Skip to content

cloud-kernel
cloud-kernel

openanolis / cloud-kernel
1 年多 前同步成功

通知 160
Star 36
Fork 7
cloud-kernel
cloud-kernel
切换分支/标签
  1. 15 6月, 2011 2 次提交
    • V
      tracing: Use NUMA allocation for per-cpu ring buffer pages · 7ea59064
      由 Vaibhav Nagarnaik 提交于 
      The tracing ring buffer is a group of per-cpu ring buffers where
allocation and logging is done on a per-cpu basis. The events that are
generated on a particular CPU are logged in the corresponding buffer.
This is to provide wait-free writes between CPUs and good NUMA node
locality while accessing the ring buffer.

However, the allocation routines consider NUMA locality only for buffer
page metadata and not for the actual buffer page. This causes the pages
to be allocated on the NUMA node local to the CPU where the allocation
routine is running at the time.

This patch fixes the problem by using a NUMA node specific allocation
routine so that the pages are allocated from a NUMA node local to the
logging CPU.

I tested with the getuid_microbench from autotest. It is a simple binary
that calls getuid() in a loop and measures the average time for the
syscall to complete. The following command was used to test:
$ getuid_microbench 1000000

Compared the numbers found on kernel with and without this patch and
found that logging latency decreases by 30-50 ns/call.
tracing with non-NUMA allocation - 569 ns/call
tracing with NUMA allocation     - 512 ns/call
Signed-off-by: NVaibhav Nagarnaik <vnagarnaik@google.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Michael Rubin <mrubin@google.com>
Cc: David Sharp <dhsharp@google.com>
Link: http://lkml.kernel.org/r/1304470602-20366-1-git-send-email-vnagarnaik@google.comSigned-off-by: NSteven Rostedt <rostedt@goodmis.org>
      7ea59064
    • V
      tracing: Schedule a delayed work to call wakeup() · e7e2ee89
      由 Vaibhav Nagarnaik 提交于 
      In using syscall tracing by concurrent processes, the wakeup() that is
called in the event commit function causes contention on the spin lock
of the waitqueue. I enabled sys_enter_getuid and sys_exit_getuid
tracepoints, and by running getuid_microbench from autotest in parallel
I found that the contention causes exponential latency increase in the
tracing path.

The autotest binary getuid_microbench calls getuid() in a tight loop for
the given number of iterations and measures the average time required to
complete a single invocation of syscall.

The patch schedules a delayed work after 2 ms once an event commit calls
to wake up the trace wait_queue. This removes the delay caused by
contention on spin lock in wakeup() and amortizes the wakeup() calls
scheduled over the 2 ms period.

In the following example, the script enables the sys_enter_getuid and
sys_exit_getuid tracepoints and runs the getuid_microbench in parallel
with the given number of processes. The output clearly shows the latency
increase caused by contentions.

$ ~/getuid.sh 1
1000000 calls in 0.720974253 s (720.974253 ns/call)

$ ~/getuid.sh 2
1000000 calls in 1.166457554 s (1166.457554 ns/call)
1000000 calls in 1.168933765 s (1168.933765 ns/call)

$ ~/getuid.sh 3
1000000 calls in 1.783827516 s (1783.827516 ns/call)
1000000 calls in 1.795553270 s (1795.553270 ns/call)
1000000 calls in 1.796493376 s (1796.493376 ns/call)

$ ~/getuid.sh 4
1000000 calls in 4.483041796 s (4483.041796 ns/call)
1000000 calls in 4.484165388 s (4484.165388 ns/call)
1000000 calls in 4.484850762 s (4484.850762 ns/call)
1000000 calls in 4.485643576 s (4485.643576 ns/call)

$ ~/getuid.sh 5
1000000 calls in 6.497521653 s (6497.521653 ns/call)
1000000 calls in 6.502000236 s (6502.000236 ns/call)
1000000 calls in 6.501709115 s (6501.709115 ns/call)
1000000 calls in 6.502124100 s (6502.124100 ns/call)
1000000 calls in 6.502936358 s (6502.936358 ns/call)

After the patch, the latencies scale better.
1000000 calls in 0.728720455 s (728.720455 ns/call)

1000000 calls in 0.842782857 s (842.782857 ns/call)
1000000 calls in 0.883803135 s (883.803135 ns/call)

1000000 calls in 0.902077764 s (902.077764 ns/call)
1000000 calls in 0.902838202 s (902.838202 ns/call)
1000000 calls in 0.908896885 s (908.896885 ns/call)

1000000 calls in 0.932523515 s (932.523515 ns/call)
1000000 calls in 0.958009672 s (958.009672 ns/call)
1000000 calls in 0.986188020 s (986.188020 ns/call)
1000000 calls in 0.989771102 s (989.771102 ns/call)

1000000 calls in 0.933518391 s (933.518391 ns/call)
1000000 calls in 0.958897947 s (958.897947 ns/call)
1000000 calls in 1.031038897 s (1031.038897 ns/call)
1000000 calls in 1.089516025 s (1089.516025 ns/call)
1000000 calls in 1.141998347 s (1141.998347 ns/call)
Signed-off-by: NVaibhav Nagarnaik <vnagarnaik@google.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Michael Rubin <mrubin@google.com>
Cc: David Sharp <dhsharp@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1305059241-7629-1-git-send-email-vnagarnaik@google.comSigned-off-by: NSteven Rostedt <rostedt@goodmis.org>
      e7e2ee89
  3. 07 6月, 2011 1 次提交
  5. 04 6月, 2011 3 次提交
  7. 03 6月, 2011 12 次提交
  9. 02 6月, 2011 6 次提交
    • A
      perf evlist: Don't die if sample_{id_all|type} is invalid · c2a70653
      由 Arnaldo Carvalho de Melo 提交于 
      Fixes two more cases where the python binding would not load:

. Not finding die(), which it shouldn't anyway, not good to just stop the
  world because some particular perf.data file is invalid, just propagate
  the error to the caller.

. Not finding perf_sample_size: fix it by moving it from event.c to evsel,
  where it belongs, as most cases are moving to operate on an evsel object.o

One of the fixed problems:

[root@emilia ~]# python
>>> import perf
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
ImportError: /home/acme/git/build/perf/python/perf.so: undefined symbol: perf_sample_size
>>>
[root@emilia ~]#

Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-1hkj7b2cvgbfnoizsekjb6c9@git.kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      c2a70653
    • A
      perf python: Use exception to propagate errors · 5c6970af
      由 Arnaldo Carvalho de Melo 提交于 
      We were using pr_debug to tell the user about not being able to parse a sample
where we should really use the python way of reporting errors: exceptions.

Fixes this problem:

[root@emilia ~]# python
>>> import perf
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
ImportError: /home/acme/git/build/perf/python/perf.so: undefined symbol: eprintf
>>>
[root@emilia ~]

As we want to keep the objects linked in the python binding (and in the future
in a shared library) minimal.

Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-m9dba9kaluas0kq8r58z191c@git.kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      5c6970af
    • A
      perf evlist: Remove dependency on debug routines · bccdaba0
      由 Arnaldo Carvalho de Melo 提交于 
      So far we avoided having to link debug.o in the python binding, keep it
that way by not using ui__warning() in evlist.c.

Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-4wtew8hd3g7ejnlehtspys2t@git.kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      bccdaba0
    • L
      Revert "mm: fail GFP_DMA allocations when ZONE_DMA is not configured" · 1fa7b6a2
      由 Linus Torvalds 提交于 
      This reverts commit a197b59a.

As rmk says:
 "Commit a197b59a (mm: fail GFP_DMA allocations when ZONE_DMA is not
  configured) is causing regressions on ARM with various drivers which
  use GFP_DMA.

  The behaviour up until now has been to silently ignore that flag when
  CONFIG_ZONE_DMA is not enabled, and to allocate from the normal zone.
  However, as a result of the above commit, such allocations now fail
  which causes drivers to fail.  These are regressions compared to the
  previous kernel version."

so just revert it.
Requested-by: NRussell King <linux@arm.linux.org.uk>
Acked-by: NAndrew Morton <akpm@linux-foundation.org>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      1fa7b6a2
    • L
      Merge git://git.infradead.org/iommu-2.6 · f0f52a94
      由 Linus Torvalds 提交于 
      * git://git.infradead.org/iommu-2.6:
  intel-iommu: Fix off-by-one in RMRR setup
  intel-iommu: Add domain check in domain_remove_one_dev_info
  intel-iommu: Remove Host Bridge devices from identity mapping
  intel-iommu: Use coherent DMA mask when requested
  intel-iommu: Dont cache iova above 32bit
  intel-iommu: Speed up processing of the identity_mapping function
  intel-iommu: Check for identity mapping candidate using system dma mask
  intel-iommu: Only unlink device domains from iommu
  intel-iommu: Enable super page (2MiB, 1GiB, etc.) support
  intel-iommu: Flush unmaps at domain_exit
  intel-iommu: Remove obsolete comment from detect_intel_iommu
  intel-iommu: fix VT-d PMR disable for TXT on S3 resume
      f0f52a94
    • L
      block: fix mismerge of the DISK_EVENT_MEDIA_CHANGE removal · 0f48f260
      由 Linus Torvalds 提交于 
      Jens' back-merge commit 698567f3 ("Merge commit 'v2.6.39' into
for-2.6.40/core") was incorrectly done, and re-introduced the
DISK_EVENT_MEDIA_CHANGE lines that had been removed earlier in commits

 - 9fd097b1 ("block: unexport DISK_EVENT_MEDIA_CHANGE for
   legacy/fringe drivers")

 - 7eec77a1 ("ide: unexport DISK_EVENT_MEDIA_CHANGE for ide-gd
   and ide-cd")

because of conflicts with the "g->flags" updates near-by by commit
d4dc210f ("block: don't block events on excl write for non-optical
devices")

As a result, we re-introduced the hanging behavior due to infinite disk
media change reports.

Tssk, tssk, people! Don't do back-merges at all, and *definitely* don't
do them to hide merge conflicts from me - especially as I'm likely
better at merging them than you are, since I do so many merges.
Reported-by: NSteven Rostedt <rostedt@goodmis.org>
Cc: Jens Axboe <jaxboe@fusionio.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      0f48f260
  11. 01 6月, 2011 16 次提交