686 lines
14 KiB
HTML
686 lines
14 KiB
HTML
|
|
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
|
|
<HTML><HEAD><TITLE>Man page of MBIND</TITLE>
|
|
</HEAD><BODY>
|
|
<H1>MBIND</H1>
|
|
Section: Linux Programmer's Manual (2)<BR>Updated: 2017-09-15<BR><A HREF="#index">Index</A>
|
|
<A HREF="/cgi-bin/man/man2html">Return to Main Contents</A><HR>
|
|
|
|
<A NAME="lbAB"> </A>
|
|
<H2>NAME</H2>
|
|
|
|
mbind - set memory policy for a memory range
|
|
<A NAME="lbAC"> </A>
|
|
<H2>SYNOPSIS</H2>
|
|
|
|
<PRE>
|
|
<B>#include <<A HREF="file:///usr/include/numaif.h">numaif.h</A>></B>
|
|
|
|
<B>long mbind(void *</B><I>addr</I><B>, unsigned long </B><I>len</I><B>, int </B><I>mode</I><B>,</B>
|
|
<B> const unsigned long *</B><I>nodemask</I><B>, unsigned long </B><I>maxnode</I><B>,</B>
|
|
<B> unsigned </B><I>flags</I><B>);</B>
|
|
|
|
Link with <I>-lnuma</I>.
|
|
</PRE>
|
|
|
|
<A NAME="lbAD"> </A>
|
|
<H2>DESCRIPTION</H2>
|
|
|
|
<B>mbind</B>()
|
|
|
|
sets the NUMA memory policy,
|
|
which consists of a policy mode and zero or more nodes,
|
|
for the memory range starting with
|
|
<I>addr</I>
|
|
|
|
and continuing for
|
|
<I>len</I>
|
|
|
|
bytes.
|
|
The memory policy defines from which node memory is allocated.
|
|
<P>
|
|
|
|
If the memory range specified by the
|
|
<I>addr</I> and <I>len</I>
|
|
|
|
arguments includes an "anonymous" region of memory---that is
|
|
a region of memory created using the
|
|
<B><A HREF="/cgi-bin/man/man2html?2+mmap">mmap</A></B>(2)
|
|
|
|
system call with the
|
|
<B>MAP_ANONYMOUS</B>---or
|
|
|
|
a memory-mapped file, mapped using the
|
|
<B><A HREF="/cgi-bin/man/man2html?2+mmap">mmap</A></B>(2)
|
|
|
|
system call with the
|
|
<B>MAP_PRIVATE</B>
|
|
|
|
flag, pages will be allocated only according to the specified
|
|
policy when the application writes (stores) to the page.
|
|
For anonymous regions, an initial read access will use a shared
|
|
page in the kernel containing all zeros.
|
|
For a file mapped with
|
|
<B>MAP_PRIVATE</B>,
|
|
|
|
an initial read access will allocate pages according to the
|
|
memory policy of the thread that causes the page to be allocated.
|
|
This may not be the thread that called
|
|
<B>mbind</B>().
|
|
|
|
<P>
|
|
|
|
The specified policy will be ignored for any
|
|
<B>MAP_SHARED</B>
|
|
|
|
mappings in the specified memory range.
|
|
Rather the pages will be allocated according to the memory policy
|
|
of the thread that caused the page to be allocated.
|
|
Again, this may not be the thread that called
|
|
<B>mbind</B>().
|
|
|
|
<P>
|
|
|
|
If the specified memory range includes a shared memory region
|
|
created using the
|
|
<B><A HREF="/cgi-bin/man/man2html?2+shmget">shmget</A></B>(2)
|
|
|
|
system call and attached using the
|
|
<B><A HREF="/cgi-bin/man/man2html?2+shmat">shmat</A></B>(2)
|
|
|
|
system call,
|
|
pages allocated for the anonymous or shared memory region will
|
|
be allocated according to the policy specified, regardless of which
|
|
process attached to the shared memory segment causes the allocation.
|
|
If, however, the shared memory region was created with the
|
|
<B>SHM_HUGETLB</B>
|
|
|
|
flag,
|
|
the huge pages will be allocated according to the policy specified
|
|
only if the page allocation is caused by the process that calls
|
|
<B>mbind</B>()
|
|
|
|
for that region.
|
|
<P>
|
|
|
|
By default,
|
|
<B>mbind</B>()
|
|
|
|
has an effect only for new allocations; if the pages inside
|
|
the range have been already touched before setting the policy,
|
|
then the policy has no effect.
|
|
This default behavior may be overridden by the
|
|
<B>MPOL_MF_MOVE</B>
|
|
|
|
and
|
|
<B>MPOL_MF_MOVE_ALL</B>
|
|
|
|
flags described below.
|
|
<P>
|
|
|
|
The
|
|
<I>mode</I>
|
|
|
|
argument must specify one of
|
|
<B>MPOL_DEFAULT</B>,
|
|
|
|
<B>MPOL_BIND</B>,
|
|
|
|
<B>MPOL_INTERLEAVE</B>,
|
|
|
|
<B>MPOL_PREFERRED</B>,
|
|
|
|
or
|
|
<B>MPOL_LOCAL</B>
|
|
|
|
(which are described in detail below).
|
|
All policy modes except
|
|
<B>MPOL_DEFAULT</B>
|
|
|
|
require the caller to specify the node or nodes to which the mode applies,
|
|
via the
|
|
<I>nodemask</I>
|
|
|
|
argument.
|
|
<P>
|
|
|
|
The
|
|
<I>mode</I>
|
|
|
|
argument may also include an optional
|
|
<I>mode flag</I>.
|
|
|
|
The supported
|
|
<I>mode flags</I>
|
|
|
|
are:
|
|
<DL COMPACT>
|
|
<DT id="1"><B>MPOL_F_STATIC_NODES</B> (since Linux-2.6.26)
|
|
|
|
<DD>
|
|
A nonempty
|
|
<I>nodemask</I>
|
|
|
|
specifies physical node IDs.
|
|
Linux does not remap the
|
|
<I>nodemask</I>
|
|
|
|
when the thread moves to a different cpuset context,
|
|
nor when the set of nodes allowed by the thread's
|
|
current cpuset context changes.
|
|
<DT id="2"><B>MPOL_F_RELATIVE_NODES</B> (since Linux-2.6.26)
|
|
|
|
<DD>
|
|
A nonempty
|
|
<I>nodemask</I>
|
|
|
|
specifies node IDs that are relative to the set of
|
|
node IDs allowed by the thread's current cpuset.
|
|
</DL>
|
|
<P>
|
|
|
|
<I>nodemask</I>
|
|
|
|
points to a bit mask of nodes containing up to
|
|
<I>maxnode</I>
|
|
|
|
bits.
|
|
The bit mask size is rounded to the next multiple of
|
|
<I>sizeof(unsigned long)</I>,
|
|
|
|
but the kernel will use bits only up to
|
|
<I>maxnode</I>.
|
|
|
|
A NULL value of
|
|
<I>nodemask</I>
|
|
|
|
or a
|
|
<I>maxnode</I>
|
|
|
|
value of zero specifies the empty set of nodes.
|
|
If the value of
|
|
<I>maxnode</I>
|
|
|
|
is zero,
|
|
the
|
|
<I>nodemask</I>
|
|
|
|
argument is ignored.
|
|
Where a
|
|
<I>nodemask</I>
|
|
|
|
is required, it must contain at least one node that is on-line,
|
|
allowed by the thread's current cpuset context
|
|
(unless the
|
|
<B>MPOL_F_STATIC_NODES</B>
|
|
|
|
mode flag is specified),
|
|
and contains memory.
|
|
<P>
|
|
|
|
The
|
|
<I>mode</I>
|
|
|
|
argument must include one of the following values:
|
|
<DL COMPACT>
|
|
<DT id="3"><B>MPOL_DEFAULT</B>
|
|
|
|
<DD>
|
|
This mode requests that any nondefault policy be removed,
|
|
restoring default behavior.
|
|
When applied to a range of memory via
|
|
<B>mbind</B>(),
|
|
|
|
this means to use the thread memory policy,
|
|
which may have been set with
|
|
<B><A HREF="/cgi-bin/man/man2html?2+set_mempolicy">set_mempolicy</A></B>(2).
|
|
|
|
If the mode of the thread memory policy is also
|
|
<B>MPOL_DEFAULT</B>,
|
|
|
|
the system-wide default policy will be used.
|
|
The system-wide default policy allocates
|
|
pages on the node of the CPU that triggers the allocation.
|
|
For
|
|
<B>MPOL_DEFAULT</B>,
|
|
|
|
the
|
|
<I>nodemask</I>
|
|
|
|
and
|
|
<I>maxnode</I>
|
|
|
|
arguments must be specify the empty set of nodes.
|
|
<DT id="4"><B>MPOL_BIND</B>
|
|
|
|
<DD>
|
|
This mode specifies a strict policy that restricts memory allocation to
|
|
the nodes specified in
|
|
<I>nodemask</I>.
|
|
|
|
If
|
|
<I>nodemask</I>
|
|
|
|
specifies more than one node, page allocations will come from
|
|
the node with sufficient free memory that is closest to
|
|
the node where the allocation takes place.
|
|
Pages will not be allocated from any node not specified in the
|
|
IR nodemask .
|
|
(Before Linux 2.6.26,
|
|
|
|
page allocations came from
|
|
the node with the lowest numeric node ID first, until that node
|
|
contained no free memory.
|
|
Allocations then came from the node with the next highest
|
|
node ID specified in
|
|
<I>nodemask</I>
|
|
|
|
and so forth, until none of the specified nodes contained free memory.)
|
|
<DT id="5"><B>MPOL_INTERLEAVE</B>
|
|
|
|
<DD>
|
|
This mode specifies that page allocations be interleaved across the
|
|
set of nodes specified in
|
|
<I>nodemask</I>.
|
|
|
|
This optimizes for bandwidth instead of latency
|
|
by spreading out pages and memory accesses to those pages across
|
|
multiple nodes.
|
|
To be effective the memory area should be fairly large,
|
|
at least 1 MB or bigger with a fairly uniform access pattern.
|
|
Accesses to a single page of the area will still be limited to
|
|
the memory bandwidth of a single node.
|
|
<DT id="6"><B>MPOL_PREFERRED</B>
|
|
|
|
<DD>
|
|
This mode sets the preferred node for allocation.
|
|
The kernel will try to allocate pages from this
|
|
node first and fall back to other nodes if the
|
|
preferred nodes is low on free memory.
|
|
If
|
|
<I>nodemask</I>
|
|
|
|
specifies more than one node ID, the first node in the
|
|
mask will be selected as the preferred node.
|
|
If the
|
|
<I>nodemask</I>
|
|
|
|
and
|
|
<I>maxnode</I>
|
|
|
|
arguments specify the empty set, then the memory is allocated on
|
|
the node of the CPU that triggered the allocation.
|
|
<DT id="7"><B>MPOL_LOCAL</B> (since Linux 3.8)
|
|
|
|
<DD>
|
|
|
|
|
|
This mode specifies "local allocation"; the memory is allocated on
|
|
the node of the CPU that triggered the allocation (the "local node").
|
|
The
|
|
<I>nodemask</I>
|
|
|
|
and
|
|
<I>maxnode</I>
|
|
|
|
arguments must specify the empty set.
|
|
If the "local node" is low on free memory,
|
|
the kernel will try to allocate memory from other nodes.
|
|
The kernel will allocate memory from the "local node"
|
|
whenever memory for this node is available.
|
|
If the "local node" is not allowed by the thread's current cpuset context,
|
|
the kernel will try to allocate memory from other nodes.
|
|
The kernel will allocate memory from the "local node" whenever
|
|
it becomes allowed by the thread's current cpuset context.
|
|
By contrast,
|
|
<B>MPOL_DEFAULT</B>
|
|
|
|
reverts to the memory policy of the thread (which may be set via
|
|
<B><A HREF="/cgi-bin/man/man2html?2+set_mempolicy">set_mempolicy</A></B>(2));
|
|
|
|
that policy may be something other than "local allocation".
|
|
</DL>
|
|
<P>
|
|
|
|
If
|
|
<B>MPOL_MF_STRICT</B>
|
|
|
|
is passed in
|
|
<I>flags</I>
|
|
|
|
and
|
|
<I>mode</I>
|
|
|
|
is not
|
|
<B>MPOL_DEFAULT</B>,
|
|
|
|
then the call fails with the error
|
|
<B>EIO</B>
|
|
|
|
if the existing pages in the memory range don't follow the policy.
|
|
|
|
|
|
|
|
|
|
<P>
|
|
|
|
If
|
|
<B>MPOL_MF_MOVE</B>
|
|
|
|
is specified in
|
|
<I>flags</I>,
|
|
|
|
then the kernel will attempt to move all the existing pages
|
|
in the memory range so that they follow the policy.
|
|
Pages that are shared with other processes will not be moved.
|
|
If
|
|
<B>MPOL_MF_STRICT</B>
|
|
|
|
is also specified, then the call fails with the error
|
|
<B>EIO</B>
|
|
|
|
if some pages could not be moved.
|
|
<P>
|
|
|
|
If
|
|
<B>MPOL_MF_MOVE_ALL</B>
|
|
|
|
is passed in
|
|
<I>flags</I>,
|
|
|
|
then the kernel will attempt to move all existing pages in the memory range
|
|
regardless of whether other processes use the pages.
|
|
The calling thread must be privileged
|
|
(<B>CAP_SYS_NICE</B>)
|
|
|
|
to use this flag.
|
|
If
|
|
<B>MPOL_MF_STRICT</B>
|
|
|
|
is also specified, then the call fails with the error
|
|
<B>EIO</B>
|
|
|
|
if some pages could not be moved.
|
|
|
|
<A NAME="lbAE"> </A>
|
|
<H2>RETURN VALUE</H2>
|
|
|
|
On success,
|
|
<B>mbind</B>()
|
|
|
|
returns 0;
|
|
on error, -1 is returned and
|
|
<I>errno</I>
|
|
|
|
is set to indicate the error.
|
|
|
|
<A NAME="lbAF"> </A>
|
|
<H2>ERRORS</H2>
|
|
|
|
|
|
<DL COMPACT>
|
|
<DT id="8"><B>EFAULT</B>
|
|
|
|
<DD>
|
|
Part or all of the memory range specified by
|
|
<I>nodemask</I>
|
|
|
|
and
|
|
<I>maxnode</I>
|
|
|
|
points outside your accessible address space.
|
|
Or, there was an unmapped hole in the specified memory range specified by
|
|
<I>addr</I>
|
|
|
|
and
|
|
<I>len</I>.
|
|
|
|
<DT id="9"><B>EINVAL</B>
|
|
|
|
<DD>
|
|
An invalid value was specified for
|
|
<I>flags</I>
|
|
|
|
or
|
|
<I>mode</I>;
|
|
|
|
or
|
|
<I>addr + len</I>
|
|
|
|
was less than
|
|
<I>addr</I>;
|
|
|
|
or
|
|
<I>addr</I>
|
|
|
|
is not a multiple of the system page size.
|
|
Or,
|
|
<I>mode</I>
|
|
|
|
is
|
|
<B>MPOL_DEFAULT</B>
|
|
|
|
and
|
|
<I>nodemask</I>
|
|
|
|
specified a nonempty set;
|
|
or
|
|
<I>mode</I>
|
|
|
|
is
|
|
<B>MPOL_BIND</B>
|
|
|
|
or
|
|
<B>MPOL_INTERLEAVE</B>
|
|
|
|
and
|
|
<I>nodemask</I>
|
|
|
|
is empty.
|
|
Or,
|
|
<I>maxnode</I>
|
|
|
|
exceeds a kernel-imposed limit.
|
|
|
|
|
|
Or,
|
|
<I>nodemask</I>
|
|
|
|
specifies one or more node IDs that are
|
|
greater than the maximum supported node ID.
|
|
Or, none of the node IDs specified by
|
|
<I>nodemask</I>
|
|
|
|
are on-line and allowed by the thread's current cpuset context,
|
|
or none of the specified nodes contain memory.
|
|
Or, the
|
|
<I>mode</I>
|
|
|
|
argument specified both
|
|
<B>MPOL_F_STATIC_NODES</B>
|
|
|
|
and
|
|
<B>MPOL_F_RELATIVE_NODES</B>.
|
|
|
|
<DT id="10"><B>EIO</B>
|
|
|
|
<DD>
|
|
<B>MPOL_MF_STRICT</B>
|
|
|
|
was specified and an existing page was already on a node
|
|
that does not follow the policy;
|
|
or
|
|
<B>MPOL_MF_MOVE</B>
|
|
|
|
or
|
|
<B>MPOL_MF_MOVE_ALL</B>
|
|
|
|
was specified and the kernel was unable to move all existing
|
|
pages in the range.
|
|
<DT id="11"><B>ENOMEM</B>
|
|
|
|
<DD>
|
|
Insufficient kernel memory was available.
|
|
<DT id="12"><B>EPERM</B>
|
|
|
|
<DD>
|
|
The
|
|
<I>flags</I>
|
|
|
|
argument included the
|
|
<B>MPOL_MF_MOVE_ALL</B>
|
|
|
|
flag and the caller does not have the
|
|
<B>CAP_SYS_NICE</B>
|
|
|
|
privilege.
|
|
|
|
</DL>
|
|
<A NAME="lbAG"> </A>
|
|
<H2>VERSIONS</H2>
|
|
|
|
The
|
|
<B>mbind</B>()
|
|
|
|
system call was added to the Linux kernel in version 2.6.7.
|
|
<A NAME="lbAH"> </A>
|
|
<H2>CONFORMING TO</H2>
|
|
|
|
This system call is Linux-specific.
|
|
<A NAME="lbAI"> </A>
|
|
<H2>NOTES</H2>
|
|
|
|
For information on library support, see
|
|
<B><A HREF="/cgi-bin/man/man2html?7+numa">numa</A></B>(7).
|
|
|
|
<P>
|
|
|
|
NUMA policy is not supported on a memory-mapped file range
|
|
that was mapped with the
|
|
<B>MAP_SHARED</B>
|
|
|
|
flag.
|
|
<P>
|
|
|
|
The
|
|
<B>MPOL_DEFAULT</B>
|
|
|
|
mode can have different effects for
|
|
<B>mbind</B>()
|
|
|
|
and
|
|
<B><A HREF="/cgi-bin/man/man2html?2+set_mempolicy">set_mempolicy</A></B>(2).
|
|
|
|
When
|
|
<B>MPOL_DEFAULT</B>
|
|
|
|
is specified for
|
|
<B><A HREF="/cgi-bin/man/man2html?2+set_mempolicy">set_mempolicy</A></B>(2),
|
|
|
|
the thread's memory policy reverts to the system default policy
|
|
or local allocation.
|
|
When
|
|
<B>MPOL_DEFAULT</B>
|
|
|
|
is specified for a range of memory using
|
|
<B>mbind</B>(),
|
|
|
|
any pages subsequently allocated for that range will use
|
|
the thread's memory policy, as set by
|
|
<B><A HREF="/cgi-bin/man/man2html?2+set_mempolicy">set_mempolicy</A></B>(2).
|
|
|
|
This effectively removes the explicit policy from the
|
|
specified range, "falling back" to a possibly nondefault
|
|
policy.
|
|
To select explicit "local allocation" for a memory range,
|
|
specify a
|
|
<I>mode</I>
|
|
|
|
of
|
|
<B>MPOL_LOCAL</B>
|
|
|
|
or
|
|
<B>MPOL_PREFERRED</B>
|
|
|
|
with an empty set of nodes.
|
|
This method will work for
|
|
<B><A HREF="/cgi-bin/man/man2html?2+set_mempolicy">set_mempolicy</A></B>(2),
|
|
|
|
as well.
|
|
<P>
|
|
|
|
Support for huge page policy was added with 2.6.16.
|
|
For interleave policy to be effective on huge page mappings the
|
|
policied memory needs to be tens of megabytes or larger.
|
|
<P>
|
|
|
|
<B>MPOL_MF_STRICT</B>
|
|
|
|
is ignored on huge page mappings.
|
|
<P>
|
|
|
|
<B>MPOL_MF_MOVE</B>
|
|
|
|
and
|
|
<B>MPOL_MF_MOVE_ALL</B>
|
|
|
|
are available only on Linux 2.6.16 and later.
|
|
<A NAME="lbAJ"> </A>
|
|
<H2>SEE ALSO</H2>
|
|
|
|
<B><A HREF="/cgi-bin/man/man2html?2+get_mempolicy">get_mempolicy</A></B>(2),
|
|
|
|
<B><A HREF="/cgi-bin/man/man2html?2+getcpu">getcpu</A></B>(2),
|
|
|
|
<B><A HREF="/cgi-bin/man/man2html?2+mmap">mmap</A></B>(2),
|
|
|
|
<B><A HREF="/cgi-bin/man/man2html?2+set_mempolicy">set_mempolicy</A></B>(2),
|
|
|
|
<B><A HREF="/cgi-bin/man/man2html?2+shmat">shmat</A></B>(2),
|
|
|
|
<B><A HREF="/cgi-bin/man/man2html?2+shmget">shmget</A></B>(2),
|
|
|
|
<B><A HREF="/cgi-bin/man/man2html?3+numa">numa</A></B>(3),
|
|
|
|
<B><A HREF="/cgi-bin/man/man2html?7+cpuset">cpuset</A></B>(7),
|
|
|
|
<B><A HREF="/cgi-bin/man/man2html?7+numa">numa</A></B>(7),
|
|
|
|
<B><A HREF="/cgi-bin/man/man2html?8+numactl">numactl</A></B>(8)
|
|
|
|
<A NAME="lbAK"> </A>
|
|
<H2>COLOPHON</H2>
|
|
|
|
This page is part of release 5.05 of the Linux
|
|
<I>man-pages</I>
|
|
|
|
project.
|
|
A description of the project,
|
|
information about reporting bugs,
|
|
and the latest version of this page,
|
|
can be found at
|
|
<A HREF="https://www.kernel.org/doc/man-pages/.">https://www.kernel.org/doc/man-pages/.</A>
|
|
<P>
|
|
|
|
<HR>
|
|
<A NAME="index"> </A><H2>Index</H2>
|
|
<DL>
|
|
<DT id="13"><A HREF="#lbAB">NAME</A><DD>
|
|
<DT id="14"><A HREF="#lbAC">SYNOPSIS</A><DD>
|
|
<DT id="15"><A HREF="#lbAD">DESCRIPTION</A><DD>
|
|
<DT id="16"><A HREF="#lbAE">RETURN VALUE</A><DD>
|
|
<DT id="17"><A HREF="#lbAF">ERRORS</A><DD>
|
|
<DT id="18"><A HREF="#lbAG">VERSIONS</A><DD>
|
|
<DT id="19"><A HREF="#lbAH">CONFORMING TO</A><DD>
|
|
<DT id="20"><A HREF="#lbAI">NOTES</A><DD>
|
|
<DT id="21"><A HREF="#lbAJ">SEE ALSO</A><DD>
|
|
<DT id="22"><A HREF="#lbAK">COLOPHON</A><DD>
|
|
</DL>
|
|
<HR>
|
|
This document was created by
|
|
<A HREF="/cgi-bin/man/man2html">man2html</A>,
|
|
using the manual pages.<BR>
|
|
Time: 00:05:33 GMT, March 31, 2021
|
|
</BODY>
|
|
</HTML>
|