Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1450259

Re: [PATCH v9 0/7] Make cpuid <-> nodeid mapping persistent

From Tejun Heo <tj@kernel.org>
Newsgroups linux.kernel
Subject Re: [PATCH v9 0/7] Make cpuid <-> nodeid mapping persistent
Date 2016-07-26 02:20 +0200
Message-ID <rYYgi-3je-17@gated-at.bofh.it> (permalink)
References <rYJAB-2kh-7@gated-at.bofh.it> <rYXtT-2Lh-1@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw


Hello, Andrew.

On Mon, Jul 25, 2016 at 04:20:22PM -0700, Andrew Morton wrote:
> > When a pool workqueue is initialized, if its cpumask belongs to a node, its
> > pool->node will be mapped to that node. And memory used by this workqueue will
> > also be allocated on that node.
> 
> Plan B is to hunt down and fix up all the workqueue structures at
> hotplug-time.  Has that option been evaluated?
> 
> Your fix is x86-only and this bug presumably affects other
> architectures, yes?  I think a "Plan B" would fix all architectures?

Yeah, that was one of the early approaches.  The issue isn't limited
to wq.  Any memory allocation can have similar issues of underlying
node association changing and we don't have any synchronization
mechanism around it.  It doesn't make any sense to make NUMA
association dynamic when the consumer surface is vastly larger and
there's nothing inherently dynamic about the association itself.

Thanks.

-- 
tejun

Back to linux.kernel | Previous | NextPrevious in thread | Next in thread | Find similar | Unroll thread


Thread

[PATCH v9 0/7] Make cpuid <-> nodeid mapping persistent Dou Liyang <douly.fnst@cn.fujitsu.com> - 2016-07-25 10:40 +0200
  [PATCH v9 3/7] x86, acpi, cpu-hotplug: Introduce cpuid_to_apicid[] array to store persistent cpuid <-> apicid mapping. Dou Liyang <douly.fnst@cn.fujitsu.com> - 2016-07-25 10:40 +0200
  [PATCH v9 4/7] x86, acpi, cpu-hotplug: Enable MADT APIs to return disabled apicid. Dou Liyang <douly.fnst@cn.fujitsu.com> - 2016-07-25 10:40 +0200
  [PATCH v9 6/7] acpi: Provide the mechanism to validate processors in the ACPI tables Dou Liyang <douly.fnst@cn.fujitsu.com> - 2016-07-25 10:40 +0200
  [PATCH v9 5/7] x86, acpi, cpu-hotplug: Set persistent cpuid <-> nodeid mapping when booting. Dou Liyang <douly.fnst@cn.fujitsu.com> - 2016-07-25 10:40 +0200
  [PATCH v9 2/7] x86, acpi, cpu-hotplug: Enable acpi to register all possible cpus at boot time. Dou Liyang <douly.fnst@cn.fujitsu.com> - 2016-07-25 10:40 +0200
  Re: [PATCH v9 0/7] Make cpuid <-> nodeid mapping persistent Andrew Morton <akpm@linux-foundation.org> - 2016-07-26 01:30 +0200
    Re: [PATCH v9 0/7] Make cpuid <-> nodeid mapping persistent Tejun Heo <tj@kernel.org> - 2016-07-26 02:20 +0200
      Re: [PATCH v9 0/7] Make cpuid <-> nodeid mapping persistent Andrew Morton <akpm@linux-foundation.org> - 2016-07-26 02:30 +0200
        Re: [PATCH v9 0/7] Make cpuid <-> nodeid mapping persistent Tejun Heo <tj@kernel.org> - 2016-07-26 03:10 +0200
    Re: [PATCH v9 0/7] Make cpuid <-> nodeid mapping persistent Dou Liyang <douly.fnst@cn.fujitsu.com> - 2016-07-26 06:10 +0200
      Re: [PATCH v9 0/7] Make cpuid <-> nodeid mapping persistent "Rafael J. Wysocki" <rjw@rjwysocki.net> - 2016-07-26 13:50 +0200
        Re: [PATCH v9 0/7] Make cpuid <-> nodeid mapping persistent Dou Liyang <douly.fnst@cn.fujitsu.com> - 2016-07-27 03:20 +0200

csiph-web