i am having an issue running memcached (v1.4.4) on multiple cores. here's my environment: windows server running VMware, so that only one core (out of eight) is enabled for the project that i am working on.
on the resource monitor, i can observe between eight and nine threads of memcached running at any given moment, even though the registry entry is not configured with the (-t) flag, so i would have expected the number of threads to be between four and five. (four is default, and as it turns out, it is not uncommon for memcached to run one additional thread than indicated) also, this version of memcached is running from a downloaded executable; it has not been compiled on the local windows server. the issue appears when enabling another core from the VM, memcached starts consuming 100% of the cpu; we have to disable the new core to go to a normal state from a performance standpoint. (note: i do not have any details on how this was done, so if the solution proves to be a graceful exit and restart, i would welcome more details) also, this is a production environment, so the server cannot be down for an extended period of time. i would welcome any ideas or suggestions -- --- You received this message because you are subscribed to the Google Groups "memcached" group. To unsubscribe from this group and stop receiving emails from it, send an email to memcached+unsubscr...@googlegroups.com. For more options, visit https://groups.google.com/groups/opt_out.
