[lkml]   [2019]   [Sep]   [25]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: [PATCH 1/2] perf script python: integrate page reclaim analyze script
On 9/25/19 6:56 PM, Tony Jones wrote:
> On 9/18/19 7:38 AM, Yafang Shao wrote:
>> A new perf script page-reclaim is introduced in this patch. This new script
>> is used to report the page reclaim details. The possible usage of this
>> script is as bellow,
>> - identify latency spike caused by direct reclaim
>> - whehter the latency spike is relevant with pageout
>> - why is page reclaim requested, i.e. whether it is because of memory
>> fragmentation
>> - page reclaim efficiency
>> etc
>> In the future we may also enhance it to analyze the memcg reclaim.
>> Bellow is how to use this script,
>> # Record, one of the following
>> $ perf record -e 'vmscan:mm_vmscan_*' ./workload
>> $ perf script record page-reclaim
>> # Report
>> $ perf script report page-reclaim
>> # Report per process latency
>> $ perf script report page-reclaim -- -p
> I tested it with global-dhp__pagereclaim-performance from mmtests and got what appears to be reasonable results and the output looks correct and useful.  However I'm not a vm expert so I can't comment further.  Hopefully someone on linux-mm can give more specific feedback.
> There is one issue with Python3,  see below.  I didn't test with Python2.

Ok, I guess this wasn't actually tested with Python3 as itervalues() is Python2 only. Any scripts need to work with both Python2.6+ and Python3.

# perf script -i /tmp/perf.out -s -- -p

Traceback (most recent call last):
File "", line 305, in trace_end
File "", line 268, in display_proc
AttributeError: 'dict' object has no attribute 'itervalues'
Fatal Python error: problem in Python trace event handler

Use a try/except to handle this.



 \ /
  Last update: 2019-09-26 05:37    [W:0.045 / U:2.916 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site