i'd like to measure the total memory (like RAM) used by a program during its execution. Ideally, something like time that runs the program and print stats when it exits.

Is there such a standard tool in the unix / linux / bsd world? Thanks.


the program i'm trying to profile takes fractions of a second to execute, so anything that implies "while running check this" won't work. that's why i'm asking for a "time" like tool.


The strace command might be of some use. It will show you in what system calls the time is being taken up:

$ strace -cTv zip /tmp/test.zip /usr/share/dict/words
  adding: usr/share/dict/words (deflated 73%)
% time     seconds  usecs/call     calls    errors syscall
------ ----------- ----------- --------- --------- ----------------
100.00    0.000055           2        34           read
  0.00    0.000000           0        21           write
  0.00    0.000000           0        12         3 open
  0.00    0.000000           0         9           close
  0.00    0.000000           0         3         3 access
  0.00    0.000000           0         1           rename
  0.00    0.000000           0         3           brk
  0.00    0.000000           0         1           gettimeofday
  0.00    0.000000           0         4           munmap
  0.00    0.000000           0         3           mprotect
  0.00    0.000000           0         6           _llseek
  0.00    0.000000           0         6           rt_sigaction
  0.00    0.000000           0        12           mmap2
  0.00    0.000000           0         8         1 stat64
  0.00    0.000000           0         1         1 lstat64
  0.00    0.000000           0         9           fstat64
  0.00    0.000000           0         1           fcntl64
  0.00    0.000000           0         1           set_thread_area
------ ----------- ----------- --------- --------- ----------------
100.00    0.000055                   141         8 total
  • how can i then relate time with memory usage? – pistacchio Jan 5 '10 at 14:37
  • If you've run it with the -c. summary you now have a list of what calls are being made. Calls like mmap2, brk indicate memory assignment (there may be others). Run under strace again but with something like strace -o /tmp/program.trc ... then you will be able to see what brk, mmap are assigning. If you are having problems with something like this you should refer it to the developer of the programs you are running, they should be able to help. – davey Jan 5 '10 at 15:33

On Linux you can read /proc/[pid]/status; the VmPeak field is the maximum virtual memory size, VmHWM is the maximum resident set size.

The getrusage() syscall might, or might not, help. The struct rusage contains e.g. a maxrss field, but at least on Linux this is never filled in.


If you don't mind repeating the execution a few times you can use ulimit -Hv to set the memory limit for the shell (in Bash) and then binary search the minimum when the application successfully exits.


I'd suggest valgrind. The massif app will report heap usage stats, at least.


No standard tool except ps (which is not so standard in regards to options/output too). This will not give you time-like usability.

You can use nmon to gather system-wide statistics, it captures memory usage of processes (it will be probably useless for short-lived processes). It supports many platforms.


You could try writing your own script that could do this. It could get the PID of the launched program and use ps or /proc/[pid]/status to get memory information about it. Of course this wouldn't totally characterize the memory usage but it should give you a good idea.


Just use process accounting (acct or psacct depending on your distribution). The process accounting log includes "memory used" statistics.

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.