[Ocfs2-devel] [PATCH 1/3] ocfs2: Optimize inode allocation by remembering last group.

[Tao Ma]

In ocfs2, the inode block search looks for the "emptiest" inode
group to allocate from. So if an inode alloc file has many equally
(or almost equally) empty groups, new inodes will tend to get
spread out amongst them, which in turn can put them all over the
disk. This is undesirable because directory operations on conceptually
"nearby" inodes force a large number of seeks.

The good thing is that in ocfs2_alloc_context, there is a field named
ac_last_group which will record the last group we allocate from. So
we can only pass the right group to it and the following allocation
will do as what we expect.

So we add ip_last_used_group in core directory inodes which records
the last used allocation group. Another field named ip_last_used_slot
is also added in case inode stealing happens. When claiming new inode,
we passed in directory's inode so that the allocation can use this
information.
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/inode.c    |    2 ++
 fs/ocfs2/inode.h    |    4 ++++
 fs/ocfs2/namei.c    |    4 ++--
 fs/ocfs2/suballoc.c |   21 +++++++++++++++++++++
 fs/ocfs2/suballoc.h |    2 ++
 5 files changed, 31 insertions(+), 2 deletions(-)

diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 288512c..c3463c1 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -350,6 +350,8 @@ void ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe,
 
 	ocfs2_set_inode_flags(inode);
 
+	OCFS2_I(inode)->ip_last_used_slot = 0;
+	OCFS2_I(inode)->ip_last_used_group = 0;
 	mlog_exit_void();
 }
 
diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
index eb3c302..e1978ac 100644
--- a/fs/ocfs2/inode.h
+++ b/fs/ocfs2/inode.h
@@ -72,6 +72,10 @@ struct ocfs2_inode_info
 
 	struct inode			vfs_inode;
 	struct jbd2_inode		ip_jinode;
+
+	/* Only valid if the inode is the dir. */
+	u32				ip_last_used_slot;
+	u64				ip_last_used_group;
 };
 
 /*
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 02c8026..a601dd5 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -469,8 +469,8 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb,
 
 	*new_fe_bh = NULL;
 
-	status = ocfs2_claim_new_inode(osb, handle, inode_ac, &suballoc_bit,
-				       &fe_blkno);
+	status = ocfs2_claim_new_inode(osb, handle, dir, parent_fe_bh,
+				       inode_ac, &suballoc_bit, &fe_blkno);
 	if (status < 0) {
 		mlog_errno(status);
 		goto leave;
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 226fe21..f75782f 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -1587,6 +1587,8 @@ bail:
 
 int ocfs2_claim_new_inode(struct ocfs2_super *osb,
 			  handle_t *handle,
+			  struct inode *dir,
+			  struct buffer_head *parent_fe_bh,
 			  struct ocfs2_alloc_context *ac,
 			  u16 *suballoc_bit,
 			  u64 *fe_blkno)
@@ -1594,6 +1596,8 @@ int ocfs2_claim_new_inode(struct ocfs2_super *osb,
 	int status;
 	unsigned int num_bits;
 	u64 bg_blkno;
+	struct ocfs2_dinode *parent_fe =
+			(struct ocfs2_dinode *)parent_fe_bh->b_data;
 
 	mlog_entry_void();
 
@@ -1602,6 +1606,21 @@ int ocfs2_claim_new_inode(struct ocfs2_super *osb,
 	BUG_ON(ac->ac_bits_wanted != 1);
 	BUG_ON(ac->ac_which != OCFS2_AC_USE_INODE);
 
+	/*
+	 * Try to allocate inodes from some specific group.
+	 *
+	 * If the parent dir has recorded the last group used in allocation,
+	 * cool, use it. Otherwise if we try to allocate new inode from the
+	 * same slot the parent dir belongs to, use the same chunk.
+	 */
+	if (OCFS2_I(dir)->ip_last_used_group &&
+	    OCFS2_I(dir)->ip_last_used_slot == ac->ac_alloc_slot)
+		ac->ac_last_group = OCFS2_I(dir)->ip_last_used_group;
+	else if (le16_to_cpu(parent_fe->i_suballoc_slot) ==
+		 ac->ac_alloc_slot)
+		ac->ac_last_group = le64_to_cpu(parent_fe->i_blkno) -
+				    le16_to_cpu(parent_fe->i_suballoc_bit);
+
 	status = ocfs2_claim_suballoc_bits(osb,
 					   ac,
 					   handle,
@@ -1620,6 +1639,8 @@ int ocfs2_claim_new_inode(struct ocfs2_super *osb,
 
 	*fe_blkno = bg_blkno + (u64) (*suballoc_bit);
 	ac->ac_bits_given++;
+	OCFS2_I(dir)->ip_last_used_group = ac->ac_last_group;
+	OCFS2_I(dir)->ip_last_used_slot = ac->ac_alloc_slot;
 	status = 0;
 bail:
 	mlog_exit(status);
diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h
index e3c13c7..ea85a4c 100644
--- a/fs/ocfs2/suballoc.h
+++ b/fs/ocfs2/suballoc.h
@@ -88,6 +88,8 @@ int ocfs2_claim_metadata(struct ocfs2_super *osb,
 			 u64 *blkno_start);
 int ocfs2_claim_new_inode(struct ocfs2_super *osb,
 			  handle_t *handle,
+			  struct inode *dir,
+			  struct buffer_head *parent_fe_bh,
 			  struct ocfs2_alloc_context *ac,
 			  u16 *suballoc_bit,
 			  u64 *fe_blkno);
-- 
1.5.4.GIT