幂等脚本与带退避的重试逻辑

什么是幂等性，以及它为何重要

防止创建文件和目录

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

CONFIG_DIR="$HOME/.myapp"
CONFIG_FILE="$CONFIG_DIR/config.ini"

# Idempotent: mkdir -p never fails if dir already exists
mkdir -p "$CONFIG_DIR"

# Idempotent: only write config if it doesn't exist yet
if [ ! -f "$CONFIG_FILE" ]; then
  echo '[defaults]' > "$CONFIG_FILE"
  echo 'timeout=30' >> "$CONFIG_FILE"
  echo "Created $CONFIG_FILE"
else
  echo "Config already exists, skipping."
fi

幂等的用户和组管理

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

APP_USER="apprunner"
APP_GROUP="appgroup"

# Idempotent group creation
if ! getent group "$APP_GROUP" &>/dev/null; then
  groupadd "$APP_GROUP"
  echo "Group '$APP_GROUP' created."
else
  echo "Group '$APP_GROUP' already exists."
fi

# Idempotent user creation
if ! id "$APP_USER" &>/dev/null; then
  useradd -m -g "$APP_GROUP" -s /bin/bash "$APP_USER"
  echo "User '$APP_USER' created."
else
  echo "User '$APP_USER' already exists."
fi

使用锁文件防止并发运行

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

LOCKFILE="/tmp/myapp_deploy.lock"

# Atomic lock acquisition using mkdir
if ! mkdir "$LOCKFILE" 2>/dev/null; then
  echo "ERROR: Another instance is running (lock: $LOCKFILE). Exiting." >&2
  exit 1
fi

# Guarantee lock removal on any exit
trap 'rmdir "$LOCKFILE"; echo "Lock released."' EXIT

echo "Lock acquired. Running deployment..."
sleep 2   # simulate work
echo "Deployment complete."

使用状态文件跟踪已完成的步骤

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

STATE_DIR="/tmp/myapp_state"
mkdir -p "$STATE_DIR"

run_step() {
  local step_name="$1"
  local step_cmd="$2"
  local marker="$STATE_DIR/${step_name}.done"

  if [ -f "$marker" ]; then
    echo "[SKIP] $step_name already completed."
    return 0
  fi

  echo "[RUN]  $step_name ..."
  eval "$step_cmd"
  touch "$marker"
  echo "[DONE] $step_name"
}

run_step "install_deps"   "echo 'Installing dependencies...'"
run_step "configure_db"   "echo 'Configuring database...'"
run_step "start_service"  "echo 'Starting service...'"

重试逻辑简介

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

# Simple fixed-delay retry (3 attempts, 2s apart)
retry() {
  local max_attempts=3
  local delay=2
  local attempt=1

  until "$@"; do
    if (( attempt >= max_attempts )); then
      echo "ERROR: Command failed after $max_attempts attempts: $*" >&2
      return 1
    fi
    echo "Attempt $attempt failed. Retrying in ${delay}s..." >&2
    sleep "$delay"
    (( attempt++ ))
  done
}

# Example: retry a curl call
retry curl --silent --fail --max-time 5 https://httpbin.org/get -o /dev/null
echo "Request succeeded."

惊群问题

实现指数退避

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

retry_with_backoff() {
  local max_attempts="${RETRY_MAX_ATTEMPTS:-5}"
  local base_delay="${RETRY_BASE_DELAY:-1}"
  local max_delay="${RETRY_MAX_DELAY:-30}"
  local attempt=0
  local delay="$base_delay"

  until "$@"; do
    (( attempt++ ))
    if (( attempt >= max_attempts )); then
      echo "ERROR: '$*' failed after $max_attempts attempts." >&2
      return 1
    fi
    echo "Attempt $attempt failed. Backing off for ${delay}s..." >&2
    sleep "$delay"
    # Double the delay, but cap it
    delay=$(( delay * 2 ))
    (( delay > max_delay )) && delay=$max_delay
  done

  echo "Command succeeded on attempt $(( attempt + 1 ))."
}

retry_with_backoff echo "Simulated success"

为退避添加抖动

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

retry_with_jitter() {
  local max_attempts="${1:-5}"; shift
  local base_delay=1
  local max_delay=32
  local attempt=0
  local cap=$base_delay

  until "$@"; do
    (( attempt++ ))
    if (( attempt >= max_attempts )); then
      echo "ERROR: Giving up after $max_attempts attempts." >&2
      return 1
    fi

    # Full jitter: random value in [0, cap]
    local jitter=$(( RANDOM % (cap + 1) ))
    echo "Attempt $attempt failed. Sleeping ${jitter}s (cap=${cap}s)..." >&2
    sleep "$jitter"

    # Grow cap exponentially, bounded by max_delay
    cap=$(( cap * 2 ))
    (( cap > max_delay )) && cap=$max_delay
  done
}

retry_with_jitter 4 curl --silent --fail --max-time 3 https://httpbin.org/get -o /dev/null
echo "Done."

在实际工作流中结合幂等性与重试

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

STATE_DIR="/tmp/deploy_state" && mkdir -p "$STATE_DIR"
LOCK="/tmp/deploy.lock"

mkdir "$LOCK" 2>/dev/null || { echo "Already running."; exit 1; }
trap 'rmdir "$LOCK"' EXIT

step_done() { [ -f "$STATE_DIR/$1.done" ]; }
mark_done() { touch "$STATE_DIR/$1.done"; }

retry_backoff() {
  local attempt=0 delay=1
  until "${@:2}"; do
    (( ++attempt >= $1 )) && { echo "Failed after $1 attempts."; return 1; }
    echo "Retry $attempt in ${delay}s..."; sleep $delay; delay=$(( delay * 2 ))
  done
}

if ! step_done "download_artifact"; then
  retry_backoff 4 curl -fsSL https://httpbin.org/get -o /tmp/artifact.json
  mark_done "download_artifact"
  echo "[DONE] download_artifact"
else
  echo "[SKIP] download_artifact"
fi

echo "Deployment finished successfully."

处理不可重试的错误

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

fetch_with_retry() {
  local url="$1"
  local max_attempts=4
  local delay=1
  local attempt=0
  local http_code

  until http_code=$(curl -s -o /dev/null -w '%{http_code}' --max-time 5 "$url"); do
    : # curl itself failed (network error)
    (( ++attempt >= max_attempts )) && { echo "Network error, giving up."; return 1; }
    sleep $delay; delay=$(( delay * 2 ))
  done

  # Permanent client errors — do not retry
  if [[ "$http_code" =~ ^4 ]]; then
    echo "ERROR: HTTP $http_code for $url — not retrying." >&2
    return 1
  fi

  # Transient server errors — retry
  if [[ "$http_code" =~ ^5 ]]; then
    (( ++attempt >= max_attempts )) && { echo "Server error, giving up."; return 1; }
    echo "HTTP $http_code — backing off ${delay}s..."
    sleep $delay; delay=$(( delay * 2 ))
    fetch_with_retry "$url"
    return
  fi

  echo "HTTP $http_code — success."
}

fetch_with_retry "https://httpbin.org/status/200"

知识检查：选择退避策略

回顾：幂等性与带退避的重试