Hang on USB disconnect #3817
Milestone
Comments
|
ZFS/SPL versions are close to 0.6.5 -- ZFS 0.6.5 - 1 commit .. 0.6.5.1 |
|
Perhaps somewhat related to #3785 system freezes when zfs is waiting for disks to spin up |
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
|
This symptom (hang on USB removal) appears to be back in 0.7.1. Again, zpool showed the device as ONLINE. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
A single USB pendrive pool. When the pendrive is disconnected, ZFS doesn't notice it (shows it as
ONLINEdespite the device not existing in/dev), and when something tries to access it, the system hangs.Backtraces and dmesg after triggering a panic with SysRq (the pendrive is
F0394B5D):https://bpaste.net/show/47a9268adc7b (3) - the drive was deliberately pulled out, and the hang happened when MPD tried to access the next song (a bit different than the others, probably because I used
sysrq-uimmediately beforesysrq-c)https://bpaste.net/show/504b0e6caf37 (2)
https://bpaste.net/show/0ea0fabc4a3b (1)
In (1) and (2) a disconnect and reconnect is visible some time before the hang.
In all 3 instances the ZFS processes hang when trying to access the pool.
Funtoo, linux 4.0.9-aufs with BFS, BFQ, UKSM and TuxOnIce patches.
The text was updated successfully, but these errors were encountered: