Merge pull request 'feat(backup): back up k3s and Gitea to AIStor with alerts and drills' (#6) from donghyeon.kang/w6-host-backups into main
This commit was merged in pull request #6.
This commit is contained in:
@@ -0,0 +1,68 @@
|
||||
#!/usr/bin/env bash
|
||||
# Back up Gitea (repositories, packages, attachments, Actions data, app.ini) to
|
||||
# AIStor (HDD sdb3). Root only. Run by platform-gitea-backup.timer.
|
||||
#
|
||||
# `gitea dump --skip-db` runs inside the live Gitea container and streams a
|
||||
# tar.gz to stdout (logs go to stderr). The database is backed up separately by
|
||||
# CloudNativePG (services/platform-postgres-backup). The dump contains app.ini,
|
||||
# whose secrets are needed to restore, so the archive is sensitive.
|
||||
set -Eeuo pipefail
|
||||
umask 077
|
||||
# shellcheck source=../lib/host-backup.sh
|
||||
source "$(dirname -- "${BASH_SOURCE[0]}")/../lib/host-backup.sh"
|
||||
|
||||
readonly NAME=gitea_backup
|
||||
readonly KCFG=/etc/rancher/k3s/k3s.yaml
|
||||
[[ "$(id -u)" -eq 0 ]] || hb_fail "run as root"
|
||||
hb_load_aistor_env
|
||||
kubectl() { command /usr/local/bin/k3s kubectl --kubeconfig "$KCFG" "$@"; }
|
||||
|
||||
started="$(date +%s)"
|
||||
previous_success="$(awk '/^platform_backup_last_success_timestamp_seconds/ {print $2}' "$TEXTFILE_DIR/$NAME.prom" 2>/dev/null || echo 0)"
|
||||
on_error() {
|
||||
hb_write_metrics "$NAME" <<PROM
|
||||
platform_backup_last_run_success{backup="gitea"} 0
|
||||
platform_backup_last_run_timestamp_seconds{backup="gitea"} $(date +%s)
|
||||
platform_backup_last_success_timestamp_seconds{backup="gitea"} ${previous_success:-0}
|
||||
PROM
|
||||
}
|
||||
trap on_error ERR
|
||||
|
||||
work="$(mktemp -d "$HB_WORK_ROOT/gitea.XXXXXX")"
|
||||
trap 'rm -rf -- "$work"' EXIT
|
||||
ts="$(date -u +%Y%m%dT%H%M%SZ)"
|
||||
archive="gitea-dump-$ts.tar.gz"
|
||||
|
||||
kubectl -n gitea exec deploy/gitea -c gitea -- \
|
||||
gitea dump --skip-db --type tar.gz --file - >"$work/$archive" 2>"$work/dump.log"
|
||||
tar -tzf "$work/$archive" >"$work/list.txt"
|
||||
grep -qx 'app.ini' "$work/list.txt" || hb_fail "the dump has no app.ini"
|
||||
repos="$(grep -c -E '^repos/[^/]+/[^/]+\.git/HEAD$' "$work/list.txt" || true)"
|
||||
(( repos > 0 )) || hb_fail "the dump has no repositories"
|
||||
sha256sum "$work/$archive" | awk '{print $1}' >"$work/$archive.sha256"
|
||||
size="$(stat -c %s "$work/$archive")"
|
||||
# What a restore must match: restore with the same Gitea version (docs/runbooks/gitea-restore.md).
|
||||
{
|
||||
echo "created=$ts"
|
||||
echo "gitea_image=$(kubectl -n gitea get deploy gitea -o jsonpath='{.spec.template.spec.containers[0].image}')"
|
||||
echo "gitea_version=$(kubectl -n gitea exec deploy/gitea -c gitea -- gitea --version 2>/dev/null | awk '{print $3}')"
|
||||
echo "repositories=$repos"
|
||||
} >"$work/$archive.meta"
|
||||
|
||||
hb_mc "$work" cp --quiet "/work/$archive" "/work/$archive.sha256" "/work/$archive.meta" "backup/$AISTOR_BUCKET/gitea/" >/dev/null
|
||||
hb_mc "$work" stat "backup/$AISTOR_BUCKET/gitea/$archive" >/dev/null
|
||||
|
||||
trap - ERR
|
||||
hb_write_metrics "$NAME" <<PROM
|
||||
# HELP platform_backup_last_success_timestamp_seconds Unix time of the last successful backup.
|
||||
# TYPE platform_backup_last_success_timestamp_seconds gauge
|
||||
platform_backup_last_success_timestamp_seconds{backup="gitea"} $(date +%s)
|
||||
platform_backup_last_run_success{backup="gitea"} 1
|
||||
platform_backup_last_run_timestamp_seconds{backup="gitea"} $(date +%s)
|
||||
platform_backup_last_size_bytes{backup="gitea"} $size
|
||||
platform_backup_last_duration_seconds{backup="gitea"} $(( $(date +%s) - started ))
|
||||
# HELP platform_backup_gitea_repositories Repositories in the last successful Gitea dump.
|
||||
# TYPE platform_backup_gitea_repositories gauge
|
||||
platform_backup_gitea_repositories $repos
|
||||
PROM
|
||||
hb_log "gitea backup $archive ($size bytes, $repos repositories) uploaded"
|
||||
@@ -0,0 +1,99 @@
|
||||
#!/usr/bin/env bash
|
||||
# Back up the k3s datastore (sqlite) and the server token to AIStor (HDD sdb3).
|
||||
# Root only. Run by platform-k3s-datastore-backup.timer (infrastructure/host/backup).
|
||||
#
|
||||
# k3s docs (datastore/backup-restore, SQLite): copy server/db and server/token;
|
||||
# the token is required to read the datastore back. `sqlite3 .backup` takes a
|
||||
# consistent copy of the live database.
|
||||
#
|
||||
# Off-host copy (prepared, off by default): set in /etc/platform-backup/aistor.env
|
||||
# OFFHOST_GPG_RECIPIENT_FILE=/etc/platform-backup/offhost-recipient.asc
|
||||
# OFFHOST_RCLONE_TARGET=<rclone remote:path>
|
||||
# The archive is then encrypted to that public key and copied with rclone.
|
||||
set -Eeuo pipefail
|
||||
umask 077
|
||||
# shellcheck source=../lib/host-backup.sh
|
||||
source "$(dirname -- "${BASH_SOURCE[0]}")/../lib/host-backup.sh"
|
||||
|
||||
readonly SERVER=/var/lib/rancher/k3s/server
|
||||
readonly NAME=k3s_datastore_backup
|
||||
[[ "$(id -u)" -eq 0 ]] || hb_fail "run as root"
|
||||
command -v sqlite3 >/dev/null || hb_fail "sqlite3 is required"
|
||||
hb_load_aistor_env
|
||||
|
||||
started="$(date +%s)"
|
||||
on_error() {
|
||||
hb_write_metrics "$NAME" <<PROM
|
||||
# HELP platform_backup_last_run_success 1 when the last run of this backup succeeded.
|
||||
# TYPE platform_backup_last_run_success gauge
|
||||
platform_backup_last_run_success{backup="k3s-datastore"} 0
|
||||
platform_backup_last_run_timestamp_seconds{backup="k3s-datastore"} $(date +%s)
|
||||
platform_backup_last_success_timestamp_seconds{backup="k3s-datastore"} ${previous_success:-0}
|
||||
PROM
|
||||
}
|
||||
previous_success="$(awk '/^platform_backup_last_success_timestamp_seconds/ {print $2}' "$TEXTFILE_DIR/$NAME.prom" 2>/dev/null || echo 0)"
|
||||
trap on_error ERR
|
||||
|
||||
work="$(mktemp -d "$HB_WORK_ROOT/k3s.XXXXXX")"
|
||||
trap 'rm -rf -- "$work"' EXIT
|
||||
ts="$(date -u +%Y%m%dT%H%M%SZ)"
|
||||
stage="$work/k3s-datastore-$ts"
|
||||
mkdir -m 0700 "$stage"
|
||||
|
||||
sqlite3 "$SERVER/db/state.db" ".backup '$stage/state.db'"
|
||||
check="$(sqlite3 "$stage/state.db" 'PRAGMA integrity_check;')"
|
||||
[[ "$check" == "ok" ]] || hb_fail "integrity_check on the copy returned: $check"
|
||||
install -m 0600 "$SERVER/token" "$stage/token"
|
||||
{
|
||||
echo "created=$ts"
|
||||
echo "k3s_version=$(/usr/local/bin/k3s --version | head -1)"
|
||||
echo "host=$(hostname)"
|
||||
echo "kine_rows=$(sqlite3 "$stage/state.db" 'SELECT COUNT(*) FROM kine;')"
|
||||
} >"$stage/META"
|
||||
tar -C "$work" -czf "$work/k3s-datastore-$ts.tar.gz" "k3s-datastore-$ts"
|
||||
sha256sum "$work/k3s-datastore-$ts.tar.gz" | awk '{print $1}' >"$work/k3s-datastore-$ts.tar.gz.sha256"
|
||||
size="$(stat -c %s "$work/k3s-datastore-$ts.tar.gz")"
|
||||
|
||||
hb_mc "$work" cp --quiet "/work/k3s-datastore-$ts.tar.gz" "/work/k3s-datastore-$ts.tar.gz.sha256" "backup/$AISTOR_BUCKET/k3s-datastore/" >/dev/null
|
||||
hb_mc "$work" stat "backup/$AISTOR_BUCKET/k3s-datastore/k3s-datastore-$ts.tar.gz" >/dev/null
|
||||
|
||||
# Local copy outside AIStor on the same HDD (sdb3). AIStor runs inside the
|
||||
# cluster this archive restores, so after losing the cluster the AIStor copy
|
||||
# cannot be read until k3s is back; this copy can. The directory sits next to
|
||||
# AIStor's drive directory (data/), so AIStor does not see it as a bucket.
|
||||
readonly LOCAL_DIR=/srv/k3s/aistor/host-backups/k3s-datastore
|
||||
install -d -m 0700 -o root -g root "$(dirname "$LOCAL_DIR")" "$LOCAL_DIR"
|
||||
install -m 0600 "$work/k3s-datastore-$ts.tar.gz" "$work/k3s-datastore-$ts.tar.gz.sha256" "$LOCAL_DIR/"
|
||||
ls -1t "$LOCAL_DIR"/k3s-datastore-*.tar.gz | tail -n +8 | while read -r old; do rm -f -- "$old" "$old.sha256"; done
|
||||
local_copies="$(ls -1 "$LOCAL_DIR"/k3s-datastore-*.tar.gz | wc -l)"
|
||||
|
||||
offhost=0
|
||||
if [[ -n "${OFFHOST_GPG_RECIPIENT_FILE:-}" && -n "${OFFHOST_RCLONE_TARGET:-}" ]]; then
|
||||
command -v rclone >/dev/null || hb_fail "OFFHOST_RCLONE_TARGET is set but rclone is not installed"
|
||||
gpg --batch --yes --trust-model always --recipient-file "$OFFHOST_GPG_RECIPIENT_FILE" \
|
||||
--output "$work/k3s-datastore-$ts.tar.gz.gpg" --encrypt "$work/k3s-datastore-$ts.tar.gz"
|
||||
rclone copyto "$work/k3s-datastore-$ts.tar.gz.gpg" "$OFFHOST_RCLONE_TARGET/k3s-datastore-$ts.tar.gz.gpg"
|
||||
offhost=1
|
||||
fi
|
||||
|
||||
trap - ERR
|
||||
hb_write_metrics "$NAME" <<PROM
|
||||
# HELP platform_backup_last_success_timestamp_seconds Unix time of the last successful backup.
|
||||
# TYPE platform_backup_last_success_timestamp_seconds gauge
|
||||
platform_backup_last_success_timestamp_seconds{backup="k3s-datastore"} $(date +%s)
|
||||
# HELP platform_backup_last_run_success 1 when the last run of this backup succeeded.
|
||||
# TYPE platform_backup_last_run_success gauge
|
||||
platform_backup_last_run_success{backup="k3s-datastore"} 1
|
||||
platform_backup_last_run_timestamp_seconds{backup="k3s-datastore"} $(date +%s)
|
||||
# HELP platform_backup_last_size_bytes Size of the last successful backup archive.
|
||||
# TYPE platform_backup_last_size_bytes gauge
|
||||
platform_backup_last_size_bytes{backup="k3s-datastore"} $size
|
||||
platform_backup_last_duration_seconds{backup="k3s-datastore"} $(( $(date +%s) - started ))
|
||||
# HELP platform_backup_local_copies Archives kept outside AIStor on the HDD.
|
||||
# TYPE platform_backup_local_copies gauge
|
||||
platform_backup_local_copies{backup="k3s-datastore"} $local_copies
|
||||
# HELP platform_backup_offhost_copy 1 when the last run also wrote the encrypted off-host copy.
|
||||
# TYPE platform_backup_offhost_copy gauge
|
||||
platform_backup_offhost_copy{backup="k3s-datastore"} $offhost
|
||||
PROM
|
||||
hb_log "k3s datastore backup k3s-datastore-$ts.tar.gz ($size bytes) uploaded; off-host=$offhost"
|
||||
@@ -0,0 +1,81 @@
|
||||
#!/usr/bin/env bash
|
||||
# Create the AIStor bucket, lifecycle rules, policy and user that the host backup
|
||||
# timers use, and the root-only /etc/platform-backup/aistor.env.
|
||||
#
|
||||
# sudo bash scripts/bootstrap/create-host-backup-credentials.sh
|
||||
#
|
||||
# Run once, by the owner, on the desktop. Refuses to run when the env file exists;
|
||||
# never rotates or deletes a bucket, policy, user or object. No key is printed.
|
||||
set -Eeuo pipefail
|
||||
set +x
|
||||
umask 077
|
||||
|
||||
readonly ROOT="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")/../.." && pwd -P)"
|
||||
# shellcheck source=../lib/host-backup.sh
|
||||
source "$ROOT/scripts/lib/host-backup.sh"
|
||||
readonly BUCKET=platform-host-backups
|
||||
readonly POLICY=platform-host-backups
|
||||
readonly QUOTA=50GiB
|
||||
readonly POLICY_FILE="$ROOT/services/platform-host-checks/bucket-policy.json"
|
||||
readonly PASS_LINE=PLATFORM_HOST_BACKUP_BOOTSTRAP_PASS
|
||||
kubectl() { command /usr/local/bin/k3s kubectl --kubeconfig /etc/rancher/k3s/k3s.yaml "$@"; }
|
||||
|
||||
[[ "$(id -u)" -eq 0 ]] || hb_fail "run with sudo"
|
||||
for c in docker jq openssl; do command -v "$c" >/dev/null || hb_fail "missing command: $c"; done
|
||||
jq -e . "$POLICY_FILE" >/dev/null || hb_fail "bucket policy is not valid JSON"
|
||||
[[ ! -e "$HOST_BACKUP_ENV" ]] || hb_fail "$HOST_BACKUP_ENV already exists; this script does not rotate it"
|
||||
|
||||
ip="$(kubectl -n object-storage get service minio -o jsonpath='{.spec.clusterIP}')"
|
||||
[[ -n "$ip" ]] || hb_fail "object-storage/minio Service not found"
|
||||
endpoint="http://${ip}:80"
|
||||
|
||||
work="$(mktemp -d)"
|
||||
trap 'rm -rf -- "$work"' EXIT
|
||||
kubectl -n object-storage get secret aistor-root-configuration -o jsonpath='{.data.config\.env}' | base64 -d >"$work/root.env"
|
||||
grep -q '^export MINIO_ROOT_USER=' "$work/root.env" || hb_fail "aistor-root-configuration has an unexpected format"
|
||||
printf 'pcbackup%s' "$(openssl rand -hex 8)" >"$work/ACCESS_KEY"
|
||||
openssl rand -hex 32 | tr -d '\n' >"$work/SECRET_KEY"
|
||||
cp "$POLICY_FILE" "$work/policy.json"
|
||||
|
||||
printf '%s\n' \
|
||||
"Bucket: $BUCKET (quota $QUOTA; expire gitea/ after 56 days, k3s-datastore/ after 30 days) on $endpoint" \
|
||||
"Policy: $POLICY (${POLICY_FILE#"$ROOT/"})" \
|
||||
"User: a new generated access key attached to $POLICY" \
|
||||
"File: $HOST_BACKUP_ENV (root, 0600)" \
|
||||
'No key value will be printed.'
|
||||
printf 'Type APPLY to create them: '
|
||||
IFS= read -r confirmation
|
||||
[[ "$confirmation" == "APPLY" ]] || hb_fail "confirmation did not match APPLY"
|
||||
|
||||
# Every mc call is silenced so no key reaches the terminal.
|
||||
docker run --rm --network host -v "$work:/run/b:ro" --tmpfs /tmp -e MC_CONFIG_DIR=/tmp/mc \
|
||||
--entrypoint /bin/sh "$MC_IMAGE" -ec '
|
||||
. /run/b/root.env
|
||||
ak="$(cat /run/b/ACCESS_KEY)"; sk="$(cat /run/b/SECRET_KEY)"
|
||||
mc alias set root "'"$endpoint"'" "$MINIO_ROOT_USER" "$MINIO_ROOT_PASSWORD" --api S3v4 >/dev/null
|
||||
mc mb --ignore-existing "root/'"$BUCKET"'" >/dev/null
|
||||
mc quota set "root/'"$BUCKET"'" --size "'"$QUOTA"'" >/dev/null
|
||||
mc ilm rule add --prefix gitea/ --expire-days 56 "root/'"$BUCKET"'" >/dev/null
|
||||
mc ilm rule add --prefix k3s-datastore/ --expire-days 30 "root/'"$BUCKET"'" >/dev/null
|
||||
mc admin policy create root "'"$POLICY"'" /run/b/policy.json >/dev/null
|
||||
mc admin user add root "$ak" "$sk" >/dev/null
|
||||
mc admin policy attach root "'"$POLICY"'" --user "$ak" >/dev/null
|
||||
mc alias set backup "'"$endpoint"'" "$ak" "$sk" --api S3v4 >/dev/null
|
||||
probe=".bootstrap-probe-$(date +%s)"
|
||||
printf probe | mc pipe "backup/'"$BUCKET"'/$probe" >/dev/null
|
||||
[ "$(mc cat "backup/'"$BUCKET"'/$probe")" = probe ]
|
||||
mc rm "backup/'"$BUCKET"'/$probe" >/dev/null
|
||||
if mc ls backup/loki >/dev/null 2>&1; then echo "the backup user can list another bucket" >&2; exit 1; fi
|
||||
echo "'"$PASS_LINE"'"' | grep -qx "$PASS_LINE" || hb_fail "bootstrap did not finish; $HOST_BACKUP_ENV was not written"
|
||||
|
||||
install -d -m 0700 -o root -g root "$(dirname "$HOST_BACKUP_ENV")"
|
||||
{
|
||||
echo "AISTOR_BUCKET=$BUCKET"
|
||||
echo "AISTOR_ACCESS_KEY=$(cat "$work/ACCESS_KEY")"
|
||||
echo "AISTOR_SECRET_KEY=$(cat "$work/SECRET_KEY")"
|
||||
echo "# Off-host encrypted copy of the k3s datastore archive (off until both are set):"
|
||||
echo "# OFFHOST_GPG_RECIPIENT_FILE=/etc/platform-backup/offhost-recipient.asc"
|
||||
echo "# OFFHOST_RCLONE_TARGET=remote:path"
|
||||
} >"$HOST_BACKUP_ENV"
|
||||
chmod 0600 "$HOST_BACKUP_ENV"
|
||||
printf '%s\n' "$PASS_LINE" "Created bucket $BUCKET, policy $POLICY, one user and $HOST_BACKUP_ENV."
|
||||
@@ -0,0 +1,78 @@
|
||||
#!/usr/bin/env bash
|
||||
# Install the host backup and check timers (infrastructure/host/backup).
|
||||
#
|
||||
# bash scripts/bootstrap/install-host-checks.sh --check # no root, changes nothing
|
||||
# sudo bash scripts/bootstrap/install-host-checks.sh --execute # install, enable, first runs
|
||||
#
|
||||
# Scripts are copied to /usr/local/lib/platform-backup (root-owned) so the root
|
||||
# timers never execute files the desktop user can edit.
|
||||
set -Eeuo pipefail
|
||||
umask 022
|
||||
|
||||
readonly ROOT="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")/../.." && pwd -P)"
|
||||
readonly LIB=/usr/local/lib/platform-backup
|
||||
readonly UNIT_DIR=/etc/systemd/system
|
||||
readonly TEXTFILE_DIR=/var/lib/node_exporter/textfile_collector
|
||||
readonly WORK_ROOT=/var/lib/platform-backup/work
|
||||
readonly USER_NAME=donghyeon
|
||||
readonly -a SCRIPTS=(
|
||||
scripts/lib/host-backup.sh:lib/host-backup.sh
|
||||
scripts/backup/k3s-datastore-backup.sh:backup/k3s-datastore-backup.sh
|
||||
scripts/backup/gitea-backup.sh:backup/gitea-backup.sh
|
||||
scripts/validate/live-drift-check-main.sh:validate/live-drift-check-main.sh
|
||||
scripts/validate/k3s-cert-expiry.sh:validate/k3s-cert-expiry.sh
|
||||
services/platform-host-checks/README.md:README.md
|
||||
)
|
||||
readonly -a TIMERS=(platform-k3s-datastore-backup platform-gitea-backup platform-live-drift-check platform-k3s-cert-expiry)
|
||||
|
||||
fail() { printf 'ERROR: %s\n' "$*" >&2; exit 1; }
|
||||
mode="${1:-}"
|
||||
[[ "$#" -eq 1 && ( "$mode" == "--check" || "$mode" == "--execute" ) ]] || { sed -n '2,8p' "$0" >&2; exit 2; }
|
||||
|
||||
echo "== check"
|
||||
for pair in "${SCRIPTS[@]}"; do
|
||||
src="${pair%%:*}"
|
||||
[[ -f "$ROOT/$src" ]] || fail "missing $src"
|
||||
[[ "$src" != *.sh ]] || bash -n "$ROOT/$src" || fail "syntax error in $src"
|
||||
done
|
||||
for t in "${TIMERS[@]}"; do
|
||||
for u in service timer; do [[ -f "$ROOT/infrastructure/host/backup/$t.$u" ]] || fail "missing $t.$u"; done
|
||||
done
|
||||
if command -v systemd-analyze >/dev/null; then
|
||||
verify_dir="$(mktemp -d)"
|
||||
trap 'rm -rf -- "$verify_dir"' EXIT
|
||||
cp "$ROOT"/infrastructure/host/backup/*.service "$ROOT"/infrastructure/host/backup/*.timer "$verify_dir/"
|
||||
# ExecStart paths do not exist before installation; only syntax and keys are checked.
|
||||
out="$(cd "$verify_dir" && systemd-analyze verify ./*.timer ./*.service 2>&1 | grep -v -E 'is not executable|No such file|Command .* is not executable' || true)"
|
||||
[[ -z "$out" ]] || { printf '%s\n' "$out" >&2; fail "systemd-analyze verify reported problems"; }
|
||||
echo " units: systemd-analyze verify clean"
|
||||
fi
|
||||
echo "== plan"
|
||||
for pair in "${SCRIPTS[@]}"; do echo " install ${pair%%:*} -> $LIB/${pair##*:}"; done
|
||||
for t in "${TIMERS[@]}"; do echo " install $UNIT_DIR/$t.service, $UNIT_DIR/$t.timer; enable --now $t.timer"; done
|
||||
echo " mkdir $TEXTFILE_DIR (root:$USER_NAME 0775), $WORK_ROOT (root 0700)"
|
||||
echo " first runs: k3s-cert-expiry, k3s-datastore-backup, gitea-backup, live-drift-check"
|
||||
[[ "$mode" == "--execute" ]] || { echo "CHECK ONLY: nothing changed"; exit 0; }
|
||||
|
||||
[[ "$(id -u)" -eq 0 ]] || fail "--execute needs root (sudo)"
|
||||
[[ -f /etc/platform-backup/aistor.env ]] || fail "run scripts/bootstrap/create-host-backup-credentials.sh first"
|
||||
echo "== install"
|
||||
for pair in "${SCRIPTS[@]}"; do
|
||||
install -D -o root -g root -m 0755 "$ROOT/${pair%%:*}" "$LIB/${pair##*:}"
|
||||
done
|
||||
install -d -o root -g "$USER_NAME" -m 0775 "$TEXTFILE_DIR"
|
||||
install -d -o root -g root -m 0700 "$WORK_ROOT"
|
||||
for t in "${TIMERS[@]}"; do
|
||||
install -o root -g root -m 0644 "$ROOT/infrastructure/host/backup/$t.service" "$ROOT/infrastructure/host/backup/$t.timer" "$UNIT_DIR/"
|
||||
done
|
||||
systemctl daemon-reload
|
||||
for t in "${TIMERS[@]}"; do systemctl enable --now "$t.timer"; done
|
||||
|
||||
echo "== first runs"
|
||||
for t in platform-k3s-cert-expiry platform-k3s-datastore-backup platform-gitea-backup platform-live-drift-check; do
|
||||
if systemctl start "$t.service"; then echo " $t: ok"; else echo " $t: FAILED (journalctl -u $t)"; fi
|
||||
done
|
||||
echo "== metrics"
|
||||
grep -h -E '^platform_' "$TEXTFILE_DIR"/*.prom || echo " no metrics yet"
|
||||
systemctl list-timers 'platform-*' --no-pager
|
||||
echo "HOST CHECKS INSTALLED"
|
||||
@@ -0,0 +1,55 @@
|
||||
#!/usr/bin/env bash
|
||||
# Shared helpers for the host backup and host check scripts. Source only.
|
||||
# shellcheck shell=bash
|
||||
|
||||
readonly HOST_BACKUP_ENV=/etc/platform-backup/aistor.env
|
||||
readonly TEXTFILE_DIR=/var/lib/node_exporter/textfile_collector
|
||||
# Backup staging (root 0700, same SSD). Not /var/tmp: dockerd must see the path.
|
||||
readonly HB_WORK_ROOT=/var/lib/platform-backup/work
|
||||
# Same pinned AIStor client as scripts/validate/aistor-s3-smoke.sh.
|
||||
readonly MC_IMAGE="quay.io/minio/aistor/mc@sha256:c5ec777c080fd6292b7529309a0f311c58c3a92e268c9c57c0901da86881949b"
|
||||
|
||||
hb_log() { printf '%s %s\n' "$(date -u +%FT%TZ)" "$*"; }
|
||||
hb_fail() { hb_log "FAIL: $*" >&2; exit 1; }
|
||||
|
||||
# Write Prometheus textfile metrics atomically: hb_write_metrics NAME <<'PROM' ... PROM
|
||||
hb_write_metrics() {
|
||||
local name="$1" tmp
|
||||
[[ -d "$TEXTFILE_DIR" ]] || { hb_log "textfile dir $TEXTFILE_DIR missing; metrics not written"; cat >/dev/null; return 0; }
|
||||
tmp="$(mktemp "$TEXTFILE_DIR/.${name}.XXXXXX")"
|
||||
cat >"$tmp"
|
||||
chmod 0644 "$tmp"
|
||||
mv -f -- "$tmp" "$TEXTFILE_DIR/${name}.prom"
|
||||
}
|
||||
|
||||
# Load the AIStor endpoint and the backup user's keys (root-only file).
|
||||
hb_load_aistor_env() {
|
||||
[[ -f "$HOST_BACKUP_ENV" ]] || hb_fail "$HOST_BACKUP_ENV is missing; run scripts/bootstrap/create-host-backup-credentials.sh"
|
||||
[[ "$(stat -c '%u %a' "$HOST_BACKUP_ENV")" == "0 600" ]] || hb_fail "$HOST_BACKUP_ENV must be owned by root with mode 0600"
|
||||
# shellcheck disable=SC1090
|
||||
. "$HOST_BACKUP_ENV"
|
||||
: "${AISTOR_BUCKET:?}" "${AISTOR_ACCESS_KEY:?}" "${AISTOR_SECRET_KEY:?}"
|
||||
# The host cannot resolve cluster DNS, so use the Service ClusterIP (port 80 -> 9000).
|
||||
if [[ -z "${AISTOR_ENDPOINT:-}" ]]; then
|
||||
local ip
|
||||
ip="$(/usr/local/bin/k3s kubectl --kubeconfig /etc/rancher/k3s/k3s.yaml -n object-storage \
|
||||
get service minio -o jsonpath='{.spec.clusterIP}')"
|
||||
[[ -n "$ip" ]] || hb_fail "cannot find the object-storage/minio Service"
|
||||
AISTOR_ENDPOINT="http://${ip}:80"
|
||||
fi
|
||||
}
|
||||
|
||||
# Run the pinned mc client on the host network with the backup user's keys.
|
||||
# The keys go through a 0600 env file, never the command line (ps would show it).
|
||||
# Usage: hb_mc <dir mounted at /work> <mc args...>
|
||||
hb_mc() {
|
||||
local work="$1"; shift
|
||||
local envfile="$work/.mc.env"
|
||||
if [[ ! -f "$envfile" ]]; then
|
||||
( umask 077; printf 'MC_HOST_backup=%s\nMC_CONFIG_DIR=/tmp/mc\n' \
|
||||
"${AISTOR_ENDPOINT/:\/\//://${AISTOR_ACCESS_KEY}:${AISTOR_SECRET_KEY}@}" >"$envfile" )
|
||||
fi
|
||||
docker run --rm --network host --user "$(id -u):$(id -g)" \
|
||||
--env-file "$envfile" -v "$work:/work" --tmpfs /tmp \
|
||||
"$MC_IMAGE" "$@"
|
||||
}
|
||||
@@ -596,3 +596,13 @@ PLATFORM_HELM_BIN=/home/donghyeon/.local/bin/helm \
|
||||
- `--textfile FILE`: `platform_live_drift_objects`, `platform_live_drift_check_success`,
|
||||
`platform_live_drift_last_run_timestamp_seconds`를 Prometheus textfile 형식으로 쓴다.
|
||||
- Secret 값의 차이는 보지 않는다.
|
||||
|
||||
## 호스트 백업·점검 시험
|
||||
|
||||
- `test-platform-host-checks-alerts.sh`: `services/platform-host-checks/prometheus-rules.yaml`의 promtool
|
||||
단위 시험(백업 신선도, 실패, 지표 없음, drift, k3s 인증서). docker 필요, 클러스터 접근 없음.
|
||||
- `k3s-cert-expiry.sh`: 6443·10250 serving 인증서 만료를 textfile 지표로 쓴다(타이머가 매일 돌림).
|
||||
- `live-drift-check-main.sh`: checkout의 작업 트리가 아니라 `origin/main`으로 `live-drift-check.sh`를 돌린다.
|
||||
- `k3s-datastore-restore-drill.sh`, `gitea-backup-restore-drill.sh`: 복원 리허설. 인자 없이 root로 돌리면 AIStor의
|
||||
최신 백업을 쓰고, `--from-dir`·`--from-file`로 로컬 사본을 줄 수 있다.
|
||||
- `test-k3s-datastore-restore-drill.sh`: 운영 데이터 없이 k3s 복원 리허설 경로를 시험한다(일회용 k3s, 시험 Secret 셋).
|
||||
|
||||
@@ -0,0 +1,75 @@
|
||||
#!/usr/bin/env bash
|
||||
# Restore drill for the Gitea backup (file level).
|
||||
#
|
||||
# sudo bash scripts/validate/gitea-backup-restore-drill.sh # latest dump in AIStor
|
||||
# bash scripts/validate/gitea-backup-restore-drill.sh --from-file DUMP.tar.gz
|
||||
#
|
||||
# Extracts the dump into a throwaway directory and checks what a restore needs:
|
||||
# app.ini is present, every repository passes `git fsck`, and the repository
|
||||
# count matches the live Gitea. The database is restored from the CloudNativePG
|
||||
# backup instead (services/platform-postgres-backup); the full restore order is
|
||||
# in docs/runbooks/gitea-restore.md. Nothing is written to the cluster.
|
||||
set -Eeuo pipefail
|
||||
umask 077
|
||||
|
||||
readonly ROOT="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")/../.." && pwd -P)"
|
||||
# shellcheck source=../lib/host-backup.sh
|
||||
source "$ROOT/scripts/lib/host-backup.sh"
|
||||
readonly NAME=gitea_restore_drill
|
||||
|
||||
from_file=""
|
||||
case "${1:-}" in
|
||||
--from-file) from_file="${2:?--from-file needs a path}" ;;
|
||||
"") ;;
|
||||
*) sed -n '2,11p' "$0" >&2; exit 2 ;;
|
||||
esac
|
||||
if [[ "$(id -u)" -eq 0 ]]; then
|
||||
kubectl() { command /usr/local/bin/k3s kubectl --kubeconfig /etc/rancher/k3s/k3s.yaml "$@"; }
|
||||
fi
|
||||
|
||||
base="$HB_WORK_ROOT"; [[ -w "$base" ]] || base="$(mktemp -d)"
|
||||
work="$(mktemp -d "$base/gitea-drill.XXXXXX")"
|
||||
trap 'rm -rf -- "$work"' EXIT
|
||||
|
||||
if [[ -z "$from_file" ]]; then
|
||||
[[ "$(id -u)" -eq 0 ]] || hb_fail "run as root to read the backup credentials"
|
||||
hb_load_aistor_env
|
||||
latest="$(hb_mc "$work" ls "backup/$AISTOR_BUCKET/gitea/" | awk '{print $NF}' | grep -E '^gitea-dump-.*\.tar\.gz$' | sort | tail -1)"
|
||||
[[ -n "$latest" ]] || hb_fail "no Gitea dump found"
|
||||
hb_mc "$work" cp --quiet "backup/$AISTOR_BUCKET/gitea/$latest" "backup/$AISTOR_BUCKET/gitea/$latest.sha256" /work/ >/dev/null
|
||||
[[ "$(sha256sum "$work/$latest" | awk '{print $1}')" == "$(cat "$work/$latest.sha256")" ]] || hb_fail "checksum mismatch for $latest"
|
||||
from_file="$work/$latest"
|
||||
hb_log "drill on $latest"
|
||||
fi
|
||||
|
||||
mkdir "$work/restore"
|
||||
tar -C "$work/restore" -xzf "$from_file"
|
||||
[[ -s "$work/restore/app.ini" ]] || hb_fail "app.ini is missing from the dump"
|
||||
for key in INTERNAL_TOKEN SECRET_KEY; do
|
||||
grep -q "^${key}[[:space:]]*=" "$work/restore/app.ini" || hb_fail "app.ini has no ${key} (needed to restore)"
|
||||
done
|
||||
|
||||
total=0 broken=0
|
||||
while IFS= read -r -d '' repo; do
|
||||
total=$((total + 1))
|
||||
if ! git -c safe.directory='*' --git-dir="$repo" fsck --no-dangling --no-progress >/dev/null 2>"$work/fsck.err"; then
|
||||
broken=$((broken + 1))
|
||||
hb_log "fsck failed: ${repo#"$work/restore/"}: $(head -1 "$work/fsck.err")"
|
||||
fi
|
||||
done < <(find "$work/restore/repos" -mindepth 2 -maxdepth 2 -type d -name '*.git' -print0)
|
||||
hb_log "repositories in dump: $total, fsck failures: $broken"
|
||||
(( total > 0 )) || hb_fail "the dump has no repositories"
|
||||
(( broken == 0 )) || hb_fail "$broken repositories failed git fsck"
|
||||
|
||||
live="$(kubectl -n gitea exec deploy/gitea -c gitea -- sh -c 'find /data/git/gitea-repositories -mindepth 2 -maxdepth 2 -name "*.git" -type d | wc -l' 2>/dev/null || echo "")"
|
||||
if [[ -n "$live" ]]; then
|
||||
hb_log "live Gitea repositories: $live"
|
||||
(( total >= live - 2 )) || hb_fail "the dump has $total repositories, live Gitea has $live"
|
||||
fi
|
||||
|
||||
hb_write_metrics "$NAME" <<PROM
|
||||
# HELP platform_backup_restore_drill_last_success_timestamp_seconds Unix time of the last successful restore drill.
|
||||
# TYPE platform_backup_restore_drill_last_success_timestamp_seconds gauge
|
||||
platform_backup_restore_drill_last_success_timestamp_seconds{backup="gitea"} $(date +%s)
|
||||
PROM
|
||||
echo "GITEA RESTORE DRILL PASS"
|
||||
@@ -0,0 +1,25 @@
|
||||
#!/usr/bin/env bash
|
||||
# Write the notAfter time of the k3s API server (6443) and kubelet (10250)
|
||||
# serving certificates as Prometheus textfile metrics. No root needed.
|
||||
# k3s renews these only when it starts and they are within 120 days of expiry
|
||||
# (docs.k3s.io cli/certificate), and the kubelet exposes no certificate metric,
|
||||
# so nothing else in the cluster watches them.
|
||||
set -Eeuo pipefail
|
||||
# shellcheck source=../lib/host-backup.sh
|
||||
source "$(dirname -- "${BASH_SOURCE[0]}")/../lib/host-backup.sh"
|
||||
|
||||
lines=""
|
||||
for target in apiserver:6443 kubelet:10250; do
|
||||
name="${target%%:*}" port="${target##*:}"
|
||||
end="$(echo | timeout 10 openssl s_client -connect "127.0.0.1:$port" 2>/dev/null | openssl x509 -noout -enddate 2>/dev/null | sed 's/^notAfter=//')" || true
|
||||
[[ -n "$end" ]] || hb_fail "could not read the $name certificate on 127.0.0.1:$port"
|
||||
lines+="platform_k3s_certificate_not_after_seconds{certificate=\"$name\"} $(date -d "$end" +%s)"$'\n'
|
||||
hb_log "$name certificate notAfter $end"
|
||||
done
|
||||
hb_write_metrics platform_k3s_certificates <<PROM
|
||||
# HELP platform_k3s_certificate_not_after_seconds notAfter of a k3s serving certificate (Unix time).
|
||||
# TYPE platform_k3s_certificate_not_after_seconds gauge
|
||||
${lines}# HELP platform_k3s_certificate_check_timestamp_seconds Unix time of the last certificate check.
|
||||
# TYPE platform_k3s_certificate_check_timestamp_seconds gauge
|
||||
platform_k3s_certificate_check_timestamp_seconds $(date +%s)
|
||||
PROM
|
||||
@@ -0,0 +1,99 @@
|
||||
#!/usr/bin/env bash
|
||||
# Restore drill for the k3s datastore backup.
|
||||
#
|
||||
# sudo bash scripts/validate/k3s-datastore-restore-drill.sh # latest backup in AIStor
|
||||
# bash scripts/validate/k3s-datastore-restore-drill.sh --from-dir DIR [--expect-secrets N]
|
||||
# DIR holds state.db and token (an extracted archive, or a test datastore)
|
||||
#
|
||||
# Starts a throwaway k3s server (same version as production, --network none,
|
||||
# no agent) on a copy of the backup, and checks that the API answers, that the
|
||||
# Secret count matches and that every Secret decrypts (the token unlocks the
|
||||
# encryption config stored in the datastore). Prints no Secret value. The
|
||||
# container and the copy are removed at the end.
|
||||
set -Eeuo pipefail
|
||||
umask 077
|
||||
|
||||
readonly ROOT="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")/../.." && pwd -P)"
|
||||
# shellcheck source=../lib/host-backup.sh
|
||||
source "$ROOT/scripts/lib/host-backup.sh"
|
||||
# Same version as the desktop server (k3s --version: v1.36.2+k3s1).
|
||||
readonly K3S_IMAGE="docker.io/rancher/k3s:v1.36.2-k3s1@sha256:6a47cea22c4b834d4ba72c89d291696b79ebe406251f90b446e4dff03513dd87"
|
||||
readonly NAME=k3s_datastore_restore_drill
|
||||
|
||||
from_dir="" expect_secrets=""
|
||||
while (( $# > 0 )); do
|
||||
case "$1" in
|
||||
--from-dir) from_dir="${2:?}"; shift 2 ;;
|
||||
--expect-secrets) expect_secrets="${2:?}"; shift 2 ;;
|
||||
*) sed -n '2,13p' "$0" >&2; exit 2 ;;
|
||||
esac
|
||||
done
|
||||
|
||||
base="${HB_WORK_ROOT}"
|
||||
[[ -w "$base" ]] || base="$(mktemp -d)"
|
||||
work="$(mktemp -d "$base/k3s-drill.XXXXXX")"
|
||||
container="k3s-restore-drill-$$"
|
||||
cleanup() {
|
||||
docker rm -f "$container" >/dev/null 2>&1 || true
|
||||
# The drill container writes as root; remove its files with the same image.
|
||||
docker run --rm -v "$work:/w" --entrypoint /bin/sh "$K3S_IMAGE" -c 'rm -rf /w/*' >/dev/null 2>&1 || true
|
||||
rm -rf -- "$work"
|
||||
}
|
||||
trap cleanup EXIT
|
||||
|
||||
if [[ -z "$from_dir" ]]; then
|
||||
[[ "$(id -u)" -eq 0 ]] || hb_fail "run as root to read the backup credentials"
|
||||
hb_load_aistor_env
|
||||
latest="$(hb_mc "$work" ls "backup/$AISTOR_BUCKET/k3s-datastore/" | awk '{print $NF}' | grep -E '^k3s-datastore-.*\.tar\.gz$' | sort | tail -1)"
|
||||
[[ -n "$latest" ]] || hb_fail "no k3s datastore backup found"
|
||||
hb_mc "$work" cp --quiet "backup/$AISTOR_BUCKET/k3s-datastore/$latest" "backup/$AISTOR_BUCKET/k3s-datastore/$latest.sha256" /work/ >/dev/null
|
||||
[[ "$(sha256sum "$work/$latest" | awk '{print $1}')" == "$(cat "$work/$latest.sha256")" ]] || hb_fail "checksum mismatch for $latest"
|
||||
tar -C "$work" -xzf "$work/$latest"
|
||||
from_dir="$(find "$work" -mindepth 1 -maxdepth 1 -type d -name 'k3s-datastore-*' | head -1)"
|
||||
hb_log "drill on $latest"
|
||||
if [[ -z "$expect_secrets" ]]; then
|
||||
expect_secrets="$(/usr/local/bin/k3s kubectl --kubeconfig /etc/rancher/k3s/k3s.yaml get secrets -A --no-headers | wc -l)"
|
||||
hb_log "live cluster has $expect_secrets Secrets (counts may differ by objects created since the backup)"
|
||||
fi
|
||||
fi
|
||||
[[ -f "$from_dir/state.db" && -f "$from_dir/token" ]] || hb_fail "$from_dir must contain state.db and token"
|
||||
|
||||
install -d -m 0700 "$work/server/db"
|
||||
cp "$from_dir/state.db" "$work/server/db/state.db"
|
||||
cp "$from_dir/token" "$work/server/token"
|
||||
[[ "$(sqlite3 "$work/server/db/state.db" 'PRAGMA integrity_check;')" == "ok" ]] || hb_fail "integrity_check failed"
|
||||
|
||||
started="$(date +%s)"
|
||||
docker run -d --name "$container" --network none --tmpfs /run --tmpfs /var/run \
|
||||
-v "$work/server:/var/lib/rancher/k3s/server" \
|
||||
"$K3S_IMAGE" server --disable-agent --secrets-encryption \
|
||||
--token-file /var/lib/rancher/k3s/server/token \
|
||||
--bind-address 127.0.0.1 --advertise-address 127.0.0.1 --node-ip 127.0.0.1 \
|
||||
--disable traefik,servicelb,metrics-server,local-storage,coredns >/dev/null
|
||||
|
||||
ready=0
|
||||
for _ in $(seq 1 60); do
|
||||
if docker exec "$container" kubectl get --raw /readyz >/dev/null 2>&1; then ready=1; break; fi
|
||||
sleep 5
|
||||
done
|
||||
if (( ready == 0 )); then
|
||||
docker logs --tail 20 "$container" 2>&1 | sed 's/^/ k3s: /' >&2
|
||||
hb_fail "restored k3s did not become ready in 5 minutes"
|
||||
fi
|
||||
namespaces="$(docker exec "$container" kubectl get namespaces --no-headers | wc -l)"
|
||||
secrets="$(docker exec "$container" kubectl get secrets -A --no-headers | wc -l)"
|
||||
# -o json decrypts every Secret on the server side; any failure makes kubectl exit non-zero.
|
||||
decrypted="$(docker exec "$container" kubectl get secrets -A -o json | python3 -I -c 'import json,sys; d=json.load(sys.stdin)["items"]; print(sum(1 for s in d if s.get("data")))')"
|
||||
hb_log "restored: namespaces=$namespaces secrets=$secrets with-data=$decrypted in $(( $(date +%s) - started ))s"
|
||||
if [[ -n "$expect_secrets" ]]; then
|
||||
diff=$(( secrets - expect_secrets ))
|
||||
(( ${diff#-} <= 5 )) || hb_fail "Secret count $secrets is far from the expected $expect_secrets"
|
||||
fi
|
||||
(( decrypted > 0 )) || hb_fail "no Secret carried data after restore"
|
||||
|
||||
hb_write_metrics "$NAME" <<PROM
|
||||
# HELP platform_backup_restore_drill_last_success_timestamp_seconds Unix time of the last successful restore drill.
|
||||
# TYPE platform_backup_restore_drill_last_success_timestamp_seconds gauge
|
||||
platform_backup_restore_drill_last_success_timestamp_seconds{backup="k3s-datastore"} $(date +%s)
|
||||
PROM
|
||||
echo "K3S DATASTORE RESTORE DRILL PASS"
|
||||
@@ -0,0 +1,16 @@
|
||||
#!/usr/bin/env bash
|
||||
# Daily drift check against origin/main (not the working tree of the checkout),
|
||||
# so local edits or a stale checkout do not hide or invent drift.
|
||||
# Run by platform-live-drift-check.timer as the desktop user.
|
||||
set -Eeuo pipefail
|
||||
readonly CHECKOUT="${PLATFORM_CHECKOUT:-/home/donghyeon/workspace/platform}"
|
||||
readonly TEXTFILE=/var/lib/node_exporter/textfile_collector/platform_live_drift.prom
|
||||
|
||||
git -C "$CHECKOUT" fetch --quiet origin main
|
||||
work="$(mktemp -d /tmp/platform-drift-main.XXXXXX)"
|
||||
trap 'rm -rf -- "$work"' EXIT
|
||||
git -C "$CHECKOUT" archive origin/main | tar -x -C "$work"
|
||||
printf 'origin/main %s\n' "$(git -C "$CHECKOUT" rev-parse --short origin/main)"
|
||||
args=(--accepted "$work/scripts/validate/live-drift-accepted.txt")
|
||||
[[ -d "$(dirname "$TEXTFILE")" ]] && args+=(--textfile "$TEXTFILE")
|
||||
bash "$work/scripts/validate/live-drift-check.sh" "${args[@]}"
|
||||
@@ -0,0 +1,41 @@
|
||||
#!/usr/bin/env bash
|
||||
# Test k3s-datastore-restore-drill.sh without production data: start a fresh,
|
||||
# network-less k3s with secrets encryption, add three test Secrets, stop it,
|
||||
# and run the drill on its state.db and token. Needs docker; no root.
|
||||
set -Eeuo pipefail
|
||||
umask 077
|
||||
|
||||
readonly ROOT="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")/../.." && pwd -P)"
|
||||
readonly K3S_IMAGE="$(sed -n 's/^readonly K3S_IMAGE="\(.*\)"$/\1/p' "$ROOT/scripts/validate/k3s-datastore-restore-drill.sh")"
|
||||
[[ -n "$K3S_IMAGE" ]] || { echo "cannot read K3S_IMAGE from the drill script" >&2; exit 1; }
|
||||
work="$(mktemp -d)"
|
||||
seed="w6-k3s-drill-seed-$$"
|
||||
cleanup() {
|
||||
docker rm -f "$seed" >/dev/null 2>&1 || true
|
||||
docker run --rm -v "$work:/w" --entrypoint /bin/sh "$K3S_IMAGE" -c 'rm -rf /w/*' >/dev/null 2>&1 || true
|
||||
rm -rf -- "$work"
|
||||
}
|
||||
trap cleanup EXIT
|
||||
mkdir -p "$work/server" "$work/copy"
|
||||
|
||||
docker run -d --name "$seed" --network none --tmpfs /run --tmpfs /var/run \
|
||||
-v "$work/server:/var/lib/rancher/k3s/server" "$K3S_IMAGE" server --disable-agent --secrets-encryption \
|
||||
--bind-address 127.0.0.1 --advertise-address 127.0.0.1 --node-ip 127.0.0.1 \
|
||||
--disable traefik,servicelb,metrics-server,local-storage,coredns >/dev/null
|
||||
for _ in $(seq 1 60); do docker exec "$seed" kubectl get --raw /readyz >/dev/null 2>&1 && break; sleep 5; done
|
||||
for i in 1 2 3; do docker exec "$seed" kubectl create secret generic "drill-test-$i" --from-literal=value="test-$i" >/dev/null; done
|
||||
expected="$(docker exec "$seed" kubectl get secrets -A --no-headers | wc -l)"
|
||||
docker stop -t 30 "$seed" >/dev/null
|
||||
docker run --rm -v "$work:/w" --entrypoint /bin/sh "$K3S_IMAGE" -c \
|
||||
"cp /w/server/db/state.db* /w/server/token /w/copy/ && chown $(id -u):$(id -g) /w/copy/*"
|
||||
# Fold the WAL into state.db, as `sqlite3 .backup` does in the real backup.
|
||||
sqlite3 "$work/copy/state.db" 'PRAGMA wal_checkpoint(TRUNCATE);' >/dev/null
|
||||
rm -f "$work/copy/state.db-wal" "$work/copy/state.db-shm"
|
||||
# The test Secrets must be stored encrypted (k8s:enc:...), so the drill really
|
||||
# proves that the token unlocks the encryption key.
|
||||
encrypted="$(sqlite3 "$work/copy/state.db" "SELECT COUNT(*) FROM kine WHERE name LIKE '/registry/secrets/default/drill-test-%' AND CAST(value AS TEXT) LIKE 'k8s:enc:%';")"
|
||||
echo "seed: $expected Secrets, encrypted test Secret rows=$encrypted"
|
||||
(( encrypted >= 3 )) || { echo "test Secrets are not encrypted at rest in the seed datastore" >&2; exit 1; }
|
||||
|
||||
bash "$ROOT/scripts/validate/k3s-datastore-restore-drill.sh" --from-dir "$work/copy" --expect-secrets "$expected"
|
||||
echo "K3S DATASTORE RESTORE DRILL TEST PASS"
|
||||
@@ -0,0 +1,151 @@
|
||||
#!/usr/bin/env bash
|
||||
# promtool unit tests for services/platform-host-checks/prometheus-rules.yaml.
|
||||
# Needs docker and python3 (PyYAML). No cluster access.
|
||||
set -Eeuo pipefail
|
||||
|
||||
readonly ROOT="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")/../.." && pwd -P)"
|
||||
# Same pinned image as test-platform-observability-rules.sh.
|
||||
readonly PROMETHEUS_IMAGE="quay.io/prometheus/prometheus:v3.13.2-distroless@sha256:ce95cfa77eff5aad28bd7a65aff19868cf78d9e17e4c254da7dfe22ade78318b"
|
||||
|
||||
work="$(mktemp -d)"
|
||||
trap 'rm -rf -- "$work"' EXIT
|
||||
python3 -I - "$ROOT/services/platform-host-checks/prometheus-rules.yaml" "$work/rules.yaml" <<'PY'
|
||||
import sys, yaml
|
||||
rule = yaml.safe_load(open(sys.argv[1]))
|
||||
yaml.safe_dump({"groups": rule["spec"]["groups"]}, open(sys.argv[2], "w"), sort_keys=False)
|
||||
PY
|
||||
|
||||
# promtool evaluates from Unix time 0, so "now" in each test is the eval_time.
|
||||
cat >"$work/tests.yaml" <<'EOF'
|
||||
rule_files:
|
||||
- rules.yaml
|
||||
evaluation_interval: 1m
|
||||
tests:
|
||||
# k3s datastore: last success at t=0; stale after 2 days, alert after 1h more.
|
||||
- interval: 1m
|
||||
input_series:
|
||||
- series: 'platform_backup_last_success_timestamp_seconds{backup="k3s-datastore"}'
|
||||
values: '0x5500'
|
||||
- series: 'platform_backup_last_run_timestamp_seconds{backup="k3s-datastore"}'
|
||||
values: '0x5500'
|
||||
- series: 'platform_backup_last_run_timestamp_seconds{backup="gitea"}'
|
||||
values: '0x5500'
|
||||
- series: 'platform_backup_last_success_timestamp_seconds{backup="gitea"}'
|
||||
values: '0x5500'
|
||||
alert_rule_test:
|
||||
- eval_time: 24h
|
||||
alertname: PlatformK3sDatastoreBackupTooOld
|
||||
exp_alerts: []
|
||||
- eval_time: 50h
|
||||
alertname: PlatformK3sDatastoreBackupTooOld
|
||||
exp_alerts:
|
||||
- exp_labels: {severity: warning}
|
||||
exp_annotations:
|
||||
summary: k3s datastore has not been backed up for more than 2 days
|
||||
description: Check `journalctl -u platform-k3s-datastore-backup` on desktop. Daily timer, 03:30 KST.
|
||||
- eval_time: 90h
|
||||
alertname: PlatformGiteaBackupTooOld
|
||||
exp_alerts: []
|
||||
- eval_time: 90h
|
||||
alertname: PlatformHostBackupMetricsAbsent
|
||||
exp_alerts: []
|
||||
- interval: 1m
|
||||
input_series:
|
||||
- series: 'platform_backup_last_success_timestamp_seconds{backup="gitea"}'
|
||||
values: '0x11700'
|
||||
alert_rule_test:
|
||||
- eval_time: 194h
|
||||
alertname: PlatformGiteaBackupTooOld
|
||||
exp_alerts:
|
||||
- exp_labels: {severity: warning}
|
||||
exp_annotations:
|
||||
summary: Gitea has not been backed up for more than 8 days
|
||||
description: Check `journalctl -u platform-gitea-backup` on desktop. Weekly timer, Sunday 04:00 KST.
|
||||
# A failed run is reported with its backup label.
|
||||
- interval: 1m
|
||||
input_series:
|
||||
- series: 'platform_backup_last_run_success{backup="gitea",instance="desktop"}'
|
||||
values: '0x30'
|
||||
- series: 'platform_backup_last_run_success{backup="k3s-datastore",instance="desktop"}'
|
||||
values: '1x30'
|
||||
alert_rule_test:
|
||||
- eval_time: 15m
|
||||
alertname: PlatformHostBackupFailed
|
||||
exp_alerts:
|
||||
- exp_labels: {severity: warning, backup: gitea}
|
||||
exp_annotations:
|
||||
summary: "The last gitea backup run failed"
|
||||
description: "Check `journalctl -u platform-gitea-backup` on desktop."
|
||||
# Metrics never written (timers or textfile collector missing).
|
||||
- interval: 1h
|
||||
input_series:
|
||||
- series: 'up{job="prometheus-node-exporter"}'
|
||||
values: '1x30'
|
||||
alert_rule_test:
|
||||
- eval_time: 25h
|
||||
alertname: PlatformHostBackupMetricsAbsent
|
||||
exp_alerts:
|
||||
- exp_labels: {severity: warning, backup: k3s-datastore}
|
||||
exp_annotations:
|
||||
summary: Host backup metrics are missing
|
||||
description: The backup timers or the node-exporter textfile collector (/var/lib/node_exporter/textfile_collector) are not running.
|
||||
- exp_labels: {severity: warning, backup: gitea}
|
||||
exp_annotations:
|
||||
summary: Host backup metrics are missing
|
||||
description: The backup timers or the node-exporter textfile collector (/var/lib/node_exporter/textfile_collector) are not running.
|
||||
# Drift for 7h fires; drift 0 does not.
|
||||
- interval: 1m
|
||||
input_series:
|
||||
- series: 'platform_live_drift_objects'
|
||||
values: '3x500'
|
||||
- series: 'platform_live_drift_last_run_timestamp_seconds'
|
||||
values: '0x500'
|
||||
- series: 'platform_live_drift_check_success'
|
||||
values: '1x500'
|
||||
alert_rule_test:
|
||||
- eval_time: 5h
|
||||
alertname: PlatformLiveDriftDetected
|
||||
exp_alerts: []
|
||||
- eval_time: 7h
|
||||
alertname: PlatformLiveDriftDetected
|
||||
exp_alerts:
|
||||
- exp_labels: {severity: warning}
|
||||
exp_annotations:
|
||||
summary: "3 live objects differ from platform-core origin/main"
|
||||
description: Run `scripts/validate/live-drift-check.sh --accepted scripts/validate/live-drift-accepted.txt` on desktop to list them.
|
||||
- eval_time: 7h
|
||||
alertname: PlatformLiveDriftCheckStale
|
||||
exp_alerts: []
|
||||
# Certificates: 50 days left -> warning only; 10 days left -> warning and critical.
|
||||
- interval: 1m
|
||||
input_series:
|
||||
- series: 'platform_k3s_certificate_not_after_seconds{certificate="apiserver"}'
|
||||
values: '4320000x200'
|
||||
- series: 'platform_k3s_certificate_not_after_seconds{certificate="kubelet"}'
|
||||
values: '864000x200'
|
||||
- series: 'platform_k3s_certificate_check_timestamp_seconds'
|
||||
values: '0x200'
|
||||
alert_rule_test:
|
||||
- eval_time: 2h
|
||||
alertname: PlatformK3sServingCertificateExpiry
|
||||
exp_alerts:
|
||||
- exp_labels: {severity: warning, certificate: apiserver}
|
||||
exp_annotations:
|
||||
summary: "k3s apiserver serving certificate expires in less than 100 days"
|
||||
description: k3s renews certificates only when it starts within 120 days of expiry. Plan a k3s restart window (docs/runbooks).
|
||||
- exp_labels: {severity: warning, certificate: kubelet}
|
||||
exp_annotations:
|
||||
summary: "k3s kubelet serving certificate expires in less than 100 days"
|
||||
description: k3s renews certificates only when it starts within 120 days of expiry. Plan a k3s restart window (docs/runbooks).
|
||||
- exp_labels: {severity: critical, certificate: kubelet}
|
||||
exp_annotations:
|
||||
summary: "k3s kubelet serving certificate expires in less than 14 days"
|
||||
description: Restart k3s (it renews certificates within 120 days of expiry) or run `k3s certificate rotate`.
|
||||
- eval_time: 2h
|
||||
alertname: PlatformK3sCertificateCheckStale
|
||||
exp_alerts: []
|
||||
EOF
|
||||
|
||||
docker run --rm --user "$(id -u):$(id -g)" -v "$work:/work:ro" -w /work --entrypoint /bin/promtool "$PROMETHEUS_IMAGE" check rules rules.yaml
|
||||
docker run --rm --user "$(id -u):$(id -g)" -v "$work:/work:ro" -w /work --entrypoint /bin/promtool "$PROMETHEUS_IMAGE" test rules tests.yaml
|
||||
echo "PLATFORM HOST CHECK ALERTS PASS"
|
||||
Reference in New Issue
Block a user