aboutsummaryrefslogtreecommitdiffstats
path: root/mm/page-writeback.c
diff options
context:
space:
mode:
authorFengguang Wu <wfg@mail.ustc.edu.cn>2007-10-17 02:30:43 -0400
committerLinus Torvalds <torvalds@woody.linux-foundation.org>2007-10-17 11:43:02 -0400
commit2e6883bdf49abd0e7f0d9b6297fc3be7ebb2250b (patch)
treeaec0418150413c7e9f43fb2ec68bfd24738b0623 /mm/page-writeback.c
parent1f7decf6d9f06dac008b8d66935c0c3b18e564f9 (diff)
writeback: introduce writeback_control.more_io to indicate more io
After making dirty a 100M file, the normal behavior is to start the writeback for all data after 30s delays. But sometimes the following happens instead: - after 30s: ~4M - after 5s: ~4M - after 5s: all remaining 92M Some analyze shows that the internal io dispatch queues goes like this: s_io s_more_io ------------------------- 1) 100M,1K 0 2) 1K 96M 3) 0 96M 1) initial state with a 100M file and a 1K file 2) 4M written, nr_to_write <= 0, so write more 3) 1K written, nr_to_write > 0, no more writes(BUG) nr_to_write > 0 in (3) fools the upper layer to think that data have all been written out. The big dirty file is actually still sitting in s_more_io. We cannot simply splice s_more_io back to s_io as soon as s_io becomes empty, and let the loop in generic_sync_sb_inodes() continue: this may starve newly expired inodes in s_dirty. It is also not an option to draw inodes from both s_more_io and s_dirty, an let the loop go on: this might lead to live locks, and might also starve other superblocks in sync time(well kupdate may still starve some superblocks, that's another bug). We have to return when a full scan of s_io completes. So nr_to_write > 0 does not necessarily mean that "all data are written". This patch introduces a flag writeback_control.more_io to indicate this situation. With it the big dirty file no longer has to wait for the next kupdate invocation 5s later. Cc: David Chinner <dgc@sgi.com> Cc: Ken Chen <kenchen@google.com> Signed-off-by: Fengguang Wu <wfg@mail.ustc.edu.cn> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/page-writeback.c')
-rw-r--r--mm/page-writeback.c9
1 files changed, 6 insertions, 3 deletions
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 334852131588..bcdbbf6c4a85 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -553,6 +553,7 @@ static void background_writeout(unsigned long _min_pages)
553 global_page_state(NR_UNSTABLE_NFS) < background_thresh 553 global_page_state(NR_UNSTABLE_NFS) < background_thresh
554 && min_pages <= 0) 554 && min_pages <= 0)
555 break; 555 break;
556 wbc.more_io = 0;
556 wbc.encountered_congestion = 0; 557 wbc.encountered_congestion = 0;
557 wbc.nr_to_write = MAX_WRITEBACK_PAGES; 558 wbc.nr_to_write = MAX_WRITEBACK_PAGES;
558 wbc.pages_skipped = 0; 559 wbc.pages_skipped = 0;
@@ -560,8 +561,9 @@ static void background_writeout(unsigned long _min_pages)
560 min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write; 561 min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
561 if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) { 562 if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
562 /* Wrote less than expected */ 563 /* Wrote less than expected */
563 congestion_wait(WRITE, HZ/10); 564 if (wbc.encountered_congestion || wbc.more_io)
564 if (!wbc.encountered_congestion) 565 congestion_wait(WRITE, HZ/10);
566 else
565 break; 567 break;
566 } 568 }
567 } 569 }
@@ -626,11 +628,12 @@ static void wb_kupdate(unsigned long arg)
626 global_page_state(NR_UNSTABLE_NFS) + 628 global_page_state(NR_UNSTABLE_NFS) +
627 (inodes_stat.nr_inodes - inodes_stat.nr_unused); 629 (inodes_stat.nr_inodes - inodes_stat.nr_unused);
628 while (nr_to_write > 0) { 630 while (nr_to_write > 0) {
631 wbc.more_io = 0;
629 wbc.encountered_congestion = 0; 632 wbc.encountered_congestion = 0;
630 wbc.nr_to_write = MAX_WRITEBACK_PAGES; 633 wbc.nr_to_write = MAX_WRITEBACK_PAGES;
631 writeback_inodes(&wbc); 634 writeback_inodes(&wbc);
632 if (wbc.nr_to_write > 0) { 635 if (wbc.nr_to_write > 0) {
633 if (wbc.encountered_congestion) 636 if (wbc.encountered_congestion || wbc.more_io)
634 congestion_wait(WRITE, HZ/10); 637 congestion_wait(WRITE, HZ/10);
635 else 638 else
636 break; /* All the old data is written */ 639 break; /* All the old data is written */