0

I'm running 5.3.9-1~dotdeb.3, with APC 3.1.9. APC cache gets totally fragmented after a 2hours of running. Isn't the apc.user_ttl = 0 supposed to keep the files cached until APC is restarted - and prevent this much fragmentation? What am I doing wrong?

apc.enabled = 1
apc.shm_segments = 1
apc.shm_size = 320M
apc.cache_by_default=1
apc.stat = 0
apc.user_ttl = 0
apc.num_files_hint = 1024
apc.mmap_file_mask = /tmp/apc.XXXXXX
apc.enable_cli = 0

Here is a screenshot:

enter image description here

1
  • I've managed to bring down the fragmentation to 10% by setting pm.max_requests to a higher value (from 50 to 250). Although this does crash php processes more often (http 502, recv() upstream errors).
    – bureq
    Feb 15, 2012 at 2:11

1 Answer 1

0

Did you raised the kernel shmmax parameter to server 320M for shared memory as well? By default it's around 8MB.

Put the following into /etc/sysctl.conf:

kernel.shmmax = 335544320

and execute

sysctl -p

as root.

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .