summaryrefslogtreecommitdiffstats
path: root/fs
AgeCommit message (Collapse)Author
2013-07-02Merge branch 'for-linus' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs Pull VFS patches (part 1) from Al Viro: "The major change in this pile is ->readdir() replacement with ->iterate(), dealing with ->f_pos races in ->readdir() instances for good. There's a lot more, but I'd prefer to split the pull request into several stages and this is the first obvious cutoff point." * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (67 commits) [readdir] constify ->actor [readdir] ->readdir() is gone [readdir] convert ecryptfs [readdir] convert coda [readdir] convert ocfs2 [readdir] convert fatfs [readdir] convert xfs [readdir] convert btrfs [readdir] convert hostfs [readdir] convert afs [readdir] convert ncpfs [readdir] convert hfsplus [readdir] convert hfs [readdir] convert befs [readdir] convert cifs [readdir] convert freevxfs [readdir] convert fuse [readdir] convert hpfs reiserfs: switch reiserfs_readdir_dentry to inode reiserfs: is_privroot_deh() needs only directory inode, actually ...
2013-07-02sync: don't block the flusher thread waiting on IODave Chinner
When sync does it's WB_SYNC_ALL writeback, it issues data Io and then immediately waits for IO completion. This is done in the context of the flusher thread, and hence completely ties up the flusher thread for the backing device until all the dirty inodes have been synced. On filesystems that are dirtying inodes constantly and quickly, this means the flusher thread can be tied up for minutes per sync call and hence badly affect system level write IO performance as the page cache cannot be cleaned quickly. We already have a wait loop for IO completion for sync(2), so cut this out of the flusher thread and delegate it to wait_sb_inodes(). Hence we can do rapid IO submission, and then wait for it all to complete. Effect of sync on fsmark before the patch: FSUse% Count Size Files/sec App Overhead ..... 0 640000 4096 35154.6 1026984 0 720000 4096 36740.3 1023844 0 800000 4096 36184.6 916599 0 880000 4096 1282.7 1054367 0 960000 4096 3951.3 918773 0 1040000 4096 40646.2 996448 0 1120000 4096 43610.1 895647 0 1200000 4096 40333.1 921048 And a single sync pass took: real 0m52.407s user 0m0.000s sys 0m0.090s After the patch, there is no impact on fsmark results, and each individual sync(2) operation run concurrently with the same fsmark workload takes roughly 7s: real 0m6.930s user 0m0.000s sys 0m0.039s IOWs, sync is 7-8x faster on a busy filesystem and does not have an adverse impact on ongoing async data write operations. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-06-29Merge branch 'for-linus' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs Pull ubifs fixes from Al Viro: "A couple of ubifs readdir/lseek race fixes. Stable fodder, really nasty..." * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: UBIFS: fix a horrid bug UBIFS: prepare to fix a horrid bug
2013-06-29Merge branch 'perf-urgent-for-linus' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip Pull perf fix from Ingo Molnar: "One more fix for a recently discovered bug" * 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: perf: Disable monitoring on setuid processes for regular users
2013-06-29[readdir] constify ->actorAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] ->readdir() is goneAl Viro
everything's converted to ->iterate() Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert ecryptfsAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert codaAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert ocfs2Al Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert fatfsAl Viro
... pox upon the idiotic ioctls; life would be much easier without those. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert xfsAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert btrfsAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert hostfsAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert afsAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert ncpfsAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert hfsplusAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert hfsAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert befsAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert cifsAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert freevxfsAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert fuseAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert hpfsAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29reiserfs: switch reiserfs_readdir_dentry to inodeAl Viro
... and clean the callers up a bit Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29reiserfs: is_privroot_deh() needs only directory inode, actuallyAl Viro
... and that - only to get the superblock. Privroot is a directory and we don't allow hardlinks to those... Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert reiserfsAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert ntfsAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert isofsAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert jffs2Al Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert f2fsAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert 9pAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert affsAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert adfsAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert logfsAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert jfsAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert cephAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert nfsAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert ext4Al Viro
and trim the living hell out bogosities in inline dir case Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert qnx6Al Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert qnx4Al Viro
... and use strnlen() instead of strlen() - it's done on untrusted data, after all. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert omfsAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert nilfs2Al Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert sysfsAl Viro
get rid of the kludges in sysfs_readdir() Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert gfs2Al Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert exofsAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert bfsAl Viro
... and get rid of that ridiculous mutex in bfs_readdir() Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert procfsAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert openpromfsAl Viro
what the hell is op_mutex for, BTW? Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert efsAl Viro
* sanity checks belong before risky operation, not after it * don't quit as soon as we'd found an entry Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert configfsAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-06-29[readdir] convert romfsAl Viro
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-02-20 08:30:04 +0000