| <html lang="en"> |
| <head> |
| <title>CPU Affinity - The GNU C Library</title> |
| <meta http-equiv="Content-Type" content="text/html"> |
| <meta name="description" content="The GNU C Library"> |
| <meta name="generator" content="makeinfo 4.13"> |
| <link title="Top" rel="start" href="index.html#Top"> |
| <link rel="up" href="Priority.html#Priority" title="Priority"> |
| <link rel="prev" href="Traditional-Scheduling.html#Traditional-Scheduling" title="Traditional Scheduling"> |
| <link href="http://www.gnu.org/software/texinfo/" rel="generator-home" title="Texinfo Homepage"> |
| <!-- |
| This file documents the GNU C library. |
| |
| This is Edition 0.12, last updated 2007-10-27, |
| of `The GNU C Library Reference Manual', for version |
| 2.8 (Sourcery G++ Lite 2011.03-41). |
| |
| Copyright (C) 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2001, 2002, |
| 2003, 2007, 2008, 2010 Free Software Foundation, Inc. |
| |
| Permission is granted to copy, distribute and/or modify this document |
| under the terms of the GNU Free Documentation License, Version 1.3 or |
| any later version published by the Free Software Foundation; with the |
| Invariant Sections being ``Free Software Needs Free Documentation'' |
| and ``GNU Lesser General Public License'', the Front-Cover texts being |
| ``A GNU Manual'', and with the Back-Cover Texts as in (a) below. A |
| copy of the license is included in the section entitled "GNU Free |
| Documentation License". |
| |
| (a) The FSF's Back-Cover Text is: ``You have the freedom to |
| copy and modify this GNU manual. Buying copies from the FSF |
| supports it in developing GNU and promoting software freedom.''--> |
| <meta http-equiv="Content-Style-Type" content="text/css"> |
| <style type="text/css"><!-- |
| pre.display { font-family:inherit } |
| pre.format { font-family:inherit } |
| pre.smalldisplay { font-family:inherit; font-size:smaller } |
| pre.smallformat { font-family:inherit; font-size:smaller } |
| pre.smallexample { font-size:smaller } |
| pre.smalllisp { font-size:smaller } |
| span.sc { font-variant:small-caps } |
| span.roman { font-family:serif; font-weight:normal; } |
| span.sansserif { font-family:sans-serif; font-weight:normal; } |
| --></style> |
| <link rel="stylesheet" type="text/css" href="../cs.css"> |
| </head> |
| <body> |
| <div class="node"> |
| <a name="CPU-Affinity"></a> |
| <p> |
| Previous: <a rel="previous" accesskey="p" href="Traditional-Scheduling.html#Traditional-Scheduling">Traditional Scheduling</a>, |
| Up: <a rel="up" accesskey="u" href="Priority.html#Priority">Priority</a> |
| <hr> |
| </div> |
| |
| <h4 class="subsection">22.3.5 Limiting execution to certain CPUs</h4> |
| |
| <p>On a multi-processor system the operating system usually distributes |
| the different processes which are runnable on all available CPUs in a |
| way which allows the system to work most efficiently. Which processes |
| and threads run can be to some extend be control with the scheduling |
| functionality described in the last sections. But which CPU finally |
| executes which process or thread is not covered. |
| |
| <p>There are a number of reasons why a program might want to have control |
| over this aspect of the system as well: |
| |
| <ul> |
| <li>One thread or process is responsible for absolutely critical work |
| which under no circumstances must be interrupted or hindered from |
| making process by other process or threads using CPU resources. In |
| this case the special process would be confined to a CPU which no |
| other process or thread is allowed to use. |
| |
| <li>The access to certain resources (RAM, I/O ports) has different costs |
| from different CPUs. This is the case in NUMA (Non-Uniform Memory |
| Architecture) machines. Preferably memory should be accessed locally |
| but this requirement is usually not visible to the scheduler. |
| Therefore forcing a process or thread to the CPUs which have local |
| access to the mostly used memory helps to significantly boost the |
| performance. |
| |
| <li>In controlled runtimes resource allocation and book-keeping work (for |
| instance garbage collection) is performance local to processors. This |
| can help to reduce locking costs if the resources do not have to be |
| protected from concurrent accesses from different processors. |
| </ul> |
| |
| <p>The POSIX standard up to this date is of not much help to solve this |
| problem. The Linux kernel provides a set of interfaces to allow |
| specifying <em>affinity sets</em> for a process. The scheduler will |
| schedule the thread or process on CPUs specified by the affinity |
| masks. The interfaces which the GNU C library define follow to some |
| extend the Linux kernel interface. |
| |
| <!-- sched.h --> |
| <!-- GNU --> |
| <div class="defun"> |
| — Data Type: <b>cpu_set_t</b><var><a name="index-cpu_005fset_005ft-2764"></a></var><br> |
| <blockquote><p>This data set is a bitset where each bit represents a CPU. How the |
| system's CPUs are mapped to bits in the bitset is system dependent. |
| The data type has a fixed size; in the unlikely case that the number |
| of bits are not sufficient to describe the CPUs of the system a |
| different interface has to be used. |
| |
| <p>This type is a GNU extension and is defined in <samp><span class="file">sched.h</span></samp>. |
| </p></blockquote></div> |
| |
| <p>To manipulate the bitset, to set and reset bits, a number of macros is |
| defined. Some of the macros take a CPU number as a parameter. Here |
| it is important to never exceed the size of the bitset. The following |
| macro specifies the number of bits in the <code>cpu_set_t</code> bitset. |
| |
| <!-- sched.h --> |
| <!-- GNU --> |
| <div class="defun"> |
| — Macro: int <b>CPU_SETSIZE</b><var><a name="index-CPU_005fSETSIZE-2765"></a></var><br> |
| <blockquote><p>The value of this macro is the maximum number of CPUs which can be |
| handled with a <code>cpu_set_t</code> object. |
| </p></blockquote></div> |
| |
| <p>The type <code>cpu_set_t</code> should be considered opaque; all |
| manipulation should happen via the next four macros. |
| |
| <!-- sched.h --> |
| <!-- GNU --> |
| <div class="defun"> |
| — Macro: void <b>CPU_ZERO</b> (<var>cpu_set_t *set</var>)<var><a name="index-CPU_005fZERO-2766"></a></var><br> |
| <blockquote><p>This macro initializes the CPU set <var>set</var> to be the empty set. |
| |
| <p>This macro is a GNU extension and is defined in <samp><span class="file">sched.h</span></samp>. |
| </p></blockquote></div> |
| |
| <!-- sched.h --> |
| <!-- GNU --> |
| <div class="defun"> |
| — Macro: void <b>CPU_SET</b> (<var>int cpu, cpu_set_t *set</var>)<var><a name="index-CPU_005fSET-2767"></a></var><br> |
| <blockquote><p>This macro adds <var>cpu</var> to the CPU set <var>set</var>. |
| |
| <p>The <var>cpu</var> parameter must not have side effects since it is |
| evaluated more than once. |
| |
| <p>This macro is a GNU extension and is defined in <samp><span class="file">sched.h</span></samp>. |
| </p></blockquote></div> |
| |
| <!-- sched.h --> |
| <!-- GNU --> |
| <div class="defun"> |
| — Macro: void <b>CPU_CLR</b> (<var>int cpu, cpu_set_t *set</var>)<var><a name="index-CPU_005fCLR-2768"></a></var><br> |
| <blockquote><p>This macro removes <var>cpu</var> from the CPU set <var>set</var>. |
| |
| <p>The <var>cpu</var> parameter must not have side effects since it is |
| evaluated more than once. |
| |
| <p>This macro is a GNU extension and is defined in <samp><span class="file">sched.h</span></samp>. |
| </p></blockquote></div> |
| |
| <!-- sched.h --> |
| <!-- GNU --> |
| <div class="defun"> |
| — Macro: int <b>CPU_ISSET</b> (<var>int cpu, const cpu_set_t *set</var>)<var><a name="index-CPU_005fISSET-2769"></a></var><br> |
| <blockquote><p>This macro returns a nonzero value (true) if <var>cpu</var> is a member |
| of the CPU set <var>set</var>, and zero (false) otherwise. |
| |
| <p>The <var>cpu</var> parameter must not have side effects since it is |
| evaluated more than once. |
| |
| <p>This macro is a GNU extension and is defined in <samp><span class="file">sched.h</span></samp>. |
| </p></blockquote></div> |
| |
| <p>CPU bitsets can be constructed from scratch or the currently installed |
| affinity mask can be retrieved from the system. |
| |
| <!-- sched.h --> |
| <!-- GNU --> |
| <div class="defun"> |
| — Function: int <b>sched_getaffinity</b> (<var>pid_t pid, size_t cpusetsize, cpu_set_t *cpuset</var>)<var><a name="index-sched_005fgetaffinity-2770"></a></var><br> |
| <blockquote> |
| <p>This functions stores the CPU affinity mask for the process or thread |
| with the ID <var>pid</var> in the <var>cpusetsize</var> bytes long bitmap |
| pointed to by <var>cpuset</var>. If successful, the function always |
| initializes all bits in the <code>cpu_set_t</code> object and returns zero. |
| |
| <p>If <var>pid</var> does not correspond to a process or thread on the system |
| the or the function fails for some other reason, it returns <code>-1</code> |
| and <code>errno</code> is set to represent the error condition. |
| |
| <dl> |
| <dt><code>ESRCH</code><dd>No process or thread with the given ID found. |
| |
| <br><dt><code>EFAULT</code><dd>The pointer <var>cpuset</var> is does not point to a valid object. |
| </dl> |
| |
| <p>This function is a GNU extension and is declared in <samp><span class="file">sched.h</span></samp>. |
| </p></blockquote></div> |
| |
| <p>Note that it is not portably possible to use this information to |
| retrieve the information for different POSIX threads. A separate |
| interface must be provided for that. |
| |
| <!-- sched.h --> |
| <!-- GNU --> |
| <div class="defun"> |
| — Function: int <b>sched_setaffinity</b> (<var>pid_t pid, size_t cpusetsize, const cpu_set_t *cpuset</var>)<var><a name="index-sched_005fsetaffinity-2771"></a></var><br> |
| <blockquote> |
| <p>This function installs the <var>cpusetsize</var> bytes long affinity mask |
| pointed to by <var>cpuset</var> for the process or thread with the ID <var>pid</var>. |
| If successful the function returns zero and the scheduler will in future |
| take the affinity information into account. |
| |
| <p>If the function fails it will return <code>-1</code> and <code>errno</code> is set |
| to the error code: |
| |
| <dl> |
| <dt><code>ESRCH</code><dd>No process or thread with the given ID found. |
| |
| <br><dt><code>EFAULT</code><dd>The pointer <var>cpuset</var> is does not point to a valid object. |
| |
| <br><dt><code>EINVAL</code><dd>The bitset is not valid. This might mean that the affinity set might |
| not leave a processor for the process or thread to run on. |
| </dl> |
| |
| <p>This function is a GNU extension and is declared in <samp><span class="file">sched.h</span></samp>. |
| </p></blockquote></div> |
| |
| </body></html> |
| |
