Messages in this thread | | | Date | Wed, 29 Jun 2011 14:14:46 -0400 | From | Josef Bacik <> | Subject | Re: [PATCH] fs: push i_mutex and filemap_write_and_wait down into ->fsync() handlers |
| |
On 06/29/2011 02:09 PM, Christoph Hellwig wrote: >> -int blkdev_fsync(struct file *filp, int datasync) >> +int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync) >> { >> struct inode *bd_inode = filp->f_mapping->host; >> struct block_device *bdev = I_BDEV(bd_inode); >> @@ -389,14 +389,10 @@ int blkdev_fsync(struct file *filp, int datasync) >> * i_mutex and doing so causes performance issues with concurrent >> * O_SYNC writers to a block device. >> */ >> - mutex_unlock(&bd_inode->i_mutex); >> - > > Now that i_mutex on entry isn't held the comment above can be removed. >
The comment is still useful since it states why we don't take the i_mutex at all, so I think it's still valuable. Thanks,
Josef
| |