Skip to content

K
Kernel

openeuler / Kernel
大约 1 年 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. 27 5月, 2011 5 次提交
  3. 24 5月, 2011 19 次提交
  5. 23 5月, 2011 1 次提交
    • L
      Btrfs: do not flush csum items of unchanged file data during treelog · 8e531cdf
      由 liubo 提交于 
      The current code relogs the entire inode every time during fsync log,
and it is much better suited to small files rather than large ones.

During my performance test, the fsync performace of large files sucks,
and we can ascribe this to the tremendous amount of csum infos of the
large ones, cause we have to flush all of these csum infos into log trees
even when there are only _one_ change in the whole file data.  Apparently,
to optimize fsync, we need to create a filter to skip the unnecessary csum
ones, that is, the corresponding file data remains unchanged before this fsync.

Here I have some test results to show, I use sysbench to do "random write + fsync".

===
sysbench --test=fileio --num-threads=1 --file-num=2 --file-block-size=4K --file-total-size=8G --file-test-mode=rndwr --file-io-mode=sync --file-extra-flags=  [prepare, run]
===

Sysbench args:
  - Number of threads: 1
  - Extra file open flags: 0
  - 2 files, 4Gb each
  - Block size 4Kb
  - Number of random requests for random IO: 10000
  - Read/Write ratio for combined random IO test: 1.50
  - Periodic FSYNC enabled, calling fsync() each 100 requests.
  - Calling fsync() at the end of test, Enabled.
  - Using synchronous I/O mode
  - Doing random write test

Sysbench results:
===
   Operations performed:  0 Read, 10000 Write, 200 Other = 10200 Total
   Read 0b  Written 39.062Mb  Total transferred 39.062Mb
===
a) without patch:  (*SPEED* : 451.01Kb/sec)
   112.75 Requests/sec executed

b) with patch:     (*SPEED* : 4.7533Mb/sec)
   1216.84 Requests/sec executed

PS: I've made a _sub transid_ stuff patch, but it does not perform as effectively as this patch,
and I'm wanderring where the problem is and trying to improve it more.
Signed-off-by: NLiu Bo <liubo2009@cn.fujitsu.com>
Signed-off-by: NChris Mason <chris.mason@oracle.com>
      8e531cdf
  7. 22 5月, 2011 1 次提交
  9. 21 5月, 2011 1 次提交
    • M
      btrfs: implement delayed inode items operation · 16cdcec7
      由 Miao Xie 提交于 
      Changelog V5 -> V6:
- Fix oom when the memory load is high, by storing the delayed nodes into the
  root's radix tree, and letting btrfs inodes go.

Changelog V4 -> V5:
- Fix the race on adding the delayed node to the inode, which is spotted by
  Chris Mason.
- Merge Chris Mason's incremental patch into this patch.
- Fix deadlock between readdir() and memory fault, which is reported by
  Itaru Kitayama.

Changelog V3 -> V4:
- Fix nested lock, which is reported by Itaru Kitayama, by updating space cache
  inode in time.

Changelog V2 -> V3:
- Fix the race between the delayed worker and the task which does delayed items
  balance, which is reported by Tsutomu Itoh.
- Modify the patch address David Sterba's comment.
- Fix the bug of the cpu recursion spinlock, reported by Chris Mason

Changelog V1 -> V2:
- break up the global rb-tree, use a list to manage the delayed nodes,
  which is created for every directory and file, and used to manage the
  delayed directory name index items and the delayed inode item.
- introduce a worker to deal with the delayed nodes.

Compare with Ext3/4, the performance of file creation and deletion on btrfs
is very poor. the reason is that btrfs must do a lot of b+ tree insertions,
such as inode item, directory name item, directory name index and so on.

If we can do some delayed b+ tree insertion or deletion, we can improve the
performance, so we made this patch which implemented delayed directory name
index insertion/deletion and delayed inode update.

Implementation:
- introduce a delayed root object into the filesystem, that use two lists to
  manage the delayed nodes which are created for every file/directory.
  One is used to manage all the delayed nodes that have delayed items. And the
  other is used to manage the delayed nodes which is waiting to be dealt with
  by the work thread.
- Every delayed node has two rb-tree, one is used to manage the directory name
  index which is going to be inserted into b+ tree, and the other is used to
  manage the directory name index which is going to be deleted from b+ tree.
- introduce a worker to deal with the delayed operation. This worker is used
  to deal with the works of the delayed directory name index items insertion
  and deletion and the delayed inode update.
  When the delayed items is beyond the lower limit, we create works for some
  delayed nodes and insert them into the work queue of the worker, and then
  go back.
  When the delayed items is beyond the upper bound, we create works for all
  the delayed nodes that haven't been dealt with, and insert them into the work
  queue of the worker, and then wait for that the untreated items is below some
  threshold value.
- When we want to insert a directory name index into b+ tree, we just add the
  information into the delayed inserting rb-tree.
  And then we check the number of the delayed items and do delayed items
  balance. (The balance policy is above.)
- When we want to delete a directory name index from the b+ tree, we search it
  in the inserting rb-tree at first. If we look it up, just drop it. If not,
  add the key of it into the delayed deleting rb-tree.
  Similar to the delayed inserting rb-tree, we also check the number of the
  delayed items and do delayed items balance.
  (The same to inserting manipulation)
- When we want to update the metadata of some inode, we cached the data of the
  inode into the delayed node. the worker will flush it into the b+ tree after
  dealing with the delayed insertion and deletion.
- We will move the delayed node to the tail of the list after we access the
  delayed node, By this way, we can cache more delayed items and merge more
  inode updates.
- If we want to commit transaction, we will deal with all the delayed node.
- the delayed node will be freed when we free the btrfs inode.
- Before we log the inode items, we commit all the directory name index items
  and the delayed inode update.

I did a quick test by the benchmark tool[1] and found we can improve the
performance of file creation by ~15%, and file deletion by ~20%.

Before applying this patch:
Create files:
        Total files: 50000
        Total time: 1.096108
        Average time: 0.000022
Delete files:
        Total files: 50000
        Total time: 1.510403
        Average time: 0.000030

After applying this patch:
Create files:
        Total files: 50000
        Total time: 0.932899
        Average time: 0.000019
Delete files:
        Total files: 50000
        Total time: 1.215732
        Average time: 0.000024

[1] http://marc.info/?l=linux-btrfs&m=128212635122920&q=p3

Many thanks for Kitayama-san's help!
Signed-off-by: NMiao Xie <miaox@cn.fujitsu.com>
Reviewed-by: NDavid Sterba <dave@jikos.cz>
Tested-by: NTsutomu Itoh <t-itoh@jp.fujitsu.com>
Tested-by: NItaru Kitayama <kitayama@cl.bb4u.ne.jp>
Signed-off-by: NChris Mason <chris.mason@oracle.com>
      16cdcec7
  11. 15 5月, 2011 5 次提交
  13. 13 5月, 2011 5 次提交
    • A
      btrfs: quasi-round-robin for chunk allocation · 73c5de00
      由 Arne Jansen 提交于 
      In a multi device setup, the chunk allocator currently always allocates
chunks on the devices in the same order. This leads to a very uneven
distribution, especially with RAID1 or RAID10 and an uneven number of
devices.
This patch always sorts the devices before allocating, and allocates the
stripes on the devices with the most available space, as long as there
is enough space available. In a low space situation, it first tries to
maximize striping.
The patch also simplifies the allocator and reduces the checks for
corner cases.
The simplification is done by several means. First, it defines the
properties of each RAID type upfront. These properties are used afterwards
instead of differentiating cases in several places.
Second, the old allocator defined a minimum stripe size for each block
group type, tried to find a large enough chunk, and if this fails just
allocates a smaller one. This is now done in one step. The largest possible
chunk (up to max_chunk_size) is searched and allocated.
Because we now have only one pass, the allocation of the map (struct
map_lookup) is moved down to the point where the number of stripes is
already known. This way we avoid reallocation of the map.
We still avoid allocating stripes that are not a multiple of STRIPE_SIZE.
      73c5de00
    • A
      btrfs: heed alloc_start · a9c9bf68
      由 Arne Jansen 提交于 
      currently alloc_start is disregarded if the requested
chunk size is bigger than (device size - alloc_start),
but smaller than the device size.
The only situation where I see this could have made sense
was when a chunk equal the size of the device has been
requested. This was possible as the allocator failed to
take alloc_start into account when calculating the request
chunk size. As this gets fixed by this patch, the workaround
is not necessary anymore.
      a9c9bf68
    • A
      btrfs: move btrfs_cmp_device_free_bytes to super.c · bcd53741
      由 Arne Jansen 提交于 
      this function won't be used here anymore, so move it super.c where it is
used for df-calculation
      bcd53741
    • D
      btrfs: use unsigned type for single bit bitfield · 4ea02885
      由 David Sterba 提交于 
      Signed-off-by: NDavid Sterba <dsterba@suse.cz>
      4ea02885
    • D
      btrfs: use printk_ratelimited instead of printk_ratelimit · 7a36ddec
      由 David Sterba 提交于 
      As per printk_ratelimit comment, it should not be used.
Signed-off-by: NDavid Sterba <dsterba@suse.cz>
      7a36ddec
  15. 12 5月, 2011 3 次提交
    • A
      btrfs: add readonly flag · 8628764e
      由 Arne Jansen 提交于 
      setting the readonly flag prevents writes in case an error is detected
Signed-off-by: NArne Jansen <sensille@gmx.net>
      8628764e
    • I
      btrfs scrub: make fixups sync · 96e36920
      由 Ilya Dryomov 提交于 
      btrfs scrub - make fixups sync, don't reuse fixup bios

Fixups are already sync for csum failures, this patch makes them sync
for EIO case as well.

Fixups are now sharing pages with the parent sbio - instead of
allocating a separate page to do a fixup we grab the page from the sbio
buffer.

Fixup bios are no longer reused.

struct fixup is no longer needed, instead pass [sbio pointer, index].

Originally this was added to look at the possibility of sharing the code
between drive swap and scrub, but it actually fixes a serious bug in
scrub code where errors that could be corrected were ignored and
reported as uncorrectable.

btrfs scrub - restore bios properly after media errors

The current code reallocates a bio after a media error.  This is a
temporary measure introduced in v3 after a serious problem related to
bio reuse was found in v2 of scrub patchset.

Basically we did not reset bv_offset and bv_len fields of the bio_vec
structure.  They are changed in case I/O error happens, for example, at
offset 512 or 1024 into the page.  Also bi_flags field wasn't properly
setup before reusing the bio.
Signed-off-by: NArne Jansen <sensille@gmx.net>
      96e36920
    • J
      btrfs: new ioctls for scrub · 475f6387
      由 Jan Schmidt 提交于 
      adds ioctls necessary to start and cancel scrubs, to get current
progress and to get info about devices to be scrubbed.
Note that the scrub is done per-device and that the ioctl only
returns after the scrub for this devices is finished or has been
canceled.
Signed-off-by: NArne Jansen <sensille@gmx.net>
      475f6387