Comment #19 on issue 375 by [email protected]: Accept4 on FreeBSD 10 -
sockets stuck in CLOSE
https://code.google.com/p/memcached/issues/detail?id=375
We tested it on 1.4.13 on FreeBSD 9 -> no problem.
Same system, 1.4.20 + lib event 1.x -> stuck
Same system, 1.4.20 + lib event 2.x -> still running after a couple of hours
What I did see today (FreeBSD 9, 1.4.20, libevent 2) is the following
behavior:
- CLOSE_WAIT is 0, then suddenly rising to high numbers in a short time
- In that time the client shows a lot of timeouts
- The client pauses for a short time -> CLOSE_WAIT cleans up and everything
is running as before
On FreeBSD 10 the CLOSE_WAIT goes up and down all the time and the client
never stops for such a long time. So there IS a difference in the way the
two systems are handling connections.
I did not run the test on a -c 256 server as the FreeBSD 9 test is still
running.
--
You received this message because this project is configured to send all
issue notifications to this address.
You may adjust your notification preferences at:
https://code.google.com/hosting/settings
--
---
You received this message because you are subscribed to the Google Groups "memcached" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
For more options, visit https://groups.google.com/d/optout.
