• Zhang, Yanmin's avatar
    sys_sync(): fix 16% performance regression in ffsb create_4k test · 3beab0b4
    Zhang, Yanmin authored
    I run many ffsb test cases on JBODs (typically 13/12 disks).  Comparing
    with kernel 2.6.30, 2.6.31-rc1 has about 16% regression with
    ffsb_create_4k.  The sub test case creates files continuously for 10
    minitues and every file is 1MB.
    
    Bisect located below patch.
    
    5cee5815 is first bad commit
    commit 5cee5815
    Author: Jan Kara <jack@suse.cz>
    Date:   Mon Apr 27 16:43:51 2009 +0200
    
        vfs: Make sys_sync() use fsync_super() (version 4)
    
        It is unnecessarily fragile to have two places (fsync_super() and do_sync())
        doing data integrity sync of the filesystem. Alter __fsync_super() to
        accommodate needs of both callers and use it. So after this patch
        __fsync_super() is the only place where we gather all the calls needed to
        properly send all data on a filesystem to disk.
    
    As a matter of fact, ffsb calls sys_sync in the end to make sure all data
    is flushed to disks and the flushing is counted into the result.  vmstat
    shows ffsb is blocked when syncing for a long time.  With 2.6.30, ffsb is
    blocked for a short time.
    
    I checked the patch and did experiments to recover the original methods.
    Eventually, the root cause is the patch deletes the calling to
    wakeup_pdflush when syncing, so only ffsb is blocked on disk I/O.
    wakeup_pdflush could ask pdflush to write back pages with ffsb at the
    same time.
    
    [akpm@linux-foundation.org: restore comment too]
    Signed-off-by: default avatarZhang Yanmin <yanmin_zhang@linux.intel.com>
    Cc: Jan Kara <jack@suse.cz>
    Cc: Al Viro <viro@zeniv.linux.org.uk>
    Acked-by: default avatarJens Axboe <jens.axboe@oracle.com>
    Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
    Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
    3beab0b4
sync.c 11.1 KB