mm2_crawler: reduce number of threads and increase timeout

This reduce the number of threads used per category by one for each
category. mm-crawler02 sometimes has to OOM kill one of the crawlers and
by using less crawl threads the crawler should not OOM any more. This
needs to be monitored to find the optimal number of threads.

This also increases the timeout for the archive crawling from 4 hours to
5 hours.

Signed-off-by: Adrian Reber <adrian@lisas.de>
This commit is contained in:
Adrian Reber 2018-05-09 17:19:55 +02:00
parent 93e3b9f7b0
commit edf8b23f12
Failed to extract signature

View file

@ -20,16 +20,16 @@
# The timeout is 4 hours, but for each category.
# Category: 'Fedora Linux'; twice a day, 20 threads
0 */12 * * * mirrormanager [ "`hostname -s`" == "mm-crawler02" ] && sleep 6h; pkill -14 -f "^/usr/bin/python2 -s /usr/bin/mm2_crawler --category=Fedora Linux"; sleep 5m; pkill -9 -f "^/usr/bin/python2 -s /usr/bin/mm2_crawler --category=Fedora Linux"; /usr/bin/mm2_crawler --category="Fedora Linux" --threads 20 --timeout-minutes 240 `/usr/local/bin/run_crawler.sh 2` > /dev/null 2>&1
0 */12 * * * mirrormanager [ "`hostname -s`" == "mm-crawler02" ] && sleep 6h; pkill -14 -f "^/usr/bin/python2 -s /usr/bin/mm2_crawler --category=Fedora Linux"; sleep 5m; pkill -9 -f "^/usr/bin/python2 -s /usr/bin/mm2_crawler --category=Fedora Linux"; /usr/bin/mm2_crawler --category="Fedora Linux" --threads 19 --timeout-minutes 240 `/usr/local/bin/run_crawler.sh 2` > /dev/null 2>&1
# Category: 'Fedora Secondary Arches'; twice a day, 10 threads
0 3,9 * * * mirrormanager [ "`hostname -s`" == "mm-crawler02" ] && sleep 1h; pkill -14 -f "^/usr/bin/python2 -s /usr/bin/mm2_crawler --category=Fedora Secondary Arches"; sleep 5m; pkill -9 -f "^/usr/bin/python2 -s /usr/bin/mm2_crawler --category=Fedora Secondary Arches"; /usr/bin/mm2_crawler --category="Fedora Secondary Arches" --threads 10 --timeout-minutes 240 `/usr/local/bin/run_crawler.sh 2` > /dev/null 2>&1
0 3,9 * * * mirrormanager [ "`hostname -s`" == "mm-crawler02" ] && sleep 1h; pkill -14 -f "^/usr/bin/python2 -s /usr/bin/mm2_crawler --category=Fedora Secondary Arches"; sleep 5m; pkill -9 -f "^/usr/bin/python2 -s /usr/bin/mm2_crawler --category=Fedora Secondary Arches"; /usr/bin/mm2_crawler --category="Fedora Secondary Arches" --threads 9 --timeout-minutes 240 `/usr/local/bin/run_crawler.sh 2` > /dev/null 2>&1
# Category: 'Fedora EPEL'; four times a day, 20 threads
45 */6 * * * mirrormanager [ "`hostname -s`" == "mm-crawler02" ] && sleep 1h; pkill -14 -f "^/usr/bin/python2 -s /usr/bin/mm2_crawler --category=Fedora EPEL"; sleep 5m; pkill -9 -f "^/usr/bin/python2 -s /usr/bin/mm2_crawler --category=Fedora EPEL"; /usr/bin/mm2_crawler --category="Fedora EPEL" --threads 20 --timeout-minutes 240 `/usr/local/bin/run_crawler.sh 2` > /dev/null 2>&1
45 */6 * * * mirrormanager [ "`hostname -s`" == "mm-crawler02" ] && sleep 1h; pkill -14 -f "^/usr/bin/python2 -s /usr/bin/mm2_crawler --category=Fedora EPEL"; sleep 5m; pkill -9 -f "^/usr/bin/python2 -s /usr/bin/mm2_crawler --category=Fedora EPEL"; /usr/bin/mm2_crawler --category="Fedora EPEL" --threads 19 --timeout-minutes 240 `/usr/local/bin/run_crawler.sh 2` > /dev/null 2>&1
# Category: 'Fedora Archive'; once a day, 10 threads
0 2 * * * mirrormanager [ "`hostname -s`" == "mm-crawler02" ] && sleep 6h; pkill -14 -f "^/usr/bin/python2 -s /usr/bin/mm2_crawler --category=Fedora Archive"; sleep 5m; pkill -9 -f "^/usr/bin/python2 -s /usr/bin/mm2_crawler --category=Fedora Archive"; /usr/bin/mm2_crawler --category="Fedora Archive" --threads 10 --timeout-minutes 240 `/usr/local/bin/run_crawler.sh 2` > /dev/null 2>&1
0 2 * * * mirrormanager [ "`hostname -s`" == "mm-crawler02" ] && sleep 6h; pkill -14 -f "^/usr/bin/python2 -s /usr/bin/mm2_crawler --category=Fedora Archive"; sleep 5m; pkill -9 -f "^/usr/bin/python2 -s /usr/bin/mm2_crawler --category=Fedora Archive"; /usr/bin/mm2_crawler --category="Fedora Archive" --threads 9 --timeout-minutes 300 `/usr/local/bin/run_crawler.sh 2` > /dev/null 2>&1
# Category: 'Fedora Other'; once a day, 10 threads
0 14 * * * mirrormanager [ "`hostname -s`" == "mm-crawler02" ] && sleep 6h; pkill -14 -f "^/usr/bin/python2 -s /usr/bin/mm2_crawler --category=Fedora Other"; sleep 5m; pkill -9 -f "^/usr/bin/python2 -s /usr/bin/mm2_crawler --category=Fedora Other"; /usr/bin/mm2_crawler --category="Fedora Other" --threads 10 --timeout-minutes 240 `/usr/local/bin/run_crawler.sh 2` > /dev/null 2>&1
0 14 * * * mirrormanager [ "`hostname -s`" == "mm-crawler02" ] && sleep 6h; pkill -14 -f "^/usr/bin/python2 -s /usr/bin/mm2_crawler --category=Fedora Other"; sleep 5m; pkill -9 -f "^/usr/bin/python2 -s /usr/bin/mm2_crawler --category=Fedora Other"; /usr/bin/mm2_crawler --category="Fedora Other" --threads 9 --timeout-minutes 240 `/usr/local/bin/run_crawler.sh 2` > /dev/null 2>&1