OpenZFS on Linux and FreeBSD
Go to file
Brian Behlendorf 5f4004efc0 Fix vdev_queue_aggregate() deadlock
This deadlock may manifest itself in slightly different ways but
at the core it is caused by a memory allocation blocking on file-
system reclaim in the zio pipeline.  This is normally impossible
because zio_execute() disables filesystem reclaim by setting
PF_FSTRANS on the thread.  However, kmem cache allocations may
still indirectly block on file system reclaim while holding the
critical vq->vq_lock as shown below.

To resolve this issue zio_buf_alloc_flags() is introduced which
allocation flags to be passed.  This can then be used in
vdev_queue_aggregate() with KM_NOSLEEP when allocating the
aggregate IO buffer.  Since aggregating the IO is purely a
performance optimization we want this to either succeed or fail
quickly.  Trying too hard to allocate this memory under the
vq->vq_lock can negatively impact performance and result in
this deadlock.

* z_wr_iss
zio_vdev_io_start
  vdev_queue_io -> Takes vq->vq_lock
    vdev_queue_io_to_issue
      vdev_queue_aggregate
        zio_buf_alloc -> Waiting on spl_kmem_cache process

* z_wr_int
zio_vdev_io_done
  vdev_queue_io_done
    mutex_lock -> Waiting on vq->vq_lock held by z_wr_iss

* txg_sync
spa_sync
  dsl_pool_sync
    zio_wait -> Waiting on zio being handled by z_wr_int

* spl_kmem_cache
spl_cache_grow_work
  kv_alloc
    spl_vmalloc
      ...
      evict
        zpl_evict_inode
          zfs_inactive
            dmu_tx_wait
              txg_wait_open -> Waiting on txg_sync

Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Chunwei Chen <david.chen@osnexus.com>
Signed-off-by: Tim Chase <tim@chase2k.com>
Closes #3808
Closes #3867
2015-12-23 17:29:34 -08:00
cmd Honor xattr=sa dataset property 2015-09-19 13:32:34 -07:00
config Skip GPL-only symbols test when cross-compiling 2015-12-23 17:29:34 -08:00
contrib Init script fixes 2015-09-29 15:27:14 -07:00
etc zfs-import: Perform verbatim import using cache file 2015-10-13 14:33:49 -07:00
include Fix vdev_queue_aggregate() deadlock 2015-12-23 17:29:34 -08:00
lib Honor xattr=sa dataset property 2015-09-19 13:32:34 -07:00
man Make zio_taskq_batch_pct user configurable 2015-12-23 17:29:34 -08:00
module Fix vdev_queue_aggregate() deadlock 2015-12-23 17:29:34 -08:00
rpm Prepare to tag zfs-0.6.5.3 2015-10-13 15:35:23 -07:00
scripts Use truncate instead of fallocate in ziltest.sh 2015-07-13 11:02:59 -07:00
udev Support parallel build trees (VPATH builds) 2015-07-17 13:42:51 -07:00
.gitignore Ignore *.{deb,rpm,tar.gz} files in the top directory. 2013-04-24 16:18:59 -07:00
.gitmodules Add zimport.sh compatibility test script 2014-02-21 12:10:31 -08:00
AUTHORS Add a missing > to AUTHORS 2014-09-02 14:18:53 -07:00
COPYRIGHT Update ZED copyright boilerplate 2015-05-11 15:07:00 -07:00
DISCLAIMER Fix minor typos and update marketing copy. 2013-03-21 12:51:06 -07:00
META Prepare to tag zfs-0.6.5.3 2015-10-13 15:35:23 -07:00
Makefile.am Support parallel build trees (VPATH builds) 2015-07-17 13:42:51 -07:00
OPENSOLARIS.LICENSE Add CDDL license file 2008-12-01 14:49:34 -08:00
README.markdown Fix minor typos and update marketing copy. 2013-03-21 12:51:06 -07:00
autogen.sh build: do not call boilerplate ourself 2013-04-02 10:55:20 -07:00
configure.ac Move dracut directory to contrib 2015-07-09 13:59:37 -07:00
copy-builtin Consistent menuconfig name 2012-08-26 13:49:37 -07:00
zfs-script-config.sh.in Initial implementation of zed (ZFS Event Daemon) 2014-04-02 13:10:03 -07:00
zfs.release.in Move zfs.release generation to configure step 2012-07-12 12:22:51 -07:00

README.markdown

Native ZFS for Linux!

ZFS is an advanced file system and volume manager which was originally developed for Solaris and is now maintained by the Illumos community.

ZFS on Linux, which is also known as ZoL, is currently feature complete. It includes fully functional and stable SPA, DMU, ZVOL, and ZPL layers.

Full documentation for installing ZoL on your favorite Linux distribution can be found at: http://zfsonlinux.org