linux-stable/fs
Filipe Manana 176840b3aa Btrfs: more efficient btrfs_drop_extent_cache
While droping extent map structures from the extent cache that cover our
target range, we would remove each extent map structure from the red black
tree and then add either 1 or 2 new extent map structures if the former
extent map covered sections outside our target range.

This change simply attempts to replace the existing extent map structure
with a new one that covers the subsection we're not interested in, instead
of doing a red black remove operation followed by an insertion operation.

The number of elements in an inode's extent map tree can get very high for large
files under random writes. For example, while running the following test:

    sysbench --test=fileio --file-num=1 --file-total-size=10G \
        --file-test-mode=rndrw --num-threads=32 --file-block-size=32768 \
        --max-requests=500000 --file-rw-ratio=2 [prepare|run]

I captured the following histogram capturing the number of extent_map items
in the red black tree while that test was running:

    Count: 122462
    Range:  1.000 - 172231.000; Mean: 96415.831; Median: 101855.000; Stddev: 49700.981
    Percentiles:  90th: 160120.000; 95th: 166335.000; 99th: 171070.000
       1.000 -    5.231:   452 |
       5.231 -  187.392:    87 |
     187.392 -  585.911:   206 |
     585.911 - 1827.438:   623 |
    1827.438 - 5695.245:  1962 #
    5695.245 - 17744.861:  6204 ####
   17744.861 - 55283.764: 21115 ############
   55283.764 - 172231.000: 91813 #####################################################

Benchmark:

    sysbench --test=fileio --file-num=1 --file-total-size=10G --file-test-mode=rndwr \
        --num-threads=64 --file-block-size=32768 --max-requests=0 --max-time=60 \
        --file-io-mode=sync --file-fsync-freq=0 [prepare|run]

Before this change: 122.1Mb/sec
After this change:  125.07Mb/sec
(averages of 5 test runs)

Test machine: quad core intel i5-3570K, 32Gb of ram, SSD

Signed-off-by: Filipe David Borba Manana <fdmanana@gmail.com>
Signed-off-by: Josef Bacik <jbacik@fb.com>
2014-03-10 15:16:57 -04:00
..
9p consolidate simple ->d_delete() instances 2013-11-15 22:04:17 -05:00
adfs
affs remove obsolete references to powertweak 2013-11-27 20:34:32 -08:00
afs
autofs4
befs
bfs
btrfs Btrfs: more efficient btrfs_drop_extent_cache 2014-03-10 15:16:57 -04:00
cachefiles Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2013-11-13 15:34:18 +09:00
ceph ceph: Avoid data inconsistency due to d-cache aliasing in readpage() 2013-12-13 09:11:38 -08:00
cifs cifs: set FILE_CREATED 2013-12-27 15:14:45 -06:00
coda
configfs configfs: fix race between dentry put and lookup 2013-11-21 16:42:27 -08:00
cramfs cramfs: mark as obsolete 2013-11-13 12:09:12 +09:00
debugfs debugfs: use list_next_entry() in debugfs_remove_recursive() 2013-11-13 12:09:24 +09:00
devpts devpts: plug the memory leak in kill_sb 2013-11-13 12:09:36 +09:00
dlm genetlink: only pass array to genl_register_family_with_ops() 2013-11-19 16:39:05 -05:00
ecryptfs Quiet static checkers by removing unneeded conditionals 2013-11-22 10:58:14 -08:00
efivarfs consolidate simple ->d_delete() instances 2013-11-15 22:04:17 -05:00
efs
exofs
exportfs exportfs: fix quadratic behavior in filehandle lookup 2013-11-09 00:16:38 -05:00
ext2 ext2: Fix oops in ext2_get_block() called from ext2_quota_write() 2013-12-04 12:26:51 +01:00
ext3 Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs 2013-11-13 15:25:47 +09:00
ext4 ext4: fix bigalloc regression 2014-01-06 14:00:23 -05:00
f2fs f2fs: issue more large discard command 2013-11-11 09:36:32 +09:00
fat
freevxfs
fscache Merge branch 'for-3.13/core' of git://git.kernel.dk/linux-block 2013-11-14 12:08:14 +09:00
fuse Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2013-11-13 15:34:18 +09:00
gfs2 GFS2: Fix unsafe dereference in dump_holder() 2014-01-02 12:18:04 +00:00
hfs fs/hfs/btree.h: remove duplicate defines 2013-11-13 12:09:32 +09:00
hfsplus block: submit_bio_wait() conversions 2013-11-24 16:33:41 -07:00
hostfs consolidate simple ->d_delete() instances 2013-11-15 22:04:17 -05:00
hpfs locks: break delegations on any attribute modification 2013-11-09 00:16:44 -05:00
hppfs
hugetlbfs
isofs
jbd
jbd2 jbd2: rename obsoleted msg JBD->JBD2 2013-12-08 21:14:59 -05:00
jffs2
jfs
lockd
logfs block: submit_bio_wait() conversions 2013-11-24 16:33:41 -07:00
minix
ncpfs
nfs NFS client bugfixes 2013-12-05 13:05:48 -08:00
nfs_common
nfsd nfsd: when reusing an existing repcache entry, unhash it first 2013-12-10 20:34:44 -05:00
nilfs2 nilfs2: fix segctor bug that causes file system corruption 2014-01-15 14:19:42 +07:00
nls
notify
ntfs iget/iget5: don't bother with ->i_lock until we find a match 2013-11-09 00:16:31 -05:00
ocfs2 tree-wide: use reinit_completion instead of INIT_COMPLETION 2013-11-15 09:32:21 +09:00
omfs
openpromfs
proc procfs: also fix proc_reg_get_unmapped_area() for !MMU case 2013-12-12 18:19:26 -08:00
pstore pstore: Don't allow high traffic options on fragile devices 2013-12-20 13:12:01 -08:00
qnx4 qnx4: i_sb is never NULL 2013-11-09 00:16:32 -05:00
qnx6
quota genetlink: make multicast groups const, prevent abuse 2013-11-19 16:39:06 -05:00
ramfs
reiserfs
romfs
squashfs Squashfs: fix failure to unlock pages on decompress error 2013-11-24 01:02:50 +00:00
sysfs sysfs: give different locking key to regular and bin files 2013-12-07 21:22:00 -08:00
sysv
ubifs Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2013-11-13 15:34:18 +09:00
udf
ufs
xfs xfs: Calling destroy_work_on_stack() to pair with INIT_WORK_ONSTACK() 2014-01-10 12:39:38 -06:00
aio.c Merge git://git.kvack.org/~bcrl/aio-next 2013-12-22 11:03:49 -08:00
anon_inodes.c
attr.c locks: break delegations on any attribute modification 2013-11-09 00:16:44 -05:00
bad_inode.c
binfmt_aout.c
binfmt_elf.c elf{,_fdpic} coredump: get rid of pointless if (siginfo->si_signo) 2013-11-09 00:16:30 -05:00
binfmt_elf_fdpic.c elf{,_fdpic} coredump: get rid of pointless if (siginfo->si_signo) 2013-11-09 00:16:30 -05:00
binfmt_em86.c
binfmt_flat.c
binfmt_misc.c
binfmt_script.c
binfmt_som.c
bio-integrity.c
bio.c bio: fix argument of __bio_add_page() for max_sectors > 0xffff 2013-11-18 12:31:27 -07:00
block_dev.c
buffer.c
char_dev.c Merge branch 'for-3.13/core' of git://git.kernel.dk/linux-block 2013-11-14 12:08:14 +09:00
compat.c
compat_binfmt_elf.c
compat_ioctl.c
coredump.c dump_emit(): use __kernel_write(), not vfs_write() 2013-11-15 22:04:09 -05:00
coredump.h
dcache.c Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace 2014-01-17 17:29:36 -08:00
dcookies.c
direct-io.c
drop_caches.c
eventfd.c
eventpoll.c epoll: do not take the nested ep->mtx on EPOLL_CTL_DEL 2014-01-02 14:40:30 -08:00
exec.c Merge git://git.infradead.org/users/eparis/audit 2013-11-21 19:18:14 -08:00
fcntl.c
fhandle.c
file.c
file_table.c Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2013-11-13 15:34:18 +09:00
filesystems.c
fs-writeback.c writeback: Fix data corruption on NFS 2013-12-14 04:21:26 +08:00
fs_struct.c
generic_acl.c
inode.c locks: break delegations on any attribute modification 2013-11-09 00:16:44 -05:00
internal.h
ioctl.c
ioprio.c
Kconfig
Kconfig.binfmt
libfs.c consolidate simple ->d_delete() instances 2013-11-15 22:04:17 -05:00
locks.c locks: missing unlock on error in generic_add_lease() 2013-11-13 07:30:53 -05:00
Makefile
mbcache.c
mount.h
mpage.c
namei.c dcache: allow word-at-a-time name hashing with big-endian CPUs 2013-12-12 10:39:01 -08:00
namespace.c vfs: Fix a regression in mounting proc 2013-11-26 20:54:52 -08:00
no-block.c
open.c locks: break delegations on any attribute modification 2013-11-09 00:16:44 -05:00
pipe.c vfs: fix subtle use-after-free of pipe_inode_info 2013-12-02 09:44:51 -08:00
pnode.c
pnode.h
posix_acl.c
proc_namespace.c
read_write.c
readdir.c
select.c Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2013-11-13 15:34:18 +09:00
seq_file.c seq_file: always clear m->count when we free m->buf 2013-11-18 19:07:53 -08:00
signalfd.c
splice.c
stack.c
stat.c vfs: split out vfs_getattr_nosec 2013-11-09 00:16:31 -05:00
statfs.c
super.c
sync.c Merge branch 'akpm' (patches from Andrew Morton) 2013-11-13 15:45:43 +09:00
timerfd.c
utimes.c locks: break delegations on any attribute modification 2013-11-09 00:16:44 -05:00
xattr.c
xattr_acl.c