632 reputation
11336
bio website craters-of-the-mind.blogspot.…
location Moscow, Russia
age 33
visits member for 5 years, 7 months
seen Nov 18 at 16:26

:-)

mailto: ag@logiceditor.com


Dec
13
comment How to reduce number of sockets in TIME_WAIT?
@Kyle: 10% according to netstat, instead of 400% according to Munin. I wonder, is this a Munin bug?
Dec
13
comment How to reduce number of sockets in TIME_WAIT?
@Kyle: I checked, it does not seem to be a grep issue. Rougly 5K connections total, 500 of them are in TIME_WAIT.
Dec
13
comment How to reduce number of sockets in TIME_WAIT?
@Kyle: No. Just tried running it as root (with sudo, and then from the root shell) — no significant difference. 429—480 sockets.
Dec
13
comment How to reduce number of sockets in TIME_WAIT?
@Kyle: even if my conntrack_count is far from the limit, perhaps the extra monitoring wouldn't hurt — to play safe.
Dec
13
comment How to reduce number of sockets in TIME_WAIT?
@Kyle: My nf_conntrack_count is 33789 now.
Dec
13
comment How to reduce number of sockets in TIME_WAIT?
@Kyle: Please advise, what line should I set my automonitoring to watch for in /var/log/messages to catch possible conntrack issues? Will "Can't alloc conntrack" do? Or something broader/narrower?
Dec
13
comment How to reduce number of sockets in TIME_WAIT?
@Kyle: Thanks. It seems that I'm not bumping against it (yet). I've got conntrack_max at 65536 and no messages in dmesg since boot 3 days ago.
Dec
13
comment How to reduce number of sockets in TIME_WAIT?
@Kyle: by conntrack you mean something like this? serverfault.com/questions/189796/error-cant-alloc-conntrack/…
Dec
13
comment How to reduce number of sockets in TIME_WAIT?
If 32K TIME_WAIT is a hard limit, I feel that getting yet another IP for machine would not work, and I would have to get a whole second front-end machine... That's a pity, event the first one is working at most at 20% of estimated capacity, judging by CPU and memory load...
Dec
13
comment How to reduce number of sockets in TIME_WAIT?
@Kyle: TCP disruption? I don't like the sound of this... :-(
Dec
13
revised How to reduce number of sockets in TIME_WAIT?
fixed to fit on page
Dec
13
revised How to reduce number of sockets in TIME_WAIT?
230 requests per second is in the peak hours
Dec
13
comment How to reduce number of sockets in TIME_WAIT?
@Kyle: I'm not sure that there is a cap at 32K sockets in TIME_WAIT. (At least, my graph does not show it — it seems to be just the natural load profile that incidentally gets flat.) Well, I expect higher load tomorrow, will see...
Dec
13
comment How to reduce number of sockets in TIME_WAIT?
@Kyle: it seems that by increasing net.ipv4.tcp_fin_timeout, I'll increase the memory consumption. What will I gain instead?
Dec
13
comment How to reduce number of sockets in TIME_WAIT?
@Kyle: sorry, I'm confused about your Update 2. How to keep net.ipv4.tcp_fin_timeout "at the 32k cap", when it is in seconds?
Dec
13
comment How to reduce number of sockets in TIME_WAIT?
RRD (Munin) is set to GAUGE
Dec
13
comment How to reduce number of sockets in TIME_WAIT?
@Kyle: The graph was captured when the TCP settings, listed in question, were in effect.
Dec
13
revised How to reduce number of sockets in TIME_WAIT?
clarified about graph
Dec
13
comment How to reduce number of sockets in TIME_WAIT?
@Kyle: sorry for a stupid question (I'm on a cargo-cult level here so far, unfortunately), but what exactly should I expect to see when I change net.ipv4.tcp_fin_timeout from 1 to 20?
Dec
13
comment How to reduce number of sockets in TIME_WAIT?
@Kyle: I probably should replace TCP socket between load balancer and worker on the same machine with domain socket as well.