||
exec /entrypoint.sh
|
||||
Reference in New Issue
Block a user