[Ocfs2-devel] [PATCH 4/8] Ocfs2: move a range of extent.

[Ocfs2-devel] [PATCH 4/8] Ocfs2: move a range of extent.

[Tristan Ye]

The range of __ocfs2_move_extent() was within one extent always, it consists
following parts:

1. Duplicates the clusters in pages to new_blkoffset, where extent to be moved.

2. Split the original extent with new extent, coalecse the nearby extents if possible

3. Append old clusters to truncate log.

Signed-off-by: Tristan Ye <tristan.ye@oracle.com>
---
 fs/ocfs2/move_extents.c |   82 +++++++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 82 insertions(+), 0 deletions(-)

diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index 3601545..7e9daab 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -156,6 +156,88 @@ unlock:
 	return ret;
 }
 
+static int __ocfs2_move_extent(handle_t *handle,
+			       struct ocfs2_move_extents_context *context,
+			       u32 cpos, u32 len, u32 p_cpos, u32 new_p_cpos)
+{
+	int ret = 0, index;
+	struct inode *inode = context->inode;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct ocfs2_extent_rec *rec, replace_rec;
+	struct ocfs2_path *path = NULL;
+	struct ocfs2_extent_list *el;
+	u64 ino = ocfs2_metadata_cache_owner(context->et.et_ci);
+	u64 old_blkno = ocfs2_clusters_to_blocks(inode->i_sb, p_cpos);
+
+	ret = ocfs2_duplicate_clusters_by_page(handle, context, cpos, p_cpos,
+					       new_p_cpos, len);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	memset(&replace_rec, 0, sizeof(replace_rec));
+	replace_rec.e_cpos = cpu_to_le32(cpos);
+	replace_rec.e_leaf_clusters = cpu_to_le16(len);
+	replace_rec.e_blkno = cpu_to_le64(ocfs2_clusters_to_blocks(inode->i_sb,
+								   new_p_cpos));
+
+	path = ocfs2_new_path_from_et(&context->et);
+	if (!path) {
+		ret = -ENOMEM;
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = ocfs2_find_path(INODE_CACHE(inode), path, cpos);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	el = path_leaf_el(path);
+
+	index = ocfs2_search_extent_list(el, cpos);
+	if (index == -1 || index >= le16_to_cpu(el->l_next_free_rec)) {
+		ocfs2_error(inode->i_sb,
+			    "Inode %llu has an extent at cpos %u which can no "
+			    "longer be found.\n",
+			    (unsigned long long)ino, cpos);
+		ret = -EROFS;
+		goto out;
+	}
+
+	rec = &el->l_recs[index];
+	replace_rec.e_flags = rec->e_flags;
+
+	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode),
+				      context->et.et_root_bh,
+				      OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = ocfs2_split_extent(handle, &context->et, path, index,
+				 &replace_rec, context->meta_ac,
+				 &context->dealloc);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ocfs2_journal_dirty(handle, context->et.et_root_bh);
+
+	/*
+	 * need I to append truncate log for old clusters?
+	 */
+	if (old_blkno)
+		ret = ocfs2_truncate_log_append(osb, handle, old_blkno, len);
+
+out:
+	return ret;
+}
+
 static int ocfs2_move_extents(struct ocfs2_move_extents_context *context)
 {
 	int status;
-- 
1.5.5

[Ocfs2-devel] [PATCH 0/8] Ocfs2: Online defragmentaion V2.

[Tristan Ye]

Changes since v1:

 *. implement following #2 strategy(simple extent_moving).

	It's a quite rough patches series v2 for online defrag/ext_moving on OCFS2, it's
workable anyway, may look ugly though;) The essence of online file defragmentation is
extents moving like what btrfs and ext4 were doing, adding 'OCFS2_IOC_MOVE_EXT' ioctl
to ocfs2 allows two strategies upon defragmentation:

1. simple-defragmentation-in-kernl, which means kernel will be responsible for
   claiming new clusters, and packing the defragmented extents according to a
   user-specified threshold.

2. simple-extents moving, in this case, userspace play much more important role
   when doing defragmentation, it needs to specify the new physical blk_offset
   where extents will be moved, kernel itself will not do anything more than
   moving the extents per requested, maybe kernel also needs to manage to
   probe/validate the new_blkoffset to guarantee enough free space around there.

Above two operations using the same OCFS2_IOC_MOVE_EXT:
-------------------------------------------------------------------------------
#define OCFS2_MOVE_EXT_FL_AUTO_DEFRAG   (0x00000001)    /* Kernel manages to
                                                           claim new clusters
                                                           as the goal place
                                                           for extents moving */
#define OCFS2_MOVE_EXT_FL_COMPLETE      (0x00000002)    /* Move or defragmenation
                                                           completely gets done.
                                                         */
struct ocfs2_move_extents {
/* All values are in bytes */
        /* in */
        __u64 me_start;         /* Virtual start in the file to move */
        __u64 me_len;           /* Length of the extents to be moved */
        __u64 me_goal;          /* Physical offset of the goal */
        __u64 me_thresh;        /* Maximum distance from goal or threshold
                                   for auto defragmentation */
        __u64 me_flags;         /* flags for the operation:
                                 * - auto defragmentation.
                                 * - refcount,xattr cases.
                                 */

        /* out */
        __u64 me_moved_len;     /* moved length, are we completely done? */
        __u64 me_new_offset;    /* Resulting physical location */
        __u32 me_reserved[2];   /* reserved for futhure */
};
-------------------------------------------------------------------------------

	Following are some interesting data gathered from simple tests:

1. Performance improvement gained on I/O reads:
-------------------------------------------------------------------------------
* Before defragmentation *

[root at ocfs2-box4 ~]# sync
[root at ocfs2-box4 ~]# echo 3>/proc/sys/vm/drop_caches 
[root at ocfs2-box4 ~]# time dd if=/storage/testfile-1 of=/dev/null
640000+0 records in
640000+0 records out
327680000 bytes (328 MB) copied, 19.9351 s, 16.4 MB/s

real	0m19.954s
user	0m0.246s
sys	0m1.111s

* Do defragmentation *

[root at ocfs2-box4 defrag]# ./defrag -s 0 -l 293601280  -t 3145728 /storage/testfile-1

* After defragmentation *

[root at ocfs2-box4 ~]# sync
[root at ocfs2-box4 ~]# echo 3>/proc/sys/vm/drop_caches
[root at ocfs2-box4 ~]# time dd if=/storage/testfile-1 of=/dev/null
640000+0 records in
640000+0 records out
327680000 bytes (328 MB) copied, 6.79885 s, 48.2 MB/s

real	0m6.969s
user	0m0.209s
sys	0m1.063s
-------------------------------------------------------------------------------


2. Extent tree layout via debugfs.ocfs2:
-------------------------------------------------------------------------------
* Before defragmentation *

        Tree Depth: 1   Count: 243   Next Free Rec: 8
        ## Offset        Clusters       Block#
        0  0             1173           86561
        1  1173          1173           84527
        2  2346          1151           81468
        3  3497          1173           76362
        4  4670          1173           74328
        5  5843          1172           66150
        6  7015          1460           70260
        7  8475          662            87680
        SubAlloc Bit: 1   SubAlloc Slot: 0
        Blknum: 86561   Next Leaf: 84527
        CRC32: abf06a6b   ECC: 44bc
        Tree Depth: 0   Count: 252   Next Free Rec: 252
        ## Offset        Clusters       Block#          Flags
        0  1             16             516104          0x0
        1  17            1              554632          0x0
        2  18            7              560144          0x0
        3  25            1              565960          0x0
        4  26            1              572632          0x
	...
	/* around 1700 extent records were hidden there */
	...
	138 9131          1              258968          0x0
        139 9132          1              259568          0x0
        140 9133          1              260168          0x0
        141 9134          1              260768          0x0
        142 9135          1              261368          0x0
        143 9136          1              261968          0x0

* After defragmentation *

      Tree Depth: 1   Count: 243   Next Free Rec: 1
	## Offset        Clusters       Block#
	0  0             9137           66081
	SubAlloc Bit: 1   SubAlloc Slot: 0
	Blknum: 66081   Next Leaf: 0
	CRC32: 22897d34   ECC: 0619
	Tree Depth: 0   Count: 252   Next Free Rec: 6
	## Offset        Clusters       Block#          Flags
	0  1             1600           4412936         0x0 
	1  1601          1595           20669448        0x0 
	2  3196          1600           9358856         0x0 
	3  4796          1404           14516232        0x0 
	4  6200          1600           21627400        0x0 
	5  7800          1337           7483400         0x0 
-------------------------------------------------------------------------------


TO-DO:

1. Adding refcount/xattr support.
2. Free space defragmentation.


Go to http://oss.oracle.com/osswiki/OCFS2/DesignDocs/OnlineDefrag for more details.


Tristan.

[Ocfs2-devel] [PATCH 1/8] Ocfs2: Adding new ioctl code 'OCFS2_IOC_MOVE_EXT' to ocfs2.

[Tristan Ye]

Patch also manages to add a manipulative struture for this ioctl.

Signed-off-by: Tristan Ye <tristan.ye@oracle.com>
---
 fs/ocfs2/ocfs2_ioctl.h |   28 ++++++++++++++++++++++++++++
 1 files changed, 28 insertions(+), 0 deletions(-)

diff --git a/fs/ocfs2/ocfs2_ioctl.h b/fs/ocfs2/ocfs2_ioctl.h
index b46f39b..25c28ec 100644
--- a/fs/ocfs2/ocfs2_ioctl.h
+++ b/fs/ocfs2/ocfs2_ioctl.h
@@ -171,4 +171,32 @@ enum ocfs2_info_type {
 
 #define OCFS2_IOC_INFO		_IOR('o', 5, struct ocfs2_info)
 
+#define OCFS2_MOVE_EXT_FL_AUTO_DEFRAG	(0x00000001)	/* Kernel manages to
+							   claim new clusters
+							   as the goal place
+							   for extents moving */
+#define OCFS2_MOVE_EXT_FL_COMPLETE	(0x00000002)	/* Move or defragmenation
+							   completely gets done.
+							 */
+struct ocfs2_move_extents {
+/* All values are in bytes */
+	/* in */
+	__u64 me_start;		/* Virtual start in the file to move */
+	__u64 me_len;		/* Length of the extents to be moved */
+	__u64 me_goal;		/* Physical offset of the goal,
+				   it's in block unit */
+	__u64 me_thresh;	/* Maximum distance from goal or threshold
+				   for auto defragmentation */
+	__u64 me_flags;		/* flags for the operation:
+				 * - auto defragmentation.
+				 * - refcount,xattr cases.
+				 */
+	/* out */
+	__u64 me_moved_len;	/* moved/defraged length */
+	__u64 me_new_offset;	/* Resulting physical location */
+	__u32 me_reserved[2];	/* reserved for futhure */
+};
+
+#define OCFS2_IOC_MOVE_EXT	_IOW('o', 6, struct ocfs2_move_extents)
+
 #endif /* OCFS2_IOCTL_H */
-- 
1.5.5

[Ocfs2-devel] [PATCH 2/8] Ocfs2: Add basic framework and source files for extent moving.

[Tristan Ye]

Patch tries to do following things:

1. Adding new files move_extents.[c|h] and fill it with basic framework.

2. Adding handler for new ioctl OCFS2_IOC_MOVE_EXT.

Signed-off-by: Tristan Ye <tristan.ye@oracle.com>
---
 fs/ocfs2/Makefile          |    1 +
 fs/ocfs2/cluster/masklog.h |    1 +
 fs/ocfs2/ioctl.c           |    5 +
 fs/ocfs2/move_extents.c    |  240 ++++++++++++++++++++++++++++++++++++++++++++
 fs/ocfs2/move_extents.h    |   22 ++++
 5 files changed, 269 insertions(+), 0 deletions(-)
 create mode 100644 fs/ocfs2/move_extents.c
 create mode 100644 fs/ocfs2/move_extents.h

diff --git a/fs/ocfs2/Makefile b/fs/ocfs2/Makefile
index 07d9fd8..5166f2d 100644
--- a/fs/ocfs2/Makefile
+++ b/fs/ocfs2/Makefile
@@ -30,6 +30,7 @@ ocfs2-objs := \
 	namei.o 		\
 	refcounttree.o		\
 	reservations.o		\
+	move_extents.o		\
 	resize.o		\
 	slot_map.o 		\
 	suballoc.o 		\
diff --git a/fs/ocfs2/cluster/masklog.h b/fs/ocfs2/cluster/masklog.h
index ea2ed9f..36f1cb2 100644
--- a/fs/ocfs2/cluster/masklog.h
+++ b/fs/ocfs2/cluster/masklog.h
@@ -121,6 +121,7 @@
 #define ML_KTHREAD	0x0000000400000000ULL /* kernel thread activity */
 #define ML_RESERVATIONS	0x0000000800000000ULL /* ocfs2 alloc reservations */
 #define ML_CLUSTER	0x0000001000000000ULL /* cluster stack */
+#define ML_MOVE_EXT	0x0000002000000000ULL /* move extents */
 
 #define MLOG_INITIAL_AND_MASK (ML_ERROR|ML_NOTICE)
 #define MLOG_INITIAL_NOT_MASK (ML_ENTRY|ML_EXIT)
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index 7a48681..b8fe7a7 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -23,6 +23,7 @@
 #include "ioctl.h"
 #include "resize.h"
 #include "refcounttree.h"
+#include "move_extents.h"
 
 #include <linux/ext2_fs.h>
 
@@ -523,6 +524,8 @@ long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 			return -EFAULT;
 
 		return ocfs2_info_handle(inode, &info, 0);
+	case OCFS2_IOC_MOVE_EXT:
+		return ocfs2_ioctl_move_extents(filp, (void __user *)arg);
 	default:
 		return -ENOTTY;
 	}
@@ -565,6 +568,8 @@ long ocfs2_compat_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 			return -EFAULT;
 
 		return ocfs2_info_handle(inode, &info, 1);
+	case OCFS2_IOC_MOVE_EXT:
+		break;
 	default:
 		return -ENOIOCTLCMD;
 	}
diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
new file mode 100644
index 0000000..9e9b9fd
--- /dev/null
+++ b/fs/ocfs2/move_extents.c
@@ -0,0 +1,240 @@
+/* -*- mode: c; c-basic-offset: 8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * move_extents.c
+ *
+ * Copyright (C) 2010 Oracle.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+#include <linux/fs.h>
+#include <linux/types.h>
+#include <linux/mount.h>
+#include <linux/swap.h>
+
+#define MLOG_MASK_PREFIX ML_MOVE_EXT
+#include <cluster/masklog.h>
+
+#include "ocfs2.h"
+#include "ocfs2_ioctl.h"
+
+#include "alloc.h"
+#include "aops.h"
+#include "dlmglue.h"
+#include "extent_map.h"
+#include "inode.h"
+#include "journal.h"
+#include "suballoc.h"
+#include "uptodate.h"
+#include "super.h"
+#include "dir.h"
+#include "buffer_head_io.h"
+#include "sysfile.h"
+#include "suballoc.h"
+#include "move_extents.h"
+
+struct ocfs2_move_extents_context {
+	struct inode *inode;
+	struct file *file;
+	int auto_defrag;
+	int credits;
+	u32 new_phys_cpos;
+	u32 clusters_moved;
+	struct ocfs2_move_extents *range;
+	struct ocfs2_extent_tree et;
+	struct ocfs2_alloc_context *meta_ac;
+	struct ocfs2_alloc_context *data_ac;
+	struct ocfs2_cached_dealloc_ctxt dealloc;
+};
+
+static int ocfs2_move_extents(struct ocfs2_move_extents_context *context)
+{
+	int status;
+	handle_t *handle;
+	struct inode *inode = context->inode;
+	struct ocfs2_dinode *di;
+	struct buffer_head *di_bh = NULL;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+
+	if (!inode)
+		return -ENOENT;
+
+	if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb))
+		return -EROFS;
+
+	mutex_lock(&inode->i_mutex);
+
+	/*
+	 * This prevents concurrent writes from other nodes
+	 */
+	status = ocfs2_rw_lock(inode, 1);
+	if (status) {
+		mlog_errno(status);
+		goto out;
+	}
+
+	status = ocfs2_inode_lock(inode, &di_bh, 1);
+	if (status) {
+		mlog_errno(status);
+		goto out_rw_unlock;
+	}
+
+	/*
+	 * rememer ip_xattr_sem also needs to be held if necessary
+	 */
+	down_write(&OCFS2_I(inode)->ip_alloc_sem);
+	/*
+	 * real extents moving codes will be fulfilled later.
+	 * 
+	 * status = __ocfs2_move_extents_range(di_bh, context);
+	 */
+	up_write(&OCFS2_I(inode)->ip_alloc_sem);
+	if (status) {
+		mlog_errno(status);
+		goto out_inode_unlock;
+	}
+
+	/*
+	 * We update ctime for these changes
+	 */
+	handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
+	if (IS_ERR(handle)) {
+		status = PTR_ERR(handle);
+		mlog_errno(status);
+		goto out_inode_unlock;
+	}
+
+	status = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
+					 OCFS2_JOURNAL_ACCESS_WRITE);
+	if (status) {
+		mlog_errno(status);
+		goto out_commit;
+	}
+
+	di = (struct ocfs2_dinode *)di_bh->b_data;
+	inode->i_ctime = CURRENT_TIME;
+	di->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec);
+	di->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
+
+	ocfs2_journal_dirty(handle, di_bh);
+
+out_commit:
+	ocfs2_commit_trans(osb, handle);
+
+out_inode_unlock:
+	brelse(di_bh);
+	ocfs2_inode_unlock(inode, 1);
+out_rw_unlock:
+	ocfs2_rw_unlock(inode, 1);
+out:
+	mutex_unlock(&inode->i_mutex);
+
+	return status;
+}
+
+int ocfs2_ioctl_move_extents(struct file *filp, void __user *argp)
+{
+	int status;
+
+	struct inode *inode = filp->f_path.dentry->d_inode;
+	struct ocfs2_move_extents range;
+	struct ocfs2_move_extents_context *context = NULL;
+
+	status = mnt_want_write(filp->f_path.mnt);
+	if (status)
+		return status;
+
+	status = -EINVAL;
+
+	if ((!S_ISREG(inode->i_mode)) || !(filp->f_mode & FMODE_WRITE))
+		goto out;
+
+	if (inode->i_flags & (S_IMMUTABLE|S_APPEND)) {
+		status = -EPERM;
+		goto out;
+	}
+
+	context = kzalloc(sizeof(struct ocfs2_move_extents_context), GFP_NOFS);
+	if (!context) {
+		status = -ENOMEM;
+		mlog_errno(status);
+		goto out;
+	}
+
+	context->inode = inode;
+	context->file = filp;
+
+	if (!argp) {
+		memset(&range, 0, sizeof(range));
+		range.me_len = (u64)-1;
+		range.me_flags |= OCFS2_MOVE_EXT_FL_AUTO_DEFRAG;
+		context->auto_defrag = 1;
+	} else {
+		if (copy_from_user(&range, (struct ocfs2_move_extents *)argp,
+				   sizeof(range))) {
+			status = -EFAULT;
+			goto out;
+		}
+	}
+
+	if (range.me_start > i_size_read(inode))
+		goto out;
+
+	if (range.me_start + range.me_len > i_size_read(inode))
+			range.me_len = i_size_read(inode) - range.me_start;
+
+	context->range = &range;
+
+	if (range.me_flags & OCFS2_MOVE_EXT_FL_AUTO_DEFRAG) {
+		context->auto_defrag = 1;
+		if (!range.me_thresh)
+			/*
+			 * ok, the default theshold for the defragmentation
+			 * is 1M, since our maximum clustersize was 1M also.
+			 * any thought?
+			 */
+			range.me_thresh = 1024 * 1024;
+	} else {
+		/*
+		 * first best-effort attempt to validate and adjust the goal
+		 * (physical address in block), while it can't guarantee later
+		 * operation can succeed all the time since global_bitmap may
+		 * change a bit over time.
+		 */
+		/*
+		 * real validation codes will be fulfilled later.
+		 *
+		 * status = ocfs2_validate_and_adjust_move_goal(inode, &range);
+		 * if (status)
+		 * 	goto out;
+		*/
+	}
+
+	status = ocfs2_move_extents(context);
+	if (status)
+		mlog_errno(status);
+out:
+	/*
+	 * movement/defragmentation may end up being partially completed,
+	 * that's the reason why we need to return userspace the finished
+	 * length and new_offset even if failure happens somewhere.
+	 */
+	if (argp) {
+		if (copy_to_user((struct ocfs2_move_extents *)argp, &range,
+				sizeof(range)))
+			status = -EFAULT;
+	}
+
+	kfree(context);
+
+	mnt_drop_write(filp->f_path.mnt);
+
+	return status;
+}
diff --git a/fs/ocfs2/move_extents.h b/fs/ocfs2/move_extents.h
new file mode 100644
index 0000000..d9f0f29
--- /dev/null
+++ b/fs/ocfs2/move_extents.h
@@ -0,0 +1,22 @@
+/* -*- mode: c; c-basic-offset: 8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * move_extents.h
+ *
+ * Copyright (C) 2010 Oracle.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+#ifndef OCFS2_MOVE_EXTENTS_H
+#define OCFS2_MOVE_EXTENTS_H
+
+int ocfs2_ioctl_move_extents(struct file *filp,  void __user *argp);
+
+#endif /* OCFS2_MOVE_EXTENTS_H */
-- 
1.5.5

[Ocfs2-devel] [PATCH 3/8] Ocfs2: Duplicate old clusters into new blk_offset by dirty and remap pages.

[Tristan Ye]

Most of codes for duplicating clusters into new_blkoffset where extent will
be moved, were copid from refcounttree's CoW logics, the intention of making
an exact copy here is to make extents moving codes work at the very beginning
,and also avoid interfering refcounttree's codes at most.

Final version will be using some common funcs with refcounttree part.

Signed-off-by: Tristan Ye <tristan.ye@oracle.com>
---
 fs/ocfs2/move_extents.c |  107 +++++++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 107 insertions(+), 0 deletions(-)

diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index 9e9b9fd..dfb3a59 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -54,6 +54,113 @@ struct ocfs2_move_extents_context {
 	struct ocfs2_cached_dealloc_ctxt dealloc;
 };
 
+static int ocfs2_clear_cow_buffer(handle_t *handle, struct buffer_head *bh)
+{
+	BUG_ON(buffer_dirty(bh));
+
+	clear_buffer_mapped(bh);
+
+	return 0;
+}
+
+#define MAX_CONTIG_BYTES        1048576
+
+static inline unsigned int ocfs2_cow_contig_clusters(struct super_block *sb)
+{
+	return ocfs2_clusters_for_bytes(sb, MAX_CONTIG_BYTES);
+}
+
+/*
+ * Duplicate clusters into new blk_offset, following codes were almost taken
+ * from refcounttree.c on CoW.
+ */
+static int ocfs2_duplicate_clusters_by_page(handle_t *handle,
+				struct ocfs2_move_extents_context *context,
+				u32 cpos, u32 old_cluster,
+				u32 new_cluster, u32 len)
+{
+	int ret = 0, partial;
+	struct inode *inode = context->inode;
+	struct ocfs2_caching_info *ci = INODE_CACHE(inode);
+	struct super_block *sb = ocfs2_metadata_cache_get_super(ci);
+	u64 new_block = ocfs2_clusters_to_blocks(sb, new_cluster);
+	struct page *page;
+	pgoff_t page_index;
+	unsigned int from, to, readahead_pages;
+	loff_t offset, end, map_end;
+	struct address_space *mapping = inode->i_mapping;
+
+	mlog(0, "old_cluster %u, new %u, len %u at offset %u\n", old_cluster,
+	     new_cluster, len, cpos);
+
+	readahead_pages =
+		(ocfs2_cow_contig_clusters(sb) <<
+		 OCFS2_SB(sb)->s_clustersize_bits) >> PAGE_CACHE_SHIFT;
+	offset = ((loff_t)cpos) << OCFS2_SB(sb)->s_clustersize_bits;
+	end = offset + (len << OCFS2_SB(sb)->s_clustersize_bits);
+
+	if (end > i_size_read(inode))
+		end = i_size_read(inode);
+
+	while (offset < end) {
+		page_index = offset >> PAGE_CACHE_SHIFT;
+		map_end = ((loff_t)page_index + 1) << PAGE_CACHE_SHIFT;
+		if (map_end > end)
+			map_end = end;
+
+		from = offset & (PAGE_CACHE_SIZE - 1);
+		to = PAGE_CACHE_SIZE;
+		if (map_end & (PAGE_CACHE_SIZE - 1))
+			to = map_end & (PAGE_CACHE_SIZE - 1);
+
+		page = find_or_create_page(mapping, page_index, GFP_NOFS);
+
+		if (PAGE_CACHE_SIZE <= OCFS2_SB(sb)->s_clustersize)
+			BUG_ON(PageDirty(page));
+
+		if (PageReadahead(page) && context->file) {
+			page_cache_async_readahead(mapping,
+						   &context->file->f_ra,
+						   context->file,
+						   page, page_index,
+						   readahead_pages);
+		}
+
+		if (!PageUptodate(page)) {
+			ret = block_read_full_page(page, ocfs2_get_block);
+			if (ret) {
+				mlog_errno(ret);
+				goto unlock;
+			}
+			lock_page(page);
+		}
+
+		if (page_has_buffers(page)) {
+			ret = walk_page_buffers(handle, page_buffers(page),
+						from, to, &partial,
+						ocfs2_clear_cow_buffer);
+			if (ret) {
+				mlog_errno(ret);
+				goto unlock;
+			}
+		}
+
+		ocfs2_map_and_dirty_page(inode,
+					 handle, from, to,
+					 page, 0, &new_block);
+		mark_page_accessed(page);
+unlock:
+		unlock_page(page);
+		page_cache_release(page);
+		page = NULL;
+		offset = map_end;
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
 static int ocfs2_move_extents(struct ocfs2_move_extents_context *context)
 {
 	int status;
-- 
1.5.5

[Ocfs2-devel] [PATCH 4/8] Ocfs2: move a range of extent.

[Tristan Ye]

The moving range of __ocfs2_move_extent() was within one extent always, it consists
following parts:

1. Duplicates the clusters in pages to new_blkoffset, where extent to be moved.

2. Split the original extent with new extent, coalecse the nearby extents if possible

3. Append old clusters to truncate log.

Signed-off-by: Tristan Ye <tristan.ye@oracle.com>
---
 fs/ocfs2/move_extents.c |   88 +++++++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 88 insertions(+), 0 deletions(-)

diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index dfb3a59..f208dcb 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -161,6 +161,94 @@ unlock:
 	return ret;
 }
 
+static int __ocfs2_move_extent(handle_t *handle,
+			       struct ocfs2_move_extents_context *context,
+			       u32 cpos, u32 len, u32 p_cpos, u32 new_p_cpos,
+			       int ext_flags)
+{
+	int ret = 0, index;
+	struct inode *inode = context->inode;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct ocfs2_extent_rec *rec, replace_rec;
+	struct ocfs2_path *path = NULL;
+	struct ocfs2_extent_list *el;
+	u64 ino = ocfs2_metadata_cache_owner(context->et.et_ci);
+	u64 old_blkno = ocfs2_clusters_to_blocks(inode->i_sb, p_cpos);
+
+	ret = ocfs2_duplicate_clusters_by_page(handle, context, cpos, p_cpos,
+					       new_p_cpos, len);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	memset(&replace_rec, 0, sizeof(replace_rec));
+	replace_rec.e_cpos = cpu_to_le32(cpos);
+	replace_rec.e_leaf_clusters = cpu_to_le16(len);
+	replace_rec.e_blkno = cpu_to_le64(ocfs2_clusters_to_blocks(inode->i_sb,
+								   new_p_cpos));
+
+	path = ocfs2_new_path_from_et(&context->et);
+	if (!path) {
+		ret = -ENOMEM;
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = ocfs2_find_path(INODE_CACHE(inode), path, cpos);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	el = path_leaf_el(path);
+
+	index = ocfs2_search_extent_list(el, cpos);
+	if (index == -1 || index >= le16_to_cpu(el->l_next_free_rec)) {
+		ocfs2_error(inode->i_sb,
+			    "Inode %llu has an extent at cpos %u which can no "
+			    "longer be found.\n",
+			    (unsigned long long)ino, cpos);
+		ret = -EROFS;
+		goto out;
+	}
+
+	rec = &el->l_recs[index];
+
+	BUG_ON(ext_flags != rec->e_flags);
+	replace_rec.e_flags = rec->e_flags;
+
+	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode),
+				      context->et.et_root_bh,
+				      OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = ocfs2_split_extent(handle, &context->et, path, index,
+				 &replace_rec, context->meta_ac,
+				 &context->dealloc);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ocfs2_journal_dirty(handle, context->et.et_root_bh);
+
+	context->new_phys_cpos = new_p_cpos;
+
+	/*
+	 * need I to append truncate log for old clusters?
+	 */
+	if (old_blkno)
+		ret = ocfs2_truncate_log_append(osb, handle, old_blkno, len);
+
+out:
+	return ret;
+}
+
+
 static int ocfs2_move_extents(struct ocfs2_move_extents_context *context)
 {
 	int status;
-- 
1.5.5

[Ocfs2-devel] [PATCH 5/8] Ocfs2: lock allocators and reserve metadata blocks and data clusters for extents moving.

[Tristan Ye]

ocfs2_lock_allocators_move_extents() was like the common ocfs2_lock_allocators(),
to lock metadata and data alloctors during extents moving, reserve appropriate
metadata blocks and data clusters, also performa a best- effort to calculate the
credits for journal transaction in one run of movement.

Signed-off-by: Tristan Ye <tristan.ye@oracle.com>
---
 fs/ocfs2/move_extents.c |   63 +++++++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 63 insertions(+), 0 deletions(-)

diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index f208dcb..42cc971 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -248,6 +248,69 @@ out:
 	return ret;
 }
 
+/*
+ * lock allocators, and reserving appropriate number of bits for
+ * meta blocks and data clusters.
+ *
+ * in some cases, we don't need to reserve clusters, just let data_ac
+ * be NULL.
+ */
+static int ocfs2_lock_allocators_move_extents(struct inode *inode,
+					struct ocfs2_extent_tree *et,
+					u32 clusters_to_move,
+					u32 extents_to_split,
+					struct ocfs2_alloc_context **meta_ac,
+					struct ocfs2_alloc_context **data_ac,
+					int extra_blocks,
+					int *credits)
+{
+	int ret, num_free_extents;
+	unsigned int max_recs_needed = 2 * extents_to_split + clusters_to_move;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+
+	num_free_extents = ocfs2_num_free_extents(osb, et);
+	if (num_free_extents < 0) {
+		ret = num_free_extents;
+		mlog_errno(ret);
+		goto out;
+	}
+
+	if (!num_free_extents ||
+	    (ocfs2_sparse_alloc(osb) && num_free_extents < max_recs_needed))
+		extra_blocks += ocfs2_extend_meta_needed(et->et_root_el);
+
+	ret = ocfs2_reserve_new_metadata_blocks(osb, extra_blocks, meta_ac);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	if (data_ac) {
+		ret = ocfs2_reserve_clusters(osb, clusters_to_move, data_ac);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+	}
+
+	*credits += ocfs2_calc_extend_credits(osb->sb, et->et_root_el,
+					      clusters_to_move + 2);
+
+	/*
+	 * we may probably update the 'ctime'.
+	 */
+	mlog(0, "reserve metadata_blocks: %d, data_clusters: %u, credits: %d\n",
+	     extra_blocks, clusters_to_move, *credits);
+out:
+	if (ret) {
+		if (*meta_ac) {
+			ocfs2_free_alloc_context(*meta_ac);
+			*meta_ac = NULL;
+		}
+	}
+
+	return ret;
+}
 
 static int ocfs2_move_extents(struct ocfs2_move_extents_context *context)
 {
-- 
1.5.5

[Ocfs2-devel] [PATCH 6/8] Ocfs2: defrag a range of extent.

[Tristan Ye]

It's a relatively complete function to accomplish defragmentation for entire
or partial extent, one journal handle was kept during the operation, it was
logically doing one more thing than ocfs2_move_extent() acutally, yes, it's
claiming the new clusters itself;-)

Signed-off-by: Tristan Ye <tristan.ye@oracle.com>
---
 fs/ocfs2/move_extents.c |   97 +++++++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 97 insertions(+), 0 deletions(-)

diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index 42cc971..d1b6f07 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -312,6 +312,103 @@ out:
 	return ret;
 }
 
+/*
+ * Using one journal handle to guarantee the data consistency in case
+ * crash happens anywhere.
+ */
+static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context,
+			       u32 cpos, u32 phys_cpos, u32 len, int ext_flags)
+{
+	int ret, credits = 0;
+	handle_t *handle;
+	struct inode *inode = context->inode;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct inode *tl_inode = osb->osb_tl_inode;
+	u32 new_phys_cpos, new_len;
+
+	ret = ocfs2_lock_allocators_move_extents(inode, &context->et, len, 1,
+						 &context->meta_ac,
+						 &context->data_ac,
+						 0, &credits);
+	if (ret) {
+		mlog_errno(ret);
+		return ret;
+	}
+
+	/*
+	 * should be using allocation reservation strategy there?
+	 *
+	 * if (context->data_ac)
+	 *	context->data_ac->ac_resv = &OCFS2_I(inode)->ip_la_data_resv;
+	 */
+
+	mutex_lock(&tl_inode->i_mutex);
+
+	if (ocfs2_truncate_log_needs_flush(osb)) {
+		ret = __ocfs2_flush_truncate_log(osb);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto out;
+		}
+	}
+
+	handle = ocfs2_start_trans(osb, credits);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = __ocfs2_claim_clusters(handle, context->data_ac, 1, len,
+				     &new_phys_cpos, &new_len);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
+	/*
+	 * we're not quite patient here to make multiple attempts for claiming
+	 * enough clusters, failure to claim clusters per-requested is not a
+	 * disaster though, it can only mean partial range of defragmentation
+	 * or extent movements gets gone, users anyway is able to have another
+	 * try as they wish anytime, since they're going to be returned a
+	 * '-ENOSPC' and completed length of this movement.
+	 */
+	if (new_len != len) {
+		mlog(0, "len_claimed: %u, len: %u\n", new_len, len);
+		context->range->me_flags &= ~OCFS2_MOVE_EXT_FL_COMPLETE;
+		ret = -ENOSPC;
+		goto out_commit;
+	}
+
+	mlog(0, "cpos: %u, phys_cpos: %u, new_phys_cpos: %u\n", cpos,
+	     phys_cpos, new_phys_cpos);
+
+	ret = __ocfs2_move_extent(handle, context, cpos, len, phys_cpos,
+				  new_phys_cpos, ext_flags);
+	if (ret)
+		mlog_errno(ret);
+
+out_commit:
+	ocfs2_commit_trans(osb, handle);
+
+out:
+	mutex_unlock(&tl_inode->i_mutex);
+
+	if (context->data_ac) {
+		ocfs2_free_alloc_context(context->data_ac);
+		context->data_ac = NULL;
+	}
+
+	if (context->meta_ac) {
+		ocfs2_free_alloc_context(context->meta_ac);
+		context->meta_ac = NULL;
+	}
+
+	return ret;
+}
+
+
 static int ocfs2_move_extents(struct ocfs2_move_extents_context *context)
 {
 	int status;
-- 
1.5.5

[Ocfs2-devel] [PATCH 7/8] Ocfs2: move entire/partial extent.

[Tristan Ye]

ocfs2_move_extent() logic will validate the goal_offset_in_block,
where extents to be moved, what's more, it also compromises a bit
to probe the appropriate region around given goal_offset when the
original goal is not able to fit the movement.

Signed-off-by: Tristan Ye <tristan.ye@oracle.com>
---
 fs/ocfs2/move_extents.c |  419 ++++++++++++++++++++++++++++++++++++++++++++++-
 1 files changed, 412 insertions(+), 7 deletions(-)

diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index d1b6f07..ce97c76 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -408,6 +408,414 @@ out:
 	return ret;
 }
 
+/*
+ * find the victim alloc group, where #blkno fits.
+ */
+static int ocfs2_find_victim_alloc_group(struct inode *inode,
+					 u64 vict_blkno,
+					 int type, int slot,
+					 int *vict_bit,
+					 struct buffer_head **ret_bh)
+{
+	int ret, i, blocks_per_unit = 1;
+	u64 blkno;
+	char namebuf[40];
+
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct buffer_head *ac_bh = NULL, *gd_bh = NULL;
+	struct ocfs2_chain_list *cl;
+	struct ocfs2_chain_rec *rec;
+	struct ocfs2_dinode *ac_dinode;
+	struct ocfs2_group_desc *bg;
+
+	ocfs2_sprintf_system_inode_name(namebuf, sizeof(namebuf), type, slot);
+	ret = ocfs2_lookup_ino_from_name(osb->sys_root_inode, namebuf,
+					 strlen(namebuf), &blkno);
+	if (ret) {
+		ret = -ENOENT;
+		goto out;
+	}
+
+	ret = ocfs2_read_blocks_sync(osb, blkno, 1, &ac_bh);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ac_dinode = (struct ocfs2_dinode *)ac_bh->b_data;
+	cl = &(ac_dinode->id2.i_chain);
+	rec = &(cl->cl_recs[0]);
+
+	if (type == GLOBAL_BITMAP_SYSTEM_INODE)
+		blocks_per_unit <<= (osb->s_clustersize_bits -
+						inode->i_sb->s_blocksize_bits);
+	/*
+	 * 'vict_blkno' was out of the valid range.
+	 */
+	if ((vict_blkno < le64_to_cpu(rec->c_blkno)) ||
+	    (vict_blkno >= (le32_to_cpu(ac_dinode->id1.bitmap1.i_total) *
+				blocks_per_unit))) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	for (i = 0; i < le16_to_cpu(cl->cl_next_free_rec); i++) {
+
+		rec = &(cl->cl_recs[i]);
+		if (!rec)
+			continue;
+
+		bg = NULL;
+
+		do {
+			if (!bg)
+				blkno = le64_to_cpu(rec->c_blkno);
+			else
+				blkno = le64_to_cpu(bg->bg_next_group);
+
+			if (gd_bh) {
+				brelse(gd_bh);
+				gd_bh = NULL;
+			}
+
+			ret = ocfs2_read_blocks_sync(osb, blkno, 1, &gd_bh);
+			if (ret) {
+				mlog_errno(ret);
+				goto out;
+			}
+
+			bg = (struct ocfs2_group_desc *)gd_bh->b_data;
+
+			if (vict_blkno < (le64_to_cpu(bg->bg_blkno) +
+						le16_to_cpu(bg->bg_bits))) {
+
+				*ret_bh = gd_bh;
+				*vict_bit = (vict_blkno - blkno) /
+							blocks_per_unit;
+				mlog(0, "find the victim group: #%llu, "
+				     "total_bits: %u, vict_bit: %u\n",
+				     blkno, le16_to_cpu(bg->bg_bits),
+				     *vict_bit);
+				goto out;
+			}
+
+		} while (le64_to_cpu(bg->bg_next_group));
+	}
+
+	ret = -EINVAL;
+out:
+	brelse(ac_bh);
+
+	/*
+	 * caller has to release the gd_bh properly.
+	 */
+	return ret;
+}
+
+/*
+ * XXX: helper to validate and adjust moving goal.
+ */
+static int ocfs2_validate_and_adjust_move_goal(struct inode *inode,
+					       struct ocfs2_move_extents *range)
+{
+	int ret, goal_bit = 0;
+
+	struct buffer_head *gd_bh = NULL;
+	struct ocfs2_group_desc *bg;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	int c_to_b = 1 << (osb->s_clustersize_bits -
+					inode->i_sb->s_blocksize_bits);
+
+	/*
+	 * validate goal sits within global_bitmap, and return the victim
+	 * group desc
+	 */
+	ret = ocfs2_find_victim_alloc_group(inode, range->me_goal,
+					    GLOBAL_BITMAP_SYSTEM_INODE,
+					    OCFS2_INVALID_SLOT,
+					    &goal_bit, &gd_bh);
+	if (ret)
+		goto out;
+
+	bg = (struct ocfs2_group_desc *)gd_bh->b_data;
+
+	/*
+	 * make goal become cluster aligned.
+	 */
+	if (range->me_goal % c_to_b)
+		range->me_goal = range->me_goal / c_to_b * c_to_b;
+
+	/*
+	 * moving goal is not allowd to start with a group desc blok(#0 blk)
+	 * let's compromise to the latter cluster.
+	 */
+	if (range->me_goal == le64_to_cpu(bg->bg_blkno))
+		range->me_goal += c_to_b;
+
+	/*
+	 * movement is not gonna cross two groups.
+	 */
+	if ((le16_to_cpu(bg->bg_bits) - goal_bit) * osb->s_clustersize <
+								range->me_len) {
+		ret = -EINVAL;
+		goto out;
+	}
+	/*
+	 * more exact validations/adjustments will be performed later during
+	 * moving operation for each extent range.
+	 */
+	mlog(0, "extents get ready to be moved to #%llu block\n",
+	     range->me_goal);
+
+out:
+	brelse(gd_bh);
+
+	return ret;
+}
+
+static void ocfs2_probe_alloc_group(struct inode *inode, struct buffer_head *bh,
+				    int *goal_bit, u32 move_len, u32 max_hop,
+				    u32 *phys_cpos)
+{
+	int i, used, last_free_bits = 0, base_bit = *goal_bit;
+	struct ocfs2_group_desc *gd = (struct ocfs2_group_desc *)bh->b_data;
+	u32 base_cpos = ocfs2_blocks_to_clusters(inode->i_sb,
+						 le64_to_cpu(gd->bg_blkno));
+
+	for (i = base_bit; i < le16_to_cpu(gd->bg_bits); i++) {
+
+		used = ocfs2_test_bit(i, (unsigned long *)gd->bg_bitmap);
+		if (used) {
+			/*
+			 * we even tried searching the free chunk by jumping
+			 * a 'max_hop' distance, but still failed.
+			 */
+			if ((i - base_bit) > max_hop) {
+				*phys_cpos = 0;
+				break;
+			}
+
+			if (last_free_bits)
+				last_free_bits = 0;
+
+			continue;
+		} else
+			last_free_bits++;
+
+		if (last_free_bits == move_len) {
+			*goal_bit = i;
+			*phys_cpos = base_cpos + i;
+			break;
+		}
+	}
+
+	mlog(0, "found phys_cpos: %u to fit the wanted moving.\n", *phys_cpos);
+}
+
+static int ocfs2_alloc_dinode_update_counts(struct inode *inode,
+				       handle_t *handle,
+				       struct buffer_head *di_bh,
+				       u32 num_bits,
+				       u16 chain)
+{
+	int ret;
+	u32 tmp_used;
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *) di_bh->b_data;
+	struct ocfs2_chain_list *cl =
+				(struct ocfs2_chain_list *) &di->id2.i_chain;
+
+	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
+				      OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret < 0) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	tmp_used = le32_to_cpu(di->id1.bitmap1.i_used);
+	di->id1.bitmap1.i_used = cpu_to_le32(num_bits + tmp_used);
+	le32_add_cpu(&cl->cl_recs[chain].c_free, -num_bits);
+	ocfs2_journal_dirty(handle, di_bh);
+
+out:
+	return ret;
+}
+
+static inline int ocfs2_block_group_set_bits(handle_t *handle,
+					     struct inode *alloc_inode,
+					     struct ocfs2_group_desc *bg,
+					     struct buffer_head *group_bh,
+					     unsigned int bit_off,
+					     unsigned int num_bits)
+{
+	int status;
+	void *bitmap = bg->bg_bitmap;
+	int journal_type = OCFS2_JOURNAL_ACCESS_WRITE;
+
+	mlog_entry_void();
+
+	/* All callers get the descriptor via
+	 * ocfs2_read_group_descriptor().  Any corruption is a code bug. */
+	BUG_ON(!OCFS2_IS_VALID_GROUP_DESC(bg));
+	BUG_ON(le16_to_cpu(bg->bg_free_bits_count) < num_bits);
+
+	mlog(0, "block_group_set_bits: off = %u, num = %u\n", bit_off,
+	     num_bits);
+
+	if (ocfs2_is_cluster_bitmap(alloc_inode))
+		journal_type = OCFS2_JOURNAL_ACCESS_UNDO;
+
+	status = ocfs2_journal_access_gd(handle,
+					 INODE_CACHE(alloc_inode),
+					 group_bh,
+					 journal_type);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail;
+	}
+
+	le16_add_cpu(&bg->bg_free_bits_count, -num_bits);
+	if (le16_to_cpu(bg->bg_free_bits_count) > le16_to_cpu(bg->bg_bits)) {
+		ocfs2_error(alloc_inode->i_sb, "Group descriptor # %llu has bit"
+			    " count %u but claims %u are freed. num_bits %d",
+			    (unsigned long long)le64_to_cpu(bg->bg_blkno),
+			    le16_to_cpu(bg->bg_bits),
+			    le16_to_cpu(bg->bg_free_bits_count), num_bits);
+		return -EROFS;
+	}
+	while (num_bits--)
+		ocfs2_set_bit(bit_off++, bitmap);
+
+	ocfs2_journal_dirty(handle, group_bh);
+
+bail:
+	mlog_exit(status);
+	return status;
+}
+
+static int ocfs2_move_extent(struct ocfs2_move_extents_context *context,
+			     u32 cpos, u32 phys_cpos, u32 *new_phys_cpos,
+			     u32 len, int ext_flags)
+{
+	int ret, credits = 0, goal_bit = 0;
+	handle_t *handle;
+	struct inode *inode = context->inode;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct inode *tl_inode = osb->osb_tl_inode;
+	struct inode *gb_inode = NULL;
+	struct buffer_head *gb_bh = NULL;
+	struct buffer_head *gd_bh = NULL;
+	struct ocfs2_group_desc *gd;
+	u32 move_max_hop = ocfs2_blocks_to_clusters(inode->i_sb,
+						    context->range->me_thresh);
+	u64 new_phys_blkno;
+
+	ret = ocfs2_lock_allocators_move_extents(inode, &context->et, len, 1,
+						 &context->meta_ac,
+						 NULL, 0, &credits);
+	if (ret) {
+		mlog_errno(ret);
+		return ret;
+	}
+
+	/*
+	 * need to count 2 extra credits for global_bitmap inode and
+	 * group descriptor.
+	 */
+	credits += OCFS2_INODE_UPDATE_CREDITS + 1;
+
+	/*
+	 * ocfs2_move_extent() didn't reserve any clusters in lock_allocators()
+	 * logic, while we still need to lock the global_bitmap.
+	 */
+	gb_inode = ocfs2_get_system_file_inode(osb, GLOBAL_BITMAP_SYSTEM_INODE,
+					       OCFS2_INVALID_SLOT);
+	if (!gb_inode) {
+		mlog(ML_ERROR, "unable to get global_bitmap inode\n");
+		ret = -EIO;
+		goto out;
+	}
+
+	mutex_lock(&gb_inode->i_mutex);
+
+	ret = ocfs2_inode_lock(gb_inode, &gb_bh, 1);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_unlock_gb_mutex;
+	}
+
+	mutex_lock(&tl_inode->i_mutex);
+
+	handle = ocfs2_start_trans(osb, credits);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		mlog_errno(ret);
+		goto out_unlock_tl_inode;
+	}
+
+	new_phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, *new_phys_cpos);
+	ret = ocfs2_find_victim_alloc_group(inode, new_phys_blkno,
+					    GLOBAL_BITMAP_SYSTEM_INODE,
+					    OCFS2_INVALID_SLOT,
+					    &goal_bit, &gd_bh);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
+	/*
+	 * probe the victim cluster group to find a proper
+	 * region to fit wanted movement, it even will perfrom
+	 * a best-effort attempt by compromising to a threshold
+	 * around the goal.
+	 */
+	ocfs2_probe_alloc_group(inode, gd_bh, &goal_bit, len, move_max_hop,
+				new_phys_cpos);
+	if (!new_phys_cpos) {
+		ret = -ENOSPC;
+		goto out_commit;
+	}
+
+	ret = __ocfs2_move_extent(handle, context, cpos, len, phys_cpos,
+				  *new_phys_cpos, ext_flags);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
+	gd = (struct ocfs2_group_desc *)gd_bh->b_data;
+	ret = ocfs2_alloc_dinode_update_counts(gb_inode, handle, gb_bh, len,
+					       le16_to_cpu(gd->bg_chain));
+	if (ret) {
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
+	ret = ocfs2_block_group_set_bits(handle, gb_inode, gd, gd_bh,
+					 goal_bit, len);
+	if (ret)
+		mlog_errno(ret);
+
+out_commit:
+	ocfs2_commit_trans(osb, handle);
+	brelse(gd_bh);
+
+out_unlock_tl_inode:
+	mutex_unlock(&tl_inode->i_mutex);
+
+	ocfs2_inode_unlock(gb_inode, 1);
+out_unlock_gb_mutex:
+	mutex_unlock(&gb_inode->i_mutex);
+	brelse(gb_bh);
+	iput(gb_inode);
+
+out:
+	if (context->meta_ac) {
+		ocfs2_free_alloc_context(context->meta_ac);
+		context->meta_ac = NULL;
+	}
+
+	return ret;
+}
 
 static int ocfs2_move_extents(struct ocfs2_move_extents_context *context)
 {
@@ -563,13 +971,10 @@ int ocfs2_ioctl_move_extents(struct file *filp, void __user *argp)
 		 * operation can succeed all the time since global_bitmap may
 		 * change a bit over time.
 		 */
-		/*
-		 * real validation codes will be fulfilled later.
-		 *
-		 * status = ocfs2_validate_and_adjust_move_goal(inode, &range);
-		 * if (status)
-		 * 	goto out;
-		*/
+
+		status = ocfs2_validate_and_adjust_move_goal(inode, &range);
+		if (status)
+			goto out;
 	}
 
 	status = ocfs2_move_extents(context);
-- 
1.5.5

[Ocfs2-devel] [PATCH 8/8] Ocfs2: move/defrag extents within a certain range.

[Tristan Ye]

The basic logic of moving extents for a file is pretty like punching-hole
sequence, walk the extents within the range as user specified, calculating
an appropriate len to defrag/move, then let ocfs2_defrag/move_extent() to
do the actual moving.

This func ends up setting 'OCFS2_MOVE_EXT_FL_COMPLETE' to userpace if operation
gets done successfully.

Signed-off-by: Tristan Ye <tristan.ye@oracle.com>
---
 fs/ocfs2/move_extents.c |  169 +++++++++++++++++++++++++++++++++++++++++++++--
 1 files changed, 164 insertions(+), 5 deletions(-)

diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index ce97c76..dd5b995 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -817,6 +817,167 @@ out:
 	return ret;
 }
 
+/*
+ * Helper to calculate the defraging length in one run according to threshold.
+ */
+static void ocfs2_calc_extent_defrag_len(u32 *alloc_size, u32 *len_defraged,
+					 u32 threshold, int *skip)
+{
+	if ((*alloc_size + *len_defraged) < threshold) {
+		/*
+		 * proceed defragmentation until we meet the thresh
+		 */
+		*len_defraged += *alloc_size;
+	} else if (*len_defraged == 0) {
+		/*
+		 * XXX: skip a large extent.
+		 */
+		*skip = 1;
+	} else {
+		/*
+		 * split this extent to coalesce with former pieces as
+		 * to reach the threshold.
+		 *
+		 * we're done here with one cycle of defragmentation
+		 * in a size of 'thresh', resetting 'len_defraged'
+		 * forces a new defragmentation.
+		 */
+		*alloc_size = threshold - *len_defraged;
+		*len_defraged = 0;
+	}
+}
+
+static int __ocfs2_move_extents_range(struct buffer_head *di_bh,
+				struct ocfs2_move_extents_context *context)
+{
+	int ret, flags, do_defrag, skip = 0;
+	u32 cpos, phys_cpos, move_start, len_to_move, alloc_size;
+	u32 len_defraged = 0, defrag_thresh, new_phys_cpos = 0;
+
+	struct inode *inode = context->inode;
+	struct ocfs2_move_extents *range = context->range;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+
+	if ((inode->i_size == 0) || (range->me_len == 0))
+		return 0;
+
+	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
+		return 0;
+
+	ocfs2_init_dinode_extent_tree(&context->et, INODE_CACHE(inode), di_bh);
+	ocfs2_init_dealloc_ctxt(&context->dealloc);
+
+	/*
+	 * TO-DO XXX:
+	 *
+	 * - refcount tree.
+	 * - xattr extents.
+	 */
+
+	do_defrag = context->auto_defrag;
+
+	/*
+	 * extents moving happens in unit of clusters, for the sake
+	 * of simplicity, we may ignore two clusters where 'byte_start'
+	 * and 'byte_start + len' were within.
+	 */
+	move_start = ocfs2_clusters_for_bytes(osb->sb, range->me_start);
+	len_to_move = (range->me_start + range->me_len) >>
+						osb->s_clustersize_bits;
+	if (len_to_move >= move_start)
+		len_to_move -= move_start;
+	else
+		len_to_move = 0;
+
+	if (do_defrag)
+		defrag_thresh = range->me_thresh >> osb->s_clustersize_bits;
+	else
+		new_phys_cpos = ocfs2_blocks_to_clusters(inode->i_sb,
+							 range->me_goal);
+
+	mlog(0, "Inode: %llu, start: %llu, len: %llu, cstart: %u, clen: %u, "
+	     "thresh: %u\n",
+	     (unsigned long long)OCFS2_I(inode)->ip_blkno,
+	     (unsigned long long)range->me_start,
+	     (unsigned long long)range->me_len,
+	     move_start, len_to_move, defrag_thresh);
+
+	cpos = move_start;
+	while (len_to_move) {
+		ret = ocfs2_get_clusters(inode, cpos, &phys_cpos, &alloc_size,
+					 &flags);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
+		if (alloc_size > len_to_move)
+			alloc_size = len_to_move;
+
+		/*
+		 * XXX: how to deal with a hole:
+		 *
+		 * - skip the hole of course
+		 * - force a new defragmentation
+		 */
+		if (!phys_cpos) {
+			if (do_defrag)
+				len_defraged = 0;
+
+			goto next;
+		}
+
+		if (do_defrag) {
+			ocfs2_calc_extent_defrag_len(&alloc_size, &len_defraged,
+						     defrag_thresh, &skip);
+			/*
+			 * skip large extents
+			 */
+			if (skip) {
+				skip = 0;
+				goto next;
+			}
+
+			mlog(0, "#Defrag: cpos: %u, phys_cpos: %u, "
+			     "alloc_size: %u, len_defraged: %u\n",
+			     cpos, phys_cpos, alloc_size, len_defraged);
+
+			ret = ocfs2_defrag_extent(context, cpos, phys_cpos,
+						  alloc_size, flags);
+		} else {
+			ret = ocfs2_move_extent(context, cpos, phys_cpos,
+						&new_phys_cpos, alloc_size,
+						flags);
+
+			new_phys_cpos += alloc_size;
+		}
+
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto out;
+		}
+
+		context->clusters_moved += alloc_size;
+next:
+		cpos += alloc_size;
+		len_to_move -= alloc_size;
+	}
+
+	range->me_flags |= OCFS2_MOVE_EXT_FL_COMPLETE;
+
+out:
+	range->me_moved_len = ocfs2_clusters_to_bytes(osb->sb,
+						      context->clusters_moved);
+	range->me_new_offset = ocfs2_clusters_to_bytes(osb->sb,
+						       context->new_phys_cpos);
+
+	ocfs2_schedule_truncate_log_flush(osb, 1);
+	ocfs2_run_deallocs(osb, &context->dealloc);
+
+	return ret;
+}
+
+
 static int ocfs2_move_extents(struct ocfs2_move_extents_context *context)
 {
 	int status;
@@ -853,11 +1014,9 @@ static int ocfs2_move_extents(struct ocfs2_move_extents_context *context)
 	 * rememer ip_xattr_sem also needs to be held if necessary
 	 */
 	down_write(&OCFS2_I(inode)->ip_alloc_sem);
-	/*
-	 * real extents moving codes will be fulfilled later.
-	 * 
-	 * status = __ocfs2_move_extents_range(di_bh, context);
-	 */
+
+	status = __ocfs2_move_extents_range(di_bh, context);
+
 	up_write(&OCFS2_I(inode)->ip_alloc_sem);
 	if (status) {
 		mlog_errno(status);
-- 
1.5.5