The tag has no usage guidance.

learn more… | top users | synonyms

1
vote
0answers
25 views

Print kernel memory layout

Userland memory layout can be inspected by looking into /proc/self/maps. I am wondering if there is a similar facility allowing to inspect runtime kernel memory layout?
2
votes
0answers
42 views

Which process wrote to which memory address? [closed]

Recently, I've been seeing a wide variety of memory-related crashes at work (C++ applications on Ubuntu 14.04). Our applications use a properietary third party library to interface with real time data ...
1
vote
0answers
121 views

How can I find which process is eating my memory? [duplicate]

My Linux system sometimes reaches 90% memory usage. We are running some Java processes, and top shows overall usage as 45%. If I stop the running processes, usage reduces to 5-10%. I want to list ...
0
votes
0answers
30 views

How to trace Hardware Performance Counters?

I would like to trace dynamically the Hardware Parformance Counters (HPC) in realtime for a running proccess. I've been googling but I can't find what I'm looking for. I've used PAPI for source code ...
1
vote
0answers
121 views

Profiling memory, disk, cpu, and time from python

I have a workflow, implemented in python, and I would like to profile memory, disk (IO), cpu, and time information in python in an unobtrusive manner. This is NOT a question of profiling code, but ...
0
votes
0answers
49 views

Cannot connect to OpenSSH when compiled with the gcc option: -finstrument-functions

I want to make custom traces of sshd. So, I have added the source file ptrace.c from here. This file enables to trace function calls (but this is not the subject of my question). So, I have modified ...
5
votes
1answer
376 views

Is there a mock program that uses the CPU on multiple cores?

I am playing around with htop, gprof, etc. I'd like a program that basically just runs on multiple cores so I can profile it and learn how to use these tools. I know I can write my own c++ code with ...
0
votes
1answer
190 views

Difference between maximum resident set size as reported by /usr/bin/time vs. getrusage?

I ran the command a.out like this: $ /usr/bin/time -f"%M" ./a.out a.out also uses the function getrusage() and prints: printf("%ld",ru.ru_maxrss); where the first ru is the struct. When I run ...
3
votes
1answer
48 views

program executing for 2 days

I have a java program which implements the Hungarian algorithm. I made changes to the existing code in such a way that the input is read from file. I have a pretty huge input around 32,000 rows for ...
1
vote
1answer
120 views

Does perf includes some “graphing” abilities?

It's possible to create a bitmap or a vector image out of the data collected by the perf profiler under linux ?
3
votes
0answers
199 views

What is the difference between the output of TOP command and Oprofile?

In the top command one of the processes is always showing a CPU usage of 4 to 5%. But in oprofile the CPU usage is 0.004%. I do not understand this. And I also noticed that even when a process is in ...
2
votes
1answer
469 views

Understanding Perf tool output

I recently installed Perf tool On my platform and wanted to use it for profiling my platform. I started profiling a standalone application.Below command I used perf start ./helloworld ...
4
votes
5answers
459 views

Run program at lower CPU speed?

It would be very useful for me to run specific programs in a Linux environment with a fixed (lower) CPU clock speed (say, runat 400mhz ./my-program --argument-of="my program" for getting that clock ...
7
votes
1answer
103 views

Time all executions in bash [duplicate]

Is there a way to run all commands in bash as if they were invoked with time in front? I want that I could type $ some_command and this will actually invoke $ time some_command.
19
votes
3answers
8k views

Determining Specific File Responsible for High I/O

This is a simple problem but the first time I've ever had to actually fix it: finding which specific files/inodes are the targets of the most I/O. I'd like to be able to get a general system overview, ...
1
vote
1answer
171 views

Establishing I/O Patterns for an Application

Are there any system tools that allow you to profile an application's usage of storage? Basically, I'm looking for information on determining whether there are more large sequential reads, tiny ...
11
votes
2answers
286 views

Locate occasional CPU kernel hog

I have a 2.6.35 PREEMPT kernel running on moderate-speed ARMv7 processor. About once every 100 - 125s, something causes the kernel to fail to process some audio-related drivers sufficiently quickly to ...
1
vote
1answer
79 views

Where is the documentation for perf events?

I cant seem to find documentation on the events listed when you do perf list; can someone point me in the right direction?
1
vote
1answer
374 views

Where to start profiling Linux kernel?

What are the standard and conventional ways of profiling the Linux kernel? I know there is perf tool but is there anything else?
40
votes
7answers
64k views

How to get execution time of a script effectively?

I would like to display the completion time of a script. What I currently do is - #!/bin/bash date ## echo the date at start # the script contents date ## echo the date at end This just show's ...
4
votes
1answer
246 views

Linux mutex spins [closed]

On Solaris I can use mpstat to see the smtx (i.e., spins on mutex or in other words locks not acquired on the first try) value. This value increasing indicates that swap is being hit too frequently ...
5
votes
2answers
3k views

Detailed Per-Process Profiling

I am looking for a way to profile a single process including time spent for CPU, I/O, memory usage over time and optionally system calls. I already know callgrind offering some basic profiling ...
2
votes
1answer
185 views

How to find what's hogging what resources? [closed]

I've found lots of similar questions, but nothing that's exactly right. I'm trying to figure out what's making one server run slower than another. I'm hoping for something that would say something ...
2
votes
1answer
635 views

How to get the maximum virtual set size of a unix process during its lifetime?

The time command includes a format parameter "M", which according to the time man page on Linux is used for the following: Maximum resident set size of the process during its lifetime, in Kilobytes. ...
0
votes
1answer
783 views

buildroot/busybox: launch bootchartd on startup

I built a custom linux image using buildroot and busybox. To speed up the boot process I'd like to use bootchartd (built-in version of busybox) to profile the process. However bootchartd is not ...
5
votes
3answers
2k views

How can I profile a shell script?

I have several programs that i'm executing in a shell script: ./myprogram1 ./myprogram2 ... I know that I can profile each individual program by editing the sourcecode, but I wanted to know if ...
8
votes
2answers
553 views

How to make linux 'perf record' work for libc and libstdc++ symbols?

I'm using perf record -g on x86-64 Linux to profile a program. Several symbols in libc or libstdc++ have 0 as a parent: __GI___strcmp_ssse3 (libc) and strcmp@plt (libstdc++) for example. (I can ...
7
votes
3answers
542 views

What are some good profiling tools for Linux?

I'm looking for some good profiling tools for Linux like OProfile. What I would like to see is how the operating system manages the interrupts, cache, read/writes, etc (lots of other intricate ...
5
votes
2answers
2k views

Command to measure TLB misses on LINUX?

Could some one direct me to a command to measure TLB misses on LINUX, please? Is it okay to consider (or approximate) minor page faults as TLB misses?
3
votes
2answers
596 views

Measuring last-level cache misses through PAPI on AMD machine running Ubuntu Linux

It looks like by default PAPI (Performance Application Programming Interface) is not supporting to measure last-level cache misses (L3) on my AMD machine running Ubuntu Linux. However, I can measure ...
1
vote
2answers
2k views

How to analyze profile data from `perf record --a` (system-wide collection)?

I am using perf from linux-2.6.36-gentoo-r4. The /proc/sys/kernel/perf_event_paranoid is set to 0, so there should be no problems from there. Because long-running application I am profiling ...
8
votes
2answers
631 views

Detect if an ELF binary was built with gprof instrumentation?

Is it possible to check if given program was compiled with GNU gprof instrumentation, i.e. with '-pg' flag passed to both compiler and linker, without running it to check if it would generate a ...
3
votes
1answer
112 views

sources for doing profiling of kernel portions?

Related to my previous post. I did not find any specific driver for which I can do profiling and benchmarking. However there is a one driver jffs2 filesystem for flash devices but I didn't know about ...