Description of problem: System swaps too aggressively and only utilises +-30% of available system memory (reading discussion threads indicates that this only shows up when the system has more than 1GB of RAM). Version-Release number of selected component (if applicable): RHEL4.3 kernel-2.6.9-34.0.1.EL How reproducible: Very Steps to Reproduce: 1. AMD Athlon 64 3000+ Processor 2. nVidia nForce4 chipset (ASUS A8N5X Motherboard) 3. 1GB of RAM Actual results: put load on the server and available system memory is +-750KB. Swap utilisation increases and processes increase slowing the system due to high iowait (aggressive memory swapping) Expected results: Should only start swapping once system memory starts getting low, no? Additional info: System was previously running RHEL3.7 without problems, MRTG display of available system memory shows the problem quite clearly (attached). RedHat do have a document called 'Understanding Virtual Memory In Red Hat Enterprise Linux 4' but I simply don't understand what I should be changing: http://people.redhat.com/nhorman/papers/rhel4_vm.pdf
Created attachment 130298 [details] MRTG graph of available system memory show system not using everything before starting to aggressively swap
hmmm...this looks a lot like bz #188141. Can you please try the U4 beat kernel and let me know if this fixes it for you. The kernel is 2.6.9-37. http://people.redhat.com/~jbaron/rhel4/
Found additional information from other people experiencing the same issue in CentOS 4: Bug ID: 0001174 Summary: Extremely high load average and 100% CPU utilization URL: http://bugs.centos.org/view.php?id=1174
Yes, i'm aware of this. I'm pretty sure the U4 beta kernel mention =ed in comment #2 will resolve this issue. Also, just to be clear no VM tuning should be needed.
The kernel-2.6.9-37.EL perfectly resolves the problem we were experiencing. Many thanks for your prompt assistance!
glad to hear that :) *** This bug has been marked as a duplicate of 188141 ***