All of lore.kernel.org
 help / color / mirror / Atom feed
From: Dario Faggioli <dario.faggioli@citrix.com>
To: xen-devel@lists.xen.org
Cc: Andrew.Cooper3@citrix.com, Wei Liu <wei.liu2@citrix.com>,
	Ian.Campbell@citrix.com, Ian.Jackson@citrix.com
Subject: [PATCH v11 0/5] Implement vcpu soft affinity for credit1 (toolstack side, leftover)
Date: Sat, 28 Jun 2014 02:35:30 +0200	[thread overview]
Message-ID: <20140628001809.29968.22845.stgit@Solace> (raw)

Here it comes v11. This posting incorporates all the feedback v10 received. For
doing so, some of the patches changed again.

The main differences from last round are:

 * we are not deprecating cpumap any longer. We stop using it in xl (as using
the arrays is more powerful and allows for some code consolidation), but we are
not throwing warnings or specifying in any header that it should not be used;

 * as a consequence of above, I think it's really better to make sure that
libxl internals only deal with vcpu (hard) affinity in one single way.
Therefore, I implemented something that IanC suggested back at v9 time, i.e.,
if a cpumap is specified and a vcpu_hard_affinity is not, I convert the former
into the latter during libxl__build_info_setdefault(). Note that it makes sense
to do this in patch 04/05 (from a patch split point of view) as it is right in
there that, if not doing such conversion, it may happen that hard and soft
affinity are set with two distinct calls to libxl_vcpu_setaffinity(), which is
something we said we don't want (because we don't like the system to be in a
transient state in between the two calls);

 * in xl, when unifying the parsing of 'cpus="1,5-8"' and 'cpus=[1, 4, 2]', I
reworked the logic a bit, so that now the spurious looking initialization
( =NULL) discussed during v10's review is no longer necessary.

Oh, and this time I compiled the series on both Sid (gcc 4.9) and Wheezy (gcc
4.7)! :-)

Branch available here:

 git://xenbits.xen.org/people/dariof/xen.git  numa/per-vcpu-affinity-v11
 http://xenbits.xen.org/gitweb/?p=people/dariof/xen.git;a=shortlog;h=refs/heads/numa/per-vcpu-affinity-v11

Regards,
Dario
---
Dario Faggioli (5):
      xl: enable getting and setting soft affinity
      xl: move away from the use of cpumap for hard affinity
      xl: move the vcpu affinity parsing in a function
      libxl/xl: make it possible to specify soft-affinity in domain config file
      libxl: automatic NUMA placement affects soft affinity


 docs/man/xl.cfg.pod.5                |   50 ++++++--
 docs/man/xl.pod.1                    |   32 ++++-
 docs/misc/xl-numa-placement.markdown |   14 ++
 tools/libxl/libxl.h                  |    3 
 tools/libxl/libxl_create.c           |   15 ++
 tools/libxl/libxl_dom.c              |   69 +++++++++--
 tools/libxl/libxl_types.idl          |    1 
 tools/libxl/xl_cmdimpl.c             |  208 +++++++++++++++++++++-------------
 tools/libxl/xl_cmdtable.c            |    2 
 9 files changed, 275 insertions(+), 119 deletions(-)

--
<<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)

             reply	other threads:[~2014-06-28  0:35 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-06-28  0:35 Dario Faggioli [this message]
2014-06-28  0:35 ` [PATCH v11 1/5] xl: enable getting and setting soft affinity Dario Faggioli
2014-06-28  0:35 ` [PATCH v11 2/5] xl: move away from the use of cpumap for hard affinity Dario Faggioli
2014-07-02 15:06   ` Ian Campbell
2014-06-28  0:35 ` [PATCH v11 3/5] xl: move the vcpu affinity parsing in a function Dario Faggioli
2014-07-02 15:17   ` Ian Campbell
2014-06-28  0:36 ` [PATCH v11 4/5] libxl/xl: make it possible to specify soft-affinity in domain config file Dario Faggioli
2014-07-02 15:21   ` Ian Campbell
2014-06-28  0:36 ` [PATCH v11 5/5] libxl: automatic NUMA placement affects soft affinity Dario Faggioli

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=20140628001809.29968.22845.stgit@Solace \
    --to=dario.faggioli@citrix.com \
    --cc=Andrew.Cooper3@citrix.com \
    --cc=Ian.Campbell@citrix.com \
    --cc=Ian.Jackson@citrix.com \
    --cc=wei.liu2@citrix.com \
    --cc=xen-devel@lists.xen.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.