From: Jason Gunthorpe <jgg-uk2M96/98Pc@public.gmane.org>
To: Steve Wise <swise-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org>
Cc: 'Bernard Metzler' <bmt-OA+xvbQnYDHMbYB6QlFGEg@public.gmane.org>,
linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Subject: Re: [PATCH v3 03/13] Attach/detach SoftiWarp to/from network and RDMA subsystem
Date: Tue, 23 Jan 2018 10:47:58 -0700 [thread overview]
Message-ID: <20180123174758.GH30670@ziepe.ca> (raw)
In-Reply-To: <014501d39471$84cdee20$8e69ca60$@opengridcomputing.com>
On Tue, Jan 23, 2018 at 11:42:20AM -0600, Steve Wise wrote:
> Since the iwarp protocols run on top of TCP/IP, there is always the case
> that some middle box resegments tcp segments differently, so a good iwarp HW
> implementation should deal with funny alignments, partial iWARP PDUs
> arriving, etc. But the RFCs, as I read them, want implementations to try
> "really hard" to avoid spanning an iWARP PDU across many TCP segments. And
> I think siw should do the same, by default.
But Bernard just said siw doesn't interoperate in certain cases
because of this - so that sounds like more than 'try really hard' ??
Or is that an overstatement and it just makes the rx side slower if
segmentation is not optimal?
Jason
--
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:[~2018-01-23 17:47 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-01-14 22:35 [PATCH v3 00/13] Request for Comments on SoftiWarp Bernard Metzler
[not found] ` <20180114223603.19961-1-bmt-OA+xvbQnYDHMbYB6QlFGEg@public.gmane.org>
2018-01-14 22:35 ` [PATCH v3 01/13] iWARP wire packet format definition Bernard Metzler
2018-01-14 22:35 ` [PATCH v3 02/13] Main SoftiWarp include file Bernard Metzler
2018-01-14 22:35 ` [PATCH v3 03/13] Attach/detach SoftiWarp to/from network and RDMA subsystem Bernard Metzler
[not found] ` <20180114223603.19961-4-bmt-OA+xvbQnYDHMbYB6QlFGEg@public.gmane.org>
2018-01-23 16:33 ` Steve Wise
2018-01-23 16:43 ` Jason Gunthorpe
[not found] ` <20180123164316.GC30670-uk2M96/98Pc@public.gmane.org>
2018-01-23 16:58 ` Steve Wise
2018-01-23 17:05 ` Jason Gunthorpe
[not found] ` <20180123170517.GE30670-uk2M96/98Pc@public.gmane.org>
2018-01-23 17:24 ` Steve Wise
2018-01-23 17:28 ` Jason Gunthorpe
[not found] ` <20180123172830.GF30670-uk2M96/98Pc@public.gmane.org>
2018-01-23 17:39 ` Bernard Metzler
2018-01-23 17:42 ` Steve Wise
2018-01-23 17:47 ` Jason Gunthorpe [this message]
[not found] ` <20180123174758.GH30670-uk2M96/98Pc@public.gmane.org>
2018-01-23 17:55 ` Steve Wise
2018-01-23 18:21 ` Bernard Metzler
2018-01-23 17:23 ` Bernard Metzler
[not found] ` <OF34749881.4216E578-ON0025821E.005F897C-0025821E.005F8983-8eTO7WVQ4XIsd+ienQ86orlN3bxYEBpz@public.gmane.org>
2018-01-23 17:43 ` Steve Wise
2018-01-23 17:21 ` Bernard Metzler
2018-01-14 22:35 ` [PATCH v3 04/13] SoftiWarp object management Bernard Metzler
2018-01-14 22:35 ` [PATCH v3 05/13] SoftiWarp application interface Bernard Metzler
[not found] ` <20180114223603.19961-6-bmt-OA+xvbQnYDHMbYB6QlFGEg@public.gmane.org>
2018-01-23 17:18 ` Steve Wise
2018-01-23 18:07 ` Bernard Metzler
[not found] ` <OF7390EC15.6C2741F2-ON0025821E.0062D222-0025821E.00639402-8eTO7WVQ4XIsd+ienQ86orlN3bxYEBpz@public.gmane.org>
2018-01-23 18:12 ` Steve Wise
2018-01-14 22:35 ` [PATCH v3 06/13] SoftiWarp connection management Bernard Metzler
[not found] ` <20180114223603.19961-7-bmt-OA+xvbQnYDHMbYB6QlFGEg@public.gmane.org>
2018-01-30 21:27 ` Steve Wise
2018-01-31 17:28 ` Bernard Metzler
2018-01-14 22:35 ` [PATCH v3 07/13] SoftiWarp application buffer management Bernard Metzler
2018-01-14 22:35 ` [PATCH v3 08/13] SoftiWarp Queue Pair methods Bernard Metzler
2018-01-14 22:35 ` [PATCH v3 09/13] SoftiWarp transmit path Bernard Metzler
2018-01-14 22:36 ` [PATCH v3 10/13] SoftiWarp receive path Bernard Metzler
2018-01-14 22:36 ` [PATCH v3 11/13] SoftiWarp Completion Queue methods Bernard Metzler
2018-01-14 22:36 ` [PATCH v3 12/13] SoftiWarp debugging code Bernard Metzler
2018-01-14 22:36 ` [PATCH v3 13/13] Add SoftiWarp to kernel build environment Bernard Metzler
2018-01-17 16:07 ` [PATCH v3 00/13] Request for Comments on SoftiWarp Steve Wise
2018-01-18 7:29 ` Leon Romanovsky
[not found] ` <20180118072958.GW13639-U/DQcQFIOTAAJjI8aNfphQ@public.gmane.org>
2018-01-18 17:03 ` Bernard Metzler
[not found] ` <OFC86A1EC5.60F00E9A-ON00258219.005DA6A4-00258219.005DBBB9-8eTO7WVQ4XIsd+ienQ86orlN3bxYEBpz@public.gmane.org>
2018-01-18 21:52 ` Steve Wise
2018-01-23 17:31 ` Bernard Metzler
2018-02-02 14:37 ` Bernard Metzler
[not found] ` <OFD1018BEE.35589194-ON00258228.00505F2B-00258228.00505F31-8eTO7WVQ4XIsd+ienQ86orlN3bxYEBpz@public.gmane.org>
2018-02-02 18:56 ` Jason Gunthorpe
[not found] ` <20180202185640.GC9080-uk2M96/98Pc@public.gmane.org>
2018-02-04 20:08 ` Bernard Metzler
[not found] ` <OFEF72EEE6.7E5C3FA5-ON0025822A.005B18E4-0025822A.006EA4BB-8eTO7WVQ4XIsd+ienQ86orlN3bxYEBpz@public.gmane.org>
2018-02-04 20:39 ` Jason Gunthorpe
2018-01-23 16:31 ` Steve Wise
2018-01-23 16:44 ` Jason Gunthorpe
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=20180123174758.GH30670@ziepe.ca \
--to=jgg-uk2m96/98pc@public.gmane.org \
--cc=bmt-OA+xvbQnYDHMbYB6QlFGEg@public.gmane.org \
--cc=linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=swise-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@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