In ocfs2, the block group search looks for the "emptiest" group
to allocate from. So if the allocator has many equally(or almost
equally) empty groups, new block group will tend to get spread
out amongst them.
We add osb_last_alloc_group in ocfs2_super to record the last used
allocation group so that next time we can allocate inode group
directly from it.
For more details, please see
http://oss.oracle.com/osswiki/OCFS2/DesignDocs/InodeAllocationStrategy.
Signed-off-by: Tao Ma <tao.ma at oracle.com>
---
fs/ocfs2/ocfs2.h | 3 +++
fs/ocfs2/suballoc.c | 18 +++++++++++++++++-
fs/ocfs2/super.c | 1 +
3 files changed, 21 insertions(+), 1 deletions(-)
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 5c77798..a99b53e 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -335,6 +335,9 @@ struct ocfs2_super
struct ocfs2_node_map osb_recovering_orphan_dirs;
unsigned int *osb_orphan_wipes;
wait_queue_head_t osb_wipe_event;
+
+ /* the group we used to allocate inodes. */
+ u64 osb_last_alloc_group;
};
#define OCFS2_SB(sb) ((struct ocfs2_super *)(sb)->s_fs_info)
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 98e32b2..3ab1135 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -49,6 +49,7 @@
#define NOT_ALLOC_NEW_GROUP 0
#define ALLOC_NEW_GROUP 0x1
#define ALLOC_NEW_GROUP_FROM_GLOBAL 0x2
+#define ALLOC_USE_RECORD_GROUP 0x4
#define OCFS2_MAX_INODES_TO_STEAL 1024
@@ -411,6 +412,11 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb,
goto bail;
}
+ if (flags & ALLOC_USE_RECORD_GROUP && osb->osb_last_alloc_group) {
+ mlog(0, "use old allocation group %llu\n",
+ (unsigned long long)osb->osb_last_alloc_group);
+ ac->ac_last_group = osb->osb_last_alloc_group;
+ }
status = ocfs2_claim_clusters(osb,
handle,
ac,
@@ -485,6 +491,15 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb,
alloc_inode->i_blocks = ocfs2_inode_sector_count(alloc_inode);
status = 0;
+
+ if (flags & ALLOC_USE_RECORD_GROUP) {
+ spin_lock(&osb->osb_lock);
+ osb->osb_last_alloc_group = ac->ac_last_group;
+ spin_unlock(&osb->osb_lock);
+ mlog(0, "after reservation, new allocation group is "
+ "%llu\n", (unsigned long long)osb->osb_last_alloc_group);
+ }
+
bail:
if (handle)
ocfs2_commit_trans(osb, handle);
@@ -713,7 +728,8 @@ int ocfs2_reserve_new_inode(struct ocfs2_super *osb,
INODE_ALLOC_SYSTEM_INODE,
osb->slot_num,
ALLOC_NEW_GROUP |
- ALLOC_NEW_GROUP_FROM_GLOBAL);
+ ALLOC_NEW_GROUP_FROM_GLOBAL |
+ ALLOC_USE_RECORD_GROUP);
if (status >= 0) {
status = 0;
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index bc43138..3593759 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -843,6 +843,7 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
osb->osb_commit_interval = parsed_options.commit_interval;
osb->local_alloc_default_bits = ocfs2_megabytes_to_clusters(sb, parsed_options.localalloc_opt);
osb->local_alloc_bits = osb->local_alloc_default_bits;
+ osb->osb_last_alloc_group = 0;
if (osb->s_mount_opt & OCFS2_MOUNT_USRQUOTA &&
!OCFS2_HAS_RO_COMPAT_FEATURE(sb,
OCFS2_FEATURE_RO_COMPAT_USRQUOTA)) {
--
1.5.4.GIT