feat: 监控告警体系统一重构 + 自动化任务调度引擎 + 监控大屏拆分
告警中心 - 新增统一告警(alert_unified)、监控告警规则(monitor_alert_rule)、指标目录(alert_metric_catalog) - 通知策略与消息分发(alert_notify_policy/dispatch/message)、静默规则 - 告警引擎按阈值/SNMP 拆分(alert_engine_monitor/snmp) 监控采集 - SNMP 常量/模板与历史指标(snmp templates/constants、snmp_metrics_history、snmp_collect) - 中间件监控 Redis 采集与种子(middleware_monitor_redis/seed) - 站点探测 pkg(siteprobe) + 站点视图(site_view) 自动化任务 - cron 调度器(cronscheduler)、脚本运行器(scriptrunner)、系统任务(systask)及运行记录(cron_job_run、system_task) 审计与凭证 - 审计设置(audit_setting) + 历史清理(auditcleaner) 前端 - 监控页面(host/middleware/site/snmp)拆分为子模块并大屏化 - 告警中心多 Tab(规则/指标目录/通知策略/静默)、任务管理组件重构、Agent CLI Markdown 渲染 - 移除旧脚本卡片/详情/日志组件,统一为 ScriptTable/ScriptCodeEditor/TerminalOutput Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
1 parent
092d0e4b9e
commit
471353e3d7
190 files changed
+16640
-3484
No files matched your search
@@ -0,0 +1,205 @@
|
||||
// 站点拨测可观测分析 — 按协议聚合指标与异常事件 // Logan.Li
|
||||
import type { SiteResult, SiteTask } from '../helpers';
|
||||
import { fmtMs, fmtTime, normalizeProbeType } from '../helpers';
|
||||
|
||||
export interface ProbeEvent {
|
||||
id: string;
|
||||
at: string;
|
||||
timeLabel: string;
|
||||
severity: 'info' | 'warn' | 'error';
|
||||
title: string;
|
||||
detail?: string;
|
||||
}
|
||||
|
||||
export interface HttpObsSummary {
|
||||
expectedCode: number;
|
||||
okCount: number;
|
||||
err4xx: number;
|
||||
err5xx: number;
|
||||
otherErr: number;
|
||||
lastCode?: number;
|
||||
lastCodeTone: string;
|
||||
events: ProbeEvent[];
|
||||
chart: Array<{ time: string; code: number; tone: string; ok: boolean }>;
|
||||
}
|
||||
|
||||
export interface SslObsSummary {
|
||||
expiry?: string;
|
||||
issuer?: string;
|
||||
days?: number;
|
||||
daysTone: string;
|
||||
handshakeMs: number;
|
||||
events: ProbeEvent[];
|
||||
chart: Array<{ time: string; days: number }>;
|
||||
}
|
||||
|
||||
export interface LatencyObsSummary {
|
||||
avg: number;
|
||||
min: number;
|
||||
max: number;
|
||||
p95: number;
|
||||
jitter: number;
|
||||
spikeCount: number;
|
||||
events: ProbeEvent[];
|
||||
chart: Array<{ time: string; latency: number; failed: boolean; spike: boolean }>;
|
||||
}
|
||||
|
||||
export interface ConnectivityObsSummary {
|
||||
upRate: string;
|
||||
failCount: number;
|
||||
lastFailAt?: string;
|
||||
events: ProbeEvent[];
|
||||
chart: Array<{ time: string; up: number; failed: boolean }>;
|
||||
}
|
||||
|
||||
const tooltipOrder = (results: SiteResult[]) => [...results].reverse();
|
||||
|
||||
function httpCodeTone(code: number, expected: number): string {
|
||||
if (code === expected || (expected === 200 && code >= 200 && code < 300)) return 'dg-text-green';
|
||||
if (code >= 500) return 'dg-text-red';
|
||||
if (code >= 400) return 'dg-text-yellow';
|
||||
return 'dg-text-red';
|
||||
}
|
||||
|
||||
function pushEvent(events: ProbeEvent[], r: SiteResult, title: string, severity: ProbeEvent['severity'], detail?: string) {
|
||||
events.push({
|
||||
id: `${r.id}-${title}`,
|
||||
at: r.checked_at,
|
||||
timeLabel: fmtTime(r.checked_at),
|
||||
severity,
|
||||
title,
|
||||
detail,
|
||||
});
|
||||
}
|
||||
|
||||
export function analyzeHttpResults(results: SiteResult[], task: SiteTask): HttpObsSummary {
|
||||
const expected = task.expected_status_code || 200;
|
||||
const chart = tooltipOrder(results).map((r) => {
|
||||
const code = r.http_status_code ?? (r.status === 'success' ? expected : 0);
|
||||
const ok = r.status === 'success' && (code === expected || (expected === 200 && code >= 200 && code < 300));
|
||||
return { time: fmtTime(r.checked_at).slice(-5), code, tone: code > 0 ? httpCodeTone(code, expected) : 'dg-text-red', ok };
|
||||
});
|
||||
let okCount = 0;
|
||||
let err4xx = 0;
|
||||
let err5xx = 0;
|
||||
let otherErr = 0;
|
||||
const events: ProbeEvent[] = [];
|
||||
for (const r of results) {
|
||||
const code = r.http_status_code ?? 0;
|
||||
if (r.status === 'success' && (code === expected || (expected === 200 && code >= 200 && code < 300))) {
|
||||
okCount++;
|
||||
continue;
|
||||
}
|
||||
if (code >= 500) {
|
||||
err5xx++;
|
||||
pushEvent(events, r, `HTTP ${code}`, 'error', r.error_message || '服务端错误');
|
||||
} else if (code >= 400) {
|
||||
err4xx++;
|
||||
pushEvent(events, r, `HTTP ${code}`, 'warn', r.error_message || '客户端/鉴权错误');
|
||||
} else if (r.status === 'timeout') {
|
||||
otherErr++;
|
||||
pushEvent(events, r, '请求超时', 'error', r.error_message);
|
||||
} else {
|
||||
otherErr++;
|
||||
pushEvent(events, r, code > 0 ? `HTTP ${code}` : '请求失败', 'error', r.error_message);
|
||||
}
|
||||
}
|
||||
const latest = results[0];
|
||||
const lastCode = latest?.http_status_code;
|
||||
return {
|
||||
expectedCode: expected,
|
||||
okCount,
|
||||
err4xx,
|
||||
err5xx,
|
||||
otherErr,
|
||||
lastCode,
|
||||
lastCodeTone: lastCode ? httpCodeTone(lastCode, expected) : 'dg-text-red',
|
||||
events: events.slice(0, 8),
|
||||
chart,
|
||||
};
|
||||
}
|
||||
|
||||
export function analyzeSslResults(results: SiteResult[], task: SiteTask): SslObsSummary {
|
||||
const latest = results.find((r) => r.ssl_days_remaining != null) ?? results[0];
|
||||
const days = latest?.ssl_days_remaining ?? task.ssl_days_remaining;
|
||||
const expiry = latest?.ssl_cert_expiry?.slice(0, 10) ?? task.ssl_cert_expiry?.slice(0, 10);
|
||||
const issuer = latest?.ssl_cert_issuer;
|
||||
const events: ProbeEvent[] = [];
|
||||
for (const r of results) {
|
||||
if (r.status !== 'success') {
|
||||
pushEvent(events, r, 'TLS 握手失败', 'error', r.error_message);
|
||||
} else if (r.ssl_days_remaining != null && r.ssl_days_remaining < 30) {
|
||||
pushEvent(events, r, `证书剩余 ${r.ssl_days_remaining} 天`, r.ssl_days_remaining <= 7 ? 'error' : 'warn', expiry);
|
||||
}
|
||||
}
|
||||
const chart = tooltipOrder(results)
|
||||
.filter((r) => r.ssl_days_remaining != null)
|
||||
.map((r) => ({ time: fmtTime(r.checked_at).slice(-5), days: r.ssl_days_remaining as number }));
|
||||
const tone = days == null ? 'text-[var(--dg-text-muted)]' : days <= 7 ? 'dg-text-red' : days <= 30 ? 'dg-text-yellow' : 'dg-text-green';
|
||||
const handshakeMs = results.length
|
||||
? results.reduce((s, r) => s + (r.response_time || r.total_time || 0), 0) / results.length
|
||||
: 0;
|
||||
return { expiry, issuer, days, daysTone: tone, handshakeMs, events: events.slice(0, 8), chart };
|
||||
}
|
||||
|
||||
function analyzeLatencyResults(results: SiteResult[], label: string): LatencyObsSummary {
|
||||
const latencies = results.map((r) => r.response_time ?? r.total_time ?? 0).filter((v) => v > 0);
|
||||
const sorted = [...latencies].sort((a, b) => a - b);
|
||||
const avg = latencies.length ? latencies.reduce((a, b) => a + b, 0) / latencies.length : 0;
|
||||
const min = sorted[0] ?? 0;
|
||||
const max = sorted[sorted.length - 1] ?? 0;
|
||||
const p95 = sorted.length ? sorted[Math.floor(sorted.length * 0.95)] ?? max : 0;
|
||||
const jitter = max - min;
|
||||
const spikeThreshold = Math.max(avg * 1.8, avg + 50);
|
||||
const events: ProbeEvent[] = [];
|
||||
let spikeCount = 0;
|
||||
const chart = tooltipOrder(results).map((r) => {
|
||||
const latency = r.response_time ?? r.total_time ?? 0;
|
||||
const failed = r.status !== 'success';
|
||||
const spike = !failed && latency > spikeThreshold;
|
||||
if (failed) pushEvent(events, r, `${label}失败`, 'error', r.error_message || r.remote_ip);
|
||||
else if (spike) {
|
||||
spikeCount++;
|
||||
pushEvent(events, r, `${label}延迟波动`, 'warn', fmtMs(latency));
|
||||
}
|
||||
return { time: fmtTime(r.checked_at).slice(-5), latency, failed, spike };
|
||||
});
|
||||
return { avg, min, max, p95, jitter, spikeCount, events: events.slice(0, 8), chart };
|
||||
}
|
||||
|
||||
export function analyzePingResults(results: SiteResult[]): LatencyObsSummary {
|
||||
return analyzeLatencyResults(results, 'PING');
|
||||
}
|
||||
|
||||
export function analyzeDnsResults(results: SiteResult[]): LatencyObsSummary {
|
||||
return analyzeLatencyResults(results, 'DNS 解析');
|
||||
}
|
||||
|
||||
export function analyzeTcpResults(results: SiteResult[]): ConnectivityObsSummary {
|
||||
const successCount = results.filter((r) => r.status === 'success').length;
|
||||
const failCount = results.length - successCount;
|
||||
const upRate = results.length > 0 ? `${(successCount / results.length * 100).toFixed(1)}%` : '--';
|
||||
const events: ProbeEvent[] = [];
|
||||
let lastFailAt: string | undefined;
|
||||
const chart = tooltipOrder(results).map((r) => {
|
||||
const failed = r.status !== 'success';
|
||||
if (failed) {
|
||||
lastFailAt = r.checked_at;
|
||||
pushEvent(events, r, 'TCP 不通', 'error', r.error_message || '连接失败');
|
||||
}
|
||||
return { time: fmtTime(r.checked_at).slice(-5), up: failed ? 0 : 100, failed };
|
||||
});
|
||||
return { upRate, failCount, lastFailAt: lastFailAt ? fmtTime(lastFailAt) : undefined, events: events.slice(0, 8), chart };
|
||||
}
|
||||
|
||||
export function getProbeObsSummary(task: SiteTask, results: SiteResult[]) {
|
||||
const type = normalizeProbeType(task.type);
|
||||
switch (type) {
|
||||
case 'HTTP': return { type, http: analyzeHttpResults(results, task) } as const;
|
||||
case 'SSL': return { type, ssl: analyzeSslResults(results, task) } as const;
|
||||
case 'PING': return { type, latency: analyzePingResults(results) } as const;
|
||||
case 'DNS': return { type, latency: analyzeDnsResults(results) } as const;
|
||||
case 'TCP': return { type, tcp: analyzeTcpResults(results) } as const;
|
||||
default: return { type: 'HTTP' as const, http: analyzeHttpResults(results, task) };
|
||||
}
|
||||
}
|
||||
Reference in new issue
Block a user