Scyld: memory leak or just caching?
Mike Weller
weller at zyvex.com
Wed Jun 27 14:21:01 PDT 2001
Sean wrote:
> Sounds like just caching to me. However, if you want to double check,
> write a simple program that malloc()'s about 100M, bpsh it over there
> and see what happens.
Ok, I wrote a program to allocate 100M of RAM. "ps -leaf" reports
100M used by the program (taking SZ * 4096k/page). However, "free"
reports an increase of only 100k, and no swap was used. Does the
kernel preallocate more RAM than it needs, and then gives it to
processes that need it? How can I learn more about kernel memory?
"ps" is uninformative.
Below is some of the info I captured :
[root at beowulf ~]# cat /home/malloc.c
#include <malloc.h>
#define NUM_MALLOCS 1
int main( )
{
int x;
for( x = 0; x < NUM_MALLOCS; ++x )
malloc( 1024 * 1024 * 100 );
sleep( 100000 );
return( 0 );
}
[root at beowulf ~]# bpsh 2 free
total used free shared buffers cached
Mem: 1572388 981924 590464 0 852724 17512
-/+ buffers/cache: 111688 1460700
Swap: 2097136 4 2097132
[root at beowulf ~]# bpsh 2 /home/malloc &
[root at beowulf ~]# bpsh 2 free
total used free shared buffers cached
Mem: 1572388 982032 590356 0 852724 17512
-/+ buffers/cache: 111796 1460592
Swap: 2097136 4 2097132
root 137 15 0 Jul12 ? 00:00:00 ps -eaf
root at beowulf /root # bpsh 2 ps -leaf|egrep "SZ|malloc"
F S UID PID PPID C PRI NI ADDR SZ WCHAN STIME TTY TIME CMD
040 T root 136 15 0 70 0 - 25871 109ec7 Jul12 ? 00:00:00 /home/malloc
root at beowulf /root # bpsh 3 free
total used free shared buffers cached
Mem: 1572388 104528 1467860 0 51116 17860
-/+ buffers/cache: 35552 1536836
Swap: 2097136 0 2097136
root at beowulf /root # bpsh 3 /home/malloc &
root at beowulf /root # bpsh 3 free
total used free shared buffers cached
Mem: 1572388 104604 1467784 0 51116 17860
-/+ buffers/cache: 35628 1536760
Swap: 2097136 0 2097136
--
Michael J. Weller, M.Sc. office: (972) 235-7881 x.242
weller at zyvex.com cell: (214) 616-6340
Zyvex Corp., 1321 N Plano facsimile: (972) 235-7882
Richardson, TX 75081 icq: 6180540
More information about the Beowulf
mailing list