[patch 1/8] cpusets v3 - Table of Contents

From: Paul Jackson (pj_at_sgi.com)
Date: 06/29/04

  • Next message: Paul Jackson: "[patch 5/8] cpusets v3 - New bitmap lists format"
    Date:	Tue, 29 Jun 2004 04:21:40 -0700 (PDT)
    To: linux-kernel@vger.kernel.org
    
    

    The following patch set is being offered for review and comment.

    Shortly, not yet, I expect to be requesting Andrew to consider it
    for inclusion in *-mm. Andrew will be glad to hear that this patch
    set (outside of Matthew Dobson's nodemask patch) has _much_ less
    impact on existing kernel code than my previous cpumask patch set ;).

    First I still need to perform further testing, obtain more feedback,
    and do some more documentation and a man page, before asking to get
    it into *-mm. My thanks to those who have reviewed it so far.

    The bulk of the code and much of the design work in this patch has
    been done by Simon Derr <Simon.Derr@bull.net> of Bull (France).
    The nodemask patch is a preliminary draft of work by Matthew
    Dobson, based on my cpumask patches.

    This version of the cpuset patch set is against 2.6.7-mm4.

    These patches provide the essential kernel support for cpusets, which
    enable identifying a hierarchy of subsets of system CPU and Memory Node
    resources and attaching tasks to these subsets. Tasks may only request
    to use (sched_setaffinity, mbind and set_mempolicy) the CPUs and Memory
    Nodes allowed to it by its cpuset. Cpusets may be strictly exclusive
    (other non-ancestral cpusets may not overlap). One can list which
    tasks are in which cpusets, and change which cpuset a task is in.
    No new system calls are used; all access and modification is via a
    cpuset virtual file system.

    See further the Cpuset Overview, item [2/9] of this email set.

    ==> I recommend that first time readers look first at items (2) Overview
        and (7) Kernel Hooks PATCH, for a better understanding of what this
        cpuset kernel patch is intended to do, and the very small kernel
        footprint required to accomplish this.

    Now I have several email messages to present. Items 2 through 8
    will be sent as replies to this first message.

      1) This table of contents.
      2) Overview of kernel cpusets - a small text document.
      3) [patch] cpumask_consts - minor fix to my cpumask patch set
      4) [patch] nodemask - nodemask patch (draft of Matthew Dobson's patch)
      5) [patch] cpuset_bitmap_lists - add bitmap lists format
      6) [patch] cpuset_new_files - Main cpuset patch - cpuset.c, cpuset.h
      7) [patch] cpuset_kernel_hooks - The few, small kernel hooks needed
      8) [patch] cpuset_proc_hooks - One more hook, for /proc/<pid>/cpuset.

    Your feedback is welcome.

    -- 
                              I won't rest till it's the best ...
                              Programmer, Linux Scalability
                              Paul Jackson <pj@sgi.com> 1.650.933.1373
    -
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.kernel.org
    More majordomo info at  http://vger.kernel.org/majordomo-info.html
    Please read the FAQ at  http://www.tux.org/lkml/
    

  • Next message: Paul Jackson: "[patch 5/8] cpusets v3 - New bitmap lists format"

    Relevant Pages

    • Re: [RFC] cpuset update_cgroup_cpus_allowed
      ... which older kernel? ... patches - they're easier to read that way - thanks. ... line above, that rereads the cpuset cpus_allowed, could get an old ... This adds a fair bit of code and complexity, relative to my patch. ...
      (Linux-Kernel)
    • 2.4.22-uv3 patch set released
      ... compile/runtime bug fixes and security updates for the current kernel ... require patches which add to the stability of the current release kernel ... This is a patch set only, it does not include kernel source. ...
      (Linux-Kernel)
    • Re: [Devel] Re: Which of the virtualization approaches is more suitable for kernel?
      ... initially and for 2.6.15), he gave the links to the broken-out patch set, both times. ... Sure we understand this is not convenient for developers who want to look at our code -- and thus we provide broken-out kernel patch sets from time to time. ...
      (Linux-Kernel)
    • Re: [RFC PATCH] Dynamic sched domains (v0.5)
      ... Thanks for the minimalist patch. ... It looks promising, more promising than before. ... overlap of allowed cpus with its parent or any other cpuset ... To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/ ...
      (Linux-Kernel)
    • Re: [PATCH] task containersv11 add tasks file interface fix for cpusets
      ... then the kernel will automatically update the cpus_allowed of all ... tasks attached to CPUs in that cpuset to allow all CPUs ... Does my patch cause any problems ...
      (Linux-Kernel)