From: Jan Kara 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. Signed-off-by: Jan Kara Signed-off-by: Wu Fengguang --- fs/fs-writeback.c | 27 +++++++++++++++++++++++---- 1 file changed, 23 insertions(+), 4 deletions(-) Fengguang, I've been testing with those writeback fixes you reposted a few days ago and I've been able to still reproduce livelocks with Jan Engelhard's test case. Using writeback tracing I've tracked the problem to the above and with this patch, sync finishes OK (well, it still takes about 15 minutes but that's about expected time given the throughput I see to the disk - the test case randomly dirties pages in a huge file). So could you please add this patch to the previous two send them to Jens for inclusion? --- linux-next.orig/fs/fs-writeback.c 2010-11-10 10:33:41.000000000 +0800 +++ linux-next/fs/fs-writeback.c 2010-11-10 10:33:45.000000000 +0800 @@ -630,6 +630,7 @@ static long wb_writeback(struct bdi_writ }; 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_writ 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_writ 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_writ 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_writ /* * 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 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/