From: Bart Van Assche <bvanassche-HInyCGIudOg@public.gmane.org>
To: Or Gerlitz <ogerlitz-VPRAkNaXOzVWk0Htik3J/w@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: Fri, 26 Jul 2013 11:27:05 +0200 [thread overview]
Message-ID: <51F240E9.5000600@acm.org> (raw)
In-Reply-To: <51F000CB.3050808-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
On 07/24/13 18:28, Or Gerlitz wrote:
> On 23/07/2013 17:47, Bart Van Assche wrote:
>> 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 ?
>
> My understanding of the API is that it assumes that the HW is capable to
> change the page shift (size) associated with certain fast_reg MR for
> each mapping.
I think you have a point here. Although I'm not sure this is what you
had in mind, using PAGE_SIZE / PAGE_SHIFT instead of SIZE_4K / SHIFT_4K
should work better on architectures with a page size larger than 4KB. On
mlx4 the largest supported page list length is 511
(MLX4_MAX_FAST_REG_PAGES). So the former option should allow to support
larger sg lists on such architectures (up to length 511) compared to the
latter (up to length 511/(64/4) = 31 for 64KB pages).
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:[~2013-07-26 9:27 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
[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 [this message]
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=51F240E9.5000600@acm.org \
--to=bvanassche-hinycgiudog@public.gmane.org \
--cc=linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=ogerlitz-VPRAkNaXOzVWk0Htik3J/w@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