feat: record launch latency in statistics for start-only jobs
StartOnly jobs previously forced DurationMS to 0 because GoSentry does not wait for the process to exit, leaving the Statistics line stuck at "last 0 ms, avg 0 ms". The runner already measures launch latency (time to spawn the process) for the History detail; this now returns that value as the run duration so the existing duration-driven stats pipeline folds it into last/avg/max. Sub-millisecond launches still round to 0 and are excluded from the average, matching prior behavior. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
@@ -89,8 +89,9 @@ flowchart LR
|
|||||||
`runner.RunJob` builds the platform-specific invocation, executes the
|
`runner.RunJob` builds the platform-specific invocation, executes the
|
||||||
command through the platform shell, captures stdout and stderr, writes one
|
command through the platform shell, captures stdout and stderr, writes one
|
||||||
timestamped `.log` file, and returns a `domain.RunRecord` containing
|
timestamped `.log` file, and returns a `domain.RunRecord` containing
|
||||||
`DurationMS` (wall-clock milliseconds from start to finish; 0 for
|
`DurationMS` (wall-clock milliseconds from start to finish; for `StartOnly`
|
||||||
`StartOnly` fire-and-forget jobs).
|
fire-and-forget jobs it measures launch latency — the time to spawn the
|
||||||
|
process — since there is no exit to wait for).
|
||||||
|
|
||||||
6. History update:
|
6. History update:
|
||||||
When a run goroutine completes, `Service` updates the job's runtime
|
When a run goroutine completes, `Service` updates the job's runtime
|
||||||
@@ -132,7 +133,7 @@ in flight increments `JobRuntime.PendingRuns`. When the current run finishes,
|
|||||||
|-------|---------|
|
|-------|---------|
|
||||||
| `RunCount` | total runs recorded |
|
| `RunCount` | total runs recorded |
|
||||||
| `FailCount` | runs that exited non-zero |
|
| `FailCount` | runs that exited non-zero |
|
||||||
| `LastDurationMS` | wall-clock time of the most recent run |
|
| `LastDurationMS` | wall-clock time of the most recent run (launch latency for `StartOnly`) |
|
||||||
| `AvgDurationMS` | mean over all runs with a recorded duration |
|
| `AvgDurationMS` | mean over all runs with a recorded duration |
|
||||||
| `MaxDurationMS` | longest recorded run |
|
| `MaxDurationMS` | longest recorded run |
|
||||||
|
|
||||||
|
|||||||
@@ -2,6 +2,14 @@
|
|||||||
|
|
||||||
All notable GoSentry changes are recorded in this file.
|
All notable GoSentry changes are recorded in this file.
|
||||||
|
|
||||||
|
## Unreleased
|
||||||
|
|
||||||
|
**Statistics:**
|
||||||
|
- `StartOnly` jobs now record launch latency (time to spawn the process) as the
|
||||||
|
run duration instead of a hard-coded `0`, so the Statistics line shows a real
|
||||||
|
last/avg/max for fire-and-forget jobs. Sub-millisecond launches still round to
|
||||||
|
0 and are excluded from the average, as before.
|
||||||
|
|
||||||
## 0.11.3 - 2026-06-29
|
## 0.11.3 - 2026-06-29
|
||||||
|
|
||||||
**Reliability fixes from an internal code review: safer runs, a real overlap
|
**Reliability fixes from an internal code review: safer runs, a real overlap
|
||||||
|
|||||||
@@ -32,7 +32,9 @@ type JobRuntime struct {
|
|||||||
AvgDurationMS int64
|
AvgDurationMS int64
|
||||||
MaxDurationMS int64
|
MaxDurationMS int64
|
||||||
// TimedRunCount is the number of runs that contributed to AvgDurationMS.
|
// TimedRunCount is the number of runs that contributed to AvgDurationMS.
|
||||||
// StartOnly and legacy duration-less runs increment RunCount but not this.
|
// Runs with no recorded duration (legacy logs, or sub-millisecond StartOnly
|
||||||
|
// launches that round to 0) increment RunCount but not this. StartOnly runs
|
||||||
|
// otherwise contribute their launch latency.
|
||||||
TimedRunCount int
|
TimedRunCount int
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
@@ -30,9 +30,9 @@ func RunJob(ctx context.Context, job *domain.Job, trigger string, logsDir string
|
|||||||
var durationMS int64
|
var durationMS int64
|
||||||
if job.StartOnly {
|
if job.StartOnly {
|
||||||
invocation := jobInvocation(ctx, *job)
|
invocation := jobInvocation(ctx, *job)
|
||||||
state, detail, output = startJobOnly(invocation, *job, started)
|
// StartOnly jobs don't wait for process exit, so the duration measures
|
||||||
// StartOnly jobs don't wait for process exit, so no meaningful duration.
|
// launch latency (time to spawn the process) rather than run time.
|
||||||
durationMS = 0
|
state, detail, output, durationMS = startJobOnly(invocation, *job, started)
|
||||||
} else {
|
} else {
|
||||||
var stdoutBuf strings.Builder
|
var stdoutBuf strings.Builder
|
||||||
var stderrBuf strings.Builder
|
var stderrBuf strings.Builder
|
||||||
@@ -72,21 +72,22 @@ func RunJob(ctx context.Context, job *domain.Job, trigger string, logsDir string
|
|||||||
}, logErr
|
}, logErr
|
||||||
}
|
}
|
||||||
|
|
||||||
func startJobOnly(invocation commandInvocation, job domain.Job, started time.Time) (string, string, string) {
|
func startJobOnly(invocation commandInvocation, job domain.Job, started time.Time) (string, string, string, int64) {
|
||||||
command := invocation.command
|
command := invocation.command
|
||||||
if invocation.hideWindow {
|
if invocation.hideWindow {
|
||||||
winproc.ConfigureHiddenWindow(command)
|
winproc.ConfigureHiddenWindow(command)
|
||||||
}
|
}
|
||||||
err := command.Start()
|
err := command.Start()
|
||||||
duration := time.Since(started).Round(time.Millisecond)
|
duration := time.Since(started).Round(time.Millisecond)
|
||||||
|
durationMS := duration.Milliseconds()
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return "Failed", fmt.Sprintf("%T: %v", err, err), startOnlyOutput(job, 0)
|
return "Failed", fmt.Sprintf("%T: %v", err, err), startOnlyOutput(job, 0), durationMS
|
||||||
}
|
}
|
||||||
pid := command.Process.Pid
|
pid := command.Process.Pid
|
||||||
if releaseErr := command.Process.Release(); releaseErr != nil {
|
if releaseErr := command.Process.Release(); releaseErr != nil {
|
||||||
return "Failed", fmt.Sprintf("process started with pid %d, but release failed: %T: %v", pid, releaseErr, releaseErr), startOnlyOutput(job, pid)
|
return "Failed", fmt.Sprintf("process started with pid %d, but release failed: %T: %v", pid, releaseErr, releaseErr), startOnlyOutput(job, pid), durationMS
|
||||||
}
|
}
|
||||||
return "OK", fmt.Sprintf("Started in %s (pid %d); not waiting for process exit", duration, pid), startOnlyOutput(job, pid)
|
return "OK", fmt.Sprintf("Started in %s (pid %d); not waiting for process exit", duration, pid), startOnlyOutput(job, pid), durationMS
|
||||||
}
|
}
|
||||||
|
|
||||||
func startOnlyOutput(job domain.Job, pid int) string {
|
func startOnlyOutput(job domain.Job, pid int) string {
|
||||||
|
|||||||
Reference in New Issue
Block a user