What is your kernel version ? On kernel >= 3.11 sysctl -w
"net.ipv4.tcp_window_scaling=0" seems to improve the situation a lot. It
also helped a lot to mitigate processes going (and sticking) in 'D' state.
Le 24/07/2014 22:08, Udo Lembke a écrit :
Hi again,
forget to say - I'm still on 0.72.2!
To get consistent RBD live snapshots, you may want to first freeze the
guest filesystem (ext4, btrfs, xfs) with a tool like [fsfreeze]. It will
basically flush the FS state to disk and blocking any future write
access while maintaining Read accesses.
[fsfreeze] http://manpages.courier-mta.org/
During on of tests, my test client painfully crashed with a couple of
mapped images. When it came back online I have not been able to rm
formerly mapped images as watchers were still registered.
Host A > rbd create test-image --size 10240
Host A > rbd map test-image
#
# after some time > 3
I had the same issue a couple of days ago. I fixed it by applying
pending patches at
https://git.kernel.org/cgit/linux/kernel/git/sage/ceph-client.git/?h=for-stable-3.10.24
According to recent mails, they should be included in next maintenance
linux release 3.10.26
On 01/09/14 17:44, Stephen
