From: Bart Van Assche <bvanassche-HInyCGIudOg@public.gmane.org>
To: Or Gerlitz <or.gerlitz-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>,
Roland Dreier <roland-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>,
Hefty Sean <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>,
Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Cc: linux-rdma <linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
Mike Christie <michaelc-hcNo3dDEHLuVc3sceRu5cw@public.gmane.org>
Subject: Re: linux rdma 3.14 merge plans
Date: Wed, 29 Jan 2014 15:13:21 +0100 [thread overview]
Message-ID: <52E90C81.9040800@acm.org> (raw)
In-Reply-To: <CAJZOPZLBECYXrpp0GY0uUvyf+XbiLHhXdVukniPXD4AWZObymg-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
On 01/28/14 22:02, Or Gerlitz wrote:
>>>> Roland, ping! the signature patches were posted > three months ago.
I have a question about RDMA and T10-DIF support. The Linux block layer,
the Linux SCSI core, Linux filesystems and block drivers all support
discontiguous buffers. These are buffers that cannot be mapped onto a
single contiguous range of virtual memory addresses. I think the RDMA
FMR and FR memory registration mechanisms only support mapping a range
of addresses that can be mapped onto a contiguous region of virtual
addresses. This means that either multiple RDMA memory regions are
needed to map a discontiguous buffer or that the buffer contents has to
be copied before associating it with a memory region. What I understood
from the mlx5 T10-DIF patch series is that the API introduced in that
patch series is such that only a single memory region per data transfer
operation is supported. This made me wonder how to support T10-DIF for
discontiguous buffers. Would one of the options below perhaps be an
appropriate solution ?
- Add a flag in struct request_queue that tells the block layer to use a
bounce buffer (data copying) for I/O requests with a discontiguous
data buffer. The block layer already supports copying data buffers for
which e.g. DMA alignment requirements are not met. Rework patch
"IB/iser: Introduce fast memory registration model" (commit
5587856c9659ac2d6ab201141aa8a5c2ff3be4cd) such that it takes advantage
of that new flag. See also blk_rq_map_user_iov() for an example of
how the block layer decides when copying a data buffer is necessary.
- Modify the patches that add T10-DIF such that discontiguous buffers
are supported.
Sorry that I had not realized this before.
Bart.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
next prev parent reply other threads:[~2014-01-29 14:13 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-01-07 21:02 linux rdma 3.14 merge plans Or Gerlitz
[not found] ` <CAJZOPZ+4yQ-sT=ks7+eiJjkxOjy5w=BmG16JVcUPiuVsof7qEA-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2014-01-08 0:51 ` Roland Dreier
[not found] ` <CAG4TOxOMmvFWnkU3DBn33rscEKh2_YfbUCKY=iY8PCVN3+nEsA-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2014-01-08 8:52 ` Sagi Grimberg
2014-01-08 9:15 ` Or Gerlitz
2014-01-08 9:37 ` Or Gerlitz
[not found] ` <52CD1C68.4050406-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2014-01-13 20:32 ` Nicholas A. Bellinger
[not found] ` <1389645171.5567.459.camel-XoQW25Eq2zviZyQQd+hFbcojREIfoBdhmpATvIKMPHk@public.gmane.org>
2014-01-15 21:15 ` Nicholas A. Bellinger
[not found] ` <CAG4TOxNa32sLxifPx_f8sW04B_qSh01WWfWjRvam6fjvFLDXSQ@mail.gmail.com>
[not found] ` <CAG4TOxNa32sLxifPx_f8sW04B_qSh01WWfWjRvam6fjvFLDXSQ-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2014-01-16 21:14 ` Nicholas A. Bellinger
[not found] ` <1389906852.5567.668.camel-XoQW25Eq2zviZyQQd+hFbcojREIfoBdhmpATvIKMPHk@public.gmane.org>
2014-01-16 21:37 ` Greg Kroah-Hartman
[not found] ` <20140116213717.GA24718-U8xfFu+wG4EAvxtiuMwx3w@public.gmane.org>
2014-01-16 21:42 ` Or Gerlitz
[not found] ` <CAJZOPZ+75yOyxrcu4s=dSxv4Ya27UyotbRWLqwC3bbh3wieihg-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2014-01-16 21:58 ` Greg Kroah-Hartman
2014-01-16 22:06 ` Nicholas A. Bellinger
2014-01-17 22:02 ` Martin K. Petersen
2014-01-18 21:42 ` Roland Dreier
2014-01-19 3:42 ` Nicholas A. Bellinger
2014-01-19 11:20 ` sagi grimberg
[not found] ` <52DBB4F1.4020400-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2014-01-20 13:56 ` Or Gerlitz
2014-01-21 22:00 ` Or Gerlitz
[not found] ` <CAJZOPZLuz-Z59agBd0Q9J2=sSG-F+Y8MrJkoGbtiF5M+CnKU1g-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2014-01-22 0:43 ` Roland Dreier
2014-01-22 4:10 ` Or Gerlitz
2014-01-22 9:48 ` Sagi Grimberg
[not found] ` <52DF93D3.6030509-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
2014-01-28 21:02 ` Or Gerlitz
[not found] ` <CAJZOPZLBECYXrpp0GY0uUvyf+XbiLHhXdVukniPXD4AWZObymg-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2014-01-29 14:13 ` Bart Van Assche [this message]
[not found] ` <52E90C81.9040800-HInyCGIudOg@public.gmane.org>
2014-01-29 15:06 ` Sagi Grimberg
[not found] ` <52E91906.70802-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
2014-01-29 16:34 ` Or Gerlitz
2014-01-29 17:56 ` Bart Van Assche
[not found] ` <52E940B2.3070901-HInyCGIudOg@public.gmane.org>
2014-01-30 8:19 ` Or Gerlitz
[not found] ` <52EA0AFA.40100-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2014-01-30 10:07 ` Bart Van Assche
[not found] ` <52EA2465.8010907-HInyCGIudOg@public.gmane.org>
2014-01-30 10:38 ` Or Gerlitz
[not found] ` <CAG4TOxPLEfyWsUDf4_371u=_=tOgW2v5J4zSz8xx73DfziZOZg-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2014-01-22 7:27 ` Nicholas A. Bellinger
2014-02-07 0:02 ` Nicholas A. Bellinger
2014-02-07 0:04 ` Roland Dreier
2014-02-25 21:10 ` Or Gerlitz
2014-03-05 9:54 ` Nicholas A. Bellinger
[not found] ` <1394013249.19539.17.camel-XoQW25Eq2zviZyQQd+hFbcojREIfoBdhmpATvIKMPHk@public.gmane.org>
2014-03-05 15:18 ` Roland Dreier
[not found] ` <CAG4TOxNRkAUH5Jsd67--ydWtUJqE1=pnVSuorgn4vNQiuYx1wg-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2014-03-05 15:38 ` Or Gerlitz
2014-03-05 19:03 ` Nicholas A. Bellinger
[not found] ` <1394046218.20601.12.camel-XoQW25Eq2zviZyQQd+hFbcojREIfoBdhmpATvIKMPHk@public.gmane.org>
2014-03-07 5:07 ` Devesh Sharma
[not found] ` <EE7902D3F51F404C82415C4803930ACD3FDDD50E-DWYeeINJQrxExQ8dmkPuX0M9+F4ksjoh@public.gmane.org>
2014-03-07 19:31 ` Roland Dreier
[not found] ` <CAL1RGDXRCZafDcFsbiG823VQ7_AVZeZqxY8JEaj=oCYRteAw_A-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2014-03-10 9:00 ` Devesh Sharma
2014-04-01 21:31 ` Or Gerlitz
2014-01-20 12:40 ` Bart Van Assche
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=52E90C81.9040800@acm.org \
--to=bvanassche-hinycgiudog@public.gmane.org \
--cc=linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=michaelc-hcNo3dDEHLuVc3sceRu5cw@public.gmane.org \
--cc=or.gerlitz-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org \
--cc=roland-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org \
--cc=sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org \
--cc=sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox