[2/5] ocfs2: retry on ENOSPC if sufficient space in truncate log

Commit Message

Andrew Morton July 28, 2016, 9:05 p.m. UTC

From: Eric Ren <[e-mail]>
Subject: ocfs2: retry on ENOSPC if sufficient space in truncate log

The testcase "mmaptruncate" in ocfs2 test suite always fails with ENOSPC
error on small volume (say less than 10G).  This testcase repeatedly
performs "extend" and "truncate" on a file.  Continuously, it truncates
the file to 1/2 of the size, and then extends to 100% of the size.  The
main bitmap will quickly run out of space because the "truncate" code
prevent truncate log from being flushed by
ocfs2_schedule_truncate_log_flush(osb, 1), while truncate log may have
cached lots of clusters.

So retry to allocate after flushing truncate log when ENOSPC is returned. 
And we cannot reuse the deleted blocks before the transaction committed. 
Fortunately, we already have a function to do this -
ocfs2_try_to_free_truncate_log().  Just need to remove the "static"
modifier and put it into the right place.

The "unlock"/"lock" code isn't elegant, but there seems to be no better
option.

[[e-mail]: locking fix]
  Link: http://lkml.kernel.org/r/[e-mail]
Link: http://lkml.kernel.org/r/[e-mail]
Signed-off-by: Eric Ren <[e-mail]>
Reviewed-by: Gang He <[e-mail]>
Reviewed-by: Joseph Qi <[e-mail]>
Cc: Mark Fasheh <[e-mail]>
Cc: Joel Becker <[e-mail]>
Cc: Junxiao Bi <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
---

 fs/ocfs2/alloc.c    |   37 +++++++++++++++++++++++++++++++++++++
 fs/ocfs2/alloc.h    |    2 ++
 fs/ocfs2/aops.c     |   37 -------------------------------------
 fs/ocfs2/suballoc.c |   20 +++++++++++++++++++-
 4 files changed, 58 insertions(+), 38 deletions(-)

Comments

Mark Fasheh July 28, 2016, 9:39 p.m. UTC | #1

On Thu, Jul 28, 2016 at 02:05:59PM -0700, Andrew Morton wrote:
> From: Eric Ren <[e-mail]>
> Subject: ocfs2: retry on ENOSPC if sufficient space in truncate log
> 
> The testcase "mmaptruncate" in ocfs2 test suite always fails with ENOSPC
> error on small volume (say less than 10G).  This testcase repeatedly
> performs "extend" and "truncate" on a file.  Continuously, it truncates
> the file to 1/2 of the size, and then extends to 100% of the size.  The
> main bitmap will quickly run out of space because the "truncate" code
> prevent truncate log from being flushed by
> ocfs2_schedule_truncate_log_flush(osb, 1), while truncate log may have
> cached lots of clusters.
> 
> So retry to allocate after flushing truncate log when ENOSPC is returned. 
> And we cannot reuse the deleted blocks before the transaction committed. 
> Fortunately, we already have a function to do this -
> ocfs2_try_to_free_truncate_log().  Just need to remove the "static"
> modifier and put it into the right place.
> 
> The "unlock"/"lock" code isn't elegant, but there seems to be no better
> option.
> 
> [[e-mail]: locking fix]
>   Link: http://lkml.kernel.org/r/[e-mail]
> Link: http://lkml.kernel.org/r/[e-mail]
> Signed-off-by: Eric Ren <[e-mail]>
> Reviewed-by: Gang He <[e-mail]>
> Reviewed-by: Joseph Qi <[e-mail]>

Thanks for this Eric.

Reviewed-by: Mark Fasheh <[e-mail]>
	--Mark


--
Mark Fasheh

Patch

diff -puN fs/ocfs2/alloc.c~ocfs2-retry-on-enospc-if-sufficient-space-in-truncate-log fs/ocfs2/alloc.c
--- a/fs/ocfs2/alloc.c~ocfs2-retry-on-enospc-if-sufficient-space-in-truncate-log
+++ a/fs/ocfs2/alloc.c
@@ -6106,6 +6106,43 @@  void ocfs2_schedule_truncate_log_flush(s
 	}
 }
 
+/*
+ * Try to flush truncate logs if we can free enough clusters from it.
+ * As for return value, "< 0" means error, "0" no space and "1" means
+ * we have freed enough spaces and let the caller try to allocate again.
+ */
+int ocfs2_try_to_free_truncate_log(struct ocfs2_super *osb,
+					unsigned int needed)
+{
+	tid_t target;
+	int ret = 0;
+	unsigned int truncated_clusters;
+
+	inode_lock(osb->osb_tl_inode);
+	truncated_clusters = osb->truncated_clusters;
+	inode_unlock(osb->osb_tl_inode);
+
+	/*
+	 * Check whether we can succeed in allocating if we free
+	 * the truncate log.
+	 */
+	if (truncated_clusters < needed)
+		goto out;
+
+	ret = ocfs2_flush_truncate_log(osb);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	if (jbd2_journal_start_commit(osb->journal->j_journal, &target)) {
+		jbd2_log_wait_commit(osb->journal->j_journal, target);
+		ret = 1;
+	}
+out:
+	return ret;
+}
+
 static int ocfs2_get_truncate_log_info(struct ocfs2_super *osb,
 				       int slot_num,
 				       struct inode **tl_inode,
diff -puN fs/ocfs2/alloc.h~ocfs2-retry-on-enospc-if-sufficient-space-in-truncate-log fs/ocfs2/alloc.h
--- a/fs/ocfs2/alloc.h~ocfs2-retry-on-enospc-if-sufficient-space-in-truncate-log
+++ a/fs/ocfs2/alloc.h
@@ -188,6 +188,8 @@  int ocfs2_truncate_log_append(struct ocf
 			      u64 start_blk,
 			      unsigned int num_clusters);
 int __ocfs2_flush_truncate_log(struct ocfs2_super *osb);
+int ocfs2_try_to_free_truncate_log(struct ocfs2_super *osb,
+				   unsigned int needed);
 
 /*
  * Process local structure which describes the block unlinks done
diff -puN fs/ocfs2/aops.c~ocfs2-retry-on-enospc-if-sufficient-space-in-truncate-log fs/ocfs2/aops.c
--- a/fs/ocfs2/aops.c~ocfs2-retry-on-enospc-if-sufficient-space-in-truncate-log
+++ a/fs/ocfs2/aops.c
@@ -1645,43 +1645,6 @@  static int ocfs2_zero_tail(struct inode
 	return ret;
 }
 
-/*
- * Try to flush truncate logs if we can free enough clusters from it.
- * As for return value, "< 0" means error, "0" no space and "1" means
- * we have freed enough spaces and let the caller try to allocate again.
- */
-static int ocfs2_try_to_free_truncate_log(struct ocfs2_super *osb,
-					  unsigned int needed)
-{
-	tid_t target;
-	int ret = 0;
-	unsigned int truncated_clusters;
-
-	inode_lock(osb->osb_tl_inode);
-	truncated_clusters = osb->truncated_clusters;
-	inode_unlock(osb->osb_tl_inode);
-
-	/*
-	 * Check whether we can succeed in allocating if we free
-	 * the truncate log.
-	 */
-	if (truncated_clusters < needed)
-		goto out;
-
-	ret = ocfs2_flush_truncate_log(osb);
-	if (ret) {
-		mlog_errno(ret);
-		goto out;
-	}
-
-	if (jbd2_journal_start_commit(osb->journal->j_journal, &target)) {
-		jbd2_log_wait_commit(osb->journal->j_journal, target);
-		ret = 1;
-	}
-out:
-	return ret;
-}
-
 int ocfs2_write_begin_nolock(struct address_space *mapping,
 			     loff_t pos, unsigned len, ocfs2_write_type_t type,
 			     struct page **pagep, void **fsdata,
diff -puN fs/ocfs2/suballoc.c~ocfs2-retry-on-enospc-if-sufficient-space-in-truncate-log fs/ocfs2/suballoc.c
--- a/fs/ocfs2/suballoc.c~ocfs2-retry-on-enospc-if-sufficient-space-in-truncate-log
+++ a/fs/ocfs2/suballoc.c
@@ -1164,7 +1164,8 @@  static int ocfs2_reserve_clusters_with_l
 					     int flags,
 					     struct ocfs2_alloc_context **ac)
 {
-	int status;
+	int status, ret = 0;
+	int retried = 0;
 
 	*ac = kzalloc(sizeof(struct ocfs2_alloc_context), GFP_KERNEL);
 	if (!(*ac)) {
@@ -1189,7 +1190,24 @@  static int ocfs2_reserve_clusters_with_l
 	}
 
 	if (status == -ENOSPC) {
+retry:
 		status = ocfs2_reserve_cluster_bitmap_bits(osb, *ac);
+		/* Retry if there is sufficient space cached in truncate log */
+		if (status == -ENOSPC && !retried) {
+			retried = 1;
+			ocfs2_inode_unlock((*ac)->ac_inode, 1);
+			inode_unlock((*ac)->ac_inode);
+
+			ret = ocfs2_try_to_free_truncate_log(osb, bits_wanted);
+			if (ret == 1)
+				goto retry;
+
+			if (ret < 0)
+				mlog_errno(ret);
+
+			inode_lock((*ac)->ac_inode);
+			ocfs2_inode_lock((*ac)->ac_inode, NULL, 1);
+		}
 		if (status < 0) {
 			if (status != -ENOSPC)
 				mlog_errno(status);