0

I have a 2 cpu server running SLES 11.4 x86-64 and it has 1.5 tb of RAM.

>free -g

             total       used       free     shared    buffers     cached
Mem:          1514        284       1230        268          0        269

Running a number crunching software, which has worked fine in the past, giving us problems lately running slow and crashing, trying to figure out why.

I tried to do a echo 3 > /proc/sys/vm/drop_caches and that did not work. It usually puts cached to zero, did not work this time.

my questions are:

  • what would cause echo 3 > /proc/sys/vm/drop_caches not to work?
  • does the cached value even matter?
  • is there another way to accurately find out current state of RAM used/cached/whatever besides the free command?
  • given this type of problem and troubleshooting, any recommendation?
Rui F Ribeiro
  • 55,929
  • 26
  • 146
  • 227
ron
  • 5,749
  • 7
  • 48
  • 84

1 Answers1

0

for the crashing part check dmesg, for the slowness try vmstat 2 and keep it running when you execute the crunshing app, it should shed some light on what the bottleneck might be.

Zaid Amireh
  • 1
  • 1