The patch titled
writeback: introduce writeback_control.more_io to indicate more io
has been added to the -mm tree. Its filename is
writeback-introduce-writeback_controlmore_io-to-indicate-more-io.patch
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
------------------------------------------------------
Subject: writeback: introduce writeback_control.more_io to indicate more io
From: Fengguang Wu <wfg@xxxxxxxxxxxxxxxx>
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@xxxxxxx>
Cc: Ken Chen <kenchen@xxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Fengguang Wu <wfg@xxxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
diff -puN fs/fs-writeback.c~writeback-introduce-writeback_controlmore_io-to-indicate-more-io fs/fs-writeback.c
--- a/fs/fs-writeback.c~writeback-introduce-writeback_controlmore_io-to-indicate-more-io
+++ a/fs/fs-writeback.c
@@ -473,6 +473,8 @@ sync_sb_inodes(struct super_block *sb, s
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 -puN include/linux/writeback.h~writeback-introduce-writeback_controlmore_io-to-indicate-more-io include/linux/writeback.h
--- a/include/linux/writeback.h~writeback-introduce-writeback_controlmore_io-to-indicate-more-io
+++ a/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 */
void *fs_private; /* For use by ->writepages() */
};
diff -puN mm/page-writeback.c~writeback-introduce-writeback_controlmore_io-to-indicate-more-io mm/page-writeback.c
--- a/mm/page-writeback.c~writeback-introduce-writeback_controlmore_io-to-indicate-more-io
+++ a/mm/page-writeback.c
@@ -553,6 +553,7 @@ static void background_writeout(unsigned
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
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 */
_
Patches currently in -mm which might be from wfg@xxxxxxxxxxxxxxxx are
i386-call-free_init_pages-with-irqs-enabled-in-alternative_instructions.patch
readahead-compacting-file_ra_state.patch
readahead-mmap-read-around-simplification.patch
readahead-combine-file_ra_stateprev_index-prev_offset-into-prev_pos.patch
readahead-combine-file_ra_stateprev_index-prev_offset-into-prev_pos-fix.patch
readahead-combine-file_ra_stateprev_index-prev_offset-into-prev_pos-fix-2.patch
radixtree-introduce-radix_tree_next_hole.patch
readahead-basic-support-of-interleaved-reads.patch
readahead-remove-the-local-copy-of-ra-in-do_generic_mapping_read.patch
readahead-remove-several-readahead-macros.patch
readahead-remove-the-limit-max_sectors_kb-imposed-on-max_readahead_kb.patch
filemap-trivial-code-cleanups.patch
filemap-convert-some-unsigned-long-to-pgoff_t.patch
make-swappiness-safer-to-use.patch
maps-pssproportional-set-size-accounting-in-smaps.patch
convert-ill-defined-log2-to-ilog2.patch
seqfile-merge-duplite-code-to-seq_open_private.patch
avoid-negative-and-full-width-shifts-in-radix-treec.patch
writeback-fix-time-ordering-of-the-per-superblock-inode-lists-8.patch
writeback-fix-ntfs-with-sb_has_dirty_inodes.patch
writeback-remove-pages_skipped-accounting-in-__block_write_full_page.patch
writeback-introduce-writeback_controlmore_io-to-indicate-more-io.patch
writeback-remove-unnecessary-wait-in-throttle_vm_writeout.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
