linux/fs
Brian Foster dc8e69bd72 xfs: optimize near mode bnobt scans with concurrent cntbt lookups
The near mode fallback algorithm consists of a left/right scan of
the bnobt. This algorithm has very poor breakdown characteristics
under worst case free space fragmentation conditions. If a suitable
extent is far enough from the locality hint, each allocation may
scan most or all of the bnobt before it completes. This causes
pathological behavior and extremely high allocation latencies.

While locality is important to near mode allocations, it is not so
important as to incur pathological allocation latency to provide the
asolute best available locality for every allocation. If the
allocation is large enough or far enough away, there is a point of
diminishing returns. As such, we can bound the overall operation by
including an iterative cntbt lookup in the broader search. The cntbt
lookup is optimized to immediately find the extent with best
locality for the given size on each iteration. Since the cntbt is
indexed by extent size, the lookup repeats with a variably
aggressive increasing search key size until it runs off the edge of
the tree.

This approach provides a natural balance between the two algorithms
for various situations. For example, the bnobt scan is able to
satisfy smaller allocations such as for inode chunks or btree blocks
more quickly where the cntbt search may have to search through a
large set of extent sizes when the search key starts off small
relative to the largest extent in the tree. On the other hand, the
cntbt search more deterministically covers the set of suitable
extents for larger data extent allocation requests that the bnobt
scan may have to search the entire tree to locate.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2019-10-21 09:04:58 -07:00
..
9p 9p pull request for inclusion in 5.4 2019-09-27 15:10:34 -07:00
adfs Merge branch 'work.adfs' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2019-07-19 11:33:22 -07:00
affs fs: affs: Initialize filesystem timestamp ranges 2019-08-30 07:27:18 -07:00
afs Merge branch 'work.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2019-09-29 19:42:07 -07:00
autofs autofs_lookup(): hold ->d_lock over playing with ->d_flags 2019-07-27 10:03:14 -04:00
befs fs: Fill in max and min timestamps in superblock 2019-08-30 07:27:17 -07:00
bfs fs: Fill in max and min timestamps in superblock 2019-08-30 07:27:17 -07:00
btrfs for-5.4-rc2-tag 2019-10-10 08:30:51 -07:00
cachefiles
ceph The highlights are: 2019-09-25 10:21:13 -07:00
cifs CIFS: Force reval dentry if LOOKUP_REVAL flag is set 2019-10-09 00:10:50 -05:00
coda y2038: add inode timestamp clamping 2019-09-19 09:42:37 -07:00
configfs configfs updates for 5.4: 2019-09-19 13:09:28 -07:00
cramfs Merge branch 'work.mount2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2019-09-19 10:06:57 -07:00
crypto fscrypt: require that key be added when setting a v2 encryption policy 2019-08-12 19:18:50 -07:00
debugfs Merge branch 'next-lockdown' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security 2019-09-28 08:14:15 -07:00
devpts devpts_pty_kill(): don't bother with d_delete() 2019-09-03 09:30:56 -04:00
dlm dlm for 5.3 2019-07-12 17:37:53 -07:00
ecryptfs - Fix error handling when ecryptfs_read_lower() encounters an error 2019-07-14 19:29:04 -07:00
efivarfs Merge branch 'work.mount0' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2019-07-19 10:42:02 -07:00
efs fs: Fill in max and min timestamps in superblock 2019-08-30 07:27:17 -07:00
erofs erofs: fix mis-inplace determination related with noio chain 2019-10-01 04:54:45 +08:00
exportfs docs: fs: convert docs without extension to ReST 2019-07-31 13:31:05 -06:00
ext2 iomap: use a srcmap for a read-modify-write I/O 2019-10-21 08:51:59 -07:00
ext4 iomap: use a srcmap for a read-modify-write I/O 2019-10-21 08:51:59 -07:00
f2fs f2fs-for-5.4-rc1 2019-09-21 14:26:33 -07:00
fat fat: delete an unnecessary check before brelse() 2019-09-25 17:51:40 -07:00
freevxfs fs: Fill in max and min timestamps in superblock 2019-08-30 07:27:17 -07:00
fscache Revert "Merge tag 'keys-acl-20190703' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs" 2019-07-10 18:43:43 -07:00
fuse add virtio-fs 2019-09-27 15:54:24 -07:00
gfs2 iomap: use a srcmap for a read-modify-write I/O 2019-10-21 08:51:59 -07:00
hfs
hfsplus fs/hfsplus/xattr.c: replace strncpy with memcpy 2019-07-16 19:23:23 -07:00
hostfs
hpfs fs: hpfs: Initialize filesystem timestamp ranges 2019-08-30 08:11:25 -07:00
hugetlbfs Merge branch 'work.mount0' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2019-07-19 10:42:02 -07:00
iomap iomap: use a srcmap for a read-modify-write I/O 2019-10-21 08:51:59 -07:00
isofs y2038: add inode timestamp clamping 2019-09-19 09:42:37 -07:00
jbd2 jbd2: remove jbd2_journal_inode_add_[write|wait] 2019-09-24 15:54:07 -07:00
jffs2 Merge branch 'work.mount3' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2019-09-26 11:33:30 -07:00
jfs y2038: add inode timestamp clamping 2019-09-19 09:42:37 -07:00
kernfs y2038: add inode timestamp clamping 2019-09-19 09:42:37 -07:00
lockd lockd: Make two symbols static 2019-07-03 17:52:09 -04:00
minix fs: Fill in max and min timestamps in superblock 2019-08-30 07:27:17 -07:00
nfs NFSv4: Fix leak of clp->cl_acceptor string 2019-10-10 16:14:02 -04:00
nfs_common
nfsd Highlights: 2019-09-27 17:00:27 -07:00
nilfs2 vfs: create a generic checking and prep function for FS_IOC_SETFLAGS 2019-07-01 08:25:34 -07:00
nls
notify Highlights: 2019-09-27 17:00:27 -07:00
ntfs ntfs: remove (un)?likely() from IS_ERR() conditions 2019-09-26 10:10:44 -07:00
ocfs2 fs: ocfs2: fix a possible null-pointer dereference in ocfs2_info_scan_inode_alloc() 2019-10-07 15:47:19 -07:00
omfs fs: omfs: Initialize filesystem timestamp ranges 2019-08-30 08:11:25 -07:00
openpromfs Merge branch 'work.mount0' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2019-07-19 10:42:02 -07:00
orangefs Orangefs: a fix and a cleanup 2019-09-19 10:21:35 -07:00
overlayfs ovl: filter of trusted xattr results in audit 2019-09-11 16:11:45 +02:00
proc Merge branch 'next-lockdown' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security 2019-09-28 08:14:15 -07:00
pstore pstore: fs superblock limits 2019-08-30 08:11:25 -07:00
qnx4 fs: Fill in max and min timestamps in superblock 2019-08-30 07:27:17 -07:00
qnx6 fs: Fill in max and min timestamps in superblock 2019-08-30 07:27:17 -07:00
quota quota: fix condition for resetting time limit in do_set_dqblk() 2019-07-31 12:04:42 +02:00
ramfs vfs: Convert ramfs, shmem, tmpfs, devtmpfs, rootfs to use the new mount API 2019-09-12 21:05:34 -04:00
reiserfs fs/reiserfs/do_balan.c: remove set but not used variable 2019-09-25 17:51:40 -07:00
romfs Merge branch 'work.mount2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2019-09-19 10:06:57 -07:00
squashfs Merge branch 'work.mount2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2019-09-19 10:06:57 -07:00
sysfs Merge branch 'work.mount0' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2019-07-19 10:42:02 -07:00
sysv fs: sysv: Initialize filesystem timestamp ranges 2019-08-30 07:27:18 -07:00
tracefs tracing: Do not create tracefs files if tracefs lockdown is in effect 2019-10-12 20:49:07 -04:00
ubifs This pull request contains the following changes for UBI, UBIFS and JFFS2: 2019-09-21 11:10:16 -07:00
udf fs-udf: Delete an unnecessary check before brelse() 2019-09-04 18:19:43 +02:00
ufs y2038: add inode timestamp clamping 2019-09-19 09:42:37 -07:00
unicode unicode: make array 'token' static const, makes object smaller 2019-09-17 11:48:24 -04:00
verity fs-verity: support builtin file signatures 2019-08-12 19:33:50 -07:00
xfs xfs: optimize near mode bnobt scans with concurrent cntbt lookups 2019-10-21 09:04:58 -07:00
aio.c Merge branch 'work.mount0' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2019-07-19 10:42:02 -07:00
anon_inodes.c Merge branch 'work.mount0' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2019-07-19 10:42:02 -07:00
attr.c timestamp_truncate: Replace users of timespec64_trunc 2019-08-30 07:27:17 -07:00
bad_inode.c
binfmt_aout.c
binfmt_elf_fdpic.c treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 152 2019-05-30 11:26:32 -07:00
binfmt_elf.c elf: don't use MAP_FIXED_NOREPLACE for elf executable mappings 2019-10-06 13:53:27 -07:00
binfmt_em86.c
binfmt_flat.c fs/binfmt_flat.c: remove set but not used variable 'inode' 2019-07-16 19:23:22 -07:00
binfmt_misc.c Merge branch 'work.mount0' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2019-07-19 10:42:02 -07:00
binfmt_script.c
block_dev.c Changes for 5.4: 2019-09-18 17:35:20 -07:00
buffer.c for-linus-20190715 2019-07-15 21:20:52 -07:00
char_dev.c
compat_binfmt_elf.c treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 193 2019-05-30 11:29:21 -07:00
compat_ioctl.c compat_ioctl: pppoe: fix PPPOEIOCSFWD handling 2019-07-30 14:42:13 -07:00
compat.c treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 500 2019-06-19 17:09:55 +02:00
coredump.c coredump: split pipe command whitespace before expanding template 2019-08-03 07:02:01 -07:00
d_path.c [PATCH] fix d_absolute_path() interplay with fsmount() 2019-08-30 19:31:09 -04:00
dax.c iomap: use a srcmap for a read-modify-write I/O 2019-10-21 08:51:59 -07:00
dcache.c Merge branch 'work.dcache2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2019-07-20 09:15:51 -07:00
dcookies.c
direct-io.c direct-io: use bio_release_pages in dio_bio_complete 2019-06-29 09:47:31 -06:00
drop_caches.c
eventfd.c
eventpoll.c PM / wakeup: Show wakeup sources stats in sysfs 2019-08-21 00:20:40 +02:00
exec.c sched/membarrier: Fix p->mm->membarrier_state racy load 2019-09-25 17:42:30 +02:00
fcntl.c
fhandle.c fs/handle.c - fix up kerneldoc 2019-08-07 21:51:47 -04:00
file_table.c vfs: Export flush_delayed_fput for use by knfsd. 2019-08-19 11:00:39 -04:00
file.c
filesystems.c
fs_context.c vfs: subtype handling moved to fuse 2019-09-06 21:28:49 +02:00
fs_parser.c vfs: Make fs_parse() handle fs_param_is_fd-type params better 2019-09-12 21:06:14 -04:00
fs_pin.c switch the remnants of releasing the mountpoint away from fs_pin 2019-07-16 22:52:37 -04:00
fs_struct.c
fs_types.c
fs-writeback.c writeback: fix use-after-free in finish_writeback_work() 2019-10-07 15:47:19 -07:00
fsopen.c Merge branch 'work.mount0' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2019-07-19 10:42:02 -07:00
inode.c mm,thp: avoid writes to file with THP in pagecache 2019-09-24 15:54:11 -07:00
internal.h Merge branch 'work.dcache2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2019-07-20 09:15:51 -07:00
io_uring.c for-linus-20191012 2019-10-13 08:15:35 -07:00
ioctl.c
Kconfig fs-verity for 5.4 2019-09-18 16:59:14 -07:00
Kconfig.binfmt binfmt_flat: make support for old format binaries optional 2019-06-24 09:16:47 +10:00
libfs.c libfs: take cursors out of list when moving past the end of directory 2019-10-09 22:57:30 -04:00
locks.c Highlights: 2019-09-27 17:00:27 -07:00
Makefile fs-verity for 5.4 2019-09-18 16:59:14 -07:00
mbcache.c
mount.h switch the remnants of releasing the mountpoint away from fs_pin 2019-07-16 22:52:37 -04:00
mpage.c blkcg, writeback: Rename wbc_account_io() to wbc_account_cgroup_owner() 2019-07-10 09:00:57 -06:00
namei.c fs/namei.c: keep track of nd->root refcount status 2019-09-03 09:30:45 -04:00
namespace.c Merge branch 'akpm' (patches from Andrew) 2019-09-26 10:29:42 -07:00
no-block.c treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 152 2019-05-30 11:26:32 -07:00
nsfs.c
open.c fs: remove unlikely() from WARN_ON() condition 2019-09-26 10:10:30 -07:00
pipe.c vfs: Convert pipe to use the new mount API 2019-05-25 18:00:07 -04:00
pnode.c fs/namespace: fix unprivileged mount propagation 2019-06-17 17:36:09 -04:00
pnode.h treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 209 2019-05-30 11:29:53 -07:00
posix_acl.c
proc_namespace.c vfs: subtype handling moved to fuse 2019-09-06 21:28:49 +02:00
read_write.c vfs: fix page locking deadlocks when deduping files 2019-08-16 18:43:24 -07:00
readdir.c uaccess: implement a proper unsafe_copy_to_user() and switch filldir over to it 2019-10-07 12:56:48 -07:00
select.c fs/select.c: use struct_size() in kmalloc() 2019-07-16 19:23:25 -07:00
seq_file.c seq_file: fix problem when seeking mid-record 2019-08-13 16:06:52 -07:00
signalfd.c
splice.c uio: make import_iovec()/compat_import_iovec() return bytes on success 2019-05-31 15:30:03 -06:00
stack.c
stat.c
statfs.c vfs: Fix EOVERFLOW testing in put_compat_statfs64 2019-10-03 14:21:35 -07:00
super.c Merge branch 'work.mount3' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2019-10-10 08:16:44 -07:00
sync.c
timerfd.c timerfd: Prepare for PREEMPT_RT 2019-08-01 20:51:23 +02:00
userfaultfd.c userfaultfd: untag user pointers 2019-09-25 17:51:41 -07:00
utimes.c utimes: Clamp the timestamps before update 2019-08-30 07:27:17 -07:00
xattr.c