<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux-toradex.git/Documentation/vm/transhuge.txt, branch v4.4.72</title>
<subtitle>Linux kernel for Apalis and Colibri modules</subtitle>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/'/>
<entry>
<title>Documentation/vm/transhuge.txt: add information about max_ptes_swap</title>
<updated>2015-11-06T03:34:48+00:00</updated>
<author>
<name>Ebru Akagunduz</name>
<email>ebru.akagunduz@gmail.com</email>
</author>
<published>2015-11-06T02:47:32+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=80f73b4b71f767f7fcd85f68be18af7795904484'/>
<id>80f73b4b71f767f7fcd85f68be18af7795904484</id>
<content type='text'>
max_ptes_swap specifies how many pages can be brought in from swap when
collapsing a group of pages into a transparent huge page.

/sys/kernel/mm/transparent_hugepage/khugepaged/max_ptes_swap

A higher value can cause excessive swap IO and waste memory.  A lower
value can prevent THPs from being collapsed, resulting fewer pages being
collapsed into THPs, and lower memory access performance.

Signed-off-by: Ebru Akagunduz &lt;ebru.akagunduz@gmail.com&gt;
Acked-by: Rik van Riel &lt;riel@redhat.com&gt;
Acked-by: David Rientjes &lt;rientjes@google.com&gt;
Cc: Oleg Nesterov &lt;oleg@redhat.com&gt;
Cc: Kirill A. Shutemov &lt;kirill.shutemov@linux.intel.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
Signed-off-by: Linus Torvalds &lt;torvalds@linux-foundation.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
max_ptes_swap specifies how many pages can be brought in from swap when
collapsing a group of pages into a transparent huge page.

/sys/kernel/mm/transparent_hugepage/khugepaged/max_ptes_swap

A higher value can cause excessive swap IO and waste memory.  A lower
value can prevent THPs from being collapsed, resulting fewer pages being
collapsed into THPs, and lower memory access performance.

Signed-off-by: Ebru Akagunduz &lt;ebru.akagunduz@gmail.com&gt;
Acked-by: Rik van Riel &lt;riel@redhat.com&gt;
Acked-by: David Rientjes &lt;rientjes@google.com&gt;
Cc: Oleg Nesterov &lt;oleg@redhat.com&gt;
Cc: Kirill A. Shutemov &lt;kirill.shutemov@linux.intel.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
Signed-off-by: Linus Torvalds &lt;torvalds@linux-foundation.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>doc: add information about max_ptes_none</title>
<updated>2015-03-20T13:41:55+00:00</updated>
<author>
<name>Ebru Akagunduz</name>
<email>ebru.akagunduz@gmail.com</email>
</author>
<published>2015-02-26T21:34:36+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=9ddfa69fb073081882505a4f69d3f0c344d9bcaf'/>
<id>9ddfa69fb073081882505a4f69d3f0c344d9bcaf</id>
<content type='text'>
max_ptes_none specifies how many extra small pages (that are
not already mapped) can be allocated when collapsing a group
of small pages into one large page.

/sys/kernel/mm/transparent_hugepage/khugepaged/max_ptes_none

A higher value leads to use additional memory for programs.
A lower value leads to gain less thp performance. Value of
max_ptes_none can waste cpu time very little, you can
ignore it.

Signed-off-by: Ebru Akagunduz &lt;ebru.akagunduz@gmail.com&gt;
Reviewed-by: Rik van Riel &lt;riel@redhat.com&gt;
Signed-off-by: Jonathan Corbet &lt;corbet@lwn.net&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
max_ptes_none specifies how many extra small pages (that are
not already mapped) can be allocated when collapsing a group
of small pages into one large page.

/sys/kernel/mm/transparent_hugepage/khugepaged/max_ptes_none

A higher value leads to use additional memory for programs.
A lower value leads to gain less thp performance. Value of
max_ptes_none can waste cpu time very little, you can
ignore it.

Signed-off-by: Ebru Akagunduz &lt;ebru.akagunduz@gmail.com&gt;
Reviewed-by: Rik van Riel &lt;riel@redhat.com&gt;
Signed-off-by: Jonathan Corbet &lt;corbet@lwn.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>doc: spelling error changes</title>
<updated>2014-05-05T13:32:05+00:00</updated>
<author>
<name>Carlos Garcia</name>
<email>carlos@cgarcia.org</email>
</author>
<published>2014-04-05T02:31:00+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=c98be0c96db00e9b6b02d31e0fa7590c54cdaaac'/>
<id>c98be0c96db00e9b6b02d31e0fa7590c54cdaaac</id>
<content type='text'>
Fixed multiple spelling errors.

Acked-by: Randy Dunlap &lt;rdunlap@infradead.org&gt;
Signed-off-by: Carlos E. Garcia &lt;carlos@cgarcia.org&gt;
Signed-off-by: Jiri Kosina &lt;jkosina@suse.cz&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Fixed multiple spelling errors.

Acked-by: Randy Dunlap &lt;rdunlap@infradead.org&gt;
Signed-off-by: Carlos E. Garcia &lt;carlos@cgarcia.org&gt;
Signed-off-by: Jiri Kosina &lt;jkosina@suse.cz&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>mm/thp: fix doc for transparent huge zero page</title>
<updated>2013-07-09T17:33:23+00:00</updated>
<author>
<name>Wanpeng Li</name>
<email>liwanp@linux.vnet.ibm.com</email>
</author>
<published>2013-07-08T23:00:16+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=f49cbdde495f62e1c2d906b16e833cec27de5e59'/>
<id>f49cbdde495f62e1c2d906b16e833cec27de5e59</id>
<content type='text'>
Transparent huge zero page is used during the page fault instead of in
khugepaged.

  # ls /sys/kernel/mm/transparent_hugepage/
  defrag  enabled  khugepaged  use_zero_page
  # ls /sys/kernel/mm/transparent_hugepage/khugepaged/
  alloc_sleep_millisecs  defrag  full_scans  max_ptes_none  pages_collapsed  pages_to_scan  scan_sleep_millisecs

This patch corrects the documentation just like the codes done.

Signed-off-by: Wanpeng Li &lt;liwanp@linux.vnet.ibm.com&gt;
Acked-by: Kirill A. Shutemov &lt;kirill.shutemov@linux.intel.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
Signed-off-by: Linus Torvalds &lt;torvalds@linux-foundation.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Transparent huge zero page is used during the page fault instead of in
khugepaged.

  # ls /sys/kernel/mm/transparent_hugepage/
  defrag  enabled  khugepaged  use_zero_page
  # ls /sys/kernel/mm/transparent_hugepage/khugepaged/
  alloc_sleep_millisecs  defrag  full_scans  max_ptes_none  pages_collapsed  pages_to_scan  scan_sleep_millisecs

This patch corrects the documentation just like the codes done.

Signed-off-by: Wanpeng Li &lt;liwanp@linux.vnet.ibm.com&gt;
Acked-by: Kirill A. Shutemov &lt;kirill.shutemov@linux.intel.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
Signed-off-by: Linus Torvalds &lt;torvalds@linux-foundation.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>thp: introduce sysfs knob to disable huge zero page</title>
<updated>2012-12-13T01:38:32+00:00</updated>
<author>
<name>Kirill A. Shutemov</name>
<email>kirill.shutemov@linux.intel.com</email>
</author>
<published>2012-12-12T21:51:12+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=79da5407eeadc740fbf4b45d6df7d7f8e6adaf2c'/>
<id>79da5407eeadc740fbf4b45d6df7d7f8e6adaf2c</id>
<content type='text'>
By default kernel tries to use huge zero page on read page fault.  It's
possible to disable huge zero page by writing 0 or enable it back by
writing 1:

echo 0 &gt;/sys/kernel/mm/transparent_hugepage/khugepaged/use_zero_page
echo 1 &gt;/sys/kernel/mm/transparent_hugepage/khugepaged/use_zero_page

Signed-off-by: Kirill A. Shutemov &lt;kirill.shutemov@linux.intel.com&gt;
Cc: Andrea Arcangeli &lt;aarcange@redhat.com&gt;
Cc: Andi Kleen &lt;ak@linux.intel.com&gt;
Cc: "H. Peter Anvin" &lt;hpa@linux.intel.com&gt;
Cc: Mel Gorman &lt;mel@csn.ul.ie&gt;
Cc: David Rientjes &lt;rientjes@google.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
Signed-off-by: Linus Torvalds &lt;torvalds@linux-foundation.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
By default kernel tries to use huge zero page on read page fault.  It's
possible to disable huge zero page by writing 0 or enable it back by
writing 1:

echo 0 &gt;/sys/kernel/mm/transparent_hugepage/khugepaged/use_zero_page
echo 1 &gt;/sys/kernel/mm/transparent_hugepage/khugepaged/use_zero_page

Signed-off-by: Kirill A. Shutemov &lt;kirill.shutemov@linux.intel.com&gt;
Cc: Andrea Arcangeli &lt;aarcange@redhat.com&gt;
Cc: Andi Kleen &lt;ak@linux.intel.com&gt;
Cc: "H. Peter Anvin" &lt;hpa@linux.intel.com&gt;
Cc: Mel Gorman &lt;mel@csn.ul.ie&gt;
Cc: David Rientjes &lt;rientjes@google.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
Signed-off-by: Linus Torvalds &lt;torvalds@linux-foundation.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>thp, vmstat: implement HZP_ALLOC and HZP_ALLOC_FAILED events</title>
<updated>2012-12-13T01:38:32+00:00</updated>
<author>
<name>Kirill A. Shutemov</name>
<email>kirill.shutemov@linux.intel.com</email>
</author>
<published>2012-12-12T21:51:09+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=d8a8e1f0da3d29d7268b3300c96a059d63901b76'/>
<id>d8a8e1f0da3d29d7268b3300c96a059d63901b76</id>
<content type='text'>
hzp_alloc is incremented every time a huge zero page is successfully
	allocated. It includes allocations which where dropped due
	race with other allocation. Note, it doesn't count every map
	of the huge zero page, only its allocation.

hzp_alloc_failed is incremented if kernel fails to allocate huge zero
	page and falls back to using small pages.

Signed-off-by: Kirill A. Shutemov &lt;kirill.shutemov@linux.intel.com&gt;
Cc: Andrea Arcangeli &lt;aarcange@redhat.com&gt;
Cc: Andi Kleen &lt;ak@linux.intel.com&gt;
Cc: "H. Peter Anvin" &lt;hpa@linux.intel.com&gt;
Cc: Mel Gorman &lt;mel@csn.ul.ie&gt;
Cc: David Rientjes &lt;rientjes@google.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
Signed-off-by: Linus Torvalds &lt;torvalds@linux-foundation.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
hzp_alloc is incremented every time a huge zero page is successfully
	allocated. It includes allocations which where dropped due
	race with other allocation. Note, it doesn't count every map
	of the huge zero page, only its allocation.

hzp_alloc_failed is incremented if kernel fails to allocate huge zero
	page and falls back to using small pages.

Signed-off-by: Kirill A. Shutemov &lt;kirill.shutemov@linux.intel.com&gt;
Cc: Andrea Arcangeli &lt;aarcange@redhat.com&gt;
Cc: Andi Kleen &lt;ak@linux.intel.com&gt;
Cc: "H. Peter Anvin" &lt;hpa@linux.intel.com&gt;
Cc: Mel Gorman &lt;mel@csn.ul.ie&gt;
Cc: David Rientjes &lt;rientjes@google.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
Signed-off-by: Linus Torvalds &lt;torvalds@linux-foundation.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>thp: change split_huge_page_pmd() interface</title>
<updated>2012-12-13T01:38:31+00:00</updated>
<author>
<name>Kirill A. Shutemov</name>
<email>kirill.shutemov@linux.intel.com</email>
</author>
<published>2012-12-12T21:50:59+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=e180377f1ae48b3cbc559c9875d9b038f7f000c6'/>
<id>e180377f1ae48b3cbc559c9875d9b038f7f000c6</id>
<content type='text'>
Pass vma instead of mm and add address parameter.

In most cases we already have vma on the stack. We provides
split_huge_page_pmd_mm() for few cases when we have mm, but not vma.

This change is preparation to huge zero pmd splitting implementation.

Signed-off-by: Kirill A. Shutemov &lt;kirill.shutemov@linux.intel.com&gt;
Cc: Andrea Arcangeli &lt;aarcange@redhat.com&gt;
Cc: Andi Kleen &lt;ak@linux.intel.com&gt;
Cc: "H. Peter Anvin" &lt;hpa@linux.intel.com&gt;
Cc: Mel Gorman &lt;mel@csn.ul.ie&gt;
Cc: David Rientjes &lt;rientjes@google.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
Signed-off-by: Linus Torvalds &lt;torvalds@linux-foundation.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Pass vma instead of mm and add address parameter.

In most cases we already have vma on the stack. We provides
split_huge_page_pmd_mm() for few cases when we have mm, but not vma.

This change is preparation to huge zero pmd splitting implementation.

Signed-off-by: Kirill A. Shutemov &lt;kirill.shutemov@linux.intel.com&gt;
Cc: Andrea Arcangeli &lt;aarcange@redhat.com&gt;
Cc: Andi Kleen &lt;ak@linux.intel.com&gt;
Cc: "H. Peter Anvin" &lt;hpa@linux.intel.com&gt;
Cc: Mel Gorman &lt;mel@csn.ul.ie&gt;
Cc: David Rientjes &lt;rientjes@google.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
Signed-off-by: Linus Torvalds &lt;torvalds@linux-foundation.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>mm: document the meminfo and vmstat fields of relevance to transparent hugepages</title>
<updated>2012-05-29T23:22:23+00:00</updated>
<author>
<name>Mel Gorman</name>
<email>mgorman@suse.de</email>
</author>
<published>2012-05-29T22:06:45+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=692569946fbf56fbb75d85c57679541f9a3550b4'/>
<id>692569946fbf56fbb75d85c57679541f9a3550b4</id>
<content type='text'>
Update Documentation/vm/transhuge.txt and
Documentation/filesystems/proc.txt with some information on monitoring
transparent huge page usage and the associated overhead.

Signed-off-by: Mel Gorman &lt;mgorman@suse.de&gt;
Signed-off-by: Andrea Arcangeli &lt;aarcange@redhat.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
Signed-off-by: Linus Torvalds &lt;torvalds@linux-foundation.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Update Documentation/vm/transhuge.txt and
Documentation/filesystems/proc.txt with some information on monitoring
transparent huge page usage and the associated overhead.

Signed-off-by: Mel Gorman &lt;mgorman@suse.de&gt;
Signed-off-by: Andrea Arcangeli &lt;aarcange@redhat.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
Signed-off-by: Linus Torvalds &lt;torvalds@linux-foundation.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>thp: fix khugepaged defrag tunable documentation</title>
<updated>2011-09-22T21:27:14+00:00</updated>
<author>
<name>David Rientjes</name>
<email>rientjes@google.com</email>
</author>
<published>2011-09-22T21:11:38+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=e369fde1af20c7c67acff3bc4a36e451f38ae7d0'/>
<id>e369fde1af20c7c67acff3bc4a36e451f38ae7d0</id>
<content type='text'>
Commit e27e6151b154 ("mm/thp: use conventional format for boolean
attributes") changed

  /sys/kernel/mm/transparent_hugepage/khugepaged/defrag

to be tuned by using 1 (enabled) or 0 (disabled) instead of "yes" and
"no", respectively.

Update the documentation.

Signed-off-by: David Rientjes &lt;rientjes@google.com&gt;
Signed-off-by: Linus Torvalds &lt;torvalds@linux-foundation.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Commit e27e6151b154 ("mm/thp: use conventional format for boolean
attributes") changed

  /sys/kernel/mm/transparent_hugepage/khugepaged/defrag

to be tuned by using 1 (enabled) or 0 (disabled) instead of "yes" and
"no", respectively.

Update the documentation.

Signed-off-by: David Rientjes &lt;rientjes@google.com&gt;
Signed-off-by: Linus Torvalds &lt;torvalds@linux-foundation.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>thp: transparent hugepage support documentation</title>
<updated>2011-01-14T01:32:38+00:00</updated>
<author>
<name>Andrea Arcangeli</name>
<email>aarcange@redhat.com</email>
</author>
<published>2011-01-13T23:46:30+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=1c9bf22c09ae14d65225d9b9619b2eb357350cd7'/>
<id>1c9bf22c09ae14d65225d9b9619b2eb357350cd7</id>
<content type='text'>
Documentation/vm/transhuge.txt

Signed-off-by: Andrea Arcangeli &lt;aarcange@redhat.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
Signed-off-by: Linus Torvalds &lt;torvalds@linux-foundation.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Documentation/vm/transhuge.txt

Signed-off-by: Andrea Arcangeli &lt;aarcange@redhat.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
Signed-off-by: Linus Torvalds &lt;torvalds@linux-foundation.org&gt;
</pre>
</div>
</content>
</entry>
</feed>
