Re: [PATCH v5] DAX: enable iostat for read/write

[Kani, Toshimitsu]

On Thu, 2017-01-12 at 10:02 -0800, Joe Perches wrote:
> On Thu, 2017-01-12 at 11:38 -0700, Toshi Kani wrote:
> > DAX IO path does not support iostat, but its metadata IO path does.
> > Therefore, iostat shows metadata IO statistics only, which has been
> > confusing to users.
> 
> []
> > diff --git a/fs/dax.c b/fs/dax.c
> 
> []
> > @@ -1058,12 +1058,24 @@ dax_iomap_rw(struct kiocb *iocb, struct
> > iov_iter *iter,
> > Â{
> > Â	struct address_space *mapping = iocb->ki_filp->f_mapping;
> > Â	struct inode *inode = mapping->host;
> > +	struct gendisk *disk = inode->i_sb->s_bdev->bd_disk;
> > Â	loff_t pos = iocb->ki_pos, ret = 0, done = 0;
> > Â	unsigned flags = 0;
> > +	unsigned long start = 0;
> > +	int do_acct = blk_queue_io_stat(disk->queue);
> > Â
> > Â	if (iov_iter_rw(iter) == WRITE)
> > Â		flags |= IOMAP_WRITE;
> > Â
> > +	if (do_acct) {
> > +		sector_t sec = iov_iter_count(iter) >> 9;
> > +
> > +		start = jiffies;
> > +		generic_start_io_acct(iov_iter_rw(iter),
> > +				ÂÂÂÂÂÂmin_t(unsigned long, 1,
> > sec),
> 
> I believe I mislead you with a thinko.
> 
> Your original code was
> 	(!sec) ? 1 : sec
> and I suggested incorrectly using min_t
> 
> It should of course be max_t.ÂÂSorry.

My bad. I should have caught it.

> Also, as sec is now sector_t (u64), perhaps this
> unsigned long cast is incorrect.

I see. Since iov_iter_count() returns a size_t value, I will use
'size_t' for 'sec' as you originally suggested. 

Thanks,
-Toshi