Re: [PATCH v1 2/6] fs: use on-stack-bio if backing device has BDI_CAP_SYNC capability

From	Minchan Kim <minchan@kernel.org>
Newsgroups	linux.kernel
Subject	Re: [PATCH v1 2/6] fs: use on-stack-bio if backing device has BDI_CAP_SYNC capability
Date	2017-08-14 10:50 +0200
Message-ID	<uejer-1Uc-27@gated-at.bofh.it> (permalink)
References	(5 earlier) <ucpei-Kz-9@gated-at.bofh.it> <ucpei-Kz-7@gated-at.bofh.it> <ucM1b-8i7-11@gated-at.bofh.it> <ucM1b-8i7-13@gated-at.bofh.it> <udfFT-2pX-11@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

Hi Christoph,

On Fri, Aug 11, 2017 at 12:46:15PM +0200, Christoph Hellwig wrote:
> On Wed, Aug 09, 2017 at 08:06:24PM -0700, Dan Williams wrote:
> > I like it, but do you think we should switch to sbvec[<constant>] to
> > preclude pathological cases where nr_pages is large?
> 
> Yes, please.

Still, I don't understand how sbvec[nr_pages] with on-stack bio in
do_mpage_readpage can help the performance.

IIUC, do_mpage_readpage works with page-base. IOW, it passes just one
page, not multiple pages so if we use on-stack bio, we just add *a page*
via bio_add_page and submit the bio before the function returning.

So, rather than sbvec[1], why de we need sbvec[nr_pages]?

Please, let me open my eyes. :)

Thanks.

Back to linux.kernel | Previous | Next | Find similar | Unroll thread

Thread

Re: [PATCH v1 2/6] fs: use on-stack-bio if backing device has  BDI_CAP_SYNC capability Minchan Kim <minchan@kernel.org> - 2017-08-14 10:50 +0200

csiph-web