Re: Implementation of MemCached in a high volume, large database, online web system (site and service)

2010-09-28 Thread ligerdave
it depends on your architecture and what type of contents you serve. for identical information, i assume the response page once created, the content wont change or in every x mins, html header and server caching stage should be modified according to the needs. memcached is good for constant

Re: Memcached make many SI (Software Interrupts)

2010-09-28 Thread Jay Paroline
We've run into this exact same issue and narrowed it down to the NIC, but don't really know where to go from there. I'm going to look up Dormando's suggestions but if anyone else has experience with this and can point us in the right direction, it would be greatly appreciated. Thanks, Jay On

Re: instrumenting memcached with sFlow

2010-09-28 Thread neilmckee
The following git fork includes these sFlow changes: http://github.com/sflow/memcached To run with sFlow enabled: ./autogen.sh ./configure --enable-sflow make ./memcached -u nobody -o sflow=on Neil On Sep 27, 9:59 am, neilmckee neil.mckee...@gmail.com wrote: I posted this patch as an

Re: Memcached make many SI (Software Interrupts)

2010-09-28 Thread Rohit Karlupia
This is a bit complicated and I still don't understand it fully, but here are few pointers. BTW all that follows has nothing specific to memcached. 1) cat /proc/interrupts This will show the list of which core(s) are handling the interrupts for given devices. Check eth0/eth1 whichever you

Re: Memcached make many SI (Software Interrupts)

2010-09-28 Thread dormando
It's a big topic, here's the stuff to google: - cat /proc/interrupts - look for eth0, eth1, etc. If you have one interrupt assigned to eth0, you have a single-queue NIC. If you have many interrupts that look like eth0-0, eth0-1, etc, you have a multi-queue NIC. These can have their interrupts