feat: choose which probes link to which agents from the admin

The panel decides the probe/agent pairs and probes always dial out. A new
fleet.auto_link setting connects every probe to every agent (default); with it
off only the pairs chosen by hand connect, and any pair can be forced on or
off. The Probes page has a link matrix with the switch and per-pair toggles.
This commit is contained in:
justme committed 2026-10-06 23:19:32 +08:00
1 parent d69581dcb5
commit 3a751a0f89
24 files changed
+731 -33

No files matched your search

@@ -13,6 +13,7 @@ public sealed class SettingsService
{
public const string SitePublic = "site.public";
public const string SiteShowBuild = "site.show_build";
public const string AutoLink = "fleet.auto_link";
public const string RawDays = "retention.raw_days";
public const string TestRawDays = "retention.test_raw_days";
public const string Metric10sHours = "retention.metric_10s_hours";
@@ -42,6 +43,7 @@ public sealed class SettingsService
[
new(SitePublic, "bool", "false", 0, 1, "Whether anonymous visitors can read the public API."),
new(SiteShowBuild, "bool", "false", 0, 1, "Whether the public pages show the versions, tags and build times of the backend, agents and probes."),
new(AutoLink, "bool", "true", 0, 1, "Whether every probe connects to every agent automatically; when off, only the links chosen by hand are connected."),
new(RawDays, "int", o.RawRetentionDays.ToString(CultureInfo.InvariantCulture), 1, 365, "Days to keep raw chunks of continuous tasks."),
new(TestRawDays, "int", o.TestRawRetentionDays.ToString(CultureInfo.InvariantCulture), 1, 365, "Days to keep raw chunks of on-demand tests."),
new(Metric10sHours, "int", o.Metric10sRetentionHours.ToString(CultureInfo.InvariantCulture), 1, 720, "Hours to keep the 10 s metric layer."),
@@ -21,9 +21,11 @@ public sealed partial class AgentService
private readonly ISettingsStore _settings;
private readonly NodeInfoService _nodes;
private readonly LinkService _links;
public AgentService(IAgentStore agents, AgentRuntime runtime, IAgentGateway gateway, TaskPlanner planner, ISettingsStore settings, NodeInfoService nodes)
public AgentService(IAgentStore agents, AgentRuntime runtime, IAgentGateway gateway, TaskPlanner planner, ISettingsStore settings, NodeInfoService nodes, LinkService links)
{
_links = links;
_nodes = nodes;
_agents = agents;
_runtime = runtime;
@@ -118,17 +120,19 @@ public sealed partial class AgentService
await _gateway.DisconnectAsync(id, "deleted", ct);
await _agents.DeleteAsync(id, ct);
await _nodes.ForgetAsync(id.Value, ct);
await _links.ForgetNodeAsync(id.Value, ct);
_runtime.Remove(id);
await AfterAgentSetChangedAsync(ct);
}
/// <summary>Probe 需要连接的 Agent 列表(所有已激活的 Agent)。版本号在列表变化时递增。</summary>
public async ValueTask<ProbeAgentList> ProbeAgentsAsync(CancellationToken ct)
/// <summary>这个 Probe 要连接的 Agent 列表(已激活、有公开地址,并且线路是开着的)。版本号在列表变化时递增。</summary>
public async ValueTask<ProbeAgentList> ProbeAgentsAsync(string probeId, CancellationToken ct)
{
LinkSnapshot links = await _links.SnapshotAsync(ct);
IReadOnlyList<AgentRecord> agents = await _agents.ListAsync(ct);
long version = long.TryParse(await _settings.GetAsync(TaskPlanner.ProbeAgentsVersionKey, ct), out long v) ? v : 0;
var result = new ProbeAgentList { Version = version };
foreach (AgentRecord agent in agents.Where(a => a.Status == NodeStatus.Active && a.PublicHost.Length > 0))
foreach (AgentRecord agent in agents.Where(a => a.Status == NodeStatus.Active && a.PublicHost.Length > 0 && links.IsLinked(probeId, a.Id.Value)))
{
result.Agents.Add(new AgentEndpoint
{
@@ -0,0 +1,68 @@
namespace Monitor.Backend.Application;
/// <summary>某一时刻的「线路」开关:自动连接的总开关,加上每一对(Probe,Agent)的手动设置。</summary>
public sealed class LinkSnapshot
{
private readonly Dictionary<(string Probe, string Agent), bool> _overrides;
public LinkSnapshot(bool auto, Dictionary<(string Probe, string Agent), bool> overrides)
{
Auto = auto;
_overrides = overrides;
}
/// <summary>自动连接:开着时,没有手动设置的 Probe 和 Agent 都会连;关着时,只有手动开启的才连。</summary>
public bool Auto { get; }
/// <summary>手动设置:<c>true</c> 强制连、<c>false</c> 强制不连、<c>null</c> 没设置(跟随自动连接)。</summary>
public bool? OverrideOf(string probeId, string agentId) => _overrides.TryGetValue((probeId, agentId), out bool value) ? value : null;
/// <summary>这一对最终连不连:手动设置优先,没有就看自动连接。</summary>
public bool IsLinked(string probeId, string agentId) => OverrideOf(probeId, agentId) ?? Auto;
}
/// <summary>
/// 哪些(Probe,Agent)要连成线路。由面板决定、Probe 主动拨出:自动连接开着时所有 Probe 和 Agent 两两连(默认),
/// 关着时只连手动选中的;每一对还可以手动强制开或关。手动设置存在设置表里(<c>link.&lt;probe&gt;.&lt;agent&gt;</c>,值 1 或 0,空表示没设置)。
/// 判断结果分别用在 Probe 的 Agent 列表、Agent 允许的 Probe(<c>peers</c>)和线路目录里;改动之后要调用 <see cref="AgentService.AfterAgentSetChangedAsync"/> 重新下发。
/// </summary>
public sealed class LinkService
{
private const string Prefix = "link.";
private readonly ISettingsStore _settings;
public LinkService(ISettingsStore settings)
{
_settings = settings;
}
public async ValueTask<LinkSnapshot> SnapshotAsync(CancellationToken ct)
{
IReadOnlyDictionary<string, string> all = await _settings.GetAllAsync(ct);
var overrides = new Dictionary<(string, string), bool>();
foreach ((string key, string value) in all)
{
string[] parts = key.Split('.');
if (parts.Length == 3 && parts[0] + "." == Prefix && value is "1" or "0")
{
overrides[(parts[1], parts[2])] = value == "1";
}
}
return new LinkSnapshot(all.GetValueOrDefault(SettingsService.AutoLink) != "false", overrides);
}
/// <summary>手动设置一对线路:<c>true</c> 强制连、<c>false</c> 强制不连、<c>null</c> 取消手动设置。</summary>
public ValueTask SetAsync(string probeId, string agentId, bool? enabled, CancellationToken ct) =>
_settings.SetAsync($"{Prefix}{probeId}.{agentId}", enabled is null ? "" : enabled.Value ? "1" : "0", ct);
/// <summary>Probe 或 Agent 被删除:清掉所有涉及它的手动设置。</summary>
public async ValueTask ForgetNodeAsync(string nodeId, CancellationToken ct)
{
foreach (string key in (await _settings.GetAllAsync(ct)).Keys.Where(k => k.StartsWith(Prefix, StringComparison.Ordinal) && k.Split('.').Skip(1).Contains(nodeId)))
{
await _settings.SetAsync(key, "", ct);
}
}
}
@@ -33,9 +33,11 @@ public sealed partial class ProbeService
private readonly IAgentGateway _gateway;
private readonly TimeProvider _time;
private readonly NodeInfoService _nodes;
private readonly LinkService _links;
public ProbeService(IProbeStore probes, IAgentStore agents, AgentRuntime runtime, IAgentGateway gateway, TimeProvider time, NodeInfoService nodes)
public ProbeService(IProbeStore probes, IAgentStore agents, AgentRuntime runtime, IAgentGateway gateway, TimeProvider time, NodeInfoService nodes, LinkService links)
{
_links = links;
_nodes = nodes;
_probes = probes;
_agents = agents;
@@ -137,6 +139,7 @@ public sealed partial class ProbeService
if (deleted)
{
await _nodes.ForgetAsync(id, ct);
await _links.ForgetNodeAsync(id, ct);
_gateway.NotifyAllTaskSetsChanged();
}
@@ -29,6 +29,7 @@ public static class ApplicationServiceCollectionExtensions
services.AddSingleton<HostStatusService>();
services.AddSingleton<NodeInfoService>();
services.AddSingleton<ProbeService>();
services.AddSingleton<LinkService>();
services.AddSingleton<LineService>();
services.AddSingleton<TestService>();
services.AddSingleton<IngestService>();
@@ -39,19 +39,22 @@ public sealed class LineService
{
private readonly AgentService _agents;
private readonly IProbeStore _probes;
private readonly LinkService _links;
public LineService(AgentService agents, IProbeStore probes)
public LineService(AgentService agents, IProbeStore probes, LinkService links)
{
_links = links;
_agents = agents;
_probes = probes;
}
/// <summary>所有线路:每个 Agent 和每个<b>未吊销</b>的 Probe 配成一对。</summary>
/// <summary>所有线路:每个 Agent 和每个<b>未吊销</b>的 Probe 配成一对,只留下线路开着的(见 <see cref="LinkService"/>);关掉的线路历史数据还在,按 id 仍然查得到。</summary>
public async ValueTask<IReadOnlyList<LineView>> ListAsync(Func<AgentView, bool> include, CancellationToken ct)
{
IReadOnlyList<AgentView> agents = await _agents.ListAsync(ct);
IReadOnlyList<ProbeRecord> probes = [.. (await _probes.ListAsync(ct)).Where(p => p.RevokedAtMs is null)];
return [.. agents.Where(include).SelectMany(a => probes.Select(p => new LineView(a, p)))];
LinkSnapshot links = await _links.SnapshotAsync(ct);
return [.. agents.Where(include).SelectMany(a => probes.Where(p => links.IsLinked(p.Id, a.Agent.Id.Value)).Select(p => new LineView(a, p)))];
}
/// <summary>
@@ -20,10 +20,12 @@ public sealed class TaskPlanner : IDisposable
private readonly IAgentStore _agents;
private readonly IProbeStore _probes;
private readonly ISettingsStore _settings;
private readonly LinkService _links;
private readonly SemaphoreSlim _gate = new(1, 1);
public TaskPlanner(ITaskStore tasks, IAgentStore agents, IProbeStore probes, ISettingsStore settings)
public TaskPlanner(ITaskStore tasks, IAgentStore agents, IProbeStore probes, ISettingsStore settings, LinkService links)
{
_links = links;
_tasks = tasks;
_agents = agents;
_probes = probes;
@@ -41,6 +43,7 @@ public sealed class TaskPlanner : IDisposable
IReadOnlyList<TaskRecord> all = await _tasks.ListAsync(ct);
IReadOnlyList<ProbeRecord> probes = await _probes.ListAsync(ct);
LinkSnapshot links = await _links.SnapshotAsync(ct);
var document = new TaskSet();
foreach (EffectiveTask task in EffectiveTasks.Compute(all, agent, filterByAgentKinds: true))
@@ -57,7 +60,7 @@ public sealed class TaskPlanner : IDisposable
});
}
foreach (ProbeRecord probe in probes.Where(p => p.RevokedAtMs is null))
foreach (ProbeRecord probe in probes.Where(p => p.RevokedAtMs is null && links.IsLinked(p.Id, agentId.Value)))
{
document.Peers.Add(new PeerSpec { ProbeId = new ProbeId(probe.Id), PublicKey = Convert.ToBase64String(probe.PublicKey) });
}