summaryrefslogtreecommitdiff
path: root/cmd/dtailhealth
diff options
context:
space:
mode:
authorPaul Buetow <paul@buetow.org>2026-07-22 23:51:18 +0300
committerPaul Buetow <paul@buetow.org>2026-07-22 23:51:18 +0300
commit849951be1d1a7ee9f9302006ccb187bf5b4e36f3 (patch)
tree496c924a03a9ea6212e29bb4699e268066ebad81 /cmd/dtailhealth
parentbf78b3abffee6d49c08ca2980156afc455994969 (diff)
feat: DTail fork — server/client feature development
Squashed development of the snonux/dtail fork's product code (internal/, cmd/) since diverging from mimecast/dtail. Major areas: - Read/output path: the former "turbo" channel-less path is now the single, default server-side read/output path for cat/grep/tail and MapReduce; the old channel-based path and its config/env toggles were removed. - MapReduce: single aggregate implementation (server + serverless) fed directly by a processor pipeline, with input-exhausted finalization via the shutdown coordinator; high-concurrency and data-race fixes. - Journal source reads (journal:unit.service) via journalctl, Linux-gated behind a journal-v1 capability. - Auth-key fast reconnect: in-memory per-user public-key cache with TTL/max-keys, registered over an authenticated session (AUTHKEY), checked before authorized_keys. - Interactive query reload (--interactive-query) with SESSION START/UPDATE generation boundaries and capability negotiation. - Client-side deadlines: --timeout / --shutdownAfter as context deadlines; follow shutdown handling. - Client logging: diagnostics-only daily log by default, opt-in payload tee via --log-payload. - Numerous correctness fixes (buffer-pool double-recycle races, EOF-sentinel leaks, glob-expansion cap, TOCTOU in CSV parsing) with accompanying unit tests. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Diffstat (limited to 'cmd/dtailhealth')
-rw-r--r--cmd/dtailhealth/main.go44
1 files changed, 33 insertions, 11 deletions
diff --git a/cmd/dtailhealth/main.go b/cmd/dtailhealth/main.go
index a0ca84e..33e84db 100644
--- a/cmd/dtailhealth/main.go
+++ b/cmd/dtailhealth/main.go
@@ -3,13 +3,12 @@ package main
import (
"context"
"flag"
+ "fmt"
"os"
"sync"
+ "time"
- "net/http"
- _ "net/http"
- _ "net/http/pprof"
-
+ "github.com/mimecast/dtail/internal/cli"
"github.com/mimecast/dtail/internal/clients"
"github.com/mimecast/dtail/internal/config"
"github.com/mimecast/dtail/internal/io/dlog"
@@ -28,11 +27,12 @@ func main() {
flag.StringVar(&args.Logger, "logger", config.DefaultHealthCheckLogger, "Logger name")
flag.StringVar(&args.LogLevel, "logLevel", "none", "Log level")
flag.StringVar(&args.ServersStr, "server", "", "Remote server to connect")
+ flag.BoolVar(&args.NoAuthKey, "no-auth-key", false, "Disable auth-key fast reconnect feature")
flag.StringVar(&pprof, "pprof", "", "Start PProf server this address")
flag.Parse()
if displayVersion {
- version.PrintAndExit()
+ version.PrintAndExit(false)
}
config.Setup(source.HealthCheck, &args, flag.Args())
@@ -43,13 +43,35 @@ func main() {
wg.Add(1)
dlog.Start(ctx, &wg, source.HealthCheck)
+ var pprofServer *cli.PProfServer
if pprof != "" {
- dlog.Client.Info("Starting PProf", pprof)
- go func() {
- panic(http.ListenAndServe(pprof, nil))
- }()
+ pprofServer, pprofErr := cli.NewPProfServer(pprof)
+ if pprofErr != nil {
+ dlog.Client.Error("Unable to start PProf", pprofErr)
+ } else {
+ dlog.Client.Info("Starting PProf", pprofServer.Address())
+ pprofServer.Start(nil)
+ }
+ }
+
+ healthClient, err := clients.NewHealthClient(args)
+ status := 0
+ if err != nil {
+ fmt.Fprintf(os.Stderr, "CRITICAL: unable to create dtailhealth client: %v\n", err)
+ status = 2
+ } else {
+ status = healthClient.Start(ctx, signal.NoCh(ctx))
+ }
+
+ if pprofServer != nil {
+ shutdownCtx, shutdownCancel := context.WithTimeout(context.Background(), 5*time.Second)
+ if err := pprofServer.Shutdown(shutdownCtx); err != nil {
+ dlog.Client.Error("Unable to stop PProf", err)
+ }
+ shutdownCancel()
}
- healthClient, _ := clients.NewHealthClient(args)
- os.Exit(healthClient.Start(ctx, signal.NoCh(ctx)))
+ cancel()
+ wg.Wait()
+ os.Exit(status)
}