From: David Gibson <david@gibson.dropbear.id.au>
To: Igor Mammedov <imammedo@redhat.com>
Cc: qemu-devel@nongnu.org, Eduardo Habkost <ehabkost@redhat.com>,
Peter Maydell <peter.maydell@linaro.org>,
Andrew Jones <drjones@redhat.com>, Eric Blake <eblake@redhat.com>,
Paolo Bonzini <pbonzini@redhat.com>,
Shannon Zhao <zhaoshenglong@huawei.com>,
qemu-arm@nongnu.org, qemu-ppc@nongnu.org
Subject: Re: [Qemu-devel] [PATCH v3 01/18] numa: move source of default CPUs to NUMA node mapping into boards
Date: Thu, 11 May 2017 14:36:25 +1000 [thread overview]
Message-ID: <20170511043625.GG14408@umbus.fritz.box> (raw)
In-Reply-To: <1494415802-227633-2-git-send-email-imammedo@redhat.com>
[-- Attachment #1: Type: text/plain, Size: 2043 bytes --]
On Wed, May 10, 2017 at 01:29:45PM +0200, Igor Mammedov wrote:
> Originally CPU threads were by default assigned in
> round-robin fashion. However it was causing issues in
> guest since CPU threads from the same socket/core could
> be placed on different NUMA nodes.
> Commit fb43b73b (pc: fix default VCPU to NUMA node mapping)
> fixed it by grouping threads within a socket on the same node
> introducing cpu_index_to_socket_id() callback and commit
> 20bb648d (spapr: Fix default NUMA node allocation for threads)
> reused callback to fix similar issues for SPAPR machine
> even though socket doesn't make much sense there.
>
> As result QEMU ended up having 3 default distribution rules
> used by 3 targets /virt-arm, spapr, pc/.
>
> In effort of moving NUMA mapping for CPUs into possible_cpus,
> generalize default mapping in numa.c by making boards decide
> on default mapping and let them explicitly tell generic
> numa code to which node a CPU thread belongs to by replacing
> cpu_index_to_socket_id() with @cpu_index_to_instance_props()
> which provides default node_id assigned by board to specified
> cpu_index.
>
> Signed-off-by: Igor Mammedov <imammedo@redhat.com>
> Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
[snip]
> +static CpuInstanceProperties
> +virt_cpu_index_to_props(MachineState *ms, unsigned cpu_index)
> +{
> + MachineClass *mc = MACHINE_GET_CLASS(ms);
> + const CPUArchIdList *possible_cpus = mc->possible_cpu_arch_ids(ms);
> +
> + assert(cpu_index < possible_cpus->len);
> + return possible_cpus->cpus[cpu_index].props;
> +}
Suggested follow up patch: Since this function is identical for x86
and ARM, we could have a "thread_granularity_cpu_index_to_props"
helper they could both reference. M
--
David Gibson | I'll have my music baroque, and my code
david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_
| _way_ _around_!
http://www.ozlabs.org/~dgibson
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 819 bytes --]
next prev parent reply other threads:[~2017-05-11 4:54 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-05-10 11:29 [Qemu-devel] [PATCH v3 00/18] numa: add '-numa cpu' option Igor Mammedov
2017-05-10 11:29 ` [Qemu-devel] [PATCH v3 01/18] numa: move source of default CPUs to NUMA node mapping into boards Igor Mammedov
2017-05-11 4:36 ` David Gibson [this message]
2017-05-10 11:29 ` [Qemu-devel] [PATCH v3 02/18] spapr: add node-id property to sPAPR core Igor Mammedov
2017-05-10 11:29 ` [Qemu-devel] [PATCH v3 03/18] pc: add node-id property to CPU Igor Mammedov
2017-05-10 11:29 ` [Qemu-devel] [PATCH v3 04/18] virt-arm: " Igor Mammedov
2017-05-10 11:29 ` [Qemu-devel] [PATCH v3 05/18] numa: add check that board supports cpu_index to node mapping Igor Mammedov
2017-05-10 11:29 ` [Qemu-devel] [PATCH v3 06/18] numa: mirror cpu to node mapping in MachineState::possible_cpus Igor Mammedov
2017-05-26 15:46 ` Eduardo Habkost
2017-05-29 13:12 ` Igor Mammedov
2017-05-29 13:36 ` Eduardo Habkost
2017-05-29 13:49 ` Igor Mammedov
2017-05-30 12:13 ` Igor Mammedov
2017-05-30 14:04 ` Eduardo Habkost
2017-05-10 11:29 ` [Qemu-devel] [PATCH v3 07/18] numa: do default mapping based on possible_cpus instead of node_cpu bitmaps Igor Mammedov
2017-05-10 11:29 ` [Qemu-devel] [PATCH v3 08/18] pc: get numa node mapping from possible_cpus instead of numa_get_node_for_cpu() Igor Mammedov
2017-05-10 11:29 ` [Qemu-devel] [PATCH v3 09/18] spapr: " Igor Mammedov
2017-05-10 11:29 ` [Qemu-devel] [PATCH v3 10/18] virt-arm: " Igor Mammedov
2017-05-10 11:29 ` [Qemu-devel] [PATCH v3 11/18] QMP: include CpuInstanceProperties into query_cpus output output Igor Mammedov
2017-05-11 4:39 ` David Gibson
2017-05-10 11:29 ` [Qemu-devel] [PATCH v3 12/18] tests: numa: add case for QMP command query-cpus Igor Mammedov
2017-05-10 11:29 ` [Qemu-devel] [PATCH v3 13/18] numa: remove no longer need numa_post_machine_init() Igor Mammedov
2017-05-10 11:29 ` [Qemu-devel] [PATCH v3 14/18] machine: call machine init from wrapper Igor Mammedov
2017-05-10 11:29 ` [Qemu-devel] [PATCH v3 15/18] numa: use possible_cpus for not mapped CPUs check Igor Mammedov
2017-05-10 11:30 ` [Qemu-devel] [PATCH v3 16/18] numa: remove node_cpu bitmaps as they are no longer used Igor Mammedov
2017-05-10 11:30 ` [Qemu-devel] [PATCH v3 17/18] numa: add '-numa cpu, ...' option for property based node mapping Igor Mammedov
2017-05-11 5:23 ` David Gibson
2017-05-10 11:30 ` [Qemu-devel] [PATCH v3 18/18] tests: check -numa node, cpu=props_list usecase Igor Mammedov
2017-05-11 13:38 ` [Qemu-devel] [PATCH v3 00/18] numa: add '-numa cpu' option Eduardo Habkost
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=20170511043625.GG14408@umbus.fritz.box \
--to=david@gibson.dropbear.id.au \
--cc=drjones@redhat.com \
--cc=eblake@redhat.com \
--cc=ehabkost@redhat.com \
--cc=imammedo@redhat.com \
--cc=pbonzini@redhat.com \
--cc=peter.maydell@linaro.org \
--cc=qemu-arm@nongnu.org \
--cc=qemu-devel@nongnu.org \
--cc=qemu-ppc@nongnu.org \
--cc=zhaoshenglong@huawei.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;
as well as URLs for NNTP newsgroup(s).