From: Artem Bityutskiy <artem.bityutskiy@xxxxxxxxxxxxxxx>
This patch makes UFS stop using the VFS '->write_super()' method along with
the 's_dirt' superblock flag, because they are on their way out.
The way we implement this is that we schedule a delay job instead relying on
's_dirt' and '->write_super()'.
The whole "superblock write-out" VFS infrastructure is served by the
'sync_supers()' kernel thread, which wakes up every 5 (by default) seconds and
writes out all dirty superblocks using the '->write_super()' call-back. But the
problem with this thread is that it wastes power by waking up the system every
5 seconds, even if there are no diry superblocks, or there are no client
file-systems which would need this (e.g., btrfs does not use
'->write_super()'). So we want to kill it completely and thus, we need to make
file-systems to stop using the '->write_super()' VFS service, and then remove
it together with the kernel thread.
Tested using fsstress from the LTP project.
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@xxxxxxxxxxxxxxx>
---
fs/ufs/balloc.c | 8 ++++----
fs/ufs/ialloc.c | 4 ++--
fs/ufs/super.c | 40 ++++++++++++++++++++++++++++++----------
fs/ufs/ufs.h | 5 +++++
fs/ufs/ufs_fs.h | 1 +
5 files changed, 42 insertions(+), 16 deletions(-)
diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c
index 42694e1..1b3e410 100644
--- a/fs/ufs/balloc.c
+++ b/fs/ufs/balloc.c
@@ -116,7 +116,7 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count)
ubh_mark_buffer_dirty (UCPI_UBH(ucpi));
if (sb->s_flags & MS_SYNCHRONOUS)
ubh_sync_block(UCPI_UBH(ucpi));
- sb->s_dirt = 1;
+ ufs_mark_sb_dirty(sb);
unlock_super (sb);
UFSD("EXIT\n");
@@ -214,7 +214,7 @@ do_more:
goto do_more;
}
- sb->s_dirt = 1;
+ ufs_mark_sb_dirty(sb);
unlock_super (sb);
UFSD("EXIT\n");
return;
@@ -557,7 +557,7 @@ static u64 ufs_add_fragments(struct inode *inode, u64 fragment,
ubh_mark_buffer_dirty (UCPI_UBH(ucpi));
if (sb->s_flags & MS_SYNCHRONOUS)
ubh_sync_block(UCPI_UBH(ucpi));
- sb->s_dirt = 1;
+ ufs_mark_sb_dirty(sb);
UFSD("EXIT, fragment %llu\n", (unsigned long long)fragment);
@@ -677,7 +677,7 @@ succed:
ubh_mark_buffer_dirty (UCPI_UBH(ucpi));
if (sb->s_flags & MS_SYNCHRONOUS)
ubh_sync_block(UCPI_UBH(ucpi));
- sb->s_dirt = 1;
+ ufs_mark_sb_dirty(sb);
result += cgno * uspi->s_fpg;
UFSD("EXIT3, result %llu\n", (unsigned long long)result);
diff --git a/fs/ufs/ialloc.c b/fs/ufs/ialloc.c
index 4ec5c10..e84cbe2 100644
--- a/fs/ufs/ialloc.c
+++ b/fs/ufs/ialloc.c
@@ -116,7 +116,7 @@ void ufs_free_inode (struct inode * inode)
if (sb->s_flags & MS_SYNCHRONOUS)
ubh_sync_block(UCPI_UBH(ucpi));
- sb->s_dirt = 1;
+ ufs_mark_sb_dirty(sb);
unlock_super (sb);
UFSD("EXIT\n");
}
@@ -288,7 +288,7 @@ cg_found:
ubh_mark_buffer_dirty (UCPI_UBH(ucpi));
if (sb->s_flags & MS_SYNCHRONOUS)
ubh_sync_block(UCPI_UBH(ucpi));
- sb->s_dirt = 1;
+ ufs_mark_sb_dirty(sb);
inode->i_ino = cg * uspi->s_ipg + bit;
inode_init_owner(inode, dir, mode);
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index ad56c6d..444927e 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -302,7 +302,7 @@ void ufs_error (struct super_block * sb, const char * function,
if (!(sb->s_flags & MS_RDONLY)) {
usb1->fs_clean = UFS_FSBAD;
ubh_mark_buffer_dirty(USPI_UBH(uspi));
- sb->s_dirt = 1;
+ ufs_mark_sb_dirty(sb);
sb->s_flags |= MS_RDONLY;
}
va_start (args, fmt);
@@ -334,7 +334,7 @@ void ufs_panic (struct super_block * sb, const char * function,
if (!(sb->s_flags & MS_RDONLY)) {
usb1->fs_clean = UFS_FSBAD;
ubh_mark_buffer_dirty(USPI_UBH(uspi));
- sb->s_dirt = 1;
+ ufs_mark_sb_dirty(sb);
}
va_start (args, fmt);
vsnprintf (error_buf, sizeof(error_buf), fmt, args);
@@ -715,7 +715,6 @@ static int ufs_sync_fs(struct super_block *sb, int wait)
ufs_set_fs_state(sb, usb1, usb3,
UFS_FSOK - fs32_to_cpu(sb, usb1->fs_time));
ufs_put_cstotal(sb);
- sb->s_dirt = 0;
UFSD("EXIT\n");
unlock_super(sb);
@@ -724,12 +723,31 @@ static int ufs_sync_fs(struct super_block *sb, int wait)
return 0;
}
-static void ufs_write_super(struct super_block *sb)
+static void delayed_sync_fs(struct work_struct *work)
{
- if (!(sb->s_flags & MS_RDONLY))
- ufs_sync_fs(sb, 1);
- else
- sb->s_dirt = 0;
+ struct ufs_sb_info *sbi;
+
+ sbi = container_of(work, struct ufs_sb_info, sync_work.work);
+
+ spin_lock(&sbi->work_lock);
+ sbi->work_queued = 0;
+ spin_unlock(&sbi->work_lock);
+
+ ufs_sync_fs(sbi->sb, 1);
+}
+
+void ufs_mark_sb_dirty(struct super_block *sb)
+{
+ struct ufs_sb_info *sbi = UFS_SB(sb);
+ unsigned long delay;
+
+ spin_lock(&sbi->work_lock);
+ if (!sbi->work_queued) {
+ delay = msecs_to_jiffies(dirty_writeback_interval * 10);
+ queue_delayed_work(system_long_wq, &sbi->sync_work, delay);
+ sbi->work_queued = 1;
+ }
+ spin_unlock(&sbi->work_lock);
}
static void ufs_put_super(struct super_block *sb)
@@ -740,6 +758,7 @@ static void ufs_put_super(struct super_block *sb)
if (!(sb->s_flags & MS_RDONLY))
ufs_put_super_internal(sb);
+ cancel_delayed_work_sync(&sbi->sync_work);
ubh_brelse_uspi (sbi->s_uspi);
kfree (sbi->s_uspi);
@@ -774,6 +793,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent)
if (!sbi)
goto failed_nomem;
sb->s_fs_info = sbi;
+ sbi->sb = sb;
UFSD("flag %u\n", (int)(sb->s_flags & MS_RDONLY));
@@ -785,6 +805,8 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent)
}
#endif
mutex_init(&sbi->mutex);
+ spin_lock_init(&sbi->work_lock);
+ INIT_DELAYED_WORK(&sbi->sync_work, delayed_sync_fs);
/*
* Set default mount options
* Parse mount options
@@ -1304,7 +1326,6 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
ufs_set_fs_state(sb, usb1, usb3,
UFS_FSOK - fs32_to_cpu(sb, usb1->fs_time));
ubh_mark_buffer_dirty (USPI_UBH(uspi));
- sb->s_dirt = 0;
sb->s_flags |= MS_RDONLY;
} else {
/*
@@ -1454,7 +1475,6 @@ static const struct super_operations ufs_super_ops = {
.write_inode = ufs_write_inode,
.evict_inode = ufs_evict_inode,
.put_super = ufs_put_super,
- .write_super = ufs_write_super,
.sync_fs = ufs_sync_fs,
.statfs = ufs_statfs,
.remount_fs = ufs_remount,
diff --git a/fs/ufs/ufs.h b/fs/ufs/ufs.h
index 528750b..343e6fc 100644
--- a/fs/ufs/ufs.h
+++ b/fs/ufs/ufs.h
@@ -20,6 +20,10 @@ struct ufs_sb_info {
unsigned s_mount_opt;
struct mutex mutex;
struct task_struct *mutex_owner;
+ struct super_block *sb;
+ int work_queued; /* non-zero if the delayed work is queued */
+ struct delayed_work sync_work; /* FS sync delayed work */
+ spinlock_t work_lock; /* protects sync_work and work_queued */
};
struct ufs_inode_info {
@@ -123,6 +127,7 @@ extern __printf(3, 4)
void ufs_error(struct super_block *, const char *, const char *, ...);
extern __printf(3, 4)
void ufs_panic(struct super_block *, const char *, const char *, ...);
+void ufs_mark_sb_dirty(struct super_block *sb);
/* symlink.c */
extern const struct inode_operations ufs_fast_symlink_inode_operations;
diff --git a/fs/ufs/ufs_fs.h b/fs/ufs/ufs_fs.h
index 8aba544..0cbd5d3 100644
--- a/fs/ufs/ufs_fs.h
+++ b/fs/ufs/ufs_fs.h
@@ -34,6 +34,7 @@
#include <linux/kernel.h>
#include <linux/stat.h>
#include <linux/fs.h>
+#include <linux/workqueue.h>
#include <asm/div64.h>
typedef __u64 __bitwise __fs64;
--
1.7.7.6
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
