From 0b5649278e39a068aaf91399941bab1b4a4a3cc2 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 9 Jun 2010 10:37:18 +1000 Subject: writeback: pay attention to wbc->nr_to_write in write_cache_pages If a filesystem writes more than one page in ->writepage, write_cache_pages fails to notice this and continues to attempt writeback when wbc->nr_to_write has gone negative - this trace was captured from XFS: wbc_writeback_start: towrt=1024 wbc_writepage: towrt=1024 wbc_writepage: towrt=0 wbc_writepage: towrt=-1 wbc_writepage: towrt=-5 wbc_writepage: towrt=-21 wbc_writepage: towrt=-85 This has adverse effects on filesystem writeback behaviour. write_cache_pages() needs to terminate after a certain number of pages are written, not after a certain number of calls to ->writepage are made. This is a regression introduced by 17bc6c30cf6bfffd816bdc53682dd46fc34a2cf4 ("vfs: Add no_nrwrite_index_update writeback control flag"), but cannot be reverted directly due to subsequent bug fixes that have gone in on top of it. Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig Signed-off-by: Linus Torvalds --- mm/page-writeback.c | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) (limited to 'mm/page-writeback.c') diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 5fa63bdf52e4..b3dbb8040ed5 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -835,7 +835,6 @@ int write_cache_pages(struct address_space *mapping, pgoff_t done_index; int cycled; int range_whole = 0; - long nr_to_write = wbc->nr_to_write; pagevec_init(&pvec, 0); if (wbc->range_cyclic) { @@ -935,11 +934,10 @@ continue_unlock: done = 1; break; } - } + } - if (nr_to_write > 0) { - nr_to_write--; - if (nr_to_write == 0 && + if (wbc->nr_to_write > 0) { + if (--wbc->nr_to_write == 0 && wbc->sync_mode == WB_SYNC_NONE) { /* * We stop writing back only if we are @@ -970,11 +968,8 @@ continue_unlock: end = writeback_index - 1; goto retry; } - if (!wbc->no_nrwrite_index_update) { - if (wbc->range_cyclic || (range_whole && nr_to_write > 0)) - mapping->writeback_index = done_index; - wbc->nr_to_write = nr_to_write; - } + if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) + mapping->writeback_index = done_index; return ret; } -- cgit v1.2.2 From d87815cb2090e07b0b0b2d73dc9740706e92c80c Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 9 Jun 2010 10:37:20 +1000 Subject: writeback: limit write_cache_pages integrity scanning to current EOF sync can currently take a really long time if a concurrent writer is extending a file. The problem is that the dirty pages on the address space grow in the same direction as write_cache_pages scans, so if the writer keeps ahead of writeback, the writeback will not terminate until the writer stops adding dirty pages. For a data integrity sync, we only need to write the pages dirty at the time we start the writeback, so we can stop scanning once we get to the page that was at the end of the file at the time the scan started. This will prevent operations like copying a large file preventing sync from completing as it will not write back pages that were dirtied after the sync was started. This does not impact the existing integrity guarantees, as any dirty page (old or new) within the EOF range at the start of the scan will still be captured. This patch will not prevent sync from blocking on large writes into holes. That requires more complex intervention while this patch only addresses the common append-case of this sync holdoff. Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig Signed-off-by: Linus Torvalds --- mm/page-writeback.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'mm/page-writeback.c') diff --git a/mm/page-writeback.c b/mm/page-writeback.c index b3dbb8040ed5..bbd396ac9546 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -851,7 +851,22 @@ int write_cache_pages(struct address_space *mapping, if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; cycled = 1; /* ignore range_cyclic tests */ + + /* + * If this is a data integrity sync, cap the writeback to the + * current end of file. Any extension to the file that occurs + * after this is a new write and we don't need to write those + * pages out to fulfil our data integrity requirements. If we + * try to write them out, we can get stuck in this scan until + * the concurrent writer stops adding dirty pages and extending + * EOF. + */ + if (wbc->sync_mode == WB_SYNC_ALL && + wbc->range_end == LLONG_MAX) { + end = i_size_read(mapping->host) >> PAGE_CACHE_SHIFT; + } } + retry: done_index = index; while (!done && (index <= end)) { -- cgit v1.2.2