public inbox for linux-rdma@vger.kernel.org
 help / color / mirror / Atom feed
From: Bart Van Assche <bvanassche-HInyCGIudOg@public.gmane.org>
To: Or Gerlitz <or.gerlitz-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
Cc: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>,
	roland-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org,
	linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
	roid-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org,
	oren-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org
Subject: Re: [PATCH for-3.11 7/7] IB/iser: Introduce fast memory registration model (FRWR)
Date: Tue, 23 Jul 2013 16:47:15 +0200	[thread overview]
Message-ID: <51EE9773.9050003@acm.org> (raw)
In-Reply-To: <CAJZOPZ+1TLQ-vwsZG8dgxhP332CQeDNOWfzGRdTbwRxLRhL95w-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>

On 07/23/13 16:21, Or Gerlitz wrote:
> Bart, iSER's FMR and FRWR code works under the assumption that an SG
> list is "4K aligned". For SGs which don't obey that assumption we're
> using bounce buffer.
>
> Note that the SG "page" size used by FMRs/FRWRs doesn't have to be 1:1
> with the OS page size, so in that respect && down the road, we will
> get rid of the bounce buffer thing with having another FMR/FRWR pool
> whose "page" size is 512B and will be used for SG which are not "4K
> aligned".

Sorry but I had overlooked the bounce buffer patch. Regarding page 
sizes: is an InfiniBand HCA required to support a page size of 512 bytes 
? To me it seems like the smallest page size supported by e.g. the 
ocrdma driver is 4KB. From ocrdma_query_device():

	attr->page_size_cap = 0xffff000;

Still regarding page sizes: shouldn't ib_alloc_fast_reg_page_list() and 
ib_alloc_fast_reg_mr() multiply the SG list length by PAGE_SIZE / 
SIZE_4K to compensate for page size differences on architectures where 
virtual memory pages are larger than 4KB ?

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

  parent reply	other threads:[~2013-07-23 14:47 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-07-18 13:25 [PATCH for-3.11 0/7] Add Fast-Reg support to the iser initiator driver Or Gerlitz
     [not found] ` <1374153931-7313-1-git-send-email-ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2013-07-18 13:25   ` [PATCH for-3.11 1/7] IB/iser: Use proper debug level value for info prints Or Gerlitz
2013-07-18 13:25   ` [PATCH for-3.11 2/7] IB/iser: Restructure allocation/deallocation of connection resources Or Gerlitz
2013-07-18 13:25   ` [PATCH for-3.11 3/7] IB/iser: Accept session->cmds_max from user space Or Gerlitz
2013-07-18 13:25   ` [PATCH for-3.11 4/7] IB/iser: Generalize rdma memory registration Or Gerlitz
2013-07-18 13:25   ` [PATCH for-3.11 5/7] IB/iser: Handle unaligned SG in separate function Or Gerlitz
2013-07-18 13:25   ` [PATCH for-3.11 6/7] IB/iser: Place the fmr pool into a union in iser's IB conn struct Or Gerlitz
2013-07-18 13:25   ` [PATCH for-3.11 7/7] IB/iser: Introduce fast memory registration model (FRWR) Or Gerlitz
     [not found]     ` <1374153931-7313-8-git-send-email-ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2013-07-22 11:46       ` Bart Van Assche
     [not found]         ` <51ED1B8E.7070703-HInyCGIudOg@public.gmane.org>
2013-07-22 13:11           ` Sagi Grimberg
     [not found]             ` <51ED2F97.2080400-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2013-07-23 11:58               ` Bart Van Assche
     [not found]                 ` <51EE6FFE.8040802-HInyCGIudOg@public.gmane.org>
2013-07-23 14:21                   ` Or Gerlitz
     [not found]                     ` <CAJZOPZ+1TLQ-vwsZG8dgxhP332CQeDNOWfzGRdTbwRxLRhL95w-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2013-07-23 14:47                       ` Bart Van Assche [this message]
     [not found]                         ` <51EE9773.9050003-HInyCGIudOg@public.gmane.org>
2013-07-24 16:47                           ` Or Gerlitz
     [not found]                         ` <51F000CB.3050808@mellanox.com>
     [not found]                           ` <51F000CB.3050808-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2013-07-26  9:27                             ` Bart Van Assche
2013-07-23 14:33                   ` Sagi Grimberg
2013-07-22 14:37           ` Or Gerlitz
2013-07-26 17:15       ` Vu Pham
     [not found]         ` <51F2AEB6.6090000-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2013-07-28  8:15           ` Or Gerlitz
     [not found]             ` <51F4D305.7090700-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2013-07-28  9:26               ` Sagi Grimberg

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=51EE9773.9050003@acm.org \
    --to=bvanassche-hinycgiudog@public.gmane.org \
    --cc=linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=or.gerlitz-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org \
    --cc=oren-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org \
    --cc=roid-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org \
    --cc=roland-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org \
    --cc=sagig-VPRAkNaXOzVWk0Htik3J/w@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