From: Dave Chinner <dchinner@xxxxxxxxxx>
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.
This commit adds a ->writepage tracepoint inside write_cache_pages() (how the
above trace was generated) and does the revert manually leaving the subsequent
bug fixes intact. ext4 is not affected by this as a previous commit in the
series stops ext4 from using the generic function.
Signed-off-by: Dave Chinner <dchinner@xxxxxxxxxx>
---
include/linux/writeback.h | 9 ---------
include/trace/events/ext4.h | 5 +----
mm/page-writeback.c | 15 +++++----------
3 files changed, 6 insertions(+), 23 deletions(-)
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index cc97d6c..52e82f3 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -56,15 +56,6 @@ struct writeback_control {
unsigned for_reclaim:1; /* Invoked from the page allocator */
unsigned range_cyclic:1; /* range_start is cyclic */
unsigned more_io:1; /* more io to be dispatched */
- /*
- * write_cache_pages() won't update wbc->nr_to_write and
- * mapping->writeback_index if no_nrwrite_index_update
- * is set. write_cache_pages() may write more than we
- * requested and we want to make sure nr_to_write and
- * writeback_index are updated in a consistent manner
- * so we use a single control to update them
- */
- unsigned no_nrwrite_index_update:1;
/*
* For WB_SYNC_ALL, the sb must always be pinned. For WB_SYNC_NONE,
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index f5b1ba9..f3865c7 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -306,7 +306,6 @@ TRACE_EVENT(ext4_da_writepages_result,
__field( int, pages_written )
__field( long, pages_skipped )
__field( char, more_io )
- __field( char, no_nrwrite_index_update )
__field( pgoff_t, writeback_index )
),
@@ -317,16 +316,14 @@ TRACE_EVENT(ext4_da_writepages_result,
__entry->pages_written = pages_written;
__entry->pages_skipped = wbc->pages_skipped;
__entry->more_io = wbc->more_io;
- __entry->no_nrwrite_index_update = wbc->no_nrwrite_index_update;
__entry->writeback_index = inode->i_mapping->writeback_index;
),
- TP_printk("dev %s ino %lu ret %d pages_written %d pages_skipped %ld more_io %d no_nrwrite_index_update %d writeback_index %lu",
+ TP_printk("dev %s ino %lu ret %d pages_written %d pages_skipped %ld more_io %d writeback_index %lu",
jbd2_dev_to_name(__entry->dev),
(unsigned long) __entry->ino, __entry->ret,
__entry->pages_written, __entry->pages_skipped,
__entry->more_io,
- __entry->no_nrwrite_index_update,
(unsigned long) __entry->writeback_index)
);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index caaf954..0fe713d 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -839,7 +839,6 @@ 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) {
@@ -940,11 +939,10 @@ 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
@@ -975,11 +973,8 @@ 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;
}
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
