From: Dario Faggioli <dario.faggioli@citrix.com>
To: xen-devel@lists.xenproject.org
Cc: George Dunlap <george.dunlap@eu.citrix.com>,
Anshul Makkar <anshul.makkar@citrix.com>
Subject: Re: [PATCH v2 07/10] xen: credit2: always mark a tickled pCPU as... tickled!
Date: Fri, 10 Feb 2017 00:48:59 +0100 [thread overview]
Message-ID: <1486684139.3042.48.camel@citrix.com> (raw)
In-Reply-To: <148664874799.595.17524826454909514715.stgit@Solace.fritz.box>
[-- Attachment #1.1: Type: text/plain, Size: 1667 bytes --]
On Thu, 2017-02-09 at 14:59 +0100, Dario Faggioli wrote:
> In fact, whether or not a pCPU has been tickled, and is
> therefore about to re-schedule, is something we look at
> and base decisions on in various places.
>
> So, let's make sure that we do that basing on accurate
> information.
>
> While there, also tweak a little bit smt_idle_mask_clear()
> (used for implementing SMT support), so that it only alter
> the relevant cpumask when there is the actual need for this.
> (This is only for reduced overhead, behavior remains the
> same).
>
So, while working on other things with this series applied, I noticed
some strange behavior, for which it turned out this patch is
responsible.
More specifically...
> diff --git a/xen/common/sched_credit2.c b/xen/common/sched_credit2.c
> index addee7b..bfb4891 100644
> @@ -1289,9 +1300,8 @@ runq_tickle(const struct scheduler *ops, struct
> csched2_vcpu *new, s_time_t now)
> sizeof(d),
> (unsigned char *)&d);
> }
> - __cpumask_set_cpu(ipid, &rqd->tickled);
> - smt_idle_mask_clear(ipid, &rqd->smt_idle);
> - cpu_raise_softirq(ipid, SCHEDULE_SOFTIRQ);
> +
> + tickle_cpu(cpu, rqd);
>
... this, quite obviously, wants to be:
tickle_cpu(ipid, rqd);
I'll fix this in v2.
Regards,
Dario
--
<<This happens because I choose it to happen!>> (Raistlin Majere)
-----------------------------------------------------------------
Dario Faggioli, Ph.D, http://about.me/dario.faggioli
Senior Software Engineer, Citrix Systems R&D Ltd., Cambridge (UK)
[-- Attachment #1.2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 819 bytes --]
[-- Attachment #2: Type: text/plain, Size: 127 bytes --]
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
next prev parent reply other threads:[~2017-02-09 23:49 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-02-09 13:58 [PATCH v2 00/10] xen: credit2: improve style, and tracing; fix two bugs Dario Faggioli
2017-02-09 13:58 ` [PATCH v2 01/10] xen: sched: harmonize debug dump output among schedulers Dario Faggioli
2017-02-15 10:17 ` George Dunlap
2017-02-15 10:31 ` Dario Faggioli
2017-02-09 13:58 ` [PATCH v2 02/10] xen: credit2: clear bit instead of skip step in runq_tickle() Dario Faggioli
2017-02-15 10:21 ` George Dunlap
2017-02-09 13:58 ` [PATCH v2 03/10] xen: credit2: improve comments' style and definition of CSFLAG-s Dario Faggioli
2017-02-15 10:44 ` George Dunlap
2017-02-09 13:58 ` [PATCH v2 04/10] xen: credit2: make accessor helpers inline functions instead of macros Dario Faggioli
2017-02-09 14:14 ` Andrew Cooper
2017-02-09 14:34 ` Jan Beulich
2017-02-09 14:36 ` Jan Beulich
2017-02-09 15:33 ` Dario Faggioli
2017-02-15 10:49 ` George Dunlap
2017-02-24 18:26 ` Dario Faggioli
2017-02-09 13:58 ` [PATCH v2 05/10] xen: credit2: tidy up functions names by removing leading '__' Dario Faggioli
2017-02-15 13:57 ` George Dunlap
2017-02-24 18:32 ` Dario Faggioli
2017-02-09 13:59 ` [PATCH v2 06/10] xen: credit2: group the runq manipulating functions Dario Faggioli
2017-02-15 14:42 ` George Dunlap
2017-02-27 18:25 ` Dario Faggioli
2017-02-09 13:59 ` [PATCH v2 07/10] xen: credit2: always mark a tickled pCPU as... tickled! Dario Faggioli
2017-02-09 23:48 ` Dario Faggioli [this message]
2017-02-15 14:55 ` George Dunlap
2017-02-09 13:59 ` [PATCH v2 08/10] xen: credit2: don't miss accounting while doing a credit reset Dario Faggioli
2017-02-15 15:07 ` George Dunlap
2017-02-09 13:59 ` [PATCH v2 09/10] xen/tools: tracing: trace (Credit2) runq traversal Dario Faggioli
2017-02-15 15:31 ` George Dunlap
2017-02-24 18:48 ` Dario Faggioli
2017-02-09 13:59 ` [PATCH v2 10/10] xen/tools: tracing: always report how long next slice will be Dario Faggioli
2017-02-15 15:40 ` George Dunlap
2017-02-27 18:12 ` Dario Faggioli
2017-02-09 14:37 ` [PATCH v2 00/10] xen: credit2: improve style, and tracing; fix two bugs Jan Beulich
2017-02-09 15:29 ` Dario Faggioli
2017-02-15 16:03 ` George Dunlap
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=1486684139.3042.48.camel@citrix.com \
--to=dario.faggioli@citrix.com \
--cc=anshul.makkar@citrix.com \
--cc=george.dunlap@eu.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).