The source for the Linux kernel used in Windows Subsystem for Linux 2 (WSL2)
Перейти к файлу
Filipe Manana 5522a27e59 btrfs: do not take the log_mutex of the subvolume when pinning the log
During a rename we pin the log to make sure no one commits a log that
reflects an ongoing rename operation, as it might result in a committed
log where it recorded the unlink of the old name without having recorded
the new name. However we are taking the subvolume's log_mutex before
incrementing the log_writers counter, which is not necessary since that
counter is atomic and we only remove the old name from the log and add
the new name to the log after we have incremented log_writers, ensuring
that no one can commit the log after we have removed the old name from
the log and before we added the new name to the log.

By taking the log_mutex lock we are just adding unnecessary contention on
the lock, which can become visible for workloads that mix renames with
fsyncs, writes for files opened with O_SYNC and unlink operations (if the
inode or its parent were fsynced before in the current transaction).

So just remove the lock and unlock of the subvolume's log_mutex at
btrfs_pin_log_trans().

Using dbench, which mixes different types of operations that end up taking
that mutex (fsyncs, renames, unlinks and writes into files opened with
O_SYNC) revealed some small gains. The following script that calls dbench
was used:

  #!/bin/bash

  DEV=/dev/nvme0n1
  MNT=/mnt/btrfs
  MOUNT_OPTIONS="-o ssd -o space_cache=v2"
  MKFS_OPTIONS="-m single -d single"
  THREADS=32

  echo "performance" | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
  mkfs.btrfs -f $MKFS_OPTIONS $DEV
  mount $MOUNT_OPTIONS $DEV $MNT

  dbench -s -t 600 -D $MNT $THREADS

  umount $MNT

The test was run on bare metal, no virtualization, on a box with 12 cores
(Intel i7-8700), 64Gb of RAM and using a NVMe device, with a kernel
configuration that is the default of typical distributions (debian in this
case), without debug options enabled (kasan, kmemleak, slub debug, debug
of page allocations, lock debugging, etc).

Results before this patch:

 Operation      Count    AvgLat    MaxLat
 ----------------------------------------
 NTCreateX    4410848     0.017   738.640
 Close        3240222     0.001     0.834
 Rename        186850     7.478  1272.476
 Unlink        890875     0.128   785.018
 Deltree          128     2.846    12.081
 Mkdir             64     0.002     0.003
 Qpathinfo    3997659     0.009    11.171
 Qfileinfo     701307     0.001     0.478
 Qfsinfo       733494     0.002     1.103
 Sfileinfo     359362     0.004     3.266
 Find         1546226     0.041     4.128
 WriteX       2202803     7.905  1376.989
 ReadX        6917775     0.003     3.887
 LockX          14392     0.002     0.043
 UnlockX        14392     0.001     0.085
 Flush         309225     0.128  1033.936

Throughput 231.555 MB/sec (sync open)  32 clients  32 procs  max_latency=1376.993 ms

Results after this patch:

Operation      Count    AvgLat    MaxLat
 ----------------------------------------
 NTCreateX    4603244     0.017   232.776
 Close        3381299     0.001     1.041
 Rename        194871     7.251  1073.165
 Unlink        929730     0.133   119.233
 Deltree          128     2.871    10.199
 Mkdir             64     0.002     0.004
 Qpathinfo    4171343     0.009    11.317
 Qfileinfo     731227     0.001     1.635
 Qfsinfo       765079     0.002     3.568
 Sfileinfo     374881     0.004     1.220
 Find         1612964     0.041     4.675
 WriteX       2296720     7.569  1178.204
 ReadX        7213633     0.003     3.075
 LockX          14976     0.002     0.076
 UnlockX        14976     0.001     0.061
 Flush         322635     0.102   579.505

Throughput 241.4 MB/sec (sync open)  32 clients  32 procs  max_latency=1178.207 ms
(+4.3% throughput, -14.4% max latency)

Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-10-07 12:06:55 +02:00
Documentation Power management fixes for 5.9-rc8 2020-10-02 10:05:56 -07:00
LICENSES LICENSES: Rename other to deprecated 2019-05-03 06:34:32 -06:00
arch Two bugfix patches. 2020-10-03 12:19:23 -07:00
block block-5.9-2020-10-02 2020-10-02 14:34:52 -07:00
certs .gitignore: add SPDX License Identifier 2020-03-25 11:50:48 +01:00
crypto Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6 2020-08-30 15:53:44 -07:00
drivers xen: branch for v5.9-rc8 2020-10-03 11:57:39 -07:00
fs btrfs: do not take the log_mutex of the subvolume when pinning the log 2020-10-07 12:06:55 +02:00
include btrfs: tracepoints: output proper root owner for trace_find_free_extent() 2020-10-07 12:06:49 +02:00
init bootconfig: init: make xbc_namebuf static 2020-09-18 22:17:05 -04:00
ipc ipc: adjust proc_ipc_sem_dointvec definition to match prototype 2020-09-05 12:14:29 -07:00
kernel Two tracing fixes: 2020-10-01 09:41:02 -07:00
lib random32: Restore __latent_entropy attribute on net_rand_state 2020-10-02 09:31:54 -07:00
mm mm/page_alloc: handle a missing case for memalloc_nocma_{save/restore} APIs 2020-10-03 11:28:12 -07:00
net Fixes: 2020-09-25 10:46:11 -07:00
samples treewide: Use fallthrough pseudo-keyword 2020-08-23 17:36:59 -05:00
scripts scripts/spelling.txt: fix malformed entry 2020-10-03 11:28:12 -07:00
security device_cgroup RCU warning fix from Amol Grover <frextrite@gmail.com> 2020-09-15 16:26:57 -07:00
sound sound fixes for 5.9-rc7 2020-09-24 09:00:05 -07:00
tools Five small fixes. The nested migration bug will be fixed 2020-09-25 17:15:19 -07:00
usr Merge branch 'work.fdpic' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2020-08-07 13:29:39 -07:00
virt KVM: fix memory leak in kvm_io_bus_unregister_dev() 2020-09-11 13:15:11 -04:00
.clang-format clang-format: Update with the latest for_each macro list 2020-09-01 12:53:42 +02:00
.cocciconfig scripts: add Linux .cocciconfig for coccinelle 2016-07-22 12:13:39 +02:00
.get_maintainer.ignore Opt out of scripts/get_maintainer.pl 2019-05-16 10:53:40 -07:00
.gitattributes .gitattributes: use 'dts' diff driver for dts files 2019-12-04 19:44:11 -08:00
.gitignore .gitignore: Add ZSTD-compressed files 2020-07-31 11:50:49 +02:00
.mailmap mailmap: add older email addresses for Kees Cook 2020-09-19 13:13:38 -07:00
COPYING COPYING: state that all contributions really are covered by this file 2020-02-10 13:32:20 -08:00
CREDITS CREDITS: Replace HTTP links with HTTPS ones 2020-07-23 14:53:58 -06:00
Kbuild kbuild: rename hostprogs-y/always to hostprogs/always-y 2020-02-04 01:53:07 +09:00
Kconfig kbuild: ensure full rebuild when the compiler is updated 2020-05-12 13:28:33 +09:00
MAINTAINERS pci-v5.9-fixes-2 2020-10-02 14:48:25 -07:00
Makefile Linux 5.9-rc8 2020-10-04 16:04:34 -07:00
README Drop all 00-INDEX files from Documentation/ 2018-09-09 15:08:58 -06:00

README

Linux kernel
============

There are several guides for kernel developers and users. These guides can
be rendered in a number of formats, like HTML and PDF. Please read
Documentation/admin-guide/README.rst first.

In order to build the documentation, use ``make htmldocs`` or
``make pdfdocs``.  The formatted documentation can also be read online at:

    https://www.kernel.org/doc/html/latest/

There are various text files in the Documentation/ subdirectory,
several of them using the Restructured Text markup notation.

Please read the Documentation/process/changes.rst file, as it contains the
requirements for building and running the kernel, and information about
the problems which may result by upgrading your kernel.