ocfs2: retry on ENOSPC if sufficient space in truncate log

Quoted 1 line

Quoted 1 line

The testcase "mmaptruncate" in ocfs2 test suite always fails with ENOSPC error on small volume (say less than 10G). This testcase creates 2 threads T1/T2 which race to "truncate"/"extend" a same file repeatedly. Specifically, T1 truncates 1/2 size of a small file while T2 extend to 100% 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 a right place.

Signed-off-by Eric Ren <[email protected]>

---
 fs/ocfs2/alloc.c    | 37 +++++++++++++++++++++++++++++++++++++
 fs/ocfs2/alloc.h    |  2 ++
 fs/ocfs2/aops.c     | 37 -------------------------------------
 fs/ocfs2/suballoc.c | 17 ++++++++++++++++-
 4 files changed, 55 insertions(+), 38 deletions(-)

fs/ocfs2/alloc.c +37 -0

index 460c0ce..7dabbc3 100644
@@ -6106,6 +6106,43 @@ void ocfs2_schedule_truncate_log_flush(struct 
 ocfs2_super *osb,
 	}
 }
 
+/*
+ * 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,

fs/ocfs2/alloc.c +0 -0

 				       struct inode **tl_inode,

fs/ocfs2/alloc.h +2 -0

index f3dc1b0..4a5152e 100644
@@ -188,6 +188,8 @@ int ocfs2_truncate_log_append(struct ocfs2_super *osb,
 			      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

fs/ocfs2/aops.c +0 -37

index c034edf..1802aef 100644
@@ -1645,43 +1645,6 @@ static int ocfs2_zero_tail(struct inode *inode, struct 
 buffer_head *di_bh,
 	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,

fs/ocfs2/aops.c +0 -0

 			     struct page **pagep, void **fsdata,

fs/ocfs2/suballoc.c +2 -1

index 2f19aee..9f7f3b6 100644
@@ -1164,7 +1164,8 @@ static int ocfs2_reserve_clusters_with_limit(struct 
 ocfs2_super *osb,
 					     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);

fs/ocfs2/suballoc.c +14 -0

 	if (!(*ac)) {

@@ -1189,7 +1190,21 @@ static int ocfs2_reserve_clusters_with_limit(struct 
 ocfs2_super *osb,
 	}
 
 	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);
+		}
 		if (status < 0) {
 			if (status != -ENOSPC)

mlog_errno(status);

Signature · 7 lines

2.6.6


_______________________________________________
Ocfs2-devel mailing list
Ocfs2-devel at oss.oracle.com 
https://oss.oracle.com/mailman/listinfo/ocfs2-devel

The testcase "mmaptruncate" in ocfs2 test suite always fails with ENOSPC error on small volume (say less than 10G). This testcase creates 2 threads T1/T2 which race to "truncate"/"extend" a same file repeatedly. Specifically, T1 truncates 1/2 size of a small file while T2 extend to 100% 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 a right place.

Signed-off-by Eric Ren <[email protected]>

---
 fs/ocfs2/alloc.c    | 37 +++++++++++++++++++++++++++++++++++++
 fs/ocfs2/alloc.h    |  2 ++
 fs/ocfs2/aops.c     | 37 -------------------------------------
 fs/ocfs2/suballoc.c | 17 ++++++++++++++++-
 4 files changed, 55 insertions(+), 38 deletions(-)

fs/ocfs2/alloc.c +37 -0

index 460c0ce..7dabbc3 100644
@@ -6106,6 +6106,43 @@ void ocfs2_schedule_truncate_log_flush(struct ocfs2_super *osb,
 	}
 }
 
+/*
+ * 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,

fs/ocfs2/alloc.h +2 -0

index f3dc1b0..4a5152e 100644
@@ -188,6 +188,8 @@ int ocfs2_truncate_log_append(struct ocfs2_super *osb,
 			      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

fs/ocfs2/aops.c +0 -37

index c034edf..1802aef 100644
@@ -1645,43 +1645,6 @@ static int ocfs2_zero_tail(struct inode *inode, struct buffer_head *di_bh,
 	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,

fs/ocfs2/suballoc.c +16 -1

index 2f19aee..9f7f3b6 100644
@@ -1164,7 +1164,8 @@ static int ocfs2_reserve_clusters_with_limit(struct ocfs2_super *osb,
 					     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 +1190,21 @@ static int ocfs2_reserve_clusters_with_limit(struct ocfs2_super *osb,
 	}
 
 	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);
+		}
 		if (status < 0) {
 			if (status != -ENOSPC)
 				mlog_errno(status);

The testcase "mmaptruncate" in ocfs2 test suite always fails with ENOSPC error on small volume (say less than 10G). This testcase creates 2 threads T1/T2 which race to "truncate"/"extend" a same file repeatedly. Specifically, T1 truncates 1/2 size of a small file while T2 extend to 100% 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 a right place.

Signed-off-by Eric Ren <[email protected]>

---
 fs/ocfs2/alloc.c    | 37 +++++++++++++++++++++++++++++++++++++
 fs/ocfs2/alloc.h    |  2 ++
 fs/ocfs2/aops.c     | 37 -------------------------------------
 fs/ocfs2/suballoc.c | 17 ++++++++++++++++-
 4 files changed, 55 insertions(+), 38 deletions(-)

fs/ocfs2/alloc.c +37 -0

index 460c0ce..7dabbc3 100644
@@ -6106,6 +6106,43 @@ void ocfs2_schedule_truncate_log_flush(struct ocfs2_super *osb,
 	}
 }
 
+/*
+ * 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,

fs/ocfs2/alloc.h +2 -0

index f3dc1b0..4a5152e 100644
@@ -188,6 +188,8 @@ int ocfs2_truncate_log_append(struct ocfs2_super *osb,
 			      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

fs/ocfs2/aops.c +0 -37

index c034edf..1802aef 100644
@@ -1645,43 +1645,6 @@ static int ocfs2_zero_tail(struct inode *inode, struct buffer_head *di_bh,
 	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,

fs/ocfs2/suballoc.c +16 -1

index 2f19aee..9f7f3b6 100644
@@ -1164,7 +1164,8 @@ static int ocfs2_reserve_clusters_with_limit(struct ocfs2_super *osb,
 					     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 +1190,21 @@ static int ocfs2_reserve_clusters_with_limit(struct ocfs2_super *osb,
 	}
 
 	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);
+		}
 		if (status < 0) {
 			if (status != -ENOSPC)
 				mlog_errno(status);

NAK, if ocfs2_try_to_free_truncate_log fails, it will lead to double ocfs2_inode_unlock and then BUG.

Quoted 169 lines

The testcase "mmaptruncate" in ocfs2 test suite always fails with ENOSPC error on small volume (say less than 10G). This testcase creates 2 threads T1/T2 which race to "truncate"/"extend" a same file repeatedly. Specifically, T1 truncates 1/2 size of a small file while T2 extend to 100% 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 a right place.

Signed-off-by Eric Ren <[email protected]>

---
  fs/ocfs2/alloc.c    | 37 +++++++++++++++++++++++++++++++++++++
  fs/ocfs2/alloc.h    |  2 ++
  fs/ocfs2/aops.c     | 37 -------------------------------------
  fs/ocfs2/suballoc.c | 17 ++++++++++++++++-
  4 files changed, 55 insertions(+), 38 deletions(-)

fs/ocfs2/alloc.c +37 -0

index 460c0ce..7dabbc3 100644
@@ -6106,6 +6106,43 @@ void ocfs2_schedule_truncate_log_flush(struct ocfs2_super *osb,
  	}
  }
 
+/*
+ * 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,

fs/ocfs2/alloc.h +2 -0

index f3dc1b0..4a5152e 100644
@@ -188,6 +188,8 @@ int ocfs2_truncate_log_append(struct ocfs2_super *osb,
  			      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

fs/ocfs2/aops.c +0 -37

index c034edf..1802aef 100644
@@ -1645,43 +1645,6 @@ static int ocfs2_zero_tail(struct inode *inode, struct buffer_head *di_bh,
  	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,

fs/ocfs2/suballoc.c +16 -1

index 2f19aee..9f7f3b6 100644
@@ -1164,7 +1164,8 @@ static int ocfs2_reserve_clusters_with_limit(struct ocfs2_super *osb,
  					     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 +1190,21 @@ static int ocfs2_reserve_clusters_with_limit(struct ocfs2_super *osb,
  	}
 
  	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);
+		}
  		if (status < 0) {
  			if (status != -ENOSPC)
  				mlog_errno(status);