From 08bafc0341f2f7920e9045bc32c40299cac8c21b Mon Sep 17 00:00:00 2001 From: Keith Mannthey Date: Tue, 25 Nov 2008 10:24:35 +0100 Subject: block: Supress Buffer I/O errors when SCSI REQ_QUIET flag set Allow the scsi request REQ_QUIET flag to be propagated to the buffer file system layer. The basic ideas is to pass the flag from the scsi request to the bio (block IO) and then to the buffer layer. The buffer layer can then suppress needless printks. This patch declutters the kernel log by removed the 40-50 (per lun) buffer io error messages seen during a boot in my multipath setup . It is a good chance any real errors will be missed in the "noise" it the logs without this patch. During boot I see blocks of messages like " __ratelimit: 211 callbacks suppressed Buffer I/O error on device sdm, logical block 5242879 Buffer I/O error on device sdm, logical block 5242879 Buffer I/O error on device sdm, logical block 5242847 Buffer I/O error on device sdm, logical block 1 Buffer I/O error on device sdm, logical block 5242878 Buffer I/O error on device sdm, logical block 5242879 Buffer I/O error on device sdm, logical block 5242879 Buffer I/O error on device sdm, logical block 5242879 Buffer I/O error on device sdm, logical block 5242879 Buffer I/O error on device sdm, logical block 5242872 " in my logs. My disk environment is multipath fiber channel using the SCSI_DH_RDAC code and multipathd. This topology includes an "active" and "ghost" path for each lun. IO's to the "ghost" path will never complete and the SCSI layer, via the scsi device handler rdac code, quick returns the IOs to theses paths and sets the REQ_QUIET scsi flag to suppress the scsi layer messages. I am wanting to extend the QUIET behavior to include the buffer file system layer to deal with these errors as well. I have been running this patch for a while now on several boxes without issue. A few runs of bonnie++ show no noticeable difference in performance in my setup. Thanks for John Stultz for the quiet_error finalization. Submitted-by: Keith Mannthey Signed-off-by: Jens Axboe --- include/linux/buffer_head.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/buffer_head.h') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 3ce64b90118c..8605f8a74df9 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -35,6 +35,7 @@ enum bh_state_bits { BH_Ordered, /* ordered write */ BH_Eopnotsupp, /* operation not supported (barrier) */ BH_Unwritten, /* Buffer is allocated on disk but not written */ + BH_Quiet, /* Buffer Error Prinks to be quiet */ BH_PrivateStart,/* not a state bit, but the first bit available * for private allocation by other entities -- cgit From fcccf502540e3d752d33b2d8e976034dee81f9f7 Mon Sep 17 00:00:00 2001 From: Takashi Sato Date: Fri, 9 Jan 2009 16:40:59 -0800 Subject: filesystem freeze: implement generic freeze feature The ioctls for the generic freeze feature are below. o Freeze the filesystem int ioctl(int fd, int FIFREEZE, arg) fd: The file descriptor of the mountpoint FIFREEZE: request code for the freeze arg: Ignored Return value: 0 if the operation succeeds. Otherwise, -1 o Unfreeze the filesystem int ioctl(int fd, int FITHAW, arg) fd: The file descriptor of the mountpoint FITHAW: request code for unfreeze arg: Ignored Return value: 0 if the operation succeeds. Otherwise, -1 Error number: If the filesystem has already been unfrozen, errno is set to EINVAL. [akpm@linux-foundation.org: fix CONFIG_BLOCK=n] Signed-off-by: Takashi Sato Signed-off-by: Masayuki Hamaguchi Cc: Cc: Cc: Christoph Hellwig Cc: Dave Kleikamp Cc: Dave Chinner Cc: Alasdair G Kergon Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/block_dev.c | 2 ++ fs/buffer.c | 74 +++++++++++++++++++++++++++++++++++++++------ fs/ioctl.c | 46 ++++++++++++++++++++++++++++ include/linux/buffer_head.h | 11 ++++++- include/linux/fs.h | 7 +++++ 5 files changed, 130 insertions(+), 10 deletions(-) (limited to 'include/linux/buffer_head.h') diff --git a/fs/block_dev.c b/fs/block_dev.c index ac7031f12ea5..b3c1efff5e1d 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -285,6 +285,8 @@ static void init_once(void *foo) INIT_LIST_HEAD(&bdev->bd_holder_list); #endif inode_init_once(&ei->vfs_inode); + /* Initialize mutex for freeze. */ + mutex_init(&bdev->bd_fsfreeze_mutex); } static inline void __bd_forget(struct inode *inode) diff --git a/fs/buffer.c b/fs/buffer.c index 87f9e537b8c3..b6e8b8632e2f 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -203,10 +203,25 @@ int fsync_bdev(struct block_device *bdev) * happen on bdev until thaw_bdev() is called. * If a superblock is found on this device, we take the s_umount semaphore * on it to make sure nobody unmounts until the snapshot creation is done. + * The reference counter (bd_fsfreeze_count) guarantees that only the last + * unfreeze process can unfreeze the frozen filesystem actually when multiple + * freeze requests arrive simultaneously. It counts up in freeze_bdev() and + * count down in thaw_bdev(). When it becomes 0, thaw_bdev() will unfreeze + * actually. */ struct super_block *freeze_bdev(struct block_device *bdev) { struct super_block *sb; + int error = 0; + + mutex_lock(&bdev->bd_fsfreeze_mutex); + if (bdev->bd_fsfreeze_count > 0) { + bdev->bd_fsfreeze_count++; + sb = get_super(bdev); + mutex_unlock(&bdev->bd_fsfreeze_mutex); + return sb; + } + bdev->bd_fsfreeze_count++; down(&bdev->bd_mount_sem); sb = get_super(bdev); @@ -221,11 +236,24 @@ struct super_block *freeze_bdev(struct block_device *bdev) sync_blockdev(sb->s_bdev); - if (sb->s_op->freeze_fs) - sb->s_op->freeze_fs(sb); + if (sb->s_op->freeze_fs) { + error = sb->s_op->freeze_fs(sb); + if (error) { + printk(KERN_ERR + "VFS:Filesystem freeze failed\n"); + sb->s_frozen = SB_UNFROZEN; + drop_super(sb); + up(&bdev->bd_mount_sem); + bdev->bd_fsfreeze_count--; + mutex_unlock(&bdev->bd_fsfreeze_mutex); + return ERR_PTR(error); + } + } } sync_blockdev(bdev); + mutex_unlock(&bdev->bd_fsfreeze_mutex); + return sb; /* thaw_bdev releases s->s_umount and bd_mount_sem */ } EXPORT_SYMBOL(freeze_bdev); @@ -237,20 +265,48 @@ EXPORT_SYMBOL(freeze_bdev); * * Unlocks the filesystem and marks it writeable again after freeze_bdev(). */ -void thaw_bdev(struct block_device *bdev, struct super_block *sb) +int thaw_bdev(struct block_device *bdev, struct super_block *sb) { + int error = 0; + + mutex_lock(&bdev->bd_fsfreeze_mutex); + if (!bdev->bd_fsfreeze_count) { + mutex_unlock(&bdev->bd_fsfreeze_mutex); + return -EINVAL; + } + + bdev->bd_fsfreeze_count--; + if (bdev->bd_fsfreeze_count > 0) { + if (sb) + drop_super(sb); + mutex_unlock(&bdev->bd_fsfreeze_mutex); + return 0; + } + if (sb) { BUG_ON(sb->s_bdev != bdev); - - if (sb->s_op->unfreeze_fs) - sb->s_op->unfreeze_fs(sb); - sb->s_frozen = SB_UNFROZEN; - smp_wmb(); - wake_up(&sb->s_wait_unfrozen); + if (!(sb->s_flags & MS_RDONLY)) { + if (sb->s_op->unfreeze_fs) { + error = sb->s_op->unfreeze_fs(sb); + if (error) { + printk(KERN_ERR + "VFS:Filesystem thaw failed\n"); + sb->s_frozen = SB_FREEZE_TRANS; + bdev->bd_fsfreeze_count++; + mutex_unlock(&bdev->bd_fsfreeze_mutex); + return error; + } + } + sb->s_frozen = SB_UNFROZEN; + smp_wmb(); + wake_up(&sb->s_wait_unfrozen); + } drop_super(sb); } up(&bdev->bd_mount_sem); + mutex_unlock(&bdev->bd_fsfreeze_mutex); + return 0; } EXPORT_SYMBOL(thaw_bdev); diff --git a/fs/ioctl.c b/fs/ioctl.c index cc3f1aa1cf7b..20b0a8a24c6b 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -439,6 +439,43 @@ static int ioctl_fioasync(unsigned int fd, struct file *filp, return error; } +static int ioctl_fsfreeze(struct file *filp) +{ + struct super_block *sb = filp->f_path.dentry->d_inode->i_sb; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + /* If filesystem doesn't support freeze feature, return. */ + if (sb->s_op->freeze_fs == NULL) + return -EOPNOTSUPP; + + /* If a blockdevice-backed filesystem isn't specified, return. */ + if (sb->s_bdev == NULL) + return -EINVAL; + + /* Freeze */ + sb = freeze_bdev(sb->s_bdev); + if (IS_ERR(sb)) + return PTR_ERR(sb); + return 0; +} + +static int ioctl_fsthaw(struct file *filp) +{ + struct super_block *sb = filp->f_path.dentry->d_inode->i_sb; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + /* If a blockdevice-backed filesystem isn't specified, return EINVAL. */ + if (sb->s_bdev == NULL) + return -EINVAL; + + /* Thaw */ + return thaw_bdev(sb->s_bdev, sb); +} + /* * When you add any new common ioctls to the switches above and below * please update compat_sys_ioctl() too. @@ -486,6 +523,15 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd, } else error = -ENOTTY; break; + + case FIFREEZE: + error = ioctl_fsfreeze(filp); + break; + + case FITHAW: + error = ioctl_fsthaw(filp); + break; + default: if (S_ISREG(filp->f_path.dentry->d_inode->i_mode)) error = file_ioctl(filp, cmd, arg); diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 8605f8a74df9..bd7ac793be19 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -171,7 +171,7 @@ void __wait_on_buffer(struct buffer_head *); wait_queue_head_t *bh_waitq_head(struct buffer_head *bh); int fsync_bdev(struct block_device *); struct super_block *freeze_bdev(struct block_device *); -void thaw_bdev(struct block_device *, struct super_block *); +int thaw_bdev(struct block_device *, struct super_block *); int fsync_super(struct super_block *); int fsync_no_super(struct block_device *); struct buffer_head *__find_get_block(struct block_device *bdev, sector_t block, @@ -346,6 +346,15 @@ static inline int remove_inode_buffers(struct inode *inode) { return 1; } static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; } static inline void invalidate_bdev(struct block_device *bdev) {} +static inline struct super_block *freeze_bdev(struct block_device *sb) +{ + return NULL; +} + +static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb) +{ + return 0; +} #endif /* CONFIG_BLOCK */ #endif /* _LINUX_BUFFER_HEAD_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 3e59182de9df..6022f44043f2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -234,6 +234,8 @@ struct inodes_stat_t { #define BMAP_IOCTL 1 /* obsolete - kept for compatibility */ #define FIBMAP _IO(0x00,1) /* bmap access */ #define FIGETBSZ _IO(0x00,2) /* get the block size used for bmap */ +#define FIFREEZE _IOWR('X', 119, int) /* Freeze */ +#define FITHAW _IOWR('X', 120, int) /* Thaw */ #define FS_IOC_GETFLAGS _IOR('f', 1, long) #define FS_IOC_SETFLAGS _IOW('f', 2, long) @@ -591,6 +593,11 @@ struct block_device { * care to not mess up bd_private for that case. */ unsigned long bd_private; + + /* The counter of freeze processes */ + int bd_fsfreeze_count; + /* Mutex for freeze */ + struct mutex bd_fsfreeze_mutex; }; /* -- cgit