i think that you have a problem in arp, or tcp stack size check netstat -a when this problem happen after 2 minutes (is you tcp with 2minutes timeout? )
2011/2/7 Roberto Spadim <[email protected]>: > for rtos: > EARPFULL (104) > > ARP table full. This error is reported by send when the ARP cache is > full. If this error occurs, increase CFG_ARPCLEN. > > > for linux you can see this message in /var/log/messages: > "21 messages suppressed Neighbour table overflow." > use this to get max values of arp table: > # echo 16384 > /proc/sys/net/ipv4/neigh/default/gc_thresh1 > # echo 32768 > /proc/sys/net/ipv4/neigh/default/gc_thresh2 > # echo 65535 > /proc/sys/net/ipv4/neigh/default/gc_thresh3 > > > > in windows i don´t know what happen... :/ sorry > but check system logs > > > 2011/2/7 <[email protected]>: >> >> Comment #5 on issue 122 by [email protected]: failed to write, and not >> due blocking: No error >> http://code.google.com/p/memcached/issues/detail?id=122 >> >> Thanks. Could you please explain what are the possible problems with arp >> table? If I use UDP, how can I make sure it's working fine without the help >> of the telnet interface? >> >> I'm using Memcached 1.4.5 one W2K8 Server R2. And I am testing the memcached >> server from the local machine using telnet. It's giving me the following >> error when I send "STATS" in telnet: >> >> <1352 server listening (auto-negotiate) >> <1368 send buffer was 8192, now 268435456 >> <1368 server listening (udp) >> <1368 server listening (udp) >> <1368 server listening (udp) >> <1368 server listening (udp) >> <1380 new auto-negotiating client connection >> 1380: Client using the ascii protocol >> <1380 stats >> Failed to write, and not due to blocking: No error >> <1380 connection closed. >> >> >> >> Thanks again. >> >> >> > > > > -- > Roberto Spadim > Spadim Technology / SPAEmpresarial > -- Roberto Spadim Spadim Technology / SPAEmpresarial
