Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 8 additions & 4 deletions results/stall.json
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,8 @@
"summary": {
"runs": 3,
"fast_burn_firing_after_s_median": 60.549,
"fast_burn_resolved_after_resume_s_median": 27.77,
"fast_burn_resolved_after_resume_s_median": 45.33,
"fast_burn_resolved_after_jobs_running_s_median": 27.77,
"jobs_running_after_resume_s_median": 18.724,
"all_exact": false
},
Expand All @@ -18,7 +19,8 @@
"fast_burn_pending_after_s": 59.188616037368774,
"fast_burn_firing_after_s": 59.388949155807495,
"jobs_running_after_resume_s": 34.94162583351135,
"fast_burn_resolved_after_resume_s": 9.206732034683228,
"fast_burn_resolved_after_jobs_running_s": 9.206732034683228,
"fast_burn_resolved_after_resume_s": 44.15,
"error_ratio_5m_at_resolve": 0.5423728813559322,
"slow_burn_state_at_end": "inactive",
"exact": false,
Expand Down Expand Up @@ -123,7 +125,8 @@
"fast_burn_pending_after_s": 61.62715005874634,
"fast_burn_firing_after_s": 61.79443311691284,
"jobs_running_after_resume_s": 18.72392702102661,
"fast_burn_resolved_after_resume_s": 27.769928216934204,
"fast_burn_resolved_after_jobs_running_s": 27.769928216934204,
"fast_burn_resolved_after_resume_s": 46.49,
"error_ratio_5m_at_resolve": 0.5423728813559322,
"slow_burn_state_at_end": "inactive",
"exact": false,
Expand Down Expand Up @@ -228,7 +231,8 @@
"fast_burn_pending_after_s": 60.38098216056824,
"fast_burn_firing_after_s": 60.54856204986572,
"jobs_running_after_resume_s": 11.509905338287354,
"fast_burn_resolved_after_resume_s": 33.82449293136597,
"fast_burn_resolved_after_jobs_running_s": 33.82449293136597,
"fast_burn_resolved_after_resume_s": 45.33,
"error_ratio_5m_at_resolve": 0.5423728813559322,
"slow_burn_state_at_end": "inactive",
"exact": false,
Expand Down
8 changes: 7 additions & 1 deletion scripts/measure.py
Original file line number Diff line number Diff line change
Expand Up @@ -396,15 +396,18 @@ def exp_stall(runs: int, rate: int, hold: int) -> None:
t_resume = time.time()
sh(*COMPOSE, "unpause", *tms)
recovered = wait_until(jobs_healthy, 300, 0.5)
# Starts when the jobs are healthy again, not at the unpause.
resolved = wait_until(lambda: "FreshnessBudgetFastBurn" not in alerts(), 600, 1)
since_resume = round(time.time() - t_resume, 2) if resolved is not None else None
burn5m = prom("sp:freshness_error_ratio:rate5m")
g.join()
rec = reconcile(run_id, wait=300)
out.append({
"paused_s": round(t_resume - t_pause, 1),
"fast_burn_pending_after_s": pending, "fast_burn_firing_after_s": fired_at,
"jobs_running_after_resume_s": recovered,
"fast_burn_resolved_after_resume_s": resolved,
"fast_burn_resolved_after_jobs_running_s": resolved,
"fast_burn_resolved_after_resume_s": since_resume,
"error_ratio_5m_at_resolve": burn5m,
"slow_burn_state_at_end": alerts().get("FreshnessBudgetSlowBurn", "inactive"),
"exact": rec["exact"], "layers": layers_exact(rec), "reconcile": rec,
Expand All @@ -416,6 +419,9 @@ def exp_stall(runs: int, rate: int, hold: int) -> None:
"fast_burn_resolved_after_resume_s_median": med(
[r["fast_burn_resolved_after_resume_s"] for r in out]
),
"fast_burn_resolved_after_jobs_running_s_median": med(
[r["fast_burn_resolved_after_jobs_running_s"] for r in out]
),
"jobs_running_after_resume_s_median": med([r["jobs_running_after_resume_s"] for r in out]),
"all_exact": all(r["exact"] for r in out),
}
Expand Down
Loading