perf: 修复 Agent 校验 CPU 热点并实现指标分层聚合与频率下发
CPU 根因:每个 Agent 请求都做一次 bcrypt 校验(实测 72ms), 30 台主机 18 req/s × 72ms ≈ 1.35 核,实测容器 CPU 135%。 - agentauth: 校验结果按 Token 哈希缓存(TTL 5min,轮换即失效), last_used_at 写入按 60s 节流。实测 CPU 135% → 1.6%,请求延迟 103ms → 1.6ms - metricagg: 新增后台逐级降采样聚合 raw→1m/5m→1h→6h/1d,取代前端手动触发 - metrics_aggregate: 补 uniq_metric_agg 唯一索引(原 idx_agg 非唯一导致 upsert 插重复行) - agent 合并配置接口 GET /agent/config:一次返回任务+探针+端口策略+频率, 配置轮询 5s→30s;服务端可下发 report_interval,Agent 热更新 ticker 无需重装 - retention: agent_reports 保留期 7d→1d(趋势由聚合表承担) - redis: 增加 maxmemory 512mb + volatile-lru - fix(upgrade): 升级脚本改为 fail-fast,修复下载失败仍报 UPGRADE_OK 的静默谎报 // Logan.Li
This commit is contained in:
1 parent
93abf81e40
commit
59320aa410
23 files changed
+902
-29
No files matched your search
@@ -19,7 +19,6 @@ type agentStaticPaths struct {
|
||||
var agentBinaryFiles = map[string]string{
|
||||
"linux-amd64": "aiops-agent-linux-amd64",
|
||||
"linux-arm64": "aiops-agent-linux-arm64",
|
||||
"darwin-arm64": "aiops-agent-darwin-arm64",
|
||||
"windows-amd64": "aiops-agent-windows-amd64.exe",
|
||||
}
|
||||
|
||||
|
||||
@@ -886,6 +886,9 @@ func Register(r *gin.Engine, db *gorm.DB, log *zap.Logger, cfg *config.Config, c
|
||||
agentGroup.GET("/health-probes/config", agentHandler.GetHealthProbesForAgent)
|
||||
// 端口策略:Agent 拉取本机端口过滤策略。
|
||||
agentGroup.GET("/port-policy", agentHandler.GetPortPolicyForAgent)
|
||||
// 合并配置:一次返回任务 + 探针 + 端口策略 + 采集频率,
|
||||
// 取代原先每 5 秒分别拉取上面三个接口的做法。 // Logan.Li
|
||||
agentGroup.GET("/config", agentHandler.GetAgentConfig)
|
||||
}
|
||||
// Agent 数据查询 + 任务管理(需要 JWT)
|
||||
agentQuery := authorized.Group("/agent")
|
||||
@@ -918,6 +921,10 @@ func Register(r *gin.Engine, db *gorm.DB, log *zap.Logger, cfg *config.Config, c
|
||||
agentQuery.POST("/batch-uninstall", agentInstallHandler.BatchUninstallAgent)
|
||||
agentQuery.POST("/batch-upgrade", agentInstallHandler.BatchUpgradeAgent)
|
||||
|
||||
// 采集策略(平台下发上报/轮询频率,Agent 热更新无需重装)
|
||||
agentQuery.GET("/settings", agentHandler.ListAgentSettings)
|
||||
agentQuery.PUT("/settings", agentHandler.SaveAgentSetting)
|
||||
|
||||
// 健康探针管理(CRUD)
|
||||
agentQuery.GET("/health-probes", agentHandler.ListHealthProbes)
|
||||
agentQuery.POST("/health-probes", agentHandler.CreateHealthProbe)
|
||||
|
||||
Reference in new issue
Block a user