Lemmy Server Performance
lemmy_server uses the Diesel ORM that automatically generates SQL statements. There are serious performance problems in June and July 2023 preventing Lemmy from scaling. Topics include caching, PostgreSQL extensions for troubleshooting, Client/Server Code/SQL Data/server operator apps/sever operator API (performance and storage monitoring), etc.
Here's how you can profile the lemmy server cpu usage with perf (a standard linux tool):
Run this to record 10 s of CPU samples:
perf record -p $(pidof lemmy_server) --call-graph=lbr -a -- sleep 10
Then run this to show the output perf report.
Screenshot example:
Post your result here. There might be something obvious causing high usage.
Thank you for sharing. Storage I/O tips?
The default Docker install, last time I looked IIRC, has rust logging cranked really high.
bcc-tools.