From: Zoltan Kiss <zoltan.kiss@citrix.com>
To: Ian Campbell <ian.campbell@citrix.com>
Cc: "xen-devel@lists.xenproject.org" <xen-devel@lists.xenproject.org>,
Wei Liu <wei.liu2@citrix.com>
Subject: Re: RING_HAS_UNCONSUMED_REQUESTS oddness
Date: Thu, 6 Mar 2014 16:31:20 +0000 [thread overview]
Message-ID: <5318A2D8.3090808@citrix.com> (raw)
In-Reply-To: <1394121221.13270.10.camel@hastur.hellion.org.uk>
On 06/03/14 15:53, Ian Campbell wrote:
> On Thu, 2014-03-06 at 15:47 +0000, Zoltan Kiss wrote:
>> By my understanding, there is no way rsp could be smaller than req, so
>> there is no point having this. Am I missing something?
>
> It happens during wraparound, i.e. after req has wrapped but rsp hasn't
> yet.
The name of the macro suggest we are interested whether the ring has
unconsumed requests, and netback uses it that way. The answer to that
question is req_prod - req_cons. And it works if prod wrapped but cons
didn't.
rsp calculates the number of "consumed but not responded" requests (it
also works well if req_cons wrapped but rsp_prod_pvt didn't), then
subtract it from the ring size. So it gives the number of unconsumed
responses + unconsumed requests + unused slots. Why do we care about it?
And as it includes the number of unconsumed requests, it couldn't be
smaller than that, could it?
Zoli
next prev parent reply other threads:[~2014-03-06 16:31 UTC|newest]
Thread overview: 53+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-03-06 15:47 RING_HAS_UNCONSUMED_REQUESTS oddness Zoltan Kiss
2014-03-06 15:53 ` Ian Campbell
2014-03-06 16:31 ` Zoltan Kiss [this message]
2014-03-06 17:30 ` Tim Deegan
2014-03-06 21:39 ` Zoltan Kiss
2014-03-07 9:23 ` Paul Durrant
2014-03-07 17:43 ` Zoltan Kiss
2014-03-07 12:02 ` Wei Liu
2014-03-07 18:58 ` Zoltan Kiss
2014-03-11 15:55 ` Ian Campbell
2014-03-11 23:34 ` Zoltan Kiss
2014-03-13 16:38 ` [PATCH RFC] xen/public/ring.h: simplify RING_HAS_UNCONSUMED_REQUESTS() Tim Deegan
2014-03-22 14:18 ` Zoltan Kiss
2014-03-22 17:14 ` Tim Deegan
2014-03-24 7:38 ` Jan Beulich
2014-03-24 9:39 ` Paul Durrant
2014-03-24 9:59 ` Jan Beulich
2014-03-24 11:03 ` Paul Durrant
2014-03-24 12:23 ` Zoltan Kiss
2014-03-24 13:52 ` Paul Durrant
2014-03-24 23:55 ` Zoltan Kiss
2014-04-03 9:38 ` Tim Deegan
2014-04-03 15:34 ` Zoltan Kiss
2014-03-11 15:44 ` RING_HAS_UNCONSUMED_REQUESTS oddness Ian Campbell
2014-03-11 23:24 ` Zoltan Kiss
2014-03-12 10:28 ` Ian Campbell
2014-03-12 10:48 ` Roger Pau Monné
2014-03-12 11:25 ` Paul Durrant
2014-03-12 11:38 ` Paul Durrant
2014-03-12 14:41 ` Zoltan Kiss
2014-03-12 15:23 ` Paul Durrant
2014-03-12 15:42 ` Wei Liu
2014-03-12 15:56 ` Paul Durrant
2014-03-12 16:02 ` Paul Durrant
2014-03-12 16:13 ` Zoltan Kiss
2014-03-12 16:42 ` Paul Durrant
2014-03-12 19:06 ` Zoltan Kiss
2014-03-13 9:26 ` Paul Durrant
2014-03-13 10:02 ` Ian Campbell
2014-03-13 10:58 ` Paul Durrant
2014-03-13 12:19 ` Ian Campbell
2014-03-13 12:28 ` Zoltan Kiss
2014-03-13 12:29 ` Paul Durrant
2014-03-13 12:44 ` Ian Campbell
2014-03-12 14:25 ` Zoltan Kiss
2014-03-12 14:27 ` Zoltan Kiss
2014-03-12 14:30 ` Ian Campbell
2014-03-12 15:14 ` Zoltan Kiss
2014-03-12 15:37 ` Ian Campbell
2014-03-12 17:14 ` Zoltan Kiss
2014-03-12 17:43 ` Ian Campbell
2014-03-12 21:10 ` Zoltan Kiss
2014-03-13 10:04 ` Ian Campbell
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=5318A2D8.3090808@citrix.com \
--to=zoltan.kiss@citrix.com \
--cc=ian.campbell@citrix.com \
--cc=wei.liu2@citrix.com \
--cc=xen-devel@lists.xenproject.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;
as well as URLs for NNTP newsgroup(s).