profiling - SQL Server Profiler: How to inspect/understand the duration for the Audit Logout event in more detail?

I am profiling some MS SQL queries with the SQL Server Profiler for my C# Application that I develop with Visual Studio and IIS Express:The duration that is given for the event "Audit Logout" (16876 ms) is the total time between login and logout. The duration for the query is only 60 ms. Login/Logout events are related to the setting up / tearing down.From What is "Audit Logout" in SQL Server Profiler?I would like to understand the time difference of 16816 ms (= 16876 ms - 60ms) in more detail. a) Is it possible to log more events (...Read more

profiling - Measuring OpenCL kernel's memory throughput

I read about global memory optimization in OpenCL. In one of the slide-shows, a very simple kernel (below) has been used to demonstrate the importance of memory coalescing.__kernel void measure(__global float* idata, __global float* odata, int offset) { int xid = get_global_id(0) + offset; odata[xid] = idata[xid];}Please see my code below which measures the running time of the kernel ret = clFinish(command_queue); size_t local_item_size = MAX_THREADS; size_t global_item_size = INPUTSIZE; struct timeval t0,t1; gettimeofday...Read more

profiling - What is "<Cycle 1>" an indication of in Xdebug?

I have an xdebug profile on a php script that I parsed with kcachegrind. Here is a screenshot showing that the most time spent inside any given function was spent inside <cycle 1> and the top 'Callers' were made from 'include' and 'include_once' in index.php.This profile was run during a stress-test using apache 'ab' so there were many concurrent connections occurring.What does <cycle 1> indicate on an xdebug profile?...Read more

Profiling Mule using Yourkit

Has somebody successfully profiled Mule standalone CE v3.4 using Yourkit?The Mule documentation: http://www.mulesoft.org/documentation/display/current/Profiling+Mule# has a download page link to download the Profiler Pack for Mule Community Edition but that link does not seem to work.What are the exact steps to be followed for remotely profiling Mule standalone server CE using Yourkit?...Read more

profiling - kcachegrind unable to open callgrind file

I'm using callgrind to profile a small piece of code. Callgrind output files are well generated, their content looks ok, but I'm unable to open them with kcachegrind: I get the following error message: Could not open file "callgrind.out.4953". Check it exists and you have enough permissions to read it.I have all permissions on files and directories they are in, but with the same issue. Also, it works well with an other project, in an other folder in the same workspace. I also precise that the processes terminate correctly in both cases....Read more

profiling - Callgrind Profile Format inclusive/self cost

I'm trying to understand the Callgrind Profile Format. I found the online descriptionI thought I understood it fairly well until I encountered the 'Extended Example':events: Instructionsfl=file1.c fn=main16 20 cfn=func1 calls=1 50 16 400 cfl=file2.c cfn=func2 calls=3 20 16 400fn=func1 51 100 cfl=file2.c cfn=func2 calls=2 20 51 300fl=file2.c fn=func2 20 700The description reads: One can see that in "main" only code from line 16 is executed where also the other functions are called. Inclusive cost of "main" is 420, which is the sum of self cost 2...Read more

profiling - valgrind reports malloc assertion failure, memcheck doesn't report any errors

Callgrind reported an assertion violation in malloc although memcheck and a usual run reveals no errors: stp: malloc.c:3096: sYSMALLOc: Assertion `(old_top == (((mbinptr) (((char *) &((av)->bins[((1) - 1) * 2])) - __builtin_offsetof (struct malloc_chunk, fd)))) && old_size == 0) || ((unsigned long) (old_size) >= (unsigned long)((((__builtin_offsetof (struct malloc_chunk, fd_nextsize))+((2 * (sizeof(size_t))) - 1)) & ~((2 * (sizeof(size_t))) - 1))) && ((old_top)->size & 0x1) && ((unsigned long)old_end & p...Read more

profiling - Showing call tree in kcachegrind

How can I use kcachegrind to get a non-graphical tree of all my function calls, in the order they were called?There are two typical ways to look at profiling data:sorted by the most expensive entriessorted in order of executionI'm looking for the latter. I can sort of get it with the "Call Graph" tab, but this omits some data, and it can be confusing the way it represents loops. I'd prefer a text view, like this:alt text http://blogs.msdn.com/blogfiles/ronang/WindowsLiveWriter/JavascriptprofilinginIE8beta2_DF55/image_thumb_5.png...Read more

profiling - Interpreting the results of time profiler and activity monitor

For a research project I had to modify a Titanium application such that it can be run in Cordova too. Now that both versions of the app are working as expected, my last task is to do some benchmarking in order to compare the Titanium version with the Cordova version.We would like to compare CPU usage, memory usage, communication speed, etc.What i had in mind is :Do some profiling on both versions with XcodeExport instrument data to CSV fileImport the CSV files in a statistical program (SPSS)Compare both versions by drawing graphs, using boxplot...Read more

Difference between Benchmarking and Profiling

I see the terms software benchmarking and profiling used sometimes interchangeably but as far as my understanding goes there's a subtile difference.Both are connected by time. But whereas benchmarking is mainly about determining a certain speed score that can be compared with other applications, profiling gives you exact information about where your application spends most of its time (or number of cycles).For me it was always like: integration testing is the counterpart to benchmarking and unit tesing the counterpart to profiling. But how does...Read more

profiling - Recommended samples for performance benchmarks?

I'm writing performance benchmarks for some of my code. This is both to compare my own implementations as I develop/experiment, and to compare against "competing" implementations. I have no problem writing these, and getting usable results.It's very well established that more samples are a good thing, as it reduces the impact of erroneous data and gives a more true result.So, if I'm profiling a given function/procedure/whatever, how many samples does it seem reasonable to get?I'm currently doing about 1 million samples for each test. These are ...Read more

Code Profiling of VSTO application

I'm looking for a free code profiler (performance profiler, not a memory profiler) which works for VSTO applications (specifically Excel in my case, but I gather that if it works for one, it should work for all). I have tried Eqatec Profiler, but it can't seem to launch the application from the profiler (The Run app button is greyed out, which I'm gathering is because the VSTO application is compiled into a dll which runs in-process with Excel.exe).If anyone has successfully used Eqatec or another free code profiler to profile a VSTO applicati...Read more

profile - Eloqua Forms - Progresive Profie / Profiling

I'm quite new in Eloqua. I'm trying to generate Progressive Profiling Forms, and as I can find in the web, there are two ways: Adding Rules, or setting Stages or Linear flow. But, I am not being able to do either.Any help?By the way, the most I could progress, is: click on Progressive Profile button, add some fields, then copy/paste HTML+JS generated, and open the form in Chrome (the whole code seems to be complete auto-sufficent). But there are many weird behaviors......Read more