1. 29 7月, 2014 1 次提交
  2. 12 7月, 2014 1 次提交
  3. 10 7月, 2014 4 次提交
    • G
      eee6160f
    • C
      f2fs: refactor flush_nat_entries codes for reducing NAT writes · aec71382
      Chao Yu 提交于
      Although building NAT journal in cursum reduce the read/write work for NAT
      block, but previous design leave us lower performance when write checkpoint
      frequently for these cases:
      1. if journal in cursum has already full, it's a bit of waste that we flush all
         nat entries to page for persistence, but not to cache any entries.
      2. if journal in cursum is not full, we fill nat entries to journal util
         journal is full, then flush the left dirty entries to disk without merge
         journaled entries, so these journaled entries may be flushed to disk at next
         checkpoint but lost chance to flushed last time.
      
      In this patch we merge dirty entries located in same NAT block to nat entry set,
      and linked all set to list, sorted ascending order by entries' count of set.
      Later we flush entries in sparse set into journal as many as we can, and then
      flush merged entries to disk. In this way we can not only gain in performance,
      but also save lifetime of flash device.
      
      In my testing environment, it shows this patch can help to reduce NAT block
      writes obviously. In hard disk test case: cost time of fsstress is stablely
      reduced by about 5%.
      
      1. virtual machine + hard disk:
      fsstress -p 20 -n 200 -l 5
      		node num	cp count	nodes/cp
      based		4599.6		1803.0		2.551
      patched		2714.6		1829.6		1.483
      
      2. virtual machine + 32g micro SD card:
      fsstress -p 20 -n 200 -l 1 -w -f chown=0 -f creat=4 -f dwrite=0
      -f fdatasync=4 -f fsync=4 -f link=0 -f mkdir=4 -f mknod=4 -f rename=5
      -f rmdir=5 -f symlink=0 -f truncate=4 -f unlink=5 -f write=0 -S
      
      		node num	cp count	nodes/cp
      based		84.5		43.7		1.933
      patched		49.2		40.0		1.23
      
      Our latency of merging op shows not bad when handling extreme case like:
      merging a great number of dirty nats:
      latency(ns)	dirty nat count
      3089219		24922
      5129423		27422
      4000250		24523
      
      change log from v1:
       o fix wrong logic in add_nat_entry when grab a new nat entry set.
       o swith to create slab cache in create_node_manager_caches.
       o use GFP_ATOMIC instead of GFP_NOFS to avoid potential long latency.
      
      change log from v2:
       o make comment position more appropriate suggested by Jaegeuk Kim.
      Signed-off-by: NChao Yu <chao2.yu@samsung.com>
      Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>
      aec71382
    • J
      f2fs: clean up an unused parameter and assignment · a014e037
      Jaegeuk Kim 提交于
      This patch cleans up simple unnecessary codes.
      Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>
      a014e037
    • J
      f2fs: introduce f2fs_do_tmpfile for code consistency · b97a9b5d
      Jaegeuk Kim 提交于
      This patch adds f2fs_do_tmpfile to eliminate the redundant init_inode_metadata
      flow.
      Throught this, we can provide the consistent lock usage, e.g., fi->i_sem,  and
      this will enable better debugging stuffs.
      Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>
      b97a9b5d
  4. 09 7月, 2014 2 次提交
  5. 08 6月, 2014 1 次提交
  6. 04 6月, 2014 2 次提交
  7. 07 5月, 2014 10 次提交
  8. 07 4月, 2014 1 次提交
    • J
      f2fs: introduce f2fs_issue_flush to avoid redundant flush issue · 6b4afdd7
      Jaegeuk Kim 提交于
      Some storage devices show relatively high latencies to complete cache_flush
      commands, even though their normal IO speed is prettry much high. In such
      the case, it needs to merge cache_flush commands as much as possible to avoid
      issuing them redundantly.
      So, this patch introduces a mount option, "-o flush_merge", to mitigate such
      the overhead.
      
      If this option is enabled by user, F2FS merges the cache_flush commands and then
      issues just one cache_flush on behalf of them. Once the single command is
      finished, F2FS sends a completion signal to all the pending threads.
      
      Note that, this option can be used under a workload consisting of very intensive
      concurrent fsync calls, while the storage handles cache_flush commands slowly.
      Signed-off-by: NJaegeuk Kim <jaegeuk.kim@samsung.com>
      6b4afdd7
  9. 01 4月, 2014 1 次提交
  10. 20 3月, 2014 3 次提交
    • J
      f2fs: skip unnecessary node writes during fsync · 479f40c4
      Jaegeuk Kim 提交于
      If multiple redundant fsync calls are triggered, we don't need to write its
      node pages with fsync mark continuously.
      
      So, this patch adds FI_NEED_FSYNC to track whether the latest node block is
      written with the fsync mark or not.
      If the mark was set, a new fsync doesn't need to write a node block.
      Otherwise, we should do a new node block with the mark for roll-forward
      recovery.
      Signed-off-by: NJaegeuk Kim <jaegeuk.kim@samsung.com>
      479f40c4
    • J
      f2fs: introduce fi->i_sem to protect fi's info · d928bfbf
      Jaegeuk Kim 提交于
      This patch introduces fi->i_sem to protect fi's info that includes xattr_ver,
      pino, i_nlink.
      This enables to remove i_mutex during f2fs_sync_file, resulting in performance
      improvement when a number of fsync calls are triggered from many concurrent
      threads.
      Signed-off-by: NJaegeuk Kim <jaegeuk.kim@samsung.com>
      d928bfbf
    • J
      f2fs: throttle the memory footprint with a sysfs entry · cdfc41c1
      Jaegeuk Kim 提交于
      This patch introduces ram_thresh, a sysfs entry, which controls the memory
      footprint used by the free nid list and the nat cache.
      
      Previously, the free nid list was controlled by MAX_FREE_NIDS, while the nat
      cache was managed by NM_WOUT_THRESHOLD.
      However, this approach cannot be applied dynamically according to the system.
      
      So, this patch adds ram_thresh that users can specify the threshold, which is
      in order of 1 / 1024.
      For example, if the total ram size is 4GB and the value is set to 10 by default,
      f2fs tries to control the number of free nids and nat caches not to consume over
      10 * (4GB / 1024) = 10MB.
      Signed-off-by: NJaegeuk Kim <jaegeuk.kim@samsung.com>
      cdfc41c1
  11. 18 3月, 2014 2 次提交
  12. 12 3月, 2014 1 次提交
  13. 10 3月, 2014 1 次提交
  14. 27 2月, 2014 4 次提交
    • C
      f2fs: use existing macro to clean up some codes · 695fd1ed
      Chao Yu 提交于
      This patch use existing macro F2FS_INODE/NEXT_FREE_BLKADDR to clean up some
      codes.
      Signed-off-by: NChao Yu <chao2.yu@samsung.com>
      Signed-off-by: NJaegeuk Kim <jaegeuk.kim@samsung.com>
      695fd1ed
    • C
      f2fs: readahead contiguous SSA blocks for f2fs_gc · 81c1a0f1
      Chao Yu 提交于
      If there are multi segments in one section, we will read those SSA blocks which
      have contiguous address one by one in f2fs_gc. It may lost performance, let's
      read ahead SSA blocks by merge multi read request.
      Signed-off-by: NChao Yu <chao2.yu@samsung.com>
      Signed-off-by: NJaegeuk Kim <jaegeuk.kim@samsung.com>
      81c1a0f1
    • J
      f2fs: add an sysfs entry to control the directory level · ab9fa662
      Jaegeuk Kim 提交于
      This patch adds an sysfs entry to control dir_level used by the large directory.
      
      The description of this entry is:
      
       dir_level                    This parameter controls the directory level to
      			      support large directory. If a directory has a
      			      number of files, it can reduce the file lookup
      			      latency by increasing this dir_level value.
      			      Otherwise, it needs to decrease this value to
      			      reduce the space overhead. The default value is 0.
      Signed-off-by: NJaegeuk Kim <jaegeuk.kim@samsung.com>
      ab9fa662
    • J
      f2fs: introduce large directory support · 38431545
      Jaegeuk Kim 提交于
      This patch introduces an i_dir_level field to support large directory.
      
      Previously, f2fs maintains multi-level hash tables to find a dentry quickly
      from a bunch of chiild dentries in a directory, and the hash tables consist of
      the following tree structure as below.
      
      In Documentation/filesystems/f2fs.txt,
      
      ----------------------
      A : bucket
      B : block
      N : MAX_DIR_HASH_DEPTH
      ----------------------
      
      level #0   | A(2B)
                 |
      level #1   | A(2B) - A(2B)
                 |
      level #2   | A(2B) - A(2B) - A(2B) - A(2B)
           .     |   .       .       .       .
      level #N/2 | A(2B) - A(2B) - A(2B) - A(2B) - A(2B) - ... - A(2B)
           .     |   .       .       .       .
      level #N   | A(4B) - A(4B) - A(4B) - A(4B) - A(4B) - ... - A(4B)
      
      But, if we can guess that a directory will handle a number of child files,
      we don't need to traverse the tree from level #0 to #N all the time.
      Since the lower level tables contain relatively small number of dentries,
      the miss ratio of the target dentry is likely to be high.
      
      In order to avoid that, we can configure the hash tables sparsely from level #0
      like this.
      
      level #0   | A(2B) - A(2B) - A(2B) - A(2B)
      
      level #1   | A(2B) - A(2B) - A(2B) - A(2B) - A(2B) - ... - A(2B)
           .     |   .       .       .       .
      level #N/2 | A(2B) - A(2B) - A(2B) - A(2B) - A(2B) - ... - A(2B)
           .     |   .       .       .       .
      level #N   | A(4B) - A(4B) - A(4B) - A(4B) - A(4B) - ... - A(4B)
      
      With this structure, we can skip the ineffective tree searches in lower level
      hash tables.
      
      This patch adds just a facility for this by introducing i_dir_level in
      f2fs_inode.
      Signed-off-by: NJaegeuk Kim <jaegeuk.kim@samsung.com>
      38431545
  15. 24 2月, 2014 3 次提交
  16. 17 2月, 2014 3 次提交