I have a simple question in mind. I want to introduce client side caching in any network or cluster file system. The caches are in-memory cache not secondary cache as in AFS but as sprite. My question is all the cache is in kernel space and if large file happens to mmap or read/write say 2 GB etc.
Generally the file blocks are cached, not the entire file. How much you can cache is limited by things like cache size, caching policies etc.
BTW, Isn't sprite a log structured file system ?
...
So how much shall i keep my cache size to have best performance.
Run benchmarks with varying cache size & you can arrive at a suitable size. Or the size can be dynamic & can be expanded or shrunk depending on memory available.
--Swapnil
-- Kernelnewbies: Help each other learn about the Linux kernel. Archive: http://mail.nl.linux.org/kernelnewbies/ FAQ: http://kernelnewbies.org/faq/
