Skip to content

K
Kernel

openeuler / Kernel
12 个月 前同步成功

通知 5
Star 0
Fork 0
K
Kernel

体验新版 GitCode，发现更多精彩内容 >>

切换分支/标签
  1. 07 10月, 2020 1 次提交
    • F
      btrfs: make fast fsyncs wait only for writeback · 48778179
      由 Filipe Manana 提交于 
      Currently regardless of a full or a fast fsync we always wait for ordered
extents to complete, and then start logging the inode after that. However
for fast fsyncs we can just wait for the writeback to complete, we don't
need to wait for the ordered extents to complete since we use the list of
modified extents maps to figure out which extents we must log and we can
get their checksums directly from the ordered extents that are still in
flight, otherwise look them up from the checksums tree.

Until commit b5e6c3e1 ("btrfs: always wait on ordered extents at
fsync time"), for fast fsyncs, we used to start logging without even
waiting for the writeback to complete first, we would wait for it to
complete after logging, while holding a transaction open, which lead to
performance issues when using cgroups and probably for other cases too,
as wait for IO while holding a transaction handle should be avoided as
much as possible. After that, for fast fsyncs, we started to wait for
ordered extents to complete before starting to log, which adds some
latency to fsyncs and we even got at least one report about a performance
drop which bisected to that particular change:

https://lore.kernel.org/linux-btrfs/20181109215148.GF23260@techsingularity.net/

This change makes fast fsyncs only wait for writeback to finish before
starting to log the inode, instead of waiting for both the writeback to
finish and for the ordered extents to complete. This brings back part of
the logic we had that extracts checksums from in flight ordered extents,
which are not yet in the checksums tree, and making sure transaction
commits wait for the completion of ordered extents previously logged
(by far most of the time they have already completed by the time a
transaction commit starts, resulting in no wait at all), to avoid any
data loss if an ordered extent completes after the transaction used to
log an inode is committed, followed by a power failure.

When there are no other tasks accessing the checksums and the subvolume
btrees, the ordered extent completion is pretty fast, typically taking
100 to 200 microseconds only in my observations. However when there are
other tasks accessing these btrees, ordered extent completion can take a
lot more time due to lock contention on nodes and leaves of these btrees.
I've seen cases over 2 milliseconds, which starts to be significant. In
particular when we do have concurrent fsyncs against different files there
is a lot of contention on the checksums btree, since we have many tasks
writing the checksums into the btree and other tasks that already started
the logging phase are doing lookups for checksums in the btree.

This change also turns all ranged fsyncs into full ranged fsyncs, which
is something we already did when not using the NO_HOLES features or when
doing a full fsync. This is to guarantee we never miss checksums due to
writeback having been triggered only for a part of an extent, and we end
up logging the full extent but only checksums for the written range, which
results in missing checksums after log replay. Allowing ranged fsyncs to
operate again only in the original range, when using the NO_HOLES feature
and doing a fast fsync is doable but requires some non trivial changes to
the writeback path, which can always be worked on later if needed, but I
don't think they are a very common use case.

Several tests were performed using fio for different numbers of concurrent
jobs, each writing and fsyncing its own file, for both sequential and
random file writes. The tests were run on bare metal, no virtualization,
on a box with 12 cores (Intel i7-8700), 64Gb of RAM and 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).

The following script that calls fio was used:

  $ cat test-fsync.sh
  #!/bin/bash

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

  if [ $# -ne 5 ]; then
    echo "Use $0 NUM_JOBS FILE_SIZE FSYNC_FREQ BLOCK_SIZE [write|randwrite]"
    exit 1
  fi

  NUM_JOBS=$1
  FILE_SIZE=$2
  FSYNC_FREQ=$3
  BLOCK_SIZE=$4
  WRITE_MODE=$5

  if [ "$WRITE_MODE" != "write" ] && [ "$WRITE_MODE" != "randwrite" ]; then
    echo "Invalid WRITE_MODE, must be 'write' or 'randwrite'"
    exit 1
  fi

  cat <<EOF > /tmp/fio-job.ini
  [writers]
  rw=$WRITE_MODE
  fsync=$FSYNC_FREQ
  fallocate=none
  group_reporting=1
  direct=0
  bs=$BLOCK_SIZE
  ioengine=sync
  size=$FILE_SIZE
  directory=$MNT
  numjobs=$NUM_JOBS
  EOF

  echo "performance" | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor

  echo
  echo "Using config:"
  echo
  cat /tmp/fio-job.ini
  echo

  umount $MNT &> /dev/null
  mkfs.btrfs -f $MKFS_OPTIONS $DEV
  mount $MOUNT_OPTIONS $DEV $MNT
  fio /tmp/fio-job.ini
  umount $MNT

The results were the following:

*************************
*** sequential writes ***
*************************

==== 1 job, 8GiB file, fsync frequency 1, block size 64KiB ====

Before patch:

WRITE: bw=36.6MiB/s (38.4MB/s), 36.6MiB/s-36.6MiB/s (38.4MB/s-38.4MB/s), io=8192MiB (8590MB), run=223689-223689msec

After patch:

WRITE: bw=40.2MiB/s (42.1MB/s), 40.2MiB/s-40.2MiB/s (42.1MB/s-42.1MB/s), io=8192MiB (8590MB), run=203980-203980msec
(+9.8%, -8.8% runtime)

==== 2 jobs, 4GiB files, fsync frequency 1, block size 64KiB ====

Before patch:

WRITE: bw=35.8MiB/s (37.5MB/s), 35.8MiB/s-35.8MiB/s (37.5MB/s-37.5MB/s), io=8192MiB (8590MB), run=228950-228950msec

After patch:

WRITE: bw=43.5MiB/s (45.6MB/s), 43.5MiB/s-43.5MiB/s (45.6MB/s-45.6MB/s), io=8192MiB (8590MB), run=188272-188272msec
(+21.5% throughput, -17.8% runtime)

==== 4 jobs, 2GiB files, fsync frequency 1, block size 64KiB ====

Before patch:

WRITE: bw=50.1MiB/s (52.6MB/s), 50.1MiB/s-50.1MiB/s (52.6MB/s-52.6MB/s), io=8192MiB (8590MB), run=163446-163446msec

After patch:

WRITE: bw=64.5MiB/s (67.6MB/s), 64.5MiB/s-64.5MiB/s (67.6MB/s-67.6MB/s), io=8192MiB (8590MB), run=126987-126987msec
(+28.7% throughput, -22.3% runtime)

==== 8 jobs, 1GiB files, fsync frequency 1, block size 64KiB ====

Before patch:

WRITE: bw=64.0MiB/s (68.1MB/s), 64.0MiB/s-64.0MiB/s (68.1MB/s-68.1MB/s), io=8192MiB (8590MB), run=126075-126075msec

After patch:

WRITE: bw=86.8MiB/s (91.0MB/s), 86.8MiB/s-86.8MiB/s (91.0MB/s-91.0MB/s), io=8192MiB (8590MB), run=94358-94358msec
(+35.6% throughput, -25.2% runtime)

==== 16 jobs, 512MiB files, fsync frequency 1, block size 64KiB ====

Before patch:

WRITE: bw=79.8MiB/s (83.6MB/s), 79.8MiB/s-79.8MiB/s (83.6MB/s-83.6MB/s), io=8192MiB (8590MB), run=102694-102694msec

After patch:

WRITE: bw=107MiB/s (112MB/s), 107MiB/s-107MiB/s (112MB/s-112MB/s), io=8192MiB (8590MB), run=76446-76446msec
(+34.1% throughput, -25.6% runtime)

==== 32 jobs, 512MiB files, fsync frequency 1, block size 64KiB ====

Before patch:

WRITE: bw=93.2MiB/s (97.7MB/s), 93.2MiB/s-93.2MiB/s (97.7MB/s-97.7MB/s), io=16.0GiB (17.2GB), run=175836-175836msec

After patch:

WRITE: bw=111MiB/s (117MB/s), 111MiB/s-111MiB/s (117MB/s-117MB/s), io=16.0GiB (17.2GB), run=147001-147001msec
(+19.1% throughput, -16.4% runtime)

==== 64 jobs, 512MiB files, fsync frequency 1, block size 64KiB ====

Before patch:

WRITE: bw=108MiB/s (114MB/s), 108MiB/s-108MiB/s (114MB/s-114MB/s), io=32.0GiB (34.4GB), run=302656-302656msec

After patch:

WRITE: bw=133MiB/s (140MB/s), 133MiB/s-133MiB/s (140MB/s-140MB/s), io=32.0GiB (34.4GB), run=246003-246003msec
(+23.1% throughput, -18.7% runtime)

************************
***   random writes  ***
************************

==== 1 job, 8GiB file, fsync frequency 16, block size 4KiB ====

Before patch:

WRITE: bw=11.5MiB/s (12.0MB/s), 11.5MiB/s-11.5MiB/s (12.0MB/s-12.0MB/s), io=8192MiB (8590MB), run=714281-714281msec

After patch:

WRITE: bw=11.6MiB/s (12.2MB/s), 11.6MiB/s-11.6MiB/s (12.2MB/s-12.2MB/s), io=8192MiB (8590MB), run=705959-705959msec
(+0.9% throughput, -1.7% runtime)

==== 2 jobs, 4GiB files, fsync frequency 16, block size 4KiB ====

Before patch:

WRITE: bw=12.8MiB/s (13.5MB/s), 12.8MiB/s-12.8MiB/s (13.5MB/s-13.5MB/s), io=8192MiB (8590MB), run=638101-638101msec

After patch:

WRITE: bw=13.1MiB/s (13.7MB/s), 13.1MiB/s-13.1MiB/s (13.7MB/s-13.7MB/s), io=8192MiB (8590MB), run=625374-625374msec
(+2.3% throughput, -2.0% runtime)

==== 4 jobs, 2GiB files, fsync frequency 16, block size 4KiB ====

Before patch:

WRITE: bw=15.4MiB/s (16.2MB/s), 15.4MiB/s-15.4MiB/s (16.2MB/s-16.2MB/s), io=8192MiB (8590MB), run=531146-531146msec

After patch:

WRITE: bw=17.8MiB/s (18.7MB/s), 17.8MiB/s-17.8MiB/s (18.7MB/s-18.7MB/s), io=8192MiB (8590MB), run=460431-460431msec
(+15.6% throughput, -13.3% runtime)

==== 8 jobs, 1GiB files, fsync frequency 16, block size 4KiB ====

Before patch:

WRITE: bw=19.9MiB/s (20.8MB/s), 19.9MiB/s-19.9MiB/s (20.8MB/s-20.8MB/s), io=8192MiB (8590MB), run=412664-412664msec

After patch:

WRITE: bw=22.2MiB/s (23.3MB/s), 22.2MiB/s-22.2MiB/s (23.3MB/s-23.3MB/s), io=8192MiB (8590MB), run=368589-368589msec
(+11.6% throughput, -10.7% runtime)

==== 16 jobs, 512MiB files, fsync frequency 16, block size 4KiB ====

Before patch:

WRITE: bw=29.3MiB/s (30.7MB/s), 29.3MiB/s-29.3MiB/s (30.7MB/s-30.7MB/s), io=8192MiB (8590MB), run=279924-279924msec

After patch:

WRITE: bw=30.4MiB/s (31.9MB/s), 30.4MiB/s-30.4MiB/s (31.9MB/s-31.9MB/s), io=8192MiB (8590MB), run=269258-269258msec
(+3.8% throughput, -3.8% runtime)

==== 32 jobs, 512MiB files, fsync frequency 16, block size 4KiB ====

Before patch:

WRITE: bw=36.9MiB/s (38.7MB/s), 36.9MiB/s-36.9MiB/s (38.7MB/s-38.7MB/s), io=16.0GiB (17.2GB), run=443581-443581msec

After patch:

WRITE: bw=41.6MiB/s (43.6MB/s), 41.6MiB/s-41.6MiB/s (43.6MB/s-43.6MB/s), io=16.0GiB (17.2GB), run=394114-394114msec
(+12.7% throughput, -11.2% runtime)

==== 64 jobs, 512MiB files, fsync frequency 16, block size 4KiB ====

Before patch:

WRITE: bw=45.9MiB/s (48.1MB/s), 45.9MiB/s-45.9MiB/s (48.1MB/s-48.1MB/s), io=32.0GiB (34.4GB), run=714614-714614msec

After patch:

WRITE: bw=48.8MiB/s (51.1MB/s), 48.8MiB/s-48.8MiB/s (51.1MB/s-51.1MB/s), io=32.0GiB (34.4GB), run=672087-672087msec
(+6.3% throughput, -6.0% runtime)
Signed-off-by: NFilipe Manana <fdmanana@suse.com>
Signed-off-by: NDavid Sterba <dsterba@suse.com>
      48778179
  3. 27 7月, 2020 11 次提交
  5. 24 3月, 2020 4 次提交
  7. 19 2月, 2020 1 次提交
  9. 20 1月, 2020 2 次提交
  11. 19 11月, 2019 1 次提交
    • F
      Btrfs: fix block group remaining RO forever after error during device replace · 042528f8
      由 Filipe Manana 提交于 
      When doing a device replace, while at scrub.c:scrub_enumerate_chunks(), we
set the block group to RO mode and then wait for any ongoing writes into
extents of the block group to complete. While doing that wait we overwrite
the value of the variable 'ret' and can break out of the loop if an error
happens without turning the block group back into RW mode. So what happens
is the following:

1) btrfs_inc_block_group_ro() returns 0, meaning it set the block group
   to RO mode (its ->ro field set to 1 or incremented to some value > 1);

2) Then btrfs_wait_ordered_roots() returns a value > 0;

3) Then if either joining or committing the transaction fails, we break
   out of the loop wihtout calling btrfs_dec_block_group_ro(), leaving
   the block group in RO mode forever.

To fix this, just remove the code that waits for ongoing writes to extents
of the block group, since it's not needed because in the initial setup
phase of a device replace operation, before starting to find all chunks
and their extents, we set the target device for replace while holding
fs_info->dev_replace->rwsem, which ensures that after releasing that
semaphore, any writes into the source device are made to the target device
as well (__btrfs_map_block() guarantees that). So while at
scrub_enumerate_chunks() we only need to worry about finding and copying
extents (from the source device to the target device) that were written
before we started the device replace operation.

Fixes: f0e9b7d6 ("Btrfs: fix race setting block group readonly during device replace")
Signed-off-by: NFilipe Manana <fdmanana@suse.com>
Signed-off-by: NDavid Sterba <dsterba@suse.com>
      042528f8
  13. 18 11月, 2019 1 次提交
    • O
      btrfs: get rid of unique workqueue helper functions · a0cac0ec
      由 Omar Sandoval 提交于 
      Commit 9e0af237 ("Btrfs: fix task hang under heavy compressed
write") worked around the issue that a recycled work item could get a
false dependency on the original work item due to how the workqueue code
guarantees non-reentrancy. It did so by giving different work functions
to different types of work.

However, the fixes in the previous few patches are more complete, as
they prevent a work item from being recycled at all (except for a tiny
window that the kernel workqueue code handles for us). This obsoletes
the previous fix, so we don't need the unique helpers for correctness.
The only other reason to keep them would be so they show up in stack
traces, but they always seem to be optimized to a tail call, so they
don't show up anyways. So, let's just get rid of the extra indirection.

While we're here, rename normal_work_helper() to the more informative
btrfs_work_helper().
Reviewed-by: NNikolay Borisov <nborisov@suse.com>
Reviewed-by: NFilipe Manana <fdmanana@suse.com>
Signed-off-by: NOmar Sandoval <osandov@fb.com>
Reviewed-by: NDavid Sterba <dsterba@suse.com>
Signed-off-by: NDavid Sterba <dsterba@suse.com>
      a0cac0ec
  15. 09 9月, 2019 1 次提交
  17. 26 7月, 2019 1 次提交
  19. 04 7月, 2019 1 次提交
  21. 01 7月, 2019 3 次提交
  23. 30 4月, 2019 2 次提交
  25. 25 4月, 2019 1 次提交
    • N
      btrfs: Switch memory allocations in async csum calculation path to kvmalloc · a3d46aea
      由 Nikolay Borisov 提交于 
      Recent multi-page biovec rework allowed creation of bios that can span
large regions - up to 128 megabytes in the case of btrfs. OTOH btrfs'
submission path currently allocates a contiguous array to store the
checksums for every bio submitted. This means we can request up to
(128mb / BTRFS_SECTOR_SIZE) * 4 bytes + 32bytes of memory from kmalloc.
On busy systems with possibly fragmented memory said kmalloc can fail
which will trigger BUG_ON due to improper error handling IO submission
context in btrfs.

Until error handling is improved or bios in btrfs limited to a more
manageable size (e.g. 1m) let's use kvmalloc to fallback to vmalloc for
such large allocations. There is no hard requirement that the memory
allocated for checksums during IO submission has to be contiguous, but
this is a simple fix that does not require several non-contiguous
allocations.

For small writes this is unlikely to have any visible effect since
kmalloc will still satisfy allocation requests as usual. For larger
requests the code will just fallback to vmalloc.

We've performed evaluation on several workload types and there was no
significant difference kmalloc vs kvmalloc.
Signed-off-by: NNikolay Borisov <nborisov@suse.com>
Reviewed-by: NDavid Sterba <dsterba@suse.com>
Signed-off-by: NDavid Sterba <dsterba@suse.com>
      a3d46aea
  27. 17 12月, 2018 1 次提交
  29. 06 8月, 2018 3 次提交
  31. 29 5月, 2018 1 次提交
  33. 12 4月, 2018 1 次提交
  35. 31 3月, 2018 1 次提交
    • Q
      btrfs: qgroup: Use separate meta reservation type for delalloc · 43b18595
      由 Qu Wenruo 提交于 
      Before this patch, btrfs qgroup is mixing per-transcation meta rsv with
preallocated meta rsv, making it quite easy to underflow qgroup meta
reservation.

Since we have the new qgroup meta rsv types, apply it to delalloc
reservation.

Now for delalloc, most of its reserved space will use META_PREALLOC qgroup
rsv type.

And for callers reducing outstanding extent like btrfs_finish_ordered_io(),
they will convert corresponding META_PREALLOC reservation to
META_PERTRANS.

This is mainly due to the fact that current qgroup numbers will only be
updated in btrfs_commit_transaction(), that's to say if we don't keep
such placeholder reservation, we can exceed qgroup limitation.

And for callers freeing outstanding extent in error handler, we will
just free META_PREALLOC bytes.

This behavior makes callers of btrfs_qgroup_release_meta() or
btrfs_qgroup_convert_meta() to be aware of which type they are.
So in this patch, btrfs_delalloc_release_metadata() and its callers get
an extra parameter to info qgroup to do correct meta convert/release.

The good news is, even we use the wrong type (convert or free), it won't
cause obvious bug, as prealloc type is always in good shape, and the
type only affects how per-trans meta is increased or not.

So the worst case will be at most metadata limitation can be sometimes
exceeded (no convert at all) or metadata limitation is reached too soon
(no free at all).
Signed-off-by: NQu Wenruo <wqu@suse.com>
Signed-off-by: NDavid Sterba <dsterba@suse.com>
      43b18595
  37. 26 3月, 2018 1 次提交
    • D
      btrfs: add more __cold annotations · e67c718b
      由 David Sterba 提交于 
      The __cold functions are placed to a special section, as they're
expected to be called rarely. This could help i-cache prefetches or help
compiler to decide which branches are more/less likely to be taken
without any other annotations needed.

Though we can't add more __exit annotations, it's still possible to add
__cold (that's also added with __exit). That way the following function
categories are tagged:

- printf wrappers, error messages
- exit helpers
Signed-off-by: NDavid Sterba <dsterba@suse.com>
      e67c718b
  39. 02 11月, 2017 1 次提交
    • J
      Btrfs: rework outstanding_extents · 8b62f87b
      由 Josef Bacik 提交于 
      Right now we do a lot of weird hoops around outstanding_extents in order
to keep the extent count consistent.  This is because we logically
transfer the outstanding_extent count from the initial reservation
through the set_delalloc_bits.  This makes it pretty difficult to get a
handle on how and when we need to mess with outstanding_extents.

Fix this by revamping the rules of how we deal with outstanding_extents.
Now instead everybody that is holding on to a delalloc extent is
required to increase the outstanding extents count for itself.  This
means we'll have something like this

btrfs_delalloc_reserve_metadata	- outstanding_extents = 1
 btrfs_set_extent_delalloc	- outstanding_extents = 2
btrfs_release_delalloc_extents	- outstanding_extents = 1

for an initial file write.  Now take the append write where we extend an
existing delalloc range but still under the maximum extent size

btrfs_delalloc_reserve_metadata - outstanding_extents = 2
  btrfs_set_extent_delalloc
    btrfs_set_bit_hook		- outstanding_extents = 3
    btrfs_merge_extent_hook	- outstanding_extents = 2
btrfs_delalloc_release_extents	- outstanding_extnets = 1

In order to make the ordered extent transition we of course must now
make ordered extents carry their own outstanding_extent reservation, so
for cow_file_range we end up with

btrfs_add_ordered_extent	- outstanding_extents = 2
clear_extent_bit		- outstanding_extents = 1
btrfs_remove_ordered_extent	- outstanding_extents = 0

This makes all manipulations of outstanding_extents much more explicit.
Every successful call to btrfs_delalloc_reserve_metadata _must_ now be
combined with btrfs_release_delalloc_extents, even in the error case, as
that is the only function that actually modifies the
outstanding_extents counter.

The drawback to this is now we are much more likely to have transient
cases where outstanding_extents is much larger than it actually should
be.  This could happen before as we manipulated the delalloc bits, but
now it happens basically at every write.  This may put more pressure on
the ENOSPC flushing code, but I think making this code simpler is worth
the cost.  I have another change coming to mitigate this side-effect
somewhat.

I also added trace points for the counter manipulation.  These were used
by a bpf script I wrote to help track down leak issues.
Signed-off-by: NJosef Bacik <jbacik@fb.com>
Signed-off-by: NDavid Sterba <dsterba@suse.com>
      8b62f87b
  41. 30 6月, 2017 1 次提交