Messages in this thread Patch in this message | | | Date | Thu, 15 Apr 2010 14:40:39 +1000 | From | Anton Blanchard <> | Subject | [PATCH] Fix regression in O_DIRECT|O_SYNC writes to block devices |
| |
We are seeing a large regression in database performance on recent kernels. The database opens a block device with O_DIRECT|O_SYNC and a number of threads write to different regions of the file at the same time.
A simple test case is below. I haven't defined DEVICE to anything since getting it wrong will destroy your data :) On an 3 disk LVM with a 64k chunk size we see about 17MB/sec and only a few threads in IO wait:
procs -----io---- -system-- -----cpu------ r b bi bo in cs us sy id wa st 0 3 0 16170 656 2259 0 0 86 14 0 0 2 0 16704 695 2408 0 0 92 8 0 0 2 0 17308 744 2653 0 0 86 14 0 0 2 0 17933 759 2777 0 0 89 10 0
Most threads are blocking in vfs_fsync_range, which has:
mutex_lock(&mapping->host->i_mutex); err = fop->fsync(file, dentry, datasync); if (!ret) ret = err; mutex_unlock(&mapping->host->i_mutex);
Commit 148f948ba877f4d3cdef036b1ff6d9f68986706a (vfs: Introduce new helpers for syncing after writing to O_SYNC file or IS_SYNC inode) offers some explanation of what is going on:
Use these new helpers for syncing from generic VFS functions. This makes O_SYNC writes to block devices acquire i_mutex for syncing. If we really care about this, we can make block_fsync() drop the i_mutex and reacquire it before it returns.
Thanks Jan for such a good commit message! The patch below drops the i_mutex in blkdev_fsync as suggested. With it the testcase improves from 17MB/s to 68M/sec:
procs -----io---- -system-- -----cpu------ r b bi bo in cs us sy id wa st 0 7 0 65536 1000 3878 0 0 70 30 0 0 34 0 69632 1016 3921 0 1 46 53 0 0 57 0 69632 1000 3921 0 0 55 45 0 0 53 0 69640 754 4111 0 0 81 19 0
I'd appreciate any comments from the I/O guys on if this is the right approach.
Testcase:
#define _GNU_SOURCE #include <stdio.h> #include <pthread.h> #include <unistd.h> #include <stdlib.h> #include <string.h> #include <sys/types.h> #include <sys/stat.h> #include <fcntl.h>
#define NR_THREADS 64 #define BUFSIZE (64 * 1024)
#define DEVICE "/dev/mapper/XXXXXX"
#define ALIGN(VAL, SIZE) (((VAL)+(SIZE)-1) & ~((SIZE)-1))
static int fd;
static void *doit(void *arg) { unsigned long offset = (long)arg; char *b, *buf;
b = malloc(BUFSIZE + 1024); buf = (char *)ALIGN((unsigned long)b, 1024); memset(buf, 0, BUFSIZE);
while (1) pwrite(fd, buf, BUFSIZE, offset); }
int main(int argc, char *argv[]) { int flags = O_RDWR|O_DIRECT; int i; unsigned long offset = 0;
if (argc > 1 && !strcmp(argv[1], "O_SYNC")) flags |= O_SYNC;
fd = open(DEVICE, flags); if (fd == -1) { perror("open"); exit(1); }
for (i = 0; i < NR_THREADS-1; i++) { pthread_t tid; pthread_create(&tid, NULL, doit, (void *)offset); offset += BUFSIZE; } doit((void *)offset);
return 0; }
Signed-off-by: Anton Blanchard <anton@samba.org> ---
Index: linux-2.6/fs/block_dev.c =================================================================== --- linux-2.6.orig/fs/block_dev.c 2010-04-14 12:55:50.000000000 +1000 +++ linux-2.6/fs/block_dev.c 2010-04-14 13:17:45.000000000 +1000 @@ -406,16 +406,24 @@ static loff_t block_llseek(struct file * int blkdev_fsync(struct file *filp, struct dentry *dentry, int datasync) { - struct block_device *bdev = I_BDEV(filp->f_mapping->host); + struct inode *bd_inode = filp->f_mapping->host; + struct block_device *bdev = I_BDEV(bd_inode); int error; + mutex_unlock(&bd_inode->i_mutex); + error = sync_blockdev(bdev); - if (error) + if (error) { + mutex_lock(&bd_inode->i_mutex); return error; + } error = blkdev_issue_flush(bdev, NULL); if (error == -EOPNOTSUPP) error = 0; + + mutex_lock(&bd_inode->i_mutex); + return error; } EXPORT_SYMBOL(blkdev_fsync);
| |