file side memcached

Artur Bergman abergman at
Fri Jun 2 00:15:43 UTC 2006

On Jun 1, 2006, at 4:50 PM, rm_memcached at wrote:

> Why not just run memcached with a larger memory size than physical  
> memory and let the kernel's swaping logic handle which blocks and  
> when get swapped out?
> I'd guess that memcached's memory access pattern (slabs and hash  
> tables) are pretty friendly to the virtual memory system, at least  
> compared to trees or other structures that need walking.
> Currently I note that some memory on the systems where I have  
> memcached running is swapped out - not sure if that's memcached  
> memory or not; but I'd guess so since the cache is so large at  
> least parts of it are likely to be relatively infrequently used.

What kernel do you trust to do any kind of swapping in a production  


More information about the memcached mailing list