0
0
mirror of https://github.com/PostHog/posthog.git synced 2024-12-01 12:21:02 +01:00
posthog/bin/docker-worker-celery
Karl-Aksel Puulmann bbd41ef04a
Use -Ofair for celery workers (#5063)
From https://medium.com/@taylorhughes/three-quick-tips-from-two-years-with-celery-c05ff9d7f9eb

> By default, preforking Celery workers distribute tasks to their worker processes as soon as they are received, regardless of whether the process is currently busy with other tasks.
> If you have a set of tasks that take varying amounts of time to complete — either deliberately or due to unpredictable network conditions, etc. — this will cause unexpected delays in total execution time for tasks in the queue.

This is 100% the case for us. This should "load balance" the tasks
better across workers.
2021-07-12 13:52:05 +03:00

83 lines
2.1 KiB
Bash
Executable File

#!/bin/bash
set -e
help () {
echo "$0 - start PostHog's Celery worker"
echo
echo "$0 [options]"
echo
echo "Options:"
echo " --help, -h show this brief help"
echo " --with-scheduler start RedBeat, the Celery scheduler (deprecates --with-beat)"
echo " --concurrency=<N> start N workers (overrides env var WEB_CONCURRENCY)"
echo
echo "Advanced Celery options (disabled by default):"
echo " --with-gossip start Celery gossip (useful for Prometheus)"
echo " --with-heartbeat start Celery internal heartbeat (normally not useful)"
echo " --with-mingle start Celery mingle (normally not useful)"
exit 0
}
with_scheduler=false
with_gossip=false
with_heartbeat=false
with_mingle=false
while test $# -gt 0; do
case "$1" in
-h|--help)
help
;;
--with-scheduler)
with_scheduler=true
shift
;;
--with-beat) # Deprecated since the name is too similar to "heartbeat"
echo "⚠️ Using docker-worker-celery with --with-beat. This argument is deprecated. Use --with-scheduler instead!"
with_scheduler=true
shift
;;
--with-gossip)
with_gossip=true
shift
;;
--with-heartbeat)
with_heartbeat=true
shift
;;
--with-mingle)
with_mingle=true
shift
;;
--concurrency*)
export WEB_CONCURRENCY=`echo $1 | sed -e 's/^[^=]*=//g'`
shift
;;
*)
break
;;
esac
done
if [ "$with_scheduler" == "true" ]; then
./bin/docker-worker-beat &
fi
FLAGS=()
FLAGS+=("-Ofair")
[ "$with_gossip" == "false" ] && FLAGS+=("--without-gossip")
[ "$with_mingle" == "false" ] && FLAGS+=("--without-mingle")
[ "$with_heartbeat" == "false" ] && FLAGS+=("--without-heartbeat")
# On Heroku $WEB_CONCURRENCY contains suggested number of forks per dyno type
# https://github.com/heroku/heroku-buildpack-python/blob/main/vendor/WEB_CONCURRENCY.sh
[[ -n "${WEB_CONCURRENCY}" ]] && FLAGS+=" --concurrency $WEB_CONCURRENCY"
echo
echo "celery -A posthog worker ${FLAGS[*]}"
echo
celery -A posthog worker ${FLAGS[*]}
# Stop the beat!
trap 'kill $(jobs -p)' EXIT