summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorJan Kara <jack@suse.cz>2011-01-14 02:45:48 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2011-01-14 04:32:32 +0300
commitb9543dac5bbc4aef0a598965b6b34f6259ab9a9b (patch)
tree255244e6bb9340d4b8ce1fa6b4d2ed4adece4b15
parentaa373cf550994623efb5d49a4d8775bafd10bbc1 (diff)
downloadlinux-b9543dac5bbc4aef0a598965b6b34f6259ab9a9b.tar.xz
writeback: avoid livelocking WB_SYNC_ALL writeback
When wb_writeback() is called in WB_SYNC_ALL mode, work->nr_to_write is usually set to LONG_MAX. The logic in wb_writeback() then calls __writeback_inodes_sb() with nr_to_write == MAX_WRITEBACK_PAGES and we easily end up with non-positive nr_to_write after the function returns, if the inode has more than MAX_WRITEBACK_PAGES dirty pages at the moment. When nr_to_write is <= 0 wb_writeback() decides we need another round of writeback but this is wrong in some cases! For example when a single large file is continuously dirtied, we would never finish syncing it because each pass would be able to write MAX_WRITEBACK_PAGES and inode dirty timestamp never gets updated (as inode is never completely clean). Thus __writeback_inodes_sb() would write the redirtied inode again and again. Fix the issue by setting nr_to_write to LONG_MAX in WB_SYNC_ALL mode. We do not need nr_to_write in WB_SYNC_ALL mode anyway since write_cache_pages() does livelock avoidance using page tagging in WB_SYNC_ALL mode. This makes wb_writeback() call __writeback_inodes_sb() only once on WB_SYNC_ALL. The latter function won't livelock because it works on - a finite set of files by doing queue_io() once at the beginning - a finite set of pages by PAGECACHE_TAG_TOWRITE page tagging After this patch, program from http://lkml.org/lkml/2010/10/24/154 is no longer able to stall sync forever. [fengguang.wu@intel.com: fix locking comment] Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Jan Engelhardt <jengelh@medozas.de> Cc: Jens Axboe <axboe@kernel.dk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--fs/fs-writeback.c27
1 files changed, 23 insertions, 4 deletions
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 9e72d04e706e..e8063c938dd2 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -630,6 +630,7 @@ static long wb_writeback(struct bdi_writeback *wb,
};
unsigned long oldest_jif;
long wrote = 0;
+ long write_chunk;
struct inode *inode;
if (wbc.for_kupdate) {
@@ -642,6 +643,24 @@ static long wb_writeback(struct bdi_writeback *wb,
wbc.range_end = LLONG_MAX;
}
+ /*
+ * WB_SYNC_ALL mode does livelock avoidance by syncing dirty
+ * inodes/pages in one big loop. Setting wbc.nr_to_write=LONG_MAX
+ * here avoids calling into writeback_inodes_wb() more than once.
+ *
+ * The intended call sequence for WB_SYNC_ALL writeback is:
+ *
+ * wb_writeback()
+ * __writeback_inodes_sb() <== called only once
+ * write_cache_pages() <== called once for each inode
+ * (quickly) tag currently dirty pages
+ * (maybe slowly) sync all tagged pages
+ */
+ if (wbc.sync_mode == WB_SYNC_NONE)
+ write_chunk = MAX_WRITEBACK_PAGES;
+ else
+ write_chunk = LONG_MAX;
+
wbc.wb_start = jiffies; /* livelock avoidance */
for (;;) {
/*
@@ -668,7 +687,7 @@ static long wb_writeback(struct bdi_writeback *wb,
break;
wbc.more_io = 0;
- wbc.nr_to_write = MAX_WRITEBACK_PAGES;
+ wbc.nr_to_write = write_chunk;
wbc.pages_skipped = 0;
trace_wbc_writeback_start(&wbc, wb->bdi);
@@ -678,8 +697,8 @@ static long wb_writeback(struct bdi_writeback *wb,
writeback_inodes_wb(wb, &wbc);
trace_wbc_writeback_written(&wbc, wb->bdi);
- work->nr_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
- wrote += MAX_WRITEBACK_PAGES - wbc.nr_to_write;
+ work->nr_pages -= write_chunk - wbc.nr_to_write;
+ wrote += write_chunk - wbc.nr_to_write;
/*
* If we consumed everything, see if we have more
@@ -694,7 +713,7 @@ static long wb_writeback(struct bdi_writeback *wb,
/*
* Did we write something? Try for more
*/
- if (wbc.nr_to_write < MAX_WRITEBACK_PAGES)
+ if (wbc.nr_to_write < write_chunk)
continue;
/*
* Nothing written. Wait for some inode to