Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Expose paused and retired workers separately in prometheus #8613

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Expose paused and retired workers separately in prometheus #8613

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
bcc262c
Expose paused and retired workers separately in prometheus
phofl Apr 11, 2024
97675e9
Merge branch 'main' into prometheus_paused_workers
phofl Apr 11, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
10 changes: 10 additions & 0 deletions distributed/http/scheduler/prometheus/core.py
View file
Open in desktop
Expand Up @@ -7,6 +7,7 @@
import toolz
from prometheus_client.core import CounterMetricFamily, GaugeMetricFamily

from distributed.core import Status
from distributed.http.prometheus import PrometheusCollector
from distributed.http.scheduler.prometheus.semaphore import SemaphoreMetricCollector
from distributed.http.scheduler.prometheus.stealing import WorkStealingMetricCollector
Expand Down Expand Up @@ -50,6 +51,15 @@ def collect(self) -> Iterator[GaugeMetricFamily | CounterMetricFamily]:
worker_states.add_metric(
["paused_or_retiring"], len(self.server.workers) - len(self.server.running)
)
paused_workers = len(
[w for w in self.server.workers.values() if w.status == Status.paused]
)
worker_states.add_metric(["paused"], paused_workers)
worker_states.add_metric(
["retiring"],
len(self.server.workers) - paused_workers - len(self.server.running),
)

yield worker_states

if self.server.monitor.monitor_gil_contention:
Expand Down
20 changes: 20 additions & 0 deletions distributed/http/scheduler/tests/test_scheduler_http.py
View file
Open in desktop
Expand Up @@ -282,6 +282,8 @@ async def fetch_metrics():
"partially_saturated": 0,
"saturated": 0,
"paused_or_retiring": 0,
"paused": 0,
"retiring": 0,
}

ev = Event()
Expand All @@ -292,6 +294,8 @@ async def fetch_metrics():
"partially_saturated": 1,
"saturated": 0,
"paused_or_retiring": 0,
"paused": 0,
"retiring": 0,
}

y = c.submit(lambda ev: ev.wait(), ev, key="y", workers=[a.address])
Expand All @@ -304,6 +308,8 @@ async def fetch_metrics():
"partially_saturated": 0,
"saturated": 1,
"paused_or_retiring": 0,
"paused": 0,
"retiring": 0,
}

a.monitor.get_process_memory = lambda: 2**40
Expand All @@ -314,8 +320,22 @@ async def fetch_metrics():
"partially_saturated": 0,
"saturated": 0,
"paused_or_retiring": 1,
"paused": 1,
"retiring": 0,
}

sa.status = Status.stopping
while sa.status != Status.stopping:
await asyncio.sleep(0.01)

assert await fetch_metrics() == {
"idle": 1,
"partially_saturated": 0,
"saturated": 0,
"paused_or_retiring": 1,
"paused": 0,
"retiring": 1,
}
await ev.set()


Expand Down