>From 44c256bbd627ae75039b99724ce3c7caa7f4fd95 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 5 Nov 2010 17:56:03 +0100 Subject: [PATCH] mm: Avoid livelocking of 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 thus we easily end up with negative nr_to_write after the function returns. wb_writeback() then 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). 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 livelock avoidance is done differently for it. 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 --- fs/fs-writeback.c | 18 ++++++++++++++---- 1 files changed, 14 insertions(+), 4 deletions(-) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 6b4d02a..d5873a6 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -629,6 +629,7 @@ 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) { @@ -640,6 +641,15 @@ static long wb_writeback(struct bdi_writeback *wb, wbc.range_start = 0; wbc.range_end = LLONG_MAX; } + /* + * In WB_SYNC_ALL mode, we just want to ignore nr_to_write as + * we need to write everything and livelock avoidance is implemented + * differently. + */ + if (wbc.sync_mode == WB_SYNC_NONE) + write_chunk = MAX_WRITEBACK_PAGES; + else + write_chunk = LONG_MAX; wbc.wb_start = jiffies; /* livelock avoidance */ for (;;) { @@ -665,7 +675,7 @@ 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); @@ -675,8 +685,8 @@ 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 @@ -691,7 +701,7 @@ 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 -- 1.7.1