]> git.baikalelectronics.ru Git - kernel.git/commit
Write back inode data pages even when the inode itself is locked
authorLinus Torvalds <torvalds@woody.linux-foundation.org>
Fri, 26 Jan 2007 20:53:20 +0000 (12:53 -0800)
committerLinus Torvalds <torvalds@woody.linux-foundation.org>
Fri, 26 Jan 2007 20:53:20 +0000 (12:53 -0800)
commit0da1d307d9456588ab2f7436a7ba6ced06fb6911
tree7c3ad379a17df033501cb2c20921da65d0029002
parentaaed24b50147e8f9a212468315a560ca7d3a2055
Write back inode data pages even when the inode itself is locked

In __writeback_single_inode(), when we find a locked inode and we're not
doing a data-integrity sync, we used to just skip writing entirely,
since we didn't want to wait for the inode to unlock.

However, there's really no reason to skip writing the data pages, which
are likely to be the the bulk of the dirty state anyway (and the main
reason why writeback was started for the non-data-integrity case, of
course!)

Acked-by: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Andrew Morton <akpm@osdl.org>,
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: David Howells <dhowells@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
fs/fs-writeback.c