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, 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 in tact. 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/writeback.h | 1 +
mm/page-writeback.c | 16 ++++++----------
3 files changed, 7 insertions(+), 19 deletions(-)
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index a74837e..488ac1c 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -55,15 +55,6 @@ 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/writeback.h b/include/trace/events/writeback.h
index 72c1a12..5dda40e 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -244,6 +244,7 @@ DEFINE_WBC_EVENT(wbc_writeback_wait);
DEFINE_WBC_EVENT(wbc_balance_dirty_start);
DEFINE_WBC_EVENT(wbc_balance_dirty_written);
DEFINE_WBC_EVENT(wbc_balance_dirty_wait);
+DEFINE_WBC_EVENT(wbc_writepage);
#endif /* _TRACE_WRITEBACK_H */
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 68eb727..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) {
@@ -921,6 +920,7 @@ continue_unlock:
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
+ trace_wbc_writepage(wbc);
ret = (*writepage)(page, wbc, data);
if (unlikely(ret)) {
if (ret == AOP_WRITEPAGE_ACTIVATE) {
@@ -939,11 +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
@@ -974,11 +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;
}
--
1.5.6.5
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
