caching_thread()s do all their work under read access to extent_commit_sem.
They give up on this read access only when need_resched() tells them, or
when they exit. As a result, somebody that wants a WRITE access to this sem,
might wait for a long time. Especially this is problematic in
cache_block_group(),
which can be called on critical paths like find_free_extent() and in commit
path via commit_cowonly_roots().
This patch is an RFC, that attempts to fix this problem, by notifying the
caching threads to give up on extent_commit_sem.
On a system with a lot of metadata (~20Gb total metadata, ~10Gb extent tree),
with increased number of caching_threads, commits were very slow,
stuck in commit_cowonly_roots, due to this issue.
With this patch, commits no longer get stuck in commit_cowonly_roots.
This patch is not indented to be applied, just a request to comment on whether
you agree this problem happens, and whether the fix goes in the right direction.
Signed-off-by: Alex Lyakas <alex.btrfs@xxxxxxxxxxxxxxxxx>
---
fs/btrfs/ctree.h | 7 +++++++
fs/btrfs/disk-io.c | 1 +
fs/btrfs/extent-tree.c | 9 +++++----
fs/btrfs/transaction.c | 2 +-
4 files changed, 14 insertions(+), 5 deletions(-)
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index c90be01..b602611 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1427,6 +1427,13 @@ struct btrfs_fs_info {
struct mutex ordered_extent_flush_mutex;
struct rw_semaphore extent_commit_sem;
+ /* notifies the readers to give up on the sem ASAP */
+ atomic_t extent_commit_sem_give_up_read;
+#define BTRFS_DOWN_WRITE_EXTENT_COMMIT_SEM(fs_info) \
+ do { atomic_inc(&(fs_info)->extent_commit_sem_give_up_read); \
+ down_write(&(fs_info)->extent_commit_sem); \
+ atomic_dec(&(fs_info)->extent_commit_sem_give_up_read); \
+ } while (0)
struct rw_semaphore cleanup_work_sem;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 69e9afb..b88e688 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2291,6 +2291,7 @@ int open_ctree(struct super_block *sb,
mutex_init(&fs_info->cleaner_mutex);
mutex_init(&fs_info->volume_mutex);
init_rwsem(&fs_info->extent_commit_sem);
+ atomic_set(&fs_info->extent_commit_sem_give_up_read, 0);
init_rwsem(&fs_info->cleanup_work_sem);
init_rwsem(&fs_info->subvol_sem);
sema_init(&fs_info->uuid_tree_rescan_sem, 1);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 95c6539..28fee78 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -442,7 +442,8 @@ next:
if (ret)
break;
- if (need_resched()) {
+ if (need_resched() ||
+ atomic_read(&fs_info->extent_commit_sem_give_up_read) > 0) {
caching_ctl->progress = last;
btrfs_release_path(path);
up_read(&fs_info->extent_commit_sem);
@@ -632,7 +633,7 @@ static int cache_block_group(struct
btrfs_block_group_cache *cache,
return 0;
}
- down_write(&fs_info->extent_commit_sem);
+ BTRFS_DOWN_WRITE_EXTENT_COMMIT_SEM(fs_info);
atomic_inc(&caching_ctl->count);
list_add_tail(&caching_ctl->list, &fs_info->caching_block_groups);
up_write(&fs_info->extent_commit_sem);
@@ -5462,7 +5463,7 @@ void btrfs_prepare_extent_commit(struct
btrfs_trans_handle *trans,
struct btrfs_block_group_cache *cache;
struct btrfs_space_info *space_info;
- down_write(&fs_info->extent_commit_sem);
+ BTRFS_DOWN_WRITE_EXTENT_COMMIT_SEM(fs_info);
list_for_each_entry_safe(caching_ctl, next,
&fs_info->caching_block_groups, list) {
@@ -8219,7 +8220,7 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
struct btrfs_caching_control *caching_ctl;
struct rb_node *n;
- down_write(&info->extent_commit_sem);
+ BTRFS_DOWN_WRITE_EXTENT_COMMIT_SEM(fs_info);
while (!list_empty(&info->caching_block_groups)) {
caching_ctl = list_entry(info->caching_block_groups.next,
struct btrfs_caching_control, list);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index cac4a3f..976d20a 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -969,7 +969,7 @@ static noinline int commit_cowonly_roots(struct
btrfs_trans_handle *trans,
return ret;
}
- down_write(&fs_info->extent_commit_sem);
+ BTRFS_DOWN_WRITE_EXTENT_COMMIT_SEM(fs_info);
switch_commit_root(fs_info->extent_root);
up_write(&fs_info->extent_commit_sem);
--
1.7.9.5
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
