Host freezes under 0.6.5.1, ubuntu vivid #3832
Milestone
Comments
|
@adrienkohlbecker this is a duplicate on #3652 and on the short list of things to be fixed in the next point release. As a short term workaround you can try setting |
|
Ah, good to know. I skimmed the list of issues and didn't think this was related to removing disks. I'll try the workaround, thanks! |
behlendorf
added a commit
that referenced
this issue
Sep 25, 2015
Commit b39c22b set the READ_SYNC and WRITE_SYNC flags for a bio based on the ZIO_PRIORITY_* flag passed in. This had the unnoticed side-effect of making the vdev_disk_io_start() synchronous for certain I/Os. This in turn resulted in vdev_disk_io_start() being able to re-dispatch zio's which would result in a RCU stalls when a disk was removed from the system. Additionally, this could negatively impact performance and explains the performance regressions reported in both #3829 and #3780. This patch resolves the issue by making the blocking behavior dependent on a 'wait' flag being passed rather than overloading the passed bio flags. Finally, the WRITE_SYNC and READ_SYNC behavior is restricted to non-rotational devices where there is no benefit to queuing to aggregate the I/O. Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Issue #3652 Issue #3780 Issue #3785 Issue #3817 Issue #3821 Issue #3829 Issue #3832 Issue #3870
|
Resolved by 5592404 which will be cherry-picked in to 0.6.5.2 release. |
behlendorf
added a commit
that referenced
this issue
Sep 30, 2015
Commit b39c22b set the READ_SYNC and WRITE_SYNC flags for a bio based on the ZIO_PRIORITY_* flag passed in. This had the unnoticed side-effect of making the vdev_disk_io_start() synchronous for certain I/Os. This in turn resulted in vdev_disk_io_start() being able to re-dispatch zio's which would result in a RCU stalls when a disk was removed from the system. Additionally, this could negatively impact performance and explains the performance regressions reported in both #3829 and #3780. This patch resolves the issue by making the blocking behavior dependent on a 'wait' flag being passed rather than overloading the passed bio flags. Finally, the WRITE_SYNC and READ_SYNC behavior is restricted to non-rotational devices where there is no benefit to queuing to aggregate the I/O. Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Issue #3652 Issue #3780 Issue #3785 Issue #3817 Issue #3821 Issue #3829 Issue #3832 Issue #3870
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hello,
I've updated my server last week, switching from Ubuntu 14.10 to 15.04, and from a custom 3.16 kernel to mainstream 3.19. My zfs version was subsequently updated to 0.6.5 from 0.6.3. This was an online upgrade, no reinstallation from scratch.
Since then, I'm getting intermittent lockups that completely freeze the system. It does not (until now) happen when the server is lightly used : only when I have a VM running and/or a docker container running.
In this case, I get around 30min to a couple hours of uptime before the host freezes and I have to force reset it.
I have updated to 0.6.5.1 yesterday, but it did not improve the problem.
I managed to take the following screenshots from the remote KVM, but that's all I have, since the display is usually sleeping when it happens, and there is nothing in syslog
This is a bit above my competencies but I'm willing to help with debug if needed.
Otherwise, is there a way for me to install 0.6.4 or 0.6.3 while this gets sorted out ? The packages have been removed from the ppa
Best,
The text was updated successfully, but these errors were encountered: