Skip to content

L
linux-davinci
Switch branch/tag
  1. 28 Oct, 2009 6 commits
  3. 30 Oct, 2009 2 commits
    • Andrew Morton's avatar
      Cc: Jeff Moyer <jmoyer@redhat.com> · 33b60a5f
      Andrew Morton authored 
      Cc: Zach Brown <zach.brown@oracle.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
      33b60a5f
    • Jeff Moyer's avatar
      Intel reported a performance regression caused by the following commit: · 621687ce
      Jeff Moyer authored 
      commit 848c4dd5
Author: Zach Brown <zach.brown@oracle.com>
Date:   Mon Aug 20 17:12:01 2007 -0700

    dio: zero struct dio with kzalloc instead of manually

    This patch uses kzalloc to zero all of struct dio rather than
    manually trying to track which fields we rely on being zero.  It
    passed aio+dio stress testing and some bug regression testing on
    ext3.

    This patch was introduced by Linus in the conversation that lead up
    to Badari's minimal fix to manually zero .map_bh.b_state in commit:

      6a648fa7

    It makes the code a bit smaller.  Maybe a couple fewer cachelines to
    load, if we're lucky:

       text    data     bss     dec     hex filename
    3285925  568506 1304616 5159047  4eb887 vmlinux
    3285797  568506 1304616 5158919  4eb807 vmlinux.patched

    I was unable to measure a stable difference in the number of cpu
    cycles spent in blockdev_direct_IO() when pushing aio+dio 256K reads
    at ~340MB/s.

    So the resulting intent of the patch isn't a performance gain but to
    avoid exposing ourselves to the risk of finding another field like
    .map_bh.b_state where we rely on zeroing but don't enforce it in the
    code.

Zach surmised that zeroing out the page array was what caused most of
the problem, and suggested the approach taken in the attached patch for
resolving the issue.  Intel re-tested with this patch and saw a 0.6%
performance gain (the original regression was 0.5%).
Signed-off-by: default avatarJeff Moyer <jmoyer@redhat.com>
Acked-by: default avatarZach Brown <zach.brown@oracle.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
      621687ce
  5. 14 Oct, 2009 1 commit
  7. 16 Oct, 2009 1 commit
  9. 30 Sep, 2009 3 commits
  11. 16 Oct, 2009 1 commit
  13. 09 Oct, 2009 1 commit
  15. 30 Sep, 2009 1 commit
  17. 24 Aug, 2009 1 commit
  19. 15 Oct, 2009 1 commit
  21. 29 Sep, 2009 1 commit
  23. 06 Oct, 2009 7 commits
  25. 13 Oct, 2009 1 commit
  27. 24 Sep, 2009 1 commit
    • Oleg Nesterov's avatar
      Thanks to Roland who pointed out de_thread() issues. · 7b9f1838
      Oleg Nesterov authored 
      Currently we add sub-threads to ->real_parent->children list.  This buys
nothing but slows down do_wait().

With this patch ->children contains only main threads (group leaders). 
The only complication is that forget_original_parent() should iterate over
sub-threads by hand, and de_thread() needs another list_replace() when it
changes ->group_leader.

Henceforth do_wait_thread() can never see task_detached() && !EXIT_DEAD
tasks, we can remove this check (and we can unify do_wait_thread() and
ptrace_do_wait()).

This change can confuse the optimistic search in mm_update_next_owner(),
but this is fixable and minor.

Perhaps badness() and oom_kill_process() should be updated, but they
should be fixed in any case.
Signed-off-by: default avatarOleg Nesterov <oleg@redhat.com>
Cc: Roland McGrath <roland@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Ratan Nalumasu <rnalumasu@gmail.com>
Cc: Vitaly Mayatskikh <vmayatsk@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
      7b9f1838
  29. 25 Sep, 2009 1 commit
    • Roland McGrath's avatar
      This adds the utrace facility, a new modular interface in the kernel for · 582156fe
      Roland McGrath authored 
      implementing user thread tracing and debugging.  This fits on top of the
tracehook_* layer, so the new code is well-isolated.

The new interface is in <linux/utrace.h> and the DocBook utrace book
describes it.  It allows for multiple separate tracing engines to work in
parallel without interfering with each other.  Higher-level tracing
facilities can be implemented as loadable kernel modules using this layer.

The new facility is made optional under CONFIG_UTRACE.  When this is not
enabled, no new code is added.  It can only be enabled on machines that
have all the prerequisites and select CONFIG_HAVE_ARCH_TRACEHOOK.

In this initial version, utrace and ptrace do not play together at all. 
If ptrace is attached to a thread, the attach calls in the utrace kernel
API return -EBUSY.  If utrace is attached to a thread, the PTRACE_ATTACH
or PTRACE_TRACEME request will return EBUSY to userland.  The old ptrace
code is otherwise unchanged and nothing using ptrace should be affected by
this patch as long as utrace is not used at the same time.  In the future
we can clean up the ptrace implementation and rework it to use the utrace
API.

[oleg@redhat.com: kill exclude_xtrace logic]
Signed-off-by: default avatarRoland McGrath <roland@redhat.com>
Signed-off-by: default avatarOleg Nesterov <oleg@redhat.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
      582156fe
  31. 30 Oct, 2009 1 commit
  33. 16 Oct, 2009 4 commits
  35. 30 Oct, 2009 1 commit
  37. 28 Oct, 2009 1 commit
  39. 16 Oct, 2009 1 commit
  41. 10 Oct, 2009 3 commits
    • Andrew Morton's avatar
      tweak comments · 9c63e80b
      Andrew Morton authored 
      Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
      9c63e80b
    • KAMEZAWA Hiroyuki's avatar
      This is a patch for coalescing access to res_counter at charging by percpu · 8c20eaa6
      KAMEZAWA Hiroyuki authored 
      caching.  At charge, memcg charges 64pages and remember it in percpu
cache.  Because it's cache, drain/flush if necessary.

This version uses public percpu area.
 2 benefits for using public percpu area.
 1. Sum of stocked charge in the system is limited to # of cpus
    not to the number of memcg. This shows better synchonization.
 2. drain code for flush/cpuhotplug is very easy (and quick)

The most important point of this patch is that we never touch res_counter
in fast path. The res_counter is system-wide shared counter which is modified
very frequently. We shouldn't touch it as far as we can for avoiding
false sharing.

On x86-64 8cpu server, I tested overheads of memcg at page fault by
running a program which does map/fault/unmap in a loop. Running
a task per a cpu by taskset and see sum of the number of page faults
in 60secs.

[without memcg config]
  40156968  page-faults              #      0.085 M/sec   ( +-   0.046% )
  27.67 cache-miss/faults

[root cgroup]
  36659599  page-faults              #      0.077 M/sec   ( +-   0.247% )
  31.58 cache miss/faults

[in a child cgroup]
  18444157  page-faults              #      0.039 M/sec   ( +-   0.133% )
  69.96 cache miss/faults

[ + coalescing uncharge patch]
  27133719  page-faults              #      0.057 M/sec   ( +-   0.155% )
  47.16 cache miss/faults

[ + coalescing uncharge patch + this patch ]
  34224709  page-faults              #      0.072 M/sec   ( +-   0.173% )
  34.69 cache miss/faults

Changelog (since Oct/2):
  - updated comments
  - replaced get_cpu_var() with __get_cpu_var() if possible.
  - removed mutex for system-wide drain. adds a counter instead of it.
  - removed CONFIG_HOTPLUG_CPU

Changelog (old):
  - rebased onto the latest mmotm
  - moved charge size check before __GFP_WAIT check for avoiding unnecesary
  - added asynchronous flush routine.
  - fixed bugs pointed out by Nishimura-san.
Signed-off-by: default avatarKAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
      8c20eaa6
    • KAMEZAWA Hiroyuki's avatar
      In massive parallel enviroment, res_counter can be a performance · ec1d6cb0
      KAMEZAWA Hiroyuki authored 
      bottleneck.  One strong techinque to reduce lock contention is reducing
calls by coalescing some amount of calls into one.

Considering charge/uncharge chatacteristic,
	- charge is done one by one via demand-paging.
	- uncharge is done by
		- in chunk at munmap, truncate, exit, execve...
		- one by one via vmscan/paging.

It seems we have a chance to coalesce uncharges for improving scalability
at unmap/truncation.

This patch is a for coalescing uncharge.  For avoiding scattering memcg's
structure to functions under /mm, this patch adds memcg batch uncharge
information to the task.  A reason for per-task batching is for making use
of caller's context information.  We do batched uncharge (deleyed
uncharge) when truncation/unmap occurs but do direct uncharge when
uncharge is called by memory reclaim (vmscan.c).

The degree of coalescing depends on callers
  - at invalidate/trucate... pagevec size
  - at unmap ....ZAP_BLOCK_SIZE
(memory itself will be freed in this degree.)
Then, we'll not coalescing too much.

On x86-64 8cpu server, I tested overheads of memcg at page fault by
running a program which does map/fault/unmap in a loop. Running
a task per a cpu by taskset and see sum of the number of page faults
in 60secs.

[without memcg config]
  40156968  page-faults              #      0.085 M/sec   ( +-   0.046% )
  27.67 cache-miss/faults
[root cgroup]
  36659599  page-faults              #      0.077 M/sec   ( +-   0.247% )
  31.58 miss/faults
[in a child cgroup]
  18444157  page-faults              #      0.039 M/sec   ( +-   0.133% )
  69.96 miss/faults
[child with this patch]
  27133719  page-faults              #      0.057 M/sec   ( +-   0.155% )
  47.16 miss/faults

We can see some amounts of improvement.
(root cgroup doesn't affected by this patch)
Another patch for "charge" will follow this and above will be improved more.

Changelog(since 2009/10/02):
 - renamed filed of memcg_batch (as pages to bytes, memsw to memsw_bytes)
 - some clean up and commentary/description updates.
 - added initialize code to copy_process(). (possible bug fix)

Changelog(old):
 - fixed !CONFIG_MEM_CGROUP case.
 - rebased onto the latest mmotm + softlimit fix patches.
 - unified patch for callers
 - added commetns.
 - make ->do_batch as bool.
 - removed css_get() at el. We don't need it.
Signed-off-by: default avatarKAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
      ec1d6cb0