Hi,
There is sample ms_print logs
--------------------------------------------------------------------------------
n time(i) total(B) useful-heap(B) extra-heap(B) stacks(B)
--------------------------------------------------------------------------------
2 124,324,407 5,391,336 3,157,786 1,181,678 1,051,872
3 235,269,541 6,438,776 5,152,084 1,283,988 2,704
4 314,147,836 6,944,764 5,417,524 1,524,540 2,700
5 388,499,397 7,679,848 5,807,858 1,869,406 2,584
6 434,297,280 8,123,952 6,044,606 2,076,602 2,744
7 511,743,402 9,019,048 6,497,310 2,518,810 2,928
8 578,499,793 9,664,128 6,841,291 2,820,101 2,736
9 667,537,310 10,521,108 7,298,190 3,219,898 3,020
69.37% (7,298,190B) (heap allocation functions) malloc/new/new[], --alloc-fns,
etc.
******************
Here if I see in most of cases useful heap s only 50/60 % of total heap.
As per dosumnetation, extra heap come from heap admin and allignment. When I
changed default heap admin value to 1, useful heap becomes almost 80%.
Should I assumne that application I am analysing is using a lot of small amount
of memory allocation.
Regards
Sachin
------------------------------------------------------------------------------
All the data continuously generated in your IT infrastructure
contains a definitive record of customers, application performance,
security threats, fraudulent activity, and more. Splunk takes this
data and makes sense of it. IT sense. And common sense.
http://p.sf.net/sfu/splunk-novd2d
_______________________________________________
Valgrind-users mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/valgrind-users
