Stack Overflow
Stack Overflow

Questions tagged [perf]

Perf is a profiler tool for Linux 2.6+ based systems.

Perf is a profiling tool for Linux 2.6+ based systems that uses the perf_events kernel interface to provide a command-line interface to underlying hardware, software and kernel performance counters. It abstracts away differences in performance counters implemented across different CPU architectures, allowing consistency across different hardware.

See also the perf wiki.

1032 questions
0
votes
1 answer

How to change input file name in perf sched record

I need to prove that when process is runnig and I remove the ELF file of this process number of free blocks and nodes in filesystem won't increase, and after I kill the process they increase. I also need to show latency in whole lifecycle of this…
Alcatrazor
  • 3
  • 4
0
votes
1 answer

profiling linux application with perf record

I've been trying to profile my C++ application in Linux by following this article on perf record. My understanding is all I need to do is run perf record program [program_options], where program is the program executable and [program options] are…
Adam
  • 8,752
  • 12
  • 54
  • 96
0
votes
1 answer

Generating Raw Intel Processor Trace With Perf

I am tasked with generating a raw Intel Processor Trace. By raw, I mean the trace conforms to the file header: struct pt_logfile_header { unsigned int magic; unsigned int version; }; And is then followed by various process, thread, xpage…
Stephen Lasky
  • 417
  • 5
  • 18
0
votes
1 answer

Linux perf tool showing weird cache miss results

I'm using linux perf tools to profile one of CRONO benchmarks, I'm specifically interested in L1 DCache Misses, so I run the program like this: perf record -e L1-dcache-read-misses -o perf/apsp.cycles apps/apsp/apsp 4 16384 16 It runs fine but…
mewais
  • 1,265
  • 3
  • 25
  • 42
0
votes
1 answer

React Perf : what does it mean to have "Connect(componentName) in printWasted?

I am using React Perf tools to find out wasted rendering/cycles. (react-addons-perf) I see lot of Connect(component-name) in the list. What does that mean? Incidentally all these Connects are those where I have passed null as a parameter. (I don't…
Abhinav
  • 722
  • 2
  • 11
  • 27
0
votes
0 answers

linux: perf cannot inject var/line probes: Mismatching build id

I've installed most recent debuginfo on a recent fedora for perfing especially for kernel vars. Am at the end of my tether. I must me doing something stupidly wrong, since checking around I saw no further complaints for most recent stable debug…
cherusk
  • 31
  • 6
0
votes
1 answer

Running perf on ARM target

I am trying to use perf tool on an ARM target. Is it possible to do 'perf annotate' on a different machine as the target has limited capabilities. thanks, GL.
user2148707
  • 93
  • 12
0
votes
1 answer

Determining Instruction Size of A process / A function call in Linux

I would like to determine how many instructions it would take for a core to finish a process. Is there a way to determine that? Hence, in a microcontroller you are able to determine the instruction size of functions, I would like to do the same…
mozcelikors
  • 2,582
  • 8
  • 43
  • 77
0
votes
2 answers

Why is IPC lower than one on a modern processor?

7703.572978 task-clock (msec) # 0.996 CPUs utilized 1,575 context-switches # 0.204 K/sec 18 cpu-migrations # 0.002 K/sec 65,975…
Kevin Dong
  • 5,001
  • 9
  • 29
  • 62
0
votes
0 answers

Monitoring Processes/Inter-process communication with Linux

I would like to find a tool that should monitor/profile processes (not what's inside processes, but process inter dependence) (inter-process communications and also indirect communications) of a process. Is there a tool to analyze and visualize…
mozcelikors
  • 2,582
  • 8
  • 43
  • 77
0
votes
0 answers

perf: comparing "CPU performance / CPU impact" of two binaries?

Let's say I have two binaries which perform the same task - they convert complex data from one format to another. I will run them on a busy server at low priority and I don't really care if one is faster than the other - I want to know which of them…
Tomasz
  • 179
  • 12
0
votes
3 answers

Cannot understand the metric returned by "perf" regarding the cache-misses

My question is about understanding the Linux perf tool metrics. I did an optimisations related to prefetch/cache-misses in my code, that is now faster. However, perf does not show me that (or more certainly, I do not understand what perf shows…
Philippe MESMEUR
  • 737
  • 8
  • 22
0
votes
1 answer

Building a flamegraph of multiple node.js processes while using --perf_basic_prof_only_functions

We currently use node clustering in order to get the most out of our machines and would like to be able to profile all processes simultaneously (only the function calls, we're using --perf_basic_prof_only_functions). While getting the information…
ttacon
  • 503
  • 3
  • 9
0
votes
0 answers

confusing perf stat results,32 threads and 2 threads

perf stat results ,the cycles are 25806004593 and time elapsed is 0.527408365 seconds for 32 threads.But for 2 threads cycles are 4109847315 and time elapsed is 1.075951973 seconds. Why are the cycles so much?cycles is not clock cycles?????? 32…
jay chen
  • 21
  • 1
0
votes
1 answer

Linux perf test on 3.10 kernel

I am trying perf test on imx6dl arm target, 2 subtests are failing on perf and are: perf test -v 15 15: Test breakpoint overflow signal handler : --- start --- count1 0, count2 0, overflow 0 failed: wrong count for bp10 failed:…
Murali
  • 1
  • 2
1 2 3
…
68 69