From: Tejun Heo <tj@kernel.org>
To: JoonSoo Kim <js1304@gmail.com>
Cc: laijs@cn.fujitsu.com, axboe@kernel.dk, jack@suse.cz,
fengguang.wu@intel.com, jmoyer@redhat.com, zab@redhat.com,
linux-kernel@vger.kernel.org, herbert@gondor.hengli.com.au,
davem@davemloft.net, linux-crypto@vger.kernel.org
Subject: Re: [PATCH 01/10] workqueue: add wq_numa_tbl_len and wq_numa_possible_cpumask[]
Date: Wed, 20 Mar 2013 07:48:59 -0700 [thread overview]
Message-ID: <20130320144859.GU3042@htj.dyndns.org> (raw)
In-Reply-To: <CAAmzW4OosERgCwGnDx7HGHOf7BxbBPNYugA_V8wbegKvOiDqgQ@mail.gmail.com>
On Wed, Mar 20, 2013 at 11:08:29PM +0900, JoonSoo Kim wrote:
> 2013/3/20 Tejun Heo <tj@kernel.org>:
> > Unbound workqueues are going to be NUMA-affine. Add wq_numa_tbl_len
> > and wq_numa_possible_cpumask[] in preparation. The former is the
> > highest NUMA node ID + 1 and the latter is masks of possibles CPUs for
> > each NUMA node.
>
> It is better to move this code to topology.c or cpumask.c,
> then it can be generally used.
Yeah, it just isn't clear where it should go. Most NUMA
initialization happens during early boot and arch-specific and
different archs expect NUMA information to be valid at different
point. We can do it from one of the early initcalls by which all NUMA
information should be valid but, I don't know, having different NUMA
information coming up at different times seems error-prone. There
would be no apparent indication that certain part is available while
others are not.
We could solve this by unifying how NUMA information is represented
and initialized. e.g. if all NUMA archs used
CONFIG_USE_PERCPU_NUMA_NODE_ID, we can simply modify
set_cpu_numa_node() to build all data structures as NUMA nodes are
discovered. Unfortunately, this isn't true yet and it's gonna be a
bit of work to get it in consistent state as it spans over multiple
architectures (not too many tho, NUMA fortunately is rare), so if
somebody can clean it up, I'll be happy to move these to topology.
Right now, I think it's best to just carry it in workqueue.c.
Thanks.
--
tejun
next prev parent reply other threads:[~2013-03-20 14:49 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-03-20 0:00 [PATCHSET wq/for-3.10] workqueue: NUMA affinity for unbound workqueues Tejun Heo
2013-03-20 0:00 ` [PATCH 01/10] workqueue: add wq_numa_tbl_len and wq_numa_possible_cpumask[] Tejun Heo
2013-03-20 14:08 ` JoonSoo Kim
2013-03-20 14:48 ` Tejun Heo [this message]
2013-03-20 15:43 ` Lai Jiangshan
2013-03-20 15:48 ` Tejun Heo
2013-03-20 16:43 ` Lai Jiangshan
2013-03-20 0:00 ` [PATCH 02/10] workqueue: drop 'H' from kworker names of unbound worker pools Tejun Heo
2013-03-20 0:00 ` [PATCH 03/10] workqueue: determine NUMA node of workers accourding to the allowed cpumask Tejun Heo
2013-03-20 0:00 ` [PATCH 04/10] workqueue: add workqueue->unbound_attrs Tejun Heo
2013-03-20 0:00 ` [PATCH 05/10] workqueue: make workqueue->name[] fixed len Tejun Heo
2013-03-20 0:00 ` [PATCH 06/10] workqueue: move hot fields of workqueue_struct to the end Tejun Heo
2013-03-20 0:00 ` [PATCH 07/10] workqueue: map an unbound workqueues to multiple per-node pool_workqueues Tejun Heo
2013-03-20 0:00 ` [PATCH 08/10] workqueue: break init_and_link_pwq() into two functions and introduce alloc_unbound_pwq() Tejun Heo
2013-03-20 15:52 ` Lai Jiangshan
2013-03-20 16:04 ` Tejun Heo
2013-03-20 0:00 ` [PATCH 09/10] workqueue: implement NUMA affinity for unbound workqueues Tejun Heo
2013-03-20 15:03 ` Lai Jiangshan
2013-03-20 15:05 ` Tejun Heo
2013-03-20 15:26 ` Lai Jiangshan
2013-03-20 15:32 ` Tejun Heo
2013-03-20 17:08 ` [PATCH v2 " Tejun Heo
2013-03-20 18:54 ` [PATCH v2 UPDATED " Tejun Heo
2013-03-20 0:00 ` [PATCH 10/10] workqueue: update sysfs interface to reflect NUMA awareness and a kernel param to disable NUMA affinity Tejun Heo
2013-03-20 12:14 ` [PATCHSET wq/for-3.10] workqueue: NUMA affinity for unbound workqueues Lai Jiangshan
2013-03-20 17:08 ` [PATCH 11/10] workqueue: use NUMA-aware allocation for pool_workqueues workqueues Tejun Heo
2013-03-20 18:57 ` [PATCHSET wq/for-3.10] workqueue: NUMA affinity for unbound workqueues Tejun Heo
2013-03-24 16:04 ` Lai Jiangshan
2013-03-24 18:55 ` Tejun Heo
2013-03-25 19:15 ` Tejun Heo
2013-03-25 20:48 ` Tejun Heo
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=20130320144859.GU3042@htj.dyndns.org \
--to=tj@kernel.org \
--cc=axboe@kernel.dk \
--cc=davem@davemloft.net \
--cc=fengguang.wu@intel.com \
--cc=herbert@gondor.hengli.com.au \
--cc=jack@suse.cz \
--cc=jmoyer@redhat.com \
--cc=js1304@gmail.com \
--cc=laijs@cn.fujitsu.com \
--cc=linux-crypto@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=zab@redhat.com \
/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
all inboxes | Powered by JetHome®