Re: [PATCH 2/9] inode: add IOP_NOTHASHED to avoid inode hash lock in evict

[Josef Bacik <jbacik@fb.com>]

On 03/12/2015 05:52 AM, Al Viro wrote:
> On Tue, Mar 10, 2015 at 03:45:17PM -0400, Josef Bacik wrote:
>> From: Dave Chinner <dchinner@redhat.com>
>>
>> Some filesystems don't use the VFS inode hash and fake the fact they
>> are hashed so that all the writeback code works correctly. However,
>> this means the evict() path still tries to remove the inode from the
>> hash, meaning that the inode_hash_lock() needs to be taken
>> unnecessarily. Hence under certain workloads the inode_hash_lock can
>> be contended even if the inode is never actually hashed.
>>
>> To avoid this, add an inode opflag to allow inode_hash_remove() to
>> avoid taking the hash lock on inodes have never actually been
>> hashed.
>
> Why bother with flags, etc. when we could just do
>
> static inline bool hlist_fake(struct hlist_node *h)
> {
> 	return h->pprev == &h->next;
> }
>
>> -	if (!inode_unhashed(inode))
>> +	if (!((inode->i_opflags & IOP_NOTHASHED) || inode_unhashed(inode)))
>
> and turn this check into
> 	if (!inode_unhashed(inode) && !hlist_fake(&inode->i_hash))
>
> instead?
>

I made the change and sent the new patch, hopefully it worked, sometimes 
my laptop screws up git-send-email.  If everything looks good to you Al 
you can pull from my tree if you don't want to scrape from the list

git://git.kernel.org/pub/scm/linux/kernel/git/josef/btrfs-next.git 
superblock-scaling

Thanks,

Josef