Sprays were on, but our community isn't that big and it doesn't tend to spam spray all that much. Still a good advice. I'll keep an eye on the folder and trim it from time to time. I was using iotop and ioping to track my i/o activities but iotop doesn't show latency so it was only useful to check if the stuttering was related to I/O. Ioping did the trick to confirm the CPU was waiting for the disk to do its reading and writing.
Yun, the read ops are mainly during map changes, as far as I know. It definitely worths to keep an eye on, since slow map changes usually cause the players to think the server crashed and move on. Thanks for the inputs. It's nice to have some numbers to work with even if they're not so precise and directly related to a single server. I actually talked to the VPS provider and he moved my server to another node (less crowded one) and here's the result: > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > *4.0 kb from . (ext4 /dev/ploop53496p1): request=8152 time=338 us4.0 kb > from . (ext4 /dev/ploop53496p1): request=8153 time=288 us 4.0 kb from . > (ext4 /dev/ploop53496p1): request=8154 time=275 us4.0 kb from . (ext4 > /dev/ploop53496p1): request=8155 time=318 us4.0 kb from . (ext4 > /dev/ploop53496p1): request=8156 time=413 us4.0 kb from . (ext4 > /dev/ploop53496p1): request=8157 time=461 us 4.0 kb from . (ext4 > /dev/ploop53496p1): request=8158 time=246 us4.0 kb from . (ext4 > /dev/ploop53496p1): request=8159 time=322 us4.0 kb from . (ext4 > /dev/ploop53496p1): request=8160 time=275 us4.0 kb from . (ext4 > /dev/ploop53496p1): request=8161 time=427 us 4.0 kb from . (ext4 > /dev/ploop53496p1): request=8162 time=327 us4.0 kb from . (ext4 > /dev/ploop53496p1): request=8163 time=331 us4.0 kb from . (ext4 > /dev/ploop53496p1): request=8164 time=330 us4.0 kb from . (ext4 > /dev/ploop53496p1): request=8165 time=291 us 4.0 kb from . (ext4 > /dev/ploop53496p1): request=8166 time=411 us4.0 kb from . (ext4 > /dev/ploop53496p1): request=8167 time=335 us4.0 kb from . (ext4 > /dev/ploop53496p1): request=8168 time=276 us4.0 kb from . (ext4 > /dev/ploop53496p1): request=8169 time=904 us 4.0 kb from . (ext4 > /dev/ploop53496p1): request=8170 time=282 us4.0 kb from . (ext4 > /dev/ploop53496p1): request=8171 time=295 us4.0 kb from . (ext4 > /dev/ploop53496p1): request=8172 time=272 us4.0 kb from . (ext4 > /dev/ploop53496p1): request=8173 time=297 us 4.0 kb from . (ext4 > /dev/ploop53496p1): request=8174 time=304 us4.0 kb from . (ext4 > /dev/ploop53496p1): request=8175 time=313 us4.0 kb from . (ext4 > /dev/ploop53496p1): request=8176 time=246 us4.0 kb from . (ext4 > /dev/ploop53496p1): request=8177 time=239 us 4.0 kb from . (ext4 > /dev/ploop53496p1): request=8178 time=266 us4.0 kb from . (ext4 > /dev/ploop53496p1): request=8179 time=524 us4.0 kb from . (ext4 > /dev/ploop53496p1): request=8180 time=316 us4.0 kb from . (ext4 > /dev/ploop53496p1): request=8181 time=432 us 4.0 kb from . (ext4 > /dev/ploop53496p1): request=8182 time=278 us4.0 kb from . (ext4 > /dev/ploop53496p1): request=8183 time=329 us4.0 kb from . (ext4 > /dev/ploop53496p1): request=8184 time=279 us* It's been like this for a couple of hours so I guess it worked nicely. It still has a couple of > 15ms (around 40~50ms) peaks but they are very rare now so I guess it's all good. I'll keep monitoring it though. I'm not 100% sure this will solve the stuttering problem. I'll check it later on and get back here to report. Hope this helps people with similar problems. _pilger _______________________________________________ To unsubscribe, edit your list preferences, or view the list archives, please visit: https://list.valvesoftware.com/cgi-bin/mailman/listinfo/hlds_linux
