Hi all, This patch series add inode steal mechanism for inode allocation. Modification from V1 to V2: 1. Add a new member in ocfs2_super which will record the slot we steal the inode successfully. This will speed up the next steal. 2. Modify the mechanism of inode stealing. Now we will start our search from the node next to it. 3. Remove the last and extra inode allocation in the local slot since there is no evidence that we will have our global bitmap be emptied enough in the time it takes us to search the other allocators. In OCFS2, we allocate the inodes from slot specific inode_alloc to avoid inode creation congestion. The local alloc file grows in a large contiguous chunk. As for a 4K bs, it grows 4M every time. So 1024 inodes will be allocated at a time. Over time, if the fs gets fragmented enough(e.g, the user has created many small files and also delete some of them), we can end up in a situation, whereby we cannot extend the inode_alloc as we don't have a large chunk free in the global_bitmap even if df shows few gigs free. More annoying is that this situation will invariably mean that while one cannot create inodes on one node but can from another node. Still more annoying is that an unused slot may have space for plenty of inodes but is unusable as the user may not be mounting as many nodes anymore. This patch series implement a solution which is to steal inodes from another slot. Now the whole inode allocation process looks like this: 1. Allocate from its own inode_alloc:000X 1) If we can reserve, OK. 2) If fails, try to allocate a large chunk and reserve once again. 2. If 1 fails, try to allocate from the ocfs2_super->inode_steal_slot. This time, Just try to reserve, we don't go for global_bitmap if this inode also can't allocate the inode. 3. If 2 fails, try the node next until we reach that steal slot again. ocfs2_super->inode_steal_slot is initalized as the node next to our own slot. And once the inode stealing successes, we will refresh it with the slot we steal inode from. It will also be reinitalized when the local truncate log or local alloc recovery is flushed in which case the global bitmap may be refreshed.
Tao Ma
2008-Feb-27 22:59 UTC
[Ocfs2-devel] [PATCH 1/3] Add a new parameter for ocfs2_reserve_suballoc_bits.V2
In some cases(Inode stealing from other nodes), we may not want
ocfs2_reserve_suballoc_bits to allocate new groups from the
global_bitmap since it may already be full. So add a new parameter
for this.
Signed-off-by: Tao Ma <tao.ma@oracle.com>
---
fs/ocfs2/suballoc.c | 22 ++++++++++++++++++----
1 files changed, 18 insertions(+), 4 deletions(-)
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 72c198a..3be4e73 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -46,6 +46,9 @@
#include "buffer_head_io.h"
+#define NOT_ALLOC_NEW_GROUP 0
+#define ALLOC_NEW_GROUP 1
+
static inline void ocfs2_debug_bg(struct ocfs2_group_desc *bg);
static inline void ocfs2_debug_suballoc_inode(struct ocfs2_dinode *fe);
static inline u16 ocfs2_find_victim_chain(struct ocfs2_chain_list *cl);
@@ -391,7 +394,8 @@ bail:
static int ocfs2_reserve_suballoc_bits(struct ocfs2_super *osb,
struct ocfs2_alloc_context *ac,
int type,
- u32 slot)
+ u32 slot,
+ int alloc_new_group)
{
int status;
u32 bits_wanted = ac->ac_bits_wanted;
@@ -446,6 +450,14 @@ static int ocfs2_reserve_suballoc_bits(struct ocfs2_super
*osb,
goto bail;
}
+ if (alloc_new_group != ALLOC_NEW_GROUP) {
+ mlog(0, "Alloc File %u Full: wanted=%u, free_bits=%u, "
+ "and we don't alloc a new group for it.\n",
+ slot, bits_wanted, free_bits);
+ status = -ENOSPC;
+ goto bail;
+ }
+
status = ocfs2_block_group_alloc(osb, alloc_inode, bh);
if (status < 0) {
if (status != -ENOSPC)
@@ -490,7 +502,8 @@ int ocfs2_reserve_new_metadata(struct ocfs2_super *osb,
(*ac)->ac_group_search = ocfs2_block_group_search;
status = ocfs2_reserve_suballoc_bits(osb, (*ac),
- EXTENT_ALLOC_SYSTEM_INODE, slot);
+ EXTENT_ALLOC_SYSTEM_INODE,
+ slot, ALLOC_NEW_GROUP);
if (status < 0) {
if (status != -ENOSPC)
mlog_errno(status);
@@ -527,7 +540,7 @@ int ocfs2_reserve_new_inode(struct ocfs2_super *osb,
status = ocfs2_reserve_suballoc_bits(osb, *ac,
INODE_ALLOC_SYSTEM_INODE,
- osb->slot_num);
+ osb->slot_num, ALLOC_NEW_GROUP);
if (status < 0) {
if (status != -ENOSPC)
mlog_errno(status);
@@ -557,7 +570,8 @@ int ocfs2_reserve_cluster_bitmap_bits(struct ocfs2_super
*osb,
status = ocfs2_reserve_suballoc_bits(osb, ac,
GLOBAL_BITMAP_SYSTEM_INODE,
- OCFS2_INVALID_SLOT);
+ OCFS2_INVALID_SLOT,
+ ALLOC_NEW_GROUP);
if (status < 0 && status != -ENOSPC) {
mlog_errno(status);
goto bail;
--
1.5.3.GIT
Tao Ma
2008-Feb-27 23:01 UTC
[Ocfs2-devel] [PATCH 2/3] Add ac_alloc_slot in ocfs2_alloc_context.V2
In inode stealing, we no longer restrict the allocation to
happen in the local node. So it is neccessary for us to add
a new member in ocfs2_alloc_context to indicate which slot
we are using for allocation. We also modify the process of
local alloc so that this member can be used there also.
Signed-off-by: Tao Ma <tao.ma@oracle.com>
---
fs/ocfs2/localalloc.c | 1 +
fs/ocfs2/suballoc.c | 1 +
fs/ocfs2/suballoc.h | 1 +
3 files changed, 3 insertions(+), 0 deletions(-)
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index add1ffd..250b4bc 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -526,6 +526,7 @@ int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb,
}
ac->ac_inode = local_alloc_inode;
+ ac->ac_alloc_slot = osb->slot_num;
ac->ac_which = OCFS2_AC_USE_LOCAL;
get_bh(osb->local_alloc_bh);
ac->ac_bh = osb->local_alloc_bh;
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 3be4e73..33d5573 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -424,6 +424,7 @@ static int ocfs2_reserve_suballoc_bits(struct ocfs2_super
*osb,
}
ac->ac_inode = alloc_inode;
+ ac->ac_alloc_slot = slot;
fe = (struct ocfs2_dinode *) bh->b_data;
if (!OCFS2_IS_VALID_DINODE(fe)) {
diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h
index 8799033..544c600 100644
--- a/fs/ocfs2/suballoc.h
+++ b/fs/ocfs2/suballoc.h
@@ -36,6 +36,7 @@ typedef int (group_search_t)(struct inode *,
struct ocfs2_alloc_context {
struct inode *ac_inode; /* which bitmap are we allocating from? */
struct buffer_head *ac_bh; /* file entry bh */
+ u32 ac_alloc_slot; /* which slot are we allocating from? */
u32 ac_bits_wanted;
u32 ac_bits_given;
#define OCFS2_AC_USE_LOCAL 1
--
1.5.3.GIT
Tao Ma
2008-Feb-27 23:01 UTC
[Ocfs2-devel] [PATCH 3/3] Add inode stealing for ocfs2_reserve_new_inode.V2
Add inode stealing for ocfs2_reserve_new_inode. Now the whole process is:
1. Allocate from its own inode_alloc:000X
1) If we can reserve, OK.
2) If fails, try to allocate a large chunk and reserve once again.
2. If 1 fails, try to allocate from the ocfs2_super->inode_steal_slot.
This time, Just try to reserve, we don't go for global_bitmap if
this inode also can't allocate the inode.
3. If 2 fails, try the node next until we reach that steal slot again.
ocfs2_super->inode_steal_slot is initalized as the node next to our own
slot. And once the inode stealing successes, we will refresh it with
the slot we steal inode from. It will also be reinitalized when the local
truncate log or local alloc recovery is flushed in which case the global
bitmap may be refreshed.
Signed-off-by: Tao Ma <tao.ma@oracle.com>
---
fs/ocfs2/alloc.c | 2 +
fs/ocfs2/localalloc.c | 2 +
fs/ocfs2/namei.c | 2 +-
fs/ocfs2/ocfs2.h | 36 +++++++++++++++++++++++++++++++++-
fs/ocfs2/suballoc.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++-
fs/ocfs2/super.c | 1 +
6 files changed, 88 insertions(+), 5 deletions(-)
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 447206e..f333cdc 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -4788,6 +4788,8 @@ static void ocfs2_truncate_log_worker(struct work_struct
*work)
status = ocfs2_flush_truncate_log(osb);
if (status < 0)
mlog_errno(status);
+ else
+ ocfs2_init_inode_steal_slot(osb);
mlog_exit(status);
}
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index 250b4bc..1965162 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -450,6 +450,8 @@ out_mutex:
iput(main_bm_inode);
out:
+ if (!status)
+ ocfs2_init_inode_steal_slot(osb);
mlog_exit(status);
return status;
}
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index ae9ad95..ab5a227 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -424,7 +424,7 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb,
fe->i_fs_generation = cpu_to_le32(osb->fs_generation);
fe->i_blkno = cpu_to_le64(fe_blkno);
fe->i_suballoc_bit = cpu_to_le16(suballoc_bit);
- fe->i_suballoc_slot = cpu_to_le16(osb->slot_num);
+ fe->i_suballoc_slot = cpu_to_le16(inode_ac->ac_alloc_slot);
fe->i_uid = cpu_to_le32(current->fsuid);
if (dir->i_mode & S_ISGID) {
fe->i_gid = cpu_to_le32(dir->i_gid);
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 6546cef..75b7fe0 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -206,11 +206,13 @@ struct ocfs2_super
u32 s_feature_incompat;
u32 s_feature_ro_compat;
- /* Protects s_next_generaion, osb_flags. Could protect more on
- * osb as it's very short lived. */
+ /* Protects s_next_generation, osb_flags and inode_steal_slot.
+ * Could protect more on osb as it's very short lived.
+ */
spinlock_t osb_lock;
u32 s_next_generation;
unsigned long osb_flags;
+ s16 inode_steal_slot;
unsigned long s_mount_opt;
unsigned int s_atime_quantum;
@@ -522,6 +524,36 @@ static inline unsigned int ocfs2_pages_per_cluster(struct
super_block *sb)
return pages_per_cluster;
}
+static inline void ocfs2_init_inode_steal_slot(struct ocfs2_super *osb)
+{
+ BUG_ON(osb->slot_num == OCFS2_INVALID_SLOT);
+
+ spin_lock(&osb->osb_lock);
+ osb->inode_steal_slot = osb->slot_num + 1;
+ if (osb->inode_steal_slot == osb->max_slots)
+ osb->inode_steal_slot = 0;
+ spin_unlock(&osb->osb_lock);
+}
+
+static inline void ocfs2_set_inode_steal_slot(struct ocfs2_super *osb,
+ u16 slot)
+{
+ spin_lock(&osb->osb_lock);
+ osb->inode_steal_slot = slot;
+ spin_unlock(&osb->osb_lock);
+}
+
+static inline u16 ocfs2_get_inode_steal_slot(struct ocfs2_super *osb)
+{
+ s16 slot;
+
+ spin_lock(&osb->osb_lock);
+ slot = osb->inode_steal_slot;
+ spin_unlock(&osb->osb_lock);
+
+ return slot;
+}
+
#define ocfs2_set_bit ext2_set_bit
#define ocfs2_clear_bit ext2_clear_bit
#define ocfs2_test_bit ext2_test_bit
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 33d5573..1657b7f 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -109,7 +109,7 @@ static inline void ocfs2_block_to_cluster_group(struct inode
*inode,
u64 *bg_blkno,
u16 *bg_bit_off);
-void ocfs2_free_alloc_context(struct ocfs2_alloc_context *ac)
+static void ocfs2_free_ac_resource(struct ocfs2_alloc_context *ac)
{
struct inode *inode = ac->ac_inode;
@@ -120,9 +120,17 @@ void ocfs2_free_alloc_context(struct ocfs2_alloc_context
*ac)
mutex_unlock(&inode->i_mutex);
iput(inode);
+ ac->ac_inode = NULL;
}
- if (ac->ac_bh)
+ if (ac->ac_bh) {
brelse(ac->ac_bh);
+ ac->ac_bh = NULL;
+ }
+}
+
+void ocfs2_free_alloc_context(struct ocfs2_alloc_context *ac)
+{
+ ocfs2_free_ac_resource(ac);
kfree(ac);
}
@@ -522,6 +530,33 @@ bail:
return status;
}
+static int ocfs2_steal_inode_from_other_nodes(struct ocfs2_super *osb,
+ struct ocfs2_alloc_context *ac)
+{
+ int status = -ENOSPC, i;
+ s16 slot = ocfs2_get_inode_steal_slot(osb);
+
+ for (i = 0; i < osb->max_slots; i++, slot++) {
+ if (slot == osb->max_slots)
+ slot = 0;
+
+ if (slot == osb->slot_num)
+ continue;
+
+ status = ocfs2_reserve_suballoc_bits(osb, ac,
+ INODE_ALLOC_SYSTEM_INODE,
+ slot, NOT_ALLOC_NEW_GROUP);
+ if (status >= 0) {
+ ocfs2_set_inode_steal_slot(osb, slot);
+ break;
+ }
+
+ ocfs2_free_ac_resource(ac);
+ }
+
+ return status;
+}
+
int ocfs2_reserve_new_inode(struct ocfs2_super *osb,
struct ocfs2_alloc_context **ac)
{
@@ -542,6 +577,17 @@ int ocfs2_reserve_new_inode(struct ocfs2_super *osb,
status = ocfs2_reserve_suballoc_bits(osb, *ac,
INODE_ALLOC_SYSTEM_INODE,
osb->slot_num, ALLOC_NEW_GROUP);
+ if (status >= 0) {
+ status = 0;
+ goto bail;
+ } else if (status < 0 && status != -ENOSPC) {
+ mlog_errno(status);
+ goto bail;
+ }
+
+ ocfs2_free_ac_resource(*ac);
+
+ status = ocfs2_steal_inode_from_other_nodes(osb, *ac);
if (status < 0) {
if (status != -ENOSPC)
mlog_errno(status);
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index bec75af..c4e82c7 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1193,6 +1193,7 @@ static int ocfs2_mount_volume(struct super_block *sb)
mlog_errno(status);
goto leave;
}
+ ocfs2_init_inode_steal_slot(osb);
/* load all node-local system inodes */
status = ocfs2_init_local_system_inodes(osb);
--
1.5.3.GIT
Mark Fasheh
2008-Feb-28 15:06 UTC
[Ocfs2-devel] [PATCH 1/3] Add a new parameter for ocfs2_reserve_suballoc_bits.V2
On Thu, Feb 28, 2008 at 02:59:04PM +0800, tao.ma wrote:> In some cases(Inode stealing from other nodes), we may not want > ocfs2_reserve_suballoc_bits to allocate new groups from the > global_bitmap since it may already be full. So add a new parameter > for this. > > Signed-off-by: Tao Ma <tao.ma@oracle.com>Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com> -- Mark Fasheh Principal Software Developer, Oracle mark.fasheh@oracle.com