feat: daily node restart controlled from the admin, connect timings as a default line task [CI]
ci/woodpecker/push/main-amd64-build Pipeline was successful

Agents and Probes exit in order at a configured time (default 04:30 UTC+8, switch and time zone in the admin settings) and the service manager starts them again; a local restart_at or MOSHIRO_RESTART_AT wins. The connect kind (TCP connect and TLS handshake timings) is now a default continuous line template, with a section on the line page.
This commit is contained in:
justme committed 2026-10-07 14:56:50 +08:00
1 parent 388619b8b6
commit 9bcef56497
37 files changed
+928 -101

No files matched your search

+35 -1
View File
@@ -126,7 +126,8 @@ public static class PlatformCheck
/// <summary>处理 Ctrl+C 和 SIGTERM:取消令牌,让各个模块有序退出。</summary>
public static class ServiceShell
{
public static async Task RunAsync(Func<CancellationToken, Task> run, INodeLog log)
/// <param name="restart">每天定时有序退出一次(见 <see cref="RestartController"/>),重新拉起由服务管理器负责。</param>
public static async Task RunAsync(Func<CancellationToken, Task> run, INodeLog log, RestartController? restart = null, TimeProvider? time = null)
{
using var cts = new CancellationTokenSource();
using PosixSignalRegistration term = PosixSignalRegistration.Create(PosixSignal.SIGTERM, context =>
@@ -156,6 +157,7 @@ public static class ServiceShell
cts.Cancel();
});
Task trimmer = TrimHeapAsync(cts.Token);
Task scheduled = restart is null ? Task.CompletedTask : WaitForRestartAsync(restart, time ?? TimeProvider.System, log, cts);
try
{
await run(cts.Token);
@@ -168,6 +170,38 @@ public static class ServiceShell
{
await cts.CancelAsync();
await trimmer;
await scheduled;
}
}
private static async Task WaitForRestartAsync(RestartController restart, TimeProvider time, INodeLog log, CancellationTokenSource cts)
{
while (!cts.IsCancellationRequested)
{
// 先取令牌、再取设置:中间被改动的话令牌会被取消,下一轮重新排
CancellationToken changed = restart.ChangeToken;
RestartSchedule? schedule = restart.Current;
using CancellationTokenSource wait = CancellationTokenSource.CreateLinkedTokenSource(cts.Token, changed);
try
{
if (schedule is null)
{
await Task.Delay(Timeout.Infinite, wait.Token);
continue;
}
DateTimeOffset next = schedule.NextAfter(time.GetUtcNow() + RestartSchedule.MinimumUptime);
log.Info("restart scheduled", ("at", next.ToString("O", System.Globalization.CultureInfo.InvariantCulture)), ("source", restart.IsLocal ? "local" : "panel"));
await Task.Delay(next - time.GetUtcNow(), time, wait.Token);
}
catch (OperationCanceledException)
{
continue; // 进程在退出,或者设置被改了:循环条件和下一轮会处理
}
log.Info("stopping", ("result", "scheduled_restart"));
await cts.CancelAsync();
return;
}
}
@@ -0,0 +1,73 @@
namespace Fleet.Hosting;
/// <summary>
/// 当前生效的定时重启:节点本地的设置优先;本地没有写时用面板下发的,面板改了之后立即重新排下一次,不需要重启进程。
/// </summary>
public sealed class RestartController : IDisposable
{
private readonly RestartSchedule? _local;
private readonly object _gate = new();
private RestartSchedule? _remote;
private CancellationTokenSource _changed = new();
public RestartController(RestartSchedule? local = null)
{
_local = local;
}
/// <summary>本地有设置时为 true:面板下发的不生效。</summary>
public bool IsLocal => _local is not null;
public RestartSchedule? Current
{
get
{
lock (_gate)
{
return _local ?? _remote;
}
}
}
/// <summary>当前设置被改动时会被取消的令牌;先取令牌、再取 <see cref="Current"/>,就不会漏掉中间的改动。</summary>
public CancellationToken ChangeToken
{
get
{
lock (_gate)
{
return _changed.Token;
}
}
}
/// <summary>面板下发的设置;为空表示面板关闭了定时重启。返回 false 表示文本不合法(节点忽略它)。</summary>
public bool SetRemote(string? text)
{
RestartSchedule? schedule = null;
if (!string.IsNullOrWhiteSpace(text) && !RestartSchedule.TryParse(text, out schedule))
{
return false;
}
CancellationTokenSource previous;
lock (_gate)
{
_remote = schedule;
previous = _changed;
_changed = new CancellationTokenSource();
}
previous.Cancel();
previous.Dispose();
return true;
}
public void Dispose()
{
lock (_gate)
{
_changed.Dispose();
}
}
}
@@ -0,0 +1,105 @@
using System.Globalization;
namespace Fleet.Hosting;
/// <summary>
/// 每天固定时刻有序退出一次,由 systemd、容器引擎或 procd 的「总是重启」拉起。写法 <c>HH:mm</c>(按 UTC)、
/// <c>HH:mm±hh:mm</c> 或 <c>HH:mm</c> 加 <c>Z</c>:容器里没有时区数据库,所以偏移要写明,例如 <c>04:00+08:00</c>。
/// 进程自己退出,不需要任何执行外部命令的能力。
/// </summary>
public sealed class RestartSchedule
{
/// <summary>环境变量,设置了就覆盖配置文件里的值。</summary>
public const string EnvironmentVariable = "MOSHIRO_RESTART_AT";
/// <summary>刚启动的一段时间内不会触发:重启之后不会因为时刻还没过去而再重启一次,也避免重启风暴。</summary>
public static readonly TimeSpan MinimumUptime = TimeSpan.FromMinutes(10);
private readonly TimeSpan _time;
private readonly TimeSpan _offset;
private RestartSchedule(TimeSpan time, TimeSpan offset)
{
_time = time;
_offset = offset;
}
public static bool TryParse(string? text, out RestartSchedule? schedule)
{
schedule = null;
string value = text?.Trim() ?? "";
// HH:mm,后面可以跟 Z 或 ±hh:mm
if (value.Length < 5 || value[2] != ':' ||
!TryTwoDigits(value, 0, out int hour) || !TryTwoDigits(value, 3, out int minute) || hour > 23 || minute > 59)
{
return false;
}
TimeSpan offset = TimeSpan.Zero;
string rest = value[5..];
if (rest.Length > 0 && rest != "Z")
{
if (rest.Length != 6 || rest[0] is not ('+' or '-') || rest[3] != ':' ||
!TryTwoDigits(rest, 1, out int offsetHours) || !TryTwoDigits(rest, 4, out int offsetMinutes) || offsetMinutes > 59)
{
return false;
}
offset = new TimeSpan(offsetHours, offsetMinutes, 0);
if (offset > TimeSpan.FromHours(14))
{
return false;
}
if (rest[0] == '-')
{
offset = -offset;
}
}
schedule = new RestartSchedule(new TimeSpan(hour, minute, 0), offset);
return true;
}
private static bool TryTwoDigits(string text, int start, out int value)
{
value = 0;
if (!char.IsAsciiDigit(text[start]) || !char.IsAsciiDigit(text[start + 1]))
{
return false;
}
value = (text[start] - '0') * 10 + (text[start + 1] - '0');
return true;
}
/// <summary>
/// 环境变量优先,其次配置文件的值;都没有就不定时重启。写错了抛 <see cref="InvalidOperationException"/>,
/// 启动时就能看到,而不是悄悄不生效。
/// </summary>
public static RestartSchedule? Resolve(string? configured)
{
string? text = Environment.GetEnvironmentVariable(EnvironmentVariable);
if (string.IsNullOrWhiteSpace(text))
{
text = configured;
}
if (string.IsNullOrWhiteSpace(text))
{
return null;
}
return TryParse(text, out RestartSchedule? schedule)
? schedule
: throw new InvalidOperationException($"restart_at must look like 04:00, 04:00Z or 04:00+08:00 (got '{text}')");
}
/// <summary>严格晚于 <paramref name="now"/> 的下一个触发时刻。</summary>
public DateTimeOffset NextAfter(DateTimeOffset now)
{
DateTimeOffset local = now.ToOffset(_offset);
DateTimeOffset candidate = new DateTimeOffset(local.Year, local.Month, local.Day, 0, 0, 0, _offset) + _time;
return candidate <= local ? candidate.AddDays(1) : candidate;
}
}
@@ -9,6 +9,7 @@
<ProjectReference Include="..\..\src\Fleet.Identity\Fleet.Identity.csproj" />
<ProjectReference Include="..\..\src\Fleet.Rpc\Fleet.Rpc.csproj" />
<ProjectReference Include="..\..\src\Fleet.Link\Fleet.Link.csproj" />
<ProjectReference Include="..\..\src\Fleet.Hosting\Fleet.Hosting.csproj" />
</ItemGroup>
<ItemGroup>
<Using Include="Xunit" />
@@ -0,0 +1,260 @@
using Fleet.Core;
using Fleet.Hosting;
namespace Fleet.Tests;
public sealed class RestartScheduleTests
{
private static RestartSchedule Parse(string text)
{
Assert.True(RestartSchedule.TryParse(text, out RestartSchedule? schedule), text);
return schedule!;
}
[Theory]
[InlineData("04:00")]
[InlineData("04:00Z")]
[InlineData("04:00+08:00")]
[InlineData("23:59-05:30")]
[InlineData(" 00:00 ")]
public void Parse_AcceptsTimeWithOptionalOffset(string text) => Parse(text);
[Theory]
[InlineData("")]
[InlineData("4:00")]
[InlineData("24:00")]
[InlineData("04:60")]
[InlineData("04:00+8:00")]
[InlineData("04:00+15:00")]
[InlineData("04:00 UTC")]
[InlineData("0400")]
[InlineData("04:00+08:60")]
public void Parse_RejectsEverythingElse(string text) => Assert.False(RestartSchedule.TryParse(text, out _));
[Fact]
public void NextAfter_IsStrictlyLater_AndRollsToTomorrow()
{
RestartSchedule utc = Parse("04:00");
Assert.Equal(new DateTimeOffset(2026, 10, 7, 4, 0, 0, TimeSpan.Zero), utc.NextAfter(new DateTimeOffset(2026, 10, 7, 3, 59, 59, TimeSpan.Zero)));
Assert.Equal(new DateTimeOffset(2026, 10, 8, 4, 0, 0, TimeSpan.Zero), utc.NextAfter(new DateTimeOffset(2026, 10, 7, 4, 0, 0, TimeSpan.Zero)));
Assert.Equal(new DateTimeOffset(2026, 10, 8, 4, 0, 0, TimeSpan.Zero), utc.NextAfter(new DateTimeOffset(2026, 10, 7, 20, 0, 0, TimeSpan.Zero)));
}
[Fact]
public void NextAfter_UsesTheWrittenOffset()
{
// 04:00+08:00 就是 UTC 前一天 20:00
RestartSchedule china = Parse("04:00+08:00");
Assert.Equal(new DateTimeOffset(2026, 10, 6, 20, 0, 0, TimeSpan.Zero), china.NextAfter(new DateTimeOffset(2026, 10, 6, 19, 0, 0, TimeSpan.Zero)));
Assert.Equal(new DateTimeOffset(2026, 10, 7, 20, 0, 0, TimeSpan.Zero), china.NextAfter(new DateTimeOffset(2026, 10, 6, 20, 0, 0, TimeSpan.Zero)));
}
[Fact]
public void NextAfter_WithMinimumUptime_DoesNotRestartAgainRightAfterARestart()
{
RestartSchedule schedule = Parse("04:00");
// 04:00:03 重启后启动:加上最短运行时间再算,下一次是明天,而不是几秒后
var started = new DateTimeOffset(2026, 10, 7, 4, 0, 3, TimeSpan.Zero);
Assert.Equal(new DateTimeOffset(2026, 10, 8, 4, 0, 0, TimeSpan.Zero), schedule.NextAfter(started + RestartSchedule.MinimumUptime));
// 03:55 启动:离 04:00 只有 5 分钟,不够最短运行时间,顺延到明天
var early = new DateTimeOffset(2026, 10, 7, 3, 55, 0, TimeSpan.Zero);
Assert.Equal(new DateTimeOffset(2026, 10, 8, 4, 0, 0, TimeSpan.Zero), schedule.NextAfter(early + RestartSchedule.MinimumUptime));
}
[Fact]
public void Resolve_ReportsABadValueInsteadOfIgnoringIt()
{
Assert.Null(RestartSchedule.Resolve(null));
Assert.Null(RestartSchedule.Resolve(" "));
InvalidOperationException error = Assert.Throws<InvalidOperationException>(() => RestartSchedule.Resolve("tomorrow"));
Assert.Contains("restart_at", error.Message);
}
[Fact]
public async Task ServiceShell_StopsAtTheScheduledTime()
{
var time = new ImmediateTimeProvider(new DateTimeOffset(2026, 10, 7, 12, 0, 0, TimeSpan.Zero));
var log = new ListLog();
bool stoppedByToken = false;
// 业务循环只在被取消时返回;定时重启到点以后令牌被取消,RunAsync 正常返回
await ServiceShell.RunAsync(async ct =>
{
try
{
await Task.Delay(Timeout.Infinite, ct);
}
catch (OperationCanceledException)
{
stoppedByToken = true;
throw;
}
}, log, new RestartController(Parse("04:00")), time).WaitAsync(TimeSpan.FromSeconds(10));
Assert.True(stoppedByToken);
Assert.Contains(log.Lines, l => l.Contains("scheduled_restart", StringComparison.Ordinal));
Assert.Contains(log.Lines, l => l.Contains("restart scheduled", StringComparison.Ordinal));
}
[Fact]
public async Task ServiceShell_PicksUpAScheduleThePanelSendsLater()
{
var time = new ImmediateTimeProvider(new DateTimeOffset(2026, 10, 7, 12, 0, 0, TimeSpan.Zero));
var log = new ListLog();
using var controller = new RestartController();
Task shell = ServiceShell.RunAsync(ct => Task.Delay(Timeout.Infinite, ct), log, controller, time);
await Task.Delay(300);
Assert.False(shell.IsCompleted, "no schedule yet: the node keeps running");
Assert.True(controller.SetRemote("04:30+08:00"));
await shell.WaitAsync(TimeSpan.FromSeconds(10));
Assert.Contains(log.Lines, l => l.Contains("scheduled_restart", StringComparison.Ordinal));
Assert.Contains(log.Lines, l => l.Contains("source=panel", StringComparison.Ordinal));
}
[Fact]
public async Task ServiceShell_ClearingTheScheduleCancelsTheRestart()
{
var time = new ManualTimeProvider(new DateTimeOffset(2026, 10, 7, 12, 0, 0, TimeSpan.Zero));
var log = new ListLog();
using var controller = new RestartController();
controller.SetRemote("04:30+08:00");
Task shell = ServiceShell.RunAsync(ct => Task.Delay(Timeout.Infinite, ct), log, controller, time);
await Task.Delay(300);
controller.SetRemote(null); // 面板关掉了
await Task.Delay(300);
Assert.False(shell.IsCompleted);
Assert.Contains(log.Lines, l => l.Contains("restart scheduled", StringComparison.Ordinal));
Assert.DoesNotContain(log.Lines, l => l.Contains("scheduled_restart", StringComparison.Ordinal));
// 清理:把进程停掉
Assert.True(controller.SetRemote("04:30+08:00"));
time.Advance();
await shell.WaitAsync(TimeSpan.FromSeconds(10));
}
[Fact]
public void Controller_LocalSettingWinsOverThePanel_AndBadTextIsRejected()
{
using var controller = new RestartController(Parse("04:00"));
Assert.True(controller.IsLocal);
Assert.True(controller.SetRemote("05:00"));
Assert.Equal(new DateTimeOffset(2026, 10, 7, 4, 0, 0, TimeSpan.Zero), controller.Current!.NextAfter(new DateTimeOffset(2026, 10, 7, 0, 0, 0, TimeSpan.Zero)));
using var remoteOnly = new RestartController();
Assert.Null(remoteOnly.Current);
Assert.False(remoteOnly.SetRemote("whenever"));
Assert.Null(remoteOnly.Current);
Assert.True(remoteOnly.SetRemote("05:00"));
Assert.NotNull(remoteOnly.Current);
Assert.True(remoteOnly.SetRemote(null));
Assert.Null(remoteOnly.Current);
}
/// <summary>计时器马上触发:用来验证「到点」之后的行为,不用真的等。</summary>
private sealed class ImmediateTimeProvider : TimeProvider
{
private readonly DateTimeOffset _now;
public ImmediateTimeProvider(DateTimeOffset now) => _now = now;
public override DateTimeOffset GetUtcNow() => _now;
public override ITimer CreateTimer(TimerCallback callback, object? state, TimeSpan dueTime, TimeSpan period)
{
// TrimHeapAsync 这类每 30 秒一次的循环也会走到这里;只让「很长」的延迟(定时重启,至少 10 分钟)马上触发
var timer = new ImmediateTimer(callback, state);
if (dueTime >= RestartSchedule.MinimumUptime)
{
ThreadPool.QueueUserWorkItem(_ => timer.Fire());
}
return timer;
}
}
/// <summary>计时器只在 <see cref="Advance"/> 时触发:用来验证「还没到点」时不会退出。</summary>
private sealed class ManualTimeProvider : TimeProvider
{
private readonly DateTimeOffset _now;
private readonly List<ImmediateTimer> _timers = [];
public ManualTimeProvider(DateTimeOffset now) => _now = now;
public override DateTimeOffset GetUtcNow() => _now;
public override ITimer CreateTimer(TimerCallback callback, object? state, TimeSpan dueTime, TimeSpan period)
{
var timer = new ImmediateTimer(callback, state);
lock (_timers)
{
_timers.Add(timer);
}
return timer;
}
public void Advance()
{
ImmediateTimer[] due;
lock (_timers)
{
due = [.. _timers];
_timers.Clear();
}
foreach (ImmediateTimer timer in due)
{
timer.Fire();
}
}
}
private sealed class ImmediateTimer : ITimer
{
private readonly TimerCallback _callback;
private readonly object? _state;
public ImmediateTimer(TimerCallback callback, object? state)
{
_callback = callback;
_state = state;
}
public void Fire() => _callback(_state);
public bool Change(TimeSpan dueTime, TimeSpan period) => true;
public void Dispose()
{
}
public ValueTask DisposeAsync() => ValueTask.CompletedTask;
}
private sealed class ListLog : INodeLog
{
private readonly List<string> _lines = [];
public IReadOnlyList<string> Lines
{
get
{
lock (_lines)
{
return [.. _lines];
}
}
}
public void Write(NodeLogLevel level, string message, params (string Key, object? Value)[] fields)
{
lock (_lines)
{
_lines.Add(message + " " + string.Join(' ', fields.Select(f => f.Key + "=" + f.Value)));
}
}
}
}