summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorFengguang Wu <wfg@mail.ustc.edu.cn>2007-10-16 23:30:43 -0700
committerLinus Torvalds <torvalds@woody.linux-foundation.org>2007-10-17 08:43:02 -0700
commit2e6883bdf49abd0e7f0d9b6297fc3be7ebb2250b (patch)
treeaec0418150413c7e9f43fb2ec68bfd24738b0623
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>
-rw-r--r--fs/fs-writeback.c2
-rw-r--r--include/linux/writeback.h1
-rw-r--r--mm/page-writeback.c9
3 files changed, 9 insertions, 3 deletions
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 414df43706c7..71c158ac60a3 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -473,6 +473,8 @@ sync_sb_inodes(struct super_block *sb, struct writeback_control *wbc)
if (wbc->nr_to_write <= 0)
break;
}
+ if (!list_empty(&sb->s_more_io))
+ wbc->more_io = 1;
return; /* Leave any unwritten inodes on s_io */
}
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 52be879793ed..1200868a5dee 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -62,6 +62,7 @@ struct writeback_control {
unsigned for_reclaim:1; /* Invoked from the page allocator */
unsigned for_writepages:1; /* This is a writepages() call */
unsigned range_cyclic:1; /* range_start is cyclic */
+ unsigned more_io:1; /* more io to be dispatched */
};
/*
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)
global_page_state(NR_UNSTABLE_NFS) < background_thresh
&& min_pages <= 0)
break;
+ wbc.more_io = 0;
wbc.encountered_congestion = 0;
wbc.nr_to_write = MAX_WRITEBACK_PAGES;
wbc.pages_skipped = 0;
@@ -560,8 +561,9 @@ static void background_writeout(unsigned long _min_pages)
min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
/* Wrote less than expected */
- congestion_wait(WRITE, HZ/10);
- if (!wbc.encountered_congestion)
+ if (wbc.encountered_congestion || wbc.more_io)
+ congestion_wait(WRITE, HZ/10);
+ else
break;
}
}
@@ -626,11 +628,12 @@ static void wb_kupdate(unsigned long arg)
global_page_state(NR_UNSTABLE_NFS) +
(inodes_stat.nr_inodes - inodes_stat.nr_unused);
while (nr_to_write > 0) {
+ wbc.more_io = 0;
wbc.encountered_congestion = 0;
wbc.nr_to_write = MAX_WRITEBACK_PAGES;
writeback_inodes(&wbc);
if (wbc.nr_to_write > 0) {
- if (wbc.encountered_congestion)
+ if (wbc.encountered_congestion || wbc.more_io)
congestion_wait(WRITE, HZ/10);
else
break; /* All the old data is written */