[PATCH stable-5.4] backport enospc issues during balance

[PATCH stable-5.4] backport enospc issues during balance

[Anand Jain]

Patch 1 is a preparatory patch to reduce conflicts. Patch 2 fixes
balance failure due to ENOSPC in btrfs/156 on arm64 systems with
pagesize=64k. Minor conflicts in fs/btrfs/block-group.c are resolved.
Thanks.

Josef Bacik (2):
  btrfs: don't pass system_chunk into can_overcommit
  btrfs: take overcommit into account in inc_block_group_ro

 fs/btrfs/block-group.c | 38 ++++++++++++++++++++++----------
 fs/btrfs/space-info.c  | 50 +++++++++++++++++-------------------------
 fs/btrfs/space-info.h  |  3 +++
 3 files changed, 49 insertions(+), 42 deletions(-)

-- 
2.18.4

[PATCH stable-5.4 1/2] btrfs: don't pass system_chunk into can_overcommit

[Anand Jain]

From: Josef Bacik <josef@toxicpanda.com>

commit 9f246926b4d5db4c5e8c78e4897757de26c95be6 upstream

We have the space_info, we can just check its flags to see if it's the
system chunk space info.

Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Signed-off-by: Anand Jain <anand.jain@oracle.com>
---
 fs/btrfs/space-info.c | 42 +++++++++++++++---------------------------
 1 file changed, 15 insertions(+), 27 deletions(-)

diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index 6f484f0d347e..e19e538d05f9 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -162,8 +162,7 @@ static inline u64 calc_global_rsv_need_space(struct btrfs_block_rsv *global)
 
 static int can_overcommit(struct btrfs_fs_info *fs_info,
 			  struct btrfs_space_info *space_info, u64 bytes,
-			  enum btrfs_reserve_flush_enum flush,
-			  bool system_chunk)
+			  enum btrfs_reserve_flush_enum flush)
 {
 	u64 profile;
 	u64 avail;
@@ -174,7 +173,7 @@ static int can_overcommit(struct btrfs_fs_info *fs_info,
 	if (space_info->flags & BTRFS_BLOCK_GROUP_DATA)
 		return 0;
 
-	if (system_chunk)
+	if (space_info->flags & BTRFS_BLOCK_GROUP_SYSTEM)
 		profile = btrfs_system_alloc_profile(fs_info);
 	else
 		profile = btrfs_metadata_alloc_profile(fs_info);
@@ -228,8 +227,7 @@ void btrfs_try_granting_tickets(struct btrfs_fs_info *fs_info,
 
 		/* Check and see if our ticket can be satisified now. */
 		if ((used + ticket->bytes <= space_info->total_bytes) ||
-		    can_overcommit(fs_info, space_info, ticket->bytes, flush,
-				   false)) {
+		    can_overcommit(fs_info, space_info, ticket->bytes, flush)) {
 			btrfs_space_info_update_bytes_may_use(fs_info,
 							      space_info,
 							      ticket->bytes);
@@ -634,8 +632,7 @@ static void flush_space(struct btrfs_fs_info *fs_info,
 
 static inline u64
 btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info,
-				 struct btrfs_space_info *space_info,
-				 bool system_chunk)
+				 struct btrfs_space_info *space_info)
 {
 	struct reserve_ticket *ticket;
 	u64 used;
@@ -651,13 +648,12 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info,
 
 	to_reclaim = min_t(u64, num_online_cpus() * SZ_1M, SZ_16M);
 	if (can_overcommit(fs_info, space_info, to_reclaim,
-			   BTRFS_RESERVE_FLUSH_ALL, system_chunk))
+			   BTRFS_RESERVE_FLUSH_ALL))
 		return 0;
 
 	used = btrfs_space_info_used(space_info, true);
 
-	if (can_overcommit(fs_info, space_info, SZ_1M,
-			   BTRFS_RESERVE_FLUSH_ALL, system_chunk))
+	if (can_overcommit(fs_info, space_info, SZ_1M, BTRFS_RESERVE_FLUSH_ALL))
 		expected = div_factor_fine(space_info->total_bytes, 95);
 	else
 		expected = div_factor_fine(space_info->total_bytes, 90);
@@ -673,7 +669,7 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info,
 
 static inline int need_do_async_reclaim(struct btrfs_fs_info *fs_info,
 					struct btrfs_space_info *space_info,
-					u64 used, bool system_chunk)
+					u64 used)
 {
 	u64 thresh = div_factor_fine(space_info->total_bytes, 98);
 
@@ -681,8 +677,7 @@ static inline int need_do_async_reclaim(struct btrfs_fs_info *fs_info,
 	if ((space_info->bytes_used + space_info->bytes_reserved) >= thresh)
 		return 0;
 
-	if (!btrfs_calc_reclaim_metadata_size(fs_info, space_info,
-					      system_chunk))
+	if (!btrfs_calc_reclaim_metadata_size(fs_info, space_info))
 		return 0;
 
 	return (used >= thresh && !btrfs_fs_closing(fs_info) &&
@@ -805,8 +800,7 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work)
 	space_info = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA);
 
 	spin_lock(&space_info->lock);
-	to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info,
-						      false);
+	to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info);
 	if (!to_reclaim) {
 		space_info->flush = 0;
 		spin_unlock(&space_info->lock);
@@ -825,8 +819,7 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work)
 			return;
 		}
 		to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info,
-							      space_info,
-							      false);
+							      space_info);
 		if (last_tickets_id == space_info->tickets_id) {
 			flush_state++;
 		} else {
@@ -898,8 +891,7 @@ static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info,
 	int flush_state;
 
 	spin_lock(&space_info->lock);
-	to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info,
-						      false);
+	to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info);
 	if (!to_reclaim) {
 		spin_unlock(&space_info->lock);
 		return;
@@ -1031,8 +1023,7 @@ static int handle_reserve_ticket(struct btrfs_fs_info *fs_info,
 static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info,
 				    struct btrfs_space_info *space_info,
 				    u64 orig_bytes,
-				    enum btrfs_reserve_flush_enum flush,
-				    bool system_chunk)
+				    enum btrfs_reserve_flush_enum flush)
 {
 	struct reserve_ticket ticket;
 	u64 used;
@@ -1054,8 +1045,7 @@ static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info,
 	 */
 	if (!pending_tickets &&
 	    ((used + orig_bytes <= space_info->total_bytes) ||
-	     can_overcommit(fs_info, space_info, orig_bytes, flush,
-			   system_chunk))) {
+	     can_overcommit(fs_info, space_info, orig_bytes, flush))) {
 		btrfs_space_info_update_bytes_may_use(fs_info, space_info,
 						      orig_bytes);
 		ret = 0;
@@ -1097,8 +1087,7 @@ static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info,
 		 * the async reclaim as we will panic.
 		 */
 		if (!test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags) &&
-		    need_do_async_reclaim(fs_info, space_info,
-					  used, system_chunk) &&
+		    need_do_async_reclaim(fs_info, space_info, used) &&
 		    !work_busy(&fs_info->async_reclaim_work)) {
 			trace_btrfs_trigger_flush(fs_info, space_info->flags,
 						  orig_bytes, flush, "preempt");
@@ -1135,10 +1124,9 @@ int btrfs_reserve_metadata_bytes(struct btrfs_root *root,
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
 	int ret;
-	bool system_chunk = (root == fs_info->chunk_root);
 
 	ret = __reserve_metadata_bytes(fs_info, block_rsv->space_info,
-				       orig_bytes, flush, system_chunk);
+				       orig_bytes, flush);
 	if (ret == -ENOSPC &&
 	    unlikely(root->orphan_cleanup_state == ORPHAN_CLEANUP_STARTED)) {
 		if (block_rsv != global_rsv &&
-- 
2.18.4

[PATCH stable-5.4 2/2] btrfs: take overcommit into account in inc_block_group_ro

[Anand Jain]

From: Josef Bacik <josef@toxicpanda.com>

commit a30a3d2067536cbcce26c055e70cc3a6ae4fd45c upstream

inc_block_group_ro does a calculation to see if we have enough room left
over if we mark this block group as read only in order to see if it's ok
to mark the block group as read only.

The problem is this calculation _only_ works for data, where our used is
always less than our total.  For metadata we will overcommit, so this
will almost always fail for metadata.

Fix this by exporting btrfs_can_overcommit, and then see if we have
enough space to remove the remaining free space in the block group we
are trying to mark read only.  If we do then we can mark this block
group as read only.

Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Signed-off-by: Anand Jain <anand.jain@oracle.com>
---
 fs/btrfs/block-group.c | 38 ++++++++++++++++++++++++++------------
 fs/btrfs/space-info.c  | 18 ++++++++++--------
 fs/btrfs/space-info.h  |  3 +++
 3 files changed, 39 insertions(+), 20 deletions(-)

diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index b167649f5f5d..ace49a999ece 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -1186,7 +1186,6 @@ static int inc_block_group_ro(struct btrfs_block_group_cache *cache, int force)
 {
 	struct btrfs_space_info *sinfo = cache->space_info;
 	u64 num_bytes;
-	u64 sinfo_used;
 	u64 min_allocable_bytes;
 	int ret = -ENOSPC;
 
@@ -1213,20 +1212,38 @@ static int inc_block_group_ro(struct btrfs_block_group_cache *cache, int force)
 
 	num_bytes = cache->key.offset - cache->reserved - cache->pinned -
 		    cache->bytes_super - btrfs_block_group_used(&cache->item);
-	sinfo_used = btrfs_space_info_used(sinfo, true);
 
 	/*
-	 * sinfo_used + num_bytes should always <= sinfo->total_bytes.
-	 *
-	 * Here we make sure if we mark this bg RO, we still have enough
-	 * free space as buffer (if min_allocable_bytes is not 0).
+	 * Data never overcommits, even in mixed mode, so do just the straight
+	 * check of left over space in how much we have allocated.
 	 */
-	if (sinfo_used + num_bytes + min_allocable_bytes <=
-	    sinfo->total_bytes) {
+	if (force) {
+		ret = 0;
+	} else if (sinfo->flags & BTRFS_BLOCK_GROUP_DATA) {
+		u64 sinfo_used = btrfs_space_info_used(sinfo, true);
+
+		/*
+		 * Here we make sure if we mark this bg RO, we still have enough
+		 * free space as buffer.
+		 */
+		if (sinfo_used + num_bytes <= sinfo->total_bytes)
+			ret = 0;
+	} else {
+		/*
+		 * We overcommit metadata, so we need to do the
+		 * btrfs_can_overcommit check here, and we need to pass in
+		 * BTRFS_RESERVE_NO_FLUSH to give ourselves the most amount of
+		 * leeway to allow us to mark this block group as read only.
+		 */
+		if (btrfs_can_overcommit(cache->fs_info, sinfo, num_bytes,
+					 BTRFS_RESERVE_NO_FLUSH))
+			ret = 0;
+	}
+
+	if (!ret) {
 		sinfo->bytes_readonly += num_bytes;
 		cache->ro++;
 		list_add_tail(&cache->ro_list, &sinfo->ro_bgs);
-		ret = 0;
 	}
 out:
 	spin_unlock(&cache->lock);
@@ -1235,9 +1252,6 @@ static int inc_block_group_ro(struct btrfs_block_group_cache *cache, int force)
 		btrfs_info(cache->fs_info,
 			"unable to make block group %llu ro",
 			cache->key.objectid);
-		btrfs_info(cache->fs_info,
-			"sinfo_used=%llu bg_num_bytes=%llu min_allocable=%llu",
-			sinfo_used, num_bytes, min_allocable_bytes);
 		btrfs_dump_space_info(cache->fs_info, cache->space_info, 0, 0);
 	}
 	return ret;
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index e19e538d05f9..90500b6c41fc 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -160,9 +160,9 @@ static inline u64 calc_global_rsv_need_space(struct btrfs_block_rsv *global)
 	return (global->size << 1);
 }
 
-static int can_overcommit(struct btrfs_fs_info *fs_info,
-			  struct btrfs_space_info *space_info, u64 bytes,
-			  enum btrfs_reserve_flush_enum flush)
+int btrfs_can_overcommit(struct btrfs_fs_info *fs_info,
+			 struct btrfs_space_info *space_info, u64 bytes,
+			 enum btrfs_reserve_flush_enum flush)
 {
 	u64 profile;
 	u64 avail;
@@ -227,7 +227,8 @@ void btrfs_try_granting_tickets(struct btrfs_fs_info *fs_info,
 
 		/* Check and see if our ticket can be satisified now. */
 		if ((used + ticket->bytes <= space_info->total_bytes) ||
-		    can_overcommit(fs_info, space_info, ticket->bytes, flush)) {
+		    btrfs_can_overcommit(fs_info, space_info, ticket->bytes,
+					 flush)) {
 			btrfs_space_info_update_bytes_may_use(fs_info,
 							      space_info,
 							      ticket->bytes);
@@ -647,13 +648,14 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info,
 		return to_reclaim;
 
 	to_reclaim = min_t(u64, num_online_cpus() * SZ_1M, SZ_16M);
-	if (can_overcommit(fs_info, space_info, to_reclaim,
-			   BTRFS_RESERVE_FLUSH_ALL))
+	if (btrfs_can_overcommit(fs_info, space_info, to_reclaim,
+				 BTRFS_RESERVE_FLUSH_ALL))
 		return 0;
 
 	used = btrfs_space_info_used(space_info, true);
 
-	if (can_overcommit(fs_info, space_info, SZ_1M, BTRFS_RESERVE_FLUSH_ALL))
+	if (btrfs_can_overcommit(fs_info, space_info, SZ_1M,
+				 BTRFS_RESERVE_FLUSH_ALL))
 		expected = div_factor_fine(space_info->total_bytes, 95);
 	else
 		expected = div_factor_fine(space_info->total_bytes, 90);
@@ -1045,7 +1047,7 @@ static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info,
 	 */
 	if (!pending_tickets &&
 	    ((used + orig_bytes <= space_info->total_bytes) ||
-	     can_overcommit(fs_info, space_info, orig_bytes, flush))) {
+	     btrfs_can_overcommit(fs_info, space_info, orig_bytes, flush))) {
 		btrfs_space_info_update_bytes_may_use(fs_info, space_info,
 						      orig_bytes);
 		ret = 0;
diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h
index 8b9a1d8fefcb..b9cffc62cafa 100644
--- a/fs/btrfs/space-info.h
+++ b/fs/btrfs/space-info.h
@@ -129,6 +129,9 @@ int btrfs_reserve_metadata_bytes(struct btrfs_root *root,
 				 enum btrfs_reserve_flush_enum flush);
 void btrfs_try_granting_tickets(struct btrfs_fs_info *fs_info,
 				struct btrfs_space_info *space_info);
+int btrfs_can_overcommit(struct btrfs_fs_info *fs_info,
+			 struct btrfs_space_info *space_info, u64 bytes,
+			 enum btrfs_reserve_flush_enum flush);
 
 static inline void btrfs_space_info_free_bytes_may_use(
 				struct btrfs_fs_info *fs_info,
-- 
2.18.4

Re: [PATCH stable-5.4] backport enospc issues during balance

[Sasha Levin]

On Wed, Oct 14, 2020 at 10:44:45AM +0800, Anand Jain wrote:
>Patch 1 is a preparatory patch to reduce conflicts. Patch 2 fixes
>balance failure due to ENOSPC in btrfs/156 on arm64 systems with
>pagesize=64k. Minor conflicts in fs/btrfs/block-group.c are resolved.
>Thanks.

Queued up, thanks!

-- 
Thanks,
Sasha