public inbox for ltp@lists.linux.it
 help / color / mirror / Atom feed
* [LTP] [PATCH v5 0/3] mm/thp: add two new case
@ 2013-04-16 14:30 Zhouping Liu
  2013-04-16 14:30 ` [LTP] [PATCH v4 1/3] mm/thp: new case thp04.c Zhouping Liu
                   ` (3 more replies)
  0 siblings, 4 replies; 7+ messages in thread
From: Zhouping Liu @ 2013-04-16 14:30 UTC (permalink / raw)
  To: LTP List

The patchset is desinged to test THP functionality.

when one process allocate hugepage aligned anonymous pages,
kernel thread 'khugepaged' controlled by sysfs knobs
/sys/kernel/mm/transparent_hugepage/* will scan them, and make
them as transparent hugepage if they are suited, you can find out
how many transparent hugepages are there in one process from
/proc/<pid>/smaps, among the file contents, 'AnonHugePages' entry
stand for transparent hugepage.

v1 to v2:
accepted Wanlong's suggestion, added some comment for '10s'
added 'static' key word for single-file-only variant.

v2 to v3:
added some comments for low memory system.

v3 to v4:
Wanglong point out that the value of khugepaged/defrag is string type,
not a numeric before applying the commit e27e6151b154 in v2.6.39-rc4,
and I checked the code again, found the current cases thp0* don't be
effected by khugepaged/defrag, so I removed the checking of
khugepaged/defrag from khugepaged_scan_done().

v4 to v5:
 1. made some cleaup
 2. updated 10s to 5s for each checking in khugepaged_scan_done()
 3. used SAFE_FILE_SCANF|PRINTF() instead of write_file()

v5 to v6:
made a little cleanup.

Zhouping Liu (3):
  mm/thp: new case thp04.c
  lib/mem: introduce a new function set_global_mempolicy()
  mm/thp: add new case thp05

 runtest/mm                         |   6 ++
 testcases/kernel/mem/include/mem.h |  12 +++
 testcases/kernel/mem/lib/mem.c     | 199 ++++++++++++++++++++++++++++++++++++-
 testcases/kernel/mem/thp/thp04.c   | 142 ++++++++++++++++++++++++++
 testcases/kernel/mem/thp/thp05.c   | 153 ++++++++++++++++++++++++++++
 5 files changed, 511 insertions(+), 1 deletion(-)
 create mode 100644 testcases/kernel/mem/thp/thp04.c
 create mode 100644 testcases/kernel/mem/thp/thp05.c

-- 
1.7.11.7


------------------------------------------------------------------------------
Precog is a next-generation analytics platform capable of advanced
analytics on semi-structured data. The platform includes APIs for building
apps and a phenomenal toolset for data science. Developers can use
our toolset for easy data analysis & visualization. Get a free account!
http://www2.precog.com/precogplatform/slashdotnewsletter
_______________________________________________
Ltp-list mailing list
Ltp-list@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/ltp-list

^ permalink raw reply	[flat|nested] 7+ messages in thread
* [LTP] [PATCH v5 0/3] mm/thp: add two new case
@ 2013-04-16 10:26 Zhouping Liu
  0 siblings, 0 replies; 7+ messages in thread
From: Zhouping Liu @ 2013-04-16 10:26 UTC (permalink / raw)
  To: LTP List

The patchset is desinged to test THP functionality.

when one process allocate hugepage aligned anonymous pages,
kernel thread 'khugepaged' controlled by sysfs knobs
/sys/kernel/mm/transparent_hugepage/* will scan them, and make
them as transparent hugepage if they are suited, you can find out
how many transparent hugepages are there in one process from
/proc/<pid>/smaps, among the file contents, 'AnonHugePages' entry
stand for transparent hugepage.

v1 to v2:
accepted Wanlong's suggestion, added some comment for '10s'
added 'static' key word for single-file-only variant.

v2 to v3:
added some comments for low memory system.

v3 to v4:
Wanglong point out that the value of khugepaged/defrag is string type,
not a numeric before applying the commit e27e6151b154 in v2.6.39-rc4,
and I checked the code again, found the current cases thp0* don't be
effected by khugepaged/defrag, so I removed the checking of
khugepaged/defrag from khugepaged_scan_done().

v4 to v5:
 1. made some cleaup
 2. updated 10s to 5s for each checking in khugepaged_scan_done()
 3. used SAFE_FILE_SCANF|PRINTF() instead of write_file()

Zhouping Liu (3):
  mm/thp: new case thp04.c
  lib/mem: introduce a new function set_global_mempolicy()
  mm/thp: add new case thp05

 runtest/mm                         |   6 ++
 testcases/kernel/mem/include/mem.h |  12 +++
 testcases/kernel/mem/lib/mem.c     | 199 ++++++++++++++++++++++++++++++++++++-
 testcases/kernel/mem/thp/thp04.c   | 142 ++++++++++++++++++++++++++
 testcases/kernel/mem/thp/thp05.c   | 155 +++++++++++++++++++++++++++++
 5 files changed, 513 insertions(+), 1 deletion(-)
 create mode 100644 testcases/kernel/mem/thp/thp04.c
 create mode 100644 testcases/kernel/mem/thp/thp05.c

-- 
1.7.11.7


------------------------------------------------------------------------------
Precog is a next-generation analytics platform capable of advanced
analytics on semi-structured data. The platform includes APIs for building
apps and a phenomenal toolset for data science. Developers can use
our toolset for easy data analysis & visualization. Get a free account!
http://www2.precog.com/precogplatform/slashdotnewsletter
_______________________________________________
Ltp-list mailing list
Ltp-list@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/ltp-list

^ permalink raw reply	[flat|nested] 7+ messages in thread

end of thread, other threads:[~2013-04-17  3:52 UTC | newest]

Thread overview: 7+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2013-04-16 14:30 [LTP] [PATCH v5 0/3] mm/thp: add two new case Zhouping Liu
2013-04-16 14:30 ` [LTP] [PATCH v4 1/3] mm/thp: new case thp04.c Zhouping Liu
2013-04-16 14:30 ` [LTP] [PATCH v4 2/3] lib/mem: introduce a new function set_global_mempolicy() Zhouping Liu
2013-04-16 14:30 ` [LTP] [PATCH v4 3/3] mm/thp: add new case thp05 Zhouping Liu
2013-04-17  3:26 ` [LTP] [PATCH v5 0/3] mm/thp: add two new case Wanlong Gao
2013-04-17  3:52   ` Zhouping Liu
  -- strict thread matches above, loose matches on Subject: below --
2013-04-16 10:26 Zhouping Liu

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox