Romex Software Forum

I agree It's not easy - but it does take an effort to make something good. Currently L1 cache does not offer much more than windows cache. Compression would be a big advantage. There are open source libraries for most compression algorithms. You could add a compression type attribute to blocks - lik...

I want to request compression (with an option to turn it on/off, choose algorithm) for cache data (not meta data). ZFS is using compression for it's cache with near zero impact on performance/cpu usage with LZ4 compression - a really high speed algorithm. I don't know what's the license for it, but ...

I don't know how possible it is to cache network drives (like samba), but caching on the remote computer doesn't do much. If I share RAM drive it's still slow for small files. The bottle neck is the protocol. I don't know why, but it's extremely slow accessing 1000s of small files - like 10 to 100 t...

ok, but what about the option to not fetch from more than one partition of a specific physical drive at a time?

So if the user expects most of the written data to not be read (like log files), then he shouldn't enable write cache. If he expects that soon the written data will be read again (like temporary tables of database) then write cache could be enabled.

Hi, I have problem with prefetch. Sometime ago I requested that prefetch of the same physical drive don't happen on the same time to speed it up. In 3.0.2 that's not only not fixed, but it got worse. I have 2 partitions cached C: and E: of the same hard disk. C: is set to start prefetch at windows b...

Does L1 write cache actually do anything if it's not deferred? Does it really speed up anything if it has to write the cache to disk right away. Isn't that the same as if there is no write cache?

I fixed the problem. The partition was copied 1:1 from an SSD. It has been on the SSD for ages, so it got very fragmented. When I copied it to a HDD booting got so slow that it was past the delay of prefetching. Defragmenting fixed it. Now booting stops before prefetch starts.

Hi, Does primocache have an algorithm to reduce penalty of big files that are read only once or full hdd backups? In such case does primocache preserves most commonly used cache? If not you might want to implement something like ARC . In fewer words arc is divided to two sections - one for recently ...

The SSD is not loosing cache. The SSD itself is disappearing, which is hard disk problem not primocache. The problem I have is with prefetch kicking in the wrong moment, while OS still haven't finished loading. If you have a lot of ram and slow hard disk the OS loading time is bigger and it overlaps...