From: Mingming Cao <cmm@us.ibm.com>
ext3_rsv_mount.patch: Adds features on top of the
ext3_rsv_base.patch:
- deal with earlier bogus -ENOSPC error
- do block reservation only for regular file
- make the ext3 reservation feature as a mount option: new mount option
added: reservation
- A pair of file ioctl commands are added for application to control the
block reservation window size.
---
25-akpm/fs/ext3/balloc.c | 61 ++++++++++++++++++++++++++++----------
25-akpm/fs/ext3/ialloc.c | 2 -
25-akpm/fs/ext3/inode.c | 2 -
25-akpm/fs/ext3/ioctl.c | 20 ++++++++++++
25-akpm/fs/ext3/super.c | 20 +++++++++++-
25-akpm/include/linux/ext3_fs.h | 42 ++++++++++++++------------
25-akpm/include/linux/ext3_fs_i.h | 2 -
7 files changed, 111 insertions(+), 38 deletions(-)
diff -puN fs/ext3/balloc.c~ext3_rsv_mount fs/ext3/balloc.c
--- 25/fs/ext3/balloc.c~ext3_rsv_mount Wed Apr 14 17:05:45 2004
+++ 25-akpm/fs/ext3/balloc.c Wed Apr 14 17:05:45 2004
@@ -714,7 +714,7 @@ static int alloc_new_reservation(struct
else
start_block = goal + group_first_block;
- size = my_rsv->rsv_goal_size;
+ size = atomic_read(&my_rsv->rsv_goal_size);
/* if we have a old reservation, discard it first */
if (!rsv_is_empty(my_rsv)) {
/*
@@ -862,7 +862,16 @@ ext3_try_to_allocate_with_rsv(struct sup
return -1;
}
-#ifdef EXT3_RESERVATION
+ /*
+ * we don't deal with reservation when
+ * filesystem is mounted without reservation
+ * or the file is not a regular file
+ * of last attemp of allocating a block with reservation turn on failed
+ */
+ if (my_rsv == NULL ) {
+ ret = ext3_try_to_allocate(sb, handle, group, bitmap_bh, goal, NULL);
+ goto out;
+ }
rsv_lock = &EXT3_SB(sb)->s_rsv_window_lock;
/*
* goal is a group relative block number (if there is a goal)
@@ -906,10 +915,7 @@ ext3_try_to_allocate_with_rsv(struct sup
if (ret >= 0)
break; /* succeed */
}
-#else
- ret = ext3_try_to_allocate(sb, handle, group, bitmap_bh, goal, NULL);
-#endif
-
+out:
if (ret >= 0) {
BUFFER_TRACE(bitmap_bh, "journal_dirty_metadata for "
"bitmap block");
@@ -937,12 +943,13 @@ ext3_try_to_allocate_with_rsv(struct sup
int ext3_new_block(handle_t *handle, struct inode *inode,
unsigned long goal, int *errp)
{
- struct buffer_head *bitmap_bh = NULL; /* bh */
- struct buffer_head *gdp_bh; /* bh2 */
- int group_no; /* i */
- int ret_block; /* j */
- int bgi; /* blockgroup iteration index */
- int target_block; /* tmp */
+ struct buffer_head *bitmap_bh = NULL;
+ struct buffer_head *gdp_bh;
+ int group_no;
+ int goal_group;
+ int ret_block;
+ int bgi; /* blockgroup iteration index */
+ int target_block;
int fatal = 0, err;
int performed_allocation = 0;
int free_blocks, root_blocks;
@@ -950,7 +957,7 @@ int ext3_new_block(handle_t *handle, str
struct ext3_group_desc *gdp;
struct ext3_super_block *es;
struct ext3_sb_info *sbi;
- struct reserve_window *my_rsv = &EXT3_I(inode)->i_rsv_window;
+ struct reserve_window *my_rsv = NULL;
#ifdef EXT3FS_DEBUG
static int goal_hits, goal_attempts;
#endif
@@ -972,7 +979,10 @@ int ext3_new_block(handle_t *handle, str
sbi = EXT3_SB(sb);
es = EXT3_SB(sb)->s_es;
ext3_debug("goal=%lu.\n", goal);
-
+#ifdef EXT3_RESERVATION
+ if (test_opt(sb, RESERVATION) && S_ISREG(inode->i_mode))
+ my_rsv = &EXT3_I(inode)->i_rsv_window;
+#endif
free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
root_blocks = le32_to_cpu(es->s_r_blocks_count);
if (free_blocks < root_blocks + 1 && !capable(CAP_SYS_RESOURCE) &&
@@ -994,6 +1004,8 @@ int ext3_new_block(handle_t *handle, str
if (!gdp)
goto io_error;
+ goal_group = group_no;
+retry:
free_blocks = le16_to_cpu(gdp->bg_free_blocks_count);
if (free_blocks > 0) {
ret_block = ((goal - le32_to_cpu(es->s_first_data_block)) %
@@ -1037,7 +1049,26 @@ int ext3_new_block(handle_t *handle, str
if (ret_block >= 0)
goto allocated;
}
-
+#ifdef EXT3_RESERVATION
+ /*
+ * We may end up a bogus ealier ENOSPC error due to
+ * filesystem is "full" of reservations, but
+ * there maybe indeed free blocks avaliable on disk
+ * In this case, we just forget about the reservations
+ * just do block allocation as without reservations.
+ */
+ if (my_rsv) {
+#ifdef EXT3_RESERVATION_DEBUG
+ printk("filesystem is fully reserved. Actual free blocks: %d. "
+ "Try to do allocation without reservation, goal_group "
+ "is %d\n",
+ free_blocks, goal_group);
+#endif
+ my_rsv = NULL;
+ group_no = goal_group;
+ goto retry;
+ }
+#endif
/* No space left on the device */
*errp = -ENOSPC;
goto out;
diff -puN fs/ext3/ialloc.c~ext3_rsv_mount fs/ext3/ialloc.c
--- 25/fs/ext3/ialloc.c~ext3_rsv_mount Wed Apr 14 17:05:45 2004
+++ 25-akpm/fs/ext3/ialloc.c Wed Apr 14 17:05:45 2004
@@ -583,7 +583,7 @@ got:
ei->i_dtime = 0;
ei->i_rsv_window.rsv_start = 0;
ei->i_rsv_window.rsv_end= 0;
- ei->i_rsv_window.rsv_goal_size = EXT3_DEFAULT_RESERVE_BLOCKS;
+ atomic_set(&ei->i_rsv_window.rsv_goal_size, EXT3_DEFAULT_RESERVE_BLOCKS);
INIT_LIST_HEAD(&ei->i_rsv_window.rsv_list);
ei->i_block_group = group;
diff -puN fs/ext3/inode.c~ext3_rsv_mount fs/ext3/inode.c
--- 25/fs/ext3/inode.c~ext3_rsv_mount Wed Apr 14 17:05:45 2004
+++ 25-akpm/fs/ext3/inode.c Wed Apr 14 17:05:45 2004
@@ -2450,7 +2450,7 @@ void ext3_read_inode(struct inode * inod
ei->i_block_group = iloc.block_group;
ei->i_rsv_window.rsv_start = 0;
ei->i_rsv_window.rsv_end= 0;
- ei->i_rsv_window.rsv_goal_size = EXT3_DEFAULT_RESERVE_BLOCKS;
+ atomic_set(&ei->i_rsv_window.rsv_goal_size, EXT3_DEFAULT_RESERVE_BLOCKS);
INIT_LIST_HEAD(&ei->i_rsv_window.rsv_list);
/*
* NOTE! The in-memory inode i_data array is in little-endian order
diff -puN fs/ext3/ioctl.c~ext3_rsv_mount fs/ext3/ioctl.c
--- 25/fs/ext3/ioctl.c~ext3_rsv_mount Wed Apr 14 17:05:45 2004
+++ 25-akpm/fs/ext3/ioctl.c Wed Apr 14 17:05:45 2004
@@ -20,6 +20,7 @@ int ext3_ioctl (struct inode * inode, st
{
struct ext3_inode_info *ei = EXT3_I(inode);
unsigned int flags;
+ unsigned short rsv_window_size;
ext3_debug ("cmd = %u, arg = %lu\n", cmd, arg);
@@ -151,6 +152,25 @@ flags_err:
return ret;
}
#endif
+#ifdef EXT3_RESERVATION
+ case EXT3_IOC_GETRSVSZ:
+ rsv_window_size = atomic_read(&ei->i_rsv_window.rsv_goal_size);
+ return put_user(rsv_window_size, (int *)arg);
+ case EXT3_IOC_SETRSVSZ:
+ if (IS_RDONLY(inode))
+ return -EROFS;
+
+ if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
+ return -EACCES;
+
+ if (get_user(rsv_window_size, (int *)arg))
+ return -EFAULT;
+
+ if (rsv_window_size > EXT3_MAX_RESERVE_BLOCKS)
+ rsv_window_size = EXT3_MAX_RESERVE_BLOCKS;
+ atomic_set(&ei->i_rsv_window.rsv_goal_size, rsv_window_size);
+ return 0;
+#endif
default:
return -ENOTTY;
}
diff -puN fs/ext3/super.c~ext3_rsv_mount fs/ext3/super.c
--- 25/fs/ext3/super.c~ext3_rsv_mount Wed Apr 14 17:05:45 2004
+++ 25-akpm/fs/ext3/super.c Wed Apr 14 17:05:45 2004
@@ -572,7 +572,8 @@ enum {
Opt_bsd_df, Opt_minix_df, Opt_grpid, Opt_nogrpid,
Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic, Opt_err_ro,
Opt_nouid32, Opt_check, Opt_nocheck, Opt_debug, Opt_oldalloc, Opt_orlov,
- Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl, Opt_noload,
+ Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl,
+ Opt_reservation, Opt_noreservation, Opt_noload,
Opt_commit, Opt_journal_update, Opt_journal_inum,
Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
@@ -604,6 +605,8 @@ static match_table_t tokens = {
{Opt_nouser_xattr, "nouser_xattr"},
{Opt_acl, "acl"},
{Opt_noacl, "noacl"},
+ {Opt_reservation, "reservation"},
+ {Opt_noreservation, "noreservation"},
{Opt_noload, "noload"},
{Opt_commit, "commit=%u"},
{Opt_journal_update, "journal=update"},
@@ -757,6 +760,19 @@ static int parse_options (char * options
printk("EXT3 (no)acl options not supported\n");
break;
#endif
+#ifdef EXT3_RESERVATION
+ case Opt_reservation:
+ set_opt(sbi->s_mount_opt, RESERVATION);
+ break;
+ case Opt_noreservation:
+ clear_opt(sbi->s_mount_opt, RESERVATION);
+ break;
+#else
+ case Opt_reservation:
+ case Opt_noreservation:
+ printk("EXT3 block reservation options not supported\n");
+ break;
+#endif
case Opt_journal_update:
/* @@@ FIXME */
/* Eventually we will want to be able to create
@@ -1456,7 +1472,7 @@ static int ext3_fill_super (struct super
INIT_LIST_HEAD(&sbi->s_rsv_window_head.rsv_list);
sbi->s_rsv_window_head.rsv_start = 0;
sbi->s_rsv_window_head.rsv_end = 0;
- sbi->s_rsv_window_head.rsv_goal_size = 0;
+ atomic_set(&sbi->s_rsv_window_head.rsv_goal_size, 0);
/*
* set up enough so that it can read an inode
diff -puN include/linux/ext3_fs.h~ext3_rsv_mount include/linux/ext3_fs.h
--- 25/include/linux/ext3_fs.h~ext3_rsv_mount Wed Apr 14 17:05:45 2004
+++ 25-akpm/include/linux/ext3_fs.h Wed Apr 14 17:05:45 2004
@@ -37,6 +37,7 @@ struct statfs;
*/
#define EXT3_RESERVATION
#define EXT3_DEFAULT_RESERVE_BLOCKS 8
+#define EXT3_MAX_RESERVE_BLOCKS 1024
/*
* Always enable hashed directories
*/
@@ -207,6 +208,10 @@ struct ext3_group_desc
#ifdef CONFIG_JBD_DEBUG
#define EXT3_IOC_WAIT_FOR_READONLY _IOR('f', 99, long)
#endif
+#ifdef EXT3_RESERVATION
+#define EXT3_IOC_GETRSVSZ _IOR('r', 1, long)
+#define EXT3_IOC_SETRSVSZ _IOW('r', 2, long)
+#endif
/*
* Structure of an inode on the disk
@@ -305,24 +310,25 @@ struct ext3_inode {
/*
* Mount flags
*/
-#define EXT3_MOUNT_CHECK 0x0001 /* Do mount-time checks */
-#define EXT3_MOUNT_OLDALLOC 0x0002 /* Don't use the new Orlov allocator */
-#define EXT3_MOUNT_GRPID 0x0004 /* Create files with directory's group */
-#define EXT3_MOUNT_DEBUG 0x0008 /* Some debugging messages */
-#define EXT3_MOUNT_ERRORS_CONT 0x0010 /* Continue on errors */
-#define EXT3_MOUNT_ERRORS_RO 0x0020 /* Remount fs ro on errors */
-#define EXT3_MOUNT_ERRORS_PANIC 0x0040 /* Panic on errors */
-#define EXT3_MOUNT_MINIX_DF 0x0080 /* Mimics the Minix statfs */
-#define EXT3_MOUNT_NOLOAD 0x0100 /* Don't use existing journal*/
-#define EXT3_MOUNT_ABORT 0x0200 /* Fatal error detected */
-#define EXT3_MOUNT_DATA_FLAGS 0x0C00 /* Mode for data writes: */
- #define EXT3_MOUNT_JOURNAL_DATA 0x0400 /* Write data to journal */
- #define EXT3_MOUNT_ORDERED_DATA 0x0800 /* Flush data before commit */
- #define EXT3_MOUNT_WRITEBACK_DATA 0x0C00 /* No data ordering */
-#define EXT3_MOUNT_UPDATE_JOURNAL 0x1000 /* Update the journal format */
-#define EXT3_MOUNT_NO_UID32 0x2000 /* Disable 32-bit UIDs */
-#define EXT3_MOUNT_XATTR_USER 0x4000 /* Extended user attributes */
-#define EXT3_MOUNT_POSIX_ACL 0x8000 /* POSIX Access Control Lists */
+#define EXT3_MOUNT_CHECK 0x00001 /* Do mount-time checks */
+#define EXT3_MOUNT_OLDALLOC 0x00002 /* Don't use the new Orlov allocator */
+#define EXT3_MOUNT_GRPID 0x00004 /* Create files with directory's group */
+#define EXT3_MOUNT_DEBUG 0x00008 /* Some debugging messages */
+#define EXT3_MOUNT_ERRORS_CONT 0x00010 /* Continue on errors */
+#define EXT3_MOUNT_ERRORS_RO 0x00020 /* Remount fs ro on errors */
+#define EXT3_MOUNT_ERRORS_PANIC 0x00040 /* Panic on errors */
+#define EXT3_MOUNT_MINIX_DF 0x00080 /* Mimics the Minix statfs */
+#define EXT3_MOUNT_NOLOAD 0x00100 /* Don't use existing journal*/
+#define EXT3_MOUNT_ABORT 0x00200 /* Fatal error detected */
+#define EXT3_MOUNT_DATA_FLAGS 0x00C00 /* Mode for data writes: */
+#define EXT3_MOUNT_JOURNAL_DATA 0x00400 /* Write data to journal */
+#define EXT3_MOUNT_ORDERED_DATA 0x00800 /* Flush data before commit */
+#define EXT3_MOUNT_WRITEBACK_DATA 0x00C00 /* No data ordering */
+#define EXT3_MOUNT_UPDATE_JOURNAL 0x01000 /* Update the journal format */
+#define EXT3_MOUNT_NO_UID32 0x02000 /* Disable 32-bit UIDs */
+#define EXT3_MOUNT_XATTR_USER 0x04000 /* Extended user attributes */
+#define EXT3_MOUNT_POSIX_ACL 0x08000 /* POSIX Access Control Lists */
+#define EXT3_MOUNT_RESERVATION 0x10000 /* Preallocation */
/* Compatibility, for having both ext2_fs.h and ext3_fs.h included at once */
#ifndef _LINUX_EXT2_FS_H
diff -puN include/linux/ext3_fs_i.h~ext3_rsv_mount include/linux/ext3_fs_i.h
--- 25/include/linux/ext3_fs_i.h~ext3_rsv_mount Wed Apr 14 17:05:45 2004
+++ 25-akpm/include/linux/ext3_fs_i.h Wed Apr 14 17:05:45 2004
@@ -22,7 +22,7 @@ struct reserve_window {
struct list_head rsv_list;
__u32 rsv_start;
__u32 rsv_end;
- unsigned short rsv_goal_size;
+ atomic_t rsv_goal_size;
};
/*
_