aboutsummaryrefslogtreecommitdiffstats
path: root/fs/f2fs
Commit message (Collapse)AuthorAgeFilesLines
* f2fs: drop obsolete node page when it is truncatedJaegeuk Kim2016-02-131-0/+4
| | | | | | | | If a node page is trucated, we'd better drop the page in the node_inode's page cache for better memory footprint. Change-Id: I3c7187676b5899c211857b9b94fad4f2a412e34d Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
* f2fs: introduce NODE_MAPPING for code consistencyJaegeuk Kim2016-02-134-31/+30
| | | | | | | | | This patch adds NODE_MAPPING which is similar as META_MAPPING introduced by Gu Zheng. Change-Id: I535e5fc3573f408245c4630934a308db06e1f999 Cc: Gu Zheng <guz.fnst@cn.fujitsu.com> Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
* f2fs: remove the orphan block page arrayGu Zheng2016-02-131-3/+4
| | | | | | | | | | | | | | As the orphan_blocks may be max to 504, so it is not security and rigorous to store such a large array in the kernel stack as Dan Carpenter said. In fact, grab_meta_page has locked the page in the page cache, and we can use find_get_page() to fetch the page safely in the downstream, so we can remove the page array directly. Change-Id: Ie73897038bc06f6a6342d6fbdab8f8ff36b2cd96 Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com> Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
* f2fs: add help function META_MAPPINGGu Zheng2016-02-135-8/+13
| | | | | | | | | Introduce help function META_MAPPING() to get the cache meta blocks' address space. Change-Id: I5dcfb055444bbdd6160c3b5b631878f135c767ad Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com> Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
* f2fs: move a branch for code redabilityJaegeuk Kim2016-02-131-5/+4
| | | | | | | This patch moves a function in f2fs_delete_entry for code readability. Change-Id: I00419bcbd9d353a95491af6d8ec8e418b45171f3 Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
* f2fs: call mark_inode_dirty to flush dirty pagesJaegeuk Kim2016-02-133-5/+8
| | | | | | | | | If a dentry page is updated, we should call mark_inode_dirty to add the inode into the dirty list, so that its dentry pages are flushed to the disk. Otherwise, the inode can be evicted without flush. Change-Id: Ia31244451976a13a69e99342c5c4f5e5238a7b4f Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
* f2fs: clean checkpatch warningsChris Fries2016-02-1311-30/+40
| | | | | | | | | Fixed a variety of trivial checkpatch warnings. The only delta should be some minor formatting on log strings that were split / too long. Change-Id: I1477b17f7d4e2acd2d5370bb389f0bd064834059 Signed-off-by: Chris Fries <cfries@motorola.com> Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
* f2fs: missing REQ_META and REQ_PRIO when sync_meta_pages(META_FLUSH)Changman Lee2016-02-131-1/+1
| | | | | | | | | | Doing sync_meta_pages with META_FLUSH when checkpoint, we overide rw using WRITE_FLUSH_FUA. At this time, we also should set REQ_META|REQ_PRIO. Change-Id: I079dc24c8d03451c942b150df7650c3967bb3ea1 Signed-off-by: Changman Lee <cm224.lee@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
* f2fs: avoid f2fs_balance_fs call during pageoutJaegeuk Kim2016-02-131-1/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch should resolve the following bug. ========================================================= [ INFO: possible irq lock inversion dependency detected ] 3.13.0-rc5.f2fs+ #6 Not tainted --------------------------------------------------------- kswapd0/41 just changed the state of lock: (&sbi->gc_mutex){+.+.-.}, at: [<ffffffffa030503e>] f2fs_balance_fs+0xae/0xd0 [f2fs] but this lock took another, RECLAIM_FS-READ-unsafe lock in the past: (&sbi->cp_rwsem){++++.?} and interrupts could create inverse lock ordering between them. other info that might help us debug this: Chain exists of: &sbi->gc_mutex --> &sbi->cp_mutex --> &sbi->cp_rwsem Possible interrupt unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&sbi->cp_rwsem); local_irq_disable(); lock(&sbi->gc_mutex); lock(&sbi->cp_mutex); <Interrupt> lock(&sbi->gc_mutex); *** DEADLOCK *** This bug is due to the f2fs_balance_fs call in f2fs_write_data_page. If f2fs_write_data_page is triggered by wbc->for_reclaim via kswapd, it should not call f2fs_balance_fs which tries to get a mutex grabbed by original syscall flow. Change-Id: I795c071696885b5d048750fb10ae53594f896a2f Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
* f2fs: add delimiter to seperate name and value in debug phraseChangman Lee2016-02-131-4/+4
| | | | | | | | | Support for f2fs-tools/tools/f2stat to monitor /sys/kernel/debug/f2fs/status Change-Id: Ic97f5b9da15129a24959d0fbaeb91e1c84c7f1ac Signed-off-by: Changman Lee <cm224.lee@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
* f2fs: use spinlock rather than mutex for better speedGu Zheng2016-02-132-13/+13
| | | | | | | | | | With the 2 previous changes, all the long time operations are moved out of the protection region, so here we can use spinlock rather than mutex (orphan_inode_mutex) for lower overhead. Change-Id: Iafe2320add741da9e119de9f30b0f90799d68b27 Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com> Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
* Fix merge conflictrogersb112016-02-131-7/+9
| | | | Change-Id: I311a4ca284237c557bdbfbc37d1929c905d3c059
* f2fs: move alloc new orphan node out of lock protection regionGu Zheng2016-02-131-6/+9
| | | | | | | | Move alloc new orphan node out of lock protection region. Change-Id: Iea8bae6e1561e1a0644416ae07177c8f165e5393 Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com> Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
* f2fs: remove the needless parameter of f2fs_wait_on_page_writebackYuan Zhong2016-02-136-7/+7
| | | | | | | | | "boo sync" parameter is never referenced in f2fs_wait_on_page_writeback. We should remove this parameter. Change-Id: I14f0cb0eba62c04a53181674d254753b6cdc0f7f Signed-off-by: Yuan Zhong <yuan.mark.zhong@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
* f2fs: add a sysfs entry to control max_victim_searchJaegeuk Kim2016-02-134-3/+12
| | | | | | | | | | | | | | | | | | | | | | | Previously during SSR and GC, the maximum number of retrials to find a victim segment was hard-coded by MAX_VICTIM_SEARCH, 4096 by default. This number makes an effect on IO locality, when SSR mode is activated, which results in performance fluctuation on some low-end devices. If max_victim_search = 4, the victim will be searched like below. ("D" represents a dirty segment, and "*" indicates a selected victim segment.) D1 D2 D3 D4 D5 D6 D7 D8 D9 [ * ] [ * ] [ * ] [ ....] This patch adds a sysfs entry to control the number dynamically through: /sys/fs/f2fs/$dev/max_victim_search Change-Id: I0f98609540351fd7451e3c23bc65f8d165ba13b6 Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
* f2fs: improve write performance under frequent fsync callsJaegeuk Kim2016-02-134-10/+11
| | | | | | | | | | | | | | | | | | | | | | | When considering a bunch of data writes with very frequent fsync calls, we are able to think the following performance regression. N: Node IO, D: Data IO, IO scheduler: cfq Issue pending IOs D1 D2 D3 D4 D1 D2 D3 D4 N1 D2 D3 D4 N1 N2 N1 D3 D4 N2 D1 --> N1 can be selected by cfq becase of the same priority of N and D. Then D3 and D4 would be delayed, resuling in performance degradation. So, when processing the fsync call, it'd better give higher priority to data IOs than node IOs by assigning WRITE and WRITE_SYNC respectively. This patch improves the random wirte performance with frequent fsync calls by up to 10%. Change-Id: I4812ac05db179d83914c7bb0942fa6738280e1ea Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
* f2fs: support 3.0arter972016-02-138-43/+83
| | | | | | | | | | Initial backporting done by nowcomputing, (https://github.com/nowcomputing/f2fs-backports.git) Additional patches required by upstream jaegeuk/f2fs.git/linux-3.4 done by arter97. Change-Id: Ibbd3a608857338482f974fa4b1a8d3c02c267d9f Signed-off-by: Park Ju Hyung <qkrwngud825@gmail.com>
* f2fs: support 3.4Jaegeuk Kim2016-02-1311-56/+49
| | | | | Change-Id: I20b6a2877e072a4b9639001fa0198837cfa74aff Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
* fs: import f2fs from ↵arter972016-02-1324-0/+14820
git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs.git (branch dev) Up-to-date with git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs.git @04a17fb17fafada39f96bfb41ceb2dc1c11b2af6 (f2fs: avoid to read inline data except first page) Change-Id: I1fc76a61defd530c4e97587980ba43e98db6119e Signed-off-by: Park Ju Hyung <qkrwngud825@gmail.com>
generated by cgit v1.1 at 2024-04-30 06:48:42 +0000