健康探针、就绪门禁与等待循环

服务为何会在启动时失败

等待模式

#!/usr/bin/env bash
set -euo pipefail

HOST="${DB_HOST:-postgres}"
PORT="${DB_PORT:-5432}"
TIMEOUT=60
INTERVAL=2
ELAPSED=0

echo "[wait-for] Waiting for ${HOST}:${PORT}..."

until nc -z "$HOST" "$PORT" 2>/dev/null; do
  if (( ELAPSED >= TIMEOUT )); then
    echo "[wait-for] Timed out after ${TIMEOUT}s waiting for ${HOST}:${PORT}" >&2
    exit 1
  fi
  echo "[wait-for] ${HOST}:${PORT} not ready — retrying in ${INTERVAL}s (${ELAPSED}s elapsed)"
  sleep "$INTERVAL"
  (( ELAPSED += INTERVAL ))
done

echo "[wait-for] ${HOST}:${PORT} is up — continuing"
exec "$@"

使用 curl 进行 HTTP 就绪性探针

#!/usr/bin/env bash
set -euo pipefail

HEALTH_URL="${HEALTH_URL:-http://localhost:8080/healthz}"
TIMEOUT=90
INTERVAL=3
ELAPSED=0

echo "[probe] Polling readiness at ${HEALTH_URL}"

until curl --fail --silent --output /dev/null \
           --max-time 2 "${HEALTH_URL}"; do
  if (( ELAPSED >= TIMEOUT )); then
    echo "[probe] Service not ready after ${TIMEOUT}s" >&2
    exit 1
  fi
  printf '[probe] Not ready yet (%ds elapsed)\n' "$ELAPSED"
  sleep "$INTERVAL"
  (( ELAPSED += INTERVAL ))
done

echo "[probe] Service is ready"
exec "$@"

等待循环中的指数退避

#!/usr/bin/env bash
set -euo pipefail

HOST="${HOST:-redis}"
PORT="${PORT:-6379}"
MAX_ATTEMPTS=8
BASE_SLEEP=1
MAX_SLEEP=30

for attempt in $(seq 1 "$MAX_ATTEMPTS"); do
  if nc -z "$HOST" "$PORT" 2>/dev/null; then
    echo "[backoff] Connected to ${HOST}:${PORT} on attempt ${attempt}"
    exec "$@"
  fi

  # Exponential backoff with jitter
  raw=$(( BASE_SLEEP * (2 ** (attempt - 1)) ))
  capped=$(( raw < MAX_SLEEP ? raw : MAX_SLEEP ))
  jitter=$(( RANDOM % 3 ))
  sleep_time=$(( capped + jitter ))

  echo "[backoff] Attempt ${attempt}/${MAX_ATTEMPTS} failed — sleeping ${sleep_time}s"
  sleep "$sleep_time"
done

echo "[backoff] ${HOST}:${PORT} unreachable after ${MAX_ATTEMPTS} attempts" >&2
exit 1

探测多个依赖项

#!/usr/bin/env bash
set -euo pipefail

wait_tcp() {
  local host="$1" port="$2" timeout="${3:-30}"
  local elapsed=0
  until nc -z "$host" "$port" 2>/dev/null; do
    (( elapsed >= timeout )) && { echo "TIMEOUT ${host}:${port}" >&2; return 1; }
    sleep 2; (( elapsed += 2 ))
  done
  echo "[ok] ${host}:${port}"
}

# Launch all probes in parallel
wait_tcp postgres 5432 60 &  PID_PG=$!
wait_tcp redis    6379 30 &  PID_RD=$!
wait_tcp rabbitmq 5672 45 &  PID_RQ=$!

# Collect results — fail fast if any probe failed
FAILED=0
for pid in $PID_PG $PID_RD $PID_RQ; do
  wait "$pid" || (( FAILED++ ))
done

if (( FAILED > 0 )); then
  echo "[entrypoint] ${FAILED} dependency probe(s) failed — aborting" >&2
  exit 1
fi

echo "[entrypoint] All dependencies ready"
exec "$@"

存活性与就绪性：针对不同探针使用不同脚本

#!/usr/bin/env bash
# liveness.sh — fast local-only check
# Used in: livenessProbe.exec.command
set -euo pipefail

PID_FILE="/var/run/app/app.pid"
HEALTH_URL="http://127.0.0.1:8080/internal/live"

# Check 1: process is running
[[ -f "$PID_FILE" ]] || { echo "PID file missing" >&2; exit 1; }
kill -0 "$(cat "$PID_FILE")" 2>/dev/null || { echo "Process dead" >&2; exit 1; }

# Check 2: local endpoint responds (2s timeout — never block)
curl --fail --silent --max-time 2 --output /dev/null "$HEALTH_URL" || {
  echo "Liveness endpoint unresponsive" >&2
  exit 1
}

echo "live"
exit 0

启动探针和 initContainers

# kubernetes/pod-with-init.yaml (illustrative — not runnable as bash)
# initContainers run sequentially before app containers
initContainers:
  - name: wait-for-postgres
    image: busybox:1.36
    command:
      - sh
      - -c
      - |
        set -e
        echo 'Waiting for postgres...'
        until nc -z postgres 5432; do
          echo 'postgres not ready — sleeping 2s'
          sleep 2
        done
        echo 'postgres is up'

  - name: run-migrations
    image: myapp:latest
    command: ['python', 'manage.py', 'migrate', '--noinput']
    envFrom:
      - secretRef:
          name: app-secrets

带 JSON 输出的健康检查脚本

#!/usr/bin/env bash
# health_check.sh — composite health with JSON output
set -uo pipefail

check_postgres() {
  pg_isready -h "${DB_HOST:-postgres}" -p "${DB_PORT:-5432}" \
             -U "${DB_USER:-app}" -t 2 &>/dev/null
}

check_redis() {
  redis-cli -h "${REDIS_HOST:-redis}" -p "${REDIS_PORT:-6379}" \
             PING 2>/dev/null | grep -q PONG
}

check_disk() {
  local usage
  usage=$(df / | awk 'NR==2{gsub(/%/,"",$5); print $5}')
  (( usage < 90 ))
}

PG_OK=0; RD_OK=0; DSK_OK=0
check_postgres && PG_OK=1
check_redis    && RD_OK=1
check_disk     && DSK_OK=1

OVERALL=$(( PG_OK && RD_OK && DSK_OK ))
STATUS=$( (( OVERALL )) && echo 'ok' || echo 'degraded' )

printf '{"status":"%s","checks":{"postgres":%s,"redis":%s,"disk":%s}}\n' \
  "$STATUS" "$PG_OK" "$RD_OK" "$DSK_OK"

(( OVERALL )) && exit 0 || exit 1

使用截止时间模式的超时工具

#!/usr/bin/env bash
set -euo pipefail

HOST="${DB_HOST:-postgres}"
PORT="${DB_PORT:-5432}"
DEADLINE=60  # seconds

# Inline poll loop, wrapped by timeout
timeout "$DEADLINE" bash -c "
  until nc -z '$HOST' '$PORT' 2>/dev/null; do
    echo '[wait] ${HOST}:${PORT} not ready...'
    sleep 2
  done
" && echo "[wait] ${HOST}:${PORT} is up" || {
  code=$?
  if (( code == 124 )); then
    echo "[wait] Timed out after ${DEADLINE}s waiting for ${HOST}:${PORT}" >&2
  else
    echo "[wait] Probe failed with exit code ${code}" >&2
  fi
  exit "$code"
}

exec "$@"

纯 Bash 实现的自包含等待脚本

#!/usr/bin/env bash
# wait-for-it.sh (pure bash, no nc/curl required)
set -uo pipefail

usage() { echo "Usage: $0 HOST:PORT [-t TIMEOUT] [-- COMMAND]"; exit 1; }

parse_hostport() {
  HOST="${1%%:*}"
  PORT="${1##*:}"
  [[ -n "$HOST" && "$PORT" =~ ^[0-9]+$ ]] || usage
}

[[ $# -ge 1 ]] || usage
parse_hostport "$1"; shift

TIMEOUT=30
[[ "${1:-}" == "-t" ]] && { TIMEOUT="$2"; shift 2; }
[[ "${1:-}" == "--" ]] && shift

wait_for() {
  local elapsed=0
  while (( elapsed < TIMEOUT )); do
    # Pure bash TCP probe — no nc, no curl
    if (exec 3<>"/dev/tcp/${HOST}/${PORT}") 2>/dev/null; then
      exec 3>&-
      return 0
    fi
    sleep 1
    (( elapsed++ ))
  done
  return 1
}

echo "Waiting for ${HOST}:${PORT} (timeout ${TIMEOUT}s)..."
if wait_for; then
  echo "${HOST}:${PORT} is available"
  [[ $# -gt 0 ]] && exec "$@"
else
  echo "Timed out waiting for ${HOST}:${PORT}" >&2
  exit 1
fi

将探针集成到 entrypoint.sh

#!/usr/bin/env bash
# docker/entrypoint.sh
set -euo pipefail

# ── 1. Validate required env vars ────────────────────────────────────
for var in DATABASE_URL REDIS_URL SECRET_KEY; do
  [[ -n "${!var:-}" ]] || { echo "FATAL: ${var} is not set" >&2; exit 1; }
done

# ── 2. Parse DB host/port from DATABASE_URL ──────────────────────────
DB_HOST=$(echo "$DATABASE_URL" | sed -E 's|.*@([^:/]+).*|\1|')
DB_PORT=$(echo "$DATABASE_URL" | sed -E 's|.*:([0-9]+)/.*|\1|')

# ── 3. Wait for dependencies ─────────────────────────────────────────
timeout 60 bash -c "
  until nc -z '${DB_HOST}' '${DB_PORT}' 2>/dev/null; do sleep 2; done
" || { echo "Database unreachable" >&2; exit 1; }

# ── 4. Run migrations ────────────────────────────────────────────────
echo "[entrypoint] Running migrations..."
python manage.py migrate --noinput

# ── 5. Hand off to CMD (exec preserves PID 1 for signal handling) ────
echo "[entrypoint] Starting application: $*"
exec "$@"

知识检查：存活性与就绪性探针

回顾：健康探针、就绪门控与等待循环