Erlang/Elixir 容器化与集群部署：Release、Docker 与 libcluster

MIX_ENV=prod mix release

defmodule MyApp.Release do
  @app :my_app

  def migrate do
    Application.load(@app)

    for repo <- Application.fetch_env!(@app, :ecto_repos) do
      {:ok, _, _} = Ecto.Migrator.with_repo(repo, &Ecto.Migrator.run(&1, :up, all: true))
    end
  end
end

kubectl run migrate --rm -it --restart=Never \
  --image=registry/my-app:1.2.3 \
  -- /app/bin/my_app eval "MyApp.Release.migrate()"

# ---------- 构建阶段 ----------
FROM hexpm/elixir:1.17.3-erlang-27.1.2-debian-bookworm-20240926-slim AS build

RUN apt-get update && apt-get install -y --no-install-recommends \
      build-essential git curl ca-certificates && rm -rf /var/lib/apt/lists/*

WORKDIR /app
RUN mix local.hex --force && mix local.rebar --force
ENV MIX_ENV=prod

# 先复制依赖清单，利用层缓存
COPY mix.exs mix.lock ./
RUN mix deps.get --only prod && mix deps.compile

COPY config config
COPY priv priv
COPY lib lib

RUN mix compile && mix release

# ---------- 运行阶段 ----------
FROM debian:bookworm-slim AS app

RUN apt-get update && apt-get install -y --no-install-recommends \
      libstdc++6 openssl libncurses6 locales ca-certificates \
    && rm -rf /var/lib/apt/lists/* \
    && sed -i '/en_US.UTF-8/s/^# //g' /etc/locale.gen && locale-gen

ENV LANG=en_US.UTF-8 LANGUAGE=en_US:en LC_ALL=en_US.UTF-8
WORKDIR /app
RUN chown nobody /app

COPY --from=build --chown=nobody:root /app/_build/prod/rel/my_app ./

USER nobody
ENV HOME=/app
EXPOSE 4000
CMD ["/app/bin/server"]

import Config

if config_env() == :prod do
  config :my_app, MyApp.Repo,
    url: System.fetch_env!("DATABASE_URL"),
    pool_size: String.to_integer(System.get_env("POOL_SIZE", "10"))

  config :my_app, MyAppWeb.Endpoint,
    http: [port: String.to_integer(System.get_env("PORT", "4000"))],
    secret_key_base: System.fetch_env!("SECRET_KEY_BASE"),
    server: true

  config :my_app, MyApp.Guardian, secret_key: System.fetch_env!("GUARDIAN_SECRET_KEY")
end

#!/bin/sh
# releases/0.1.0/env.sh
export RELEASE_DISTRIBUTION="name"
export RELEASE_NODE="my_app@${POD_IP:-127.0.0.1}"
export RELEASE_COOKIE="$(cat /run/secrets/erlang_cookie 2>/dev/null || echo 'local_dev_cookie')"
export RELEASE_TMP="/tmp"

export ERL_FLAGS="+S 2:2 +sbwt none +sbwtdcpu none +sbwtdio none"

# vm.args 片段：固定分布式端口范围，便于网络策略放行
-kernel inet_dist_listen_min 9100
-kernel inet_dist_listen_max 9155

config :libcluster,
  topologies: [
    k8s: [
      strategy: Cluster.Strategy.Kubernetes.DNS,
      config: [service: "my-app-headless", application_name: "my_app",
               polling_interval: 5_000]
    ]
  ]

spec:
  replicas: 3
  strategy:
    type: RollingUpdate
    rollingUpdate: {maxSurge: 1, maxUnavailable: 0}   # 先起新的，再停旧的
  template:
    spec:
      terminationGracePeriodSeconds: 60
      containers:
        - name: app
          image: registry/my-app:1.2.3
          env:
            - name: POD_IP
              valueFrom: {fieldRef: {fieldPath: status.podIP}}
          lifecycle:
            preStop: {exec: {command: ["/bin/sh", "-c", "sleep 5"]}}   # 等 LB 摘除
          readinessProbe: {httpGet: {path: /ready, port: 4000}, periodSeconds: 5}
          livenessProbe: {httpGet: {path: /health, port: 4000}, periodSeconds: 10, failureThreshold: 3}
          resources:
            limits: {cpu: "2", memory: 2Gi}

defmodule MyAppWeb.HealthController do
  use MyAppWeb, :controller

  # 存活探针：只检查进程本身能否响应
  def health(conn, _params), do: send_resp(conn, 200, "ok")

  # 就绪探针：检查依赖与集群状态
  def ready(conn, _params) do
    checks = %{db: db_ready?(), cluster: cluster_ready?()}

    if Enum.all?(checks, fn {_, v} -> v end) do
      json(conn, %{status: "ready"})
    else
      conn |> put_status(503) |> json(%{status: "not_ready", checks: checks})
    end
  end

  defp db_ready?, do: match?({:ok, _}, Ecto.Adapters.SQL.query(MyApp.Repo, "SELECT 1", []))

  defp cluster_ready? do
    expected = String.to_integer(System.get_env("EXPECTED_NODES", "1")) - 1
    length(Node.list()) >= expected
  end
end

# 让 supervisor 给子进程足够的关闭时间（默认仅 5000ms）
{MyApp.Repo, shutdown: 30_000},
{MyApp.Workers, shutdown: 60_000}