OpenZFS on Linux and FreeBSD
Go to file
Brian Behlendorf 3b9fd93d0b Fix zsb->z_hold_mtx deadlock
The zfs_znode_hold_enter() / zfs_znode_hold_exit() functions are used to
serialize access to a znode and its SA buffer while the object is being
created or destroyed.  This kind of locking would normally reside in the
znode itself but in this case that's impossible because the znode and SA
buffer may not yet exist.  Therefore the locking is handled externally
with an array of mutexs and AVLs trees which contain per-object locks.

In zfs_znode_hold_enter() a per-object lock is created as needed, inserted
in to the correct AVL tree and finally the per-object lock is held.  In
zfs_znode_hold_exit() the process is reversed.  The per-object lock is
released, removed from the AVL tree and destroyed if there are no waiters.

This scheme has two important properties:

1) No memory allocations are performed while holding one of the z_hold_locks.
   This ensures evict(), which can be called from direct memory reclaim, will
   never block waiting on a z_hold_locks which just happens to have hashed
   to the same index.

2) All locks used to serialize access to an object are per-object and never
   shared.  This minimizes lock contention without creating a large number
   of dedicated locks.

On the downside it does require znode_lock_t structures to be frequently
allocated and freed.  However, because these are backed by a kmem cache
and very short lived this cost is minimal.

Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #4106
2016-01-29 09:52:12 -08:00
cmd Update arcstat.py to remove deprecated rmis reference. 2015-12-23 17:29:34 -08:00
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 zsb->z_hold_mtx deadlock 2016-01-29 09:52:12 -08:00
lib sysmacros: Make P2ROUNDUP not trigger int overflow 2015-12-23 17:29:35 -08:00
man Make zio_taskq_batch_pct user configurable 2015-12-23 17:29:34 -08:00
module Fix zsb->z_hold_mtx deadlock 2016-01-29 09:52:12 -08:00
rpm Prepare to tag zfs-0.6.5.4 2016-01-08 16:08:18 -08:00
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-0.6.5.4 2016-01-08 16:08:18 -08:00
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
TEST Follow 0/-E convention for module load errors 2015-12-23 17:29:35 -08:00
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 Fix --enable-linux-builtin 2015-12-23 17:29:34 -08:00
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