Current-Users archive

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index][Old Index]

Re: SSD



2009/7/13 Miles Nordin <carton%ivy.net@localhost>:
>>>>>> "ms" == Michal Suchanek <hramrach%centrum.cz@localhost> writes:
>
> Â Âms> Slow write performance tends to be the major factor behind
> Â Âms> slow adoption of SSDs
>
> People on the ZFS list say the SSD's with SATA interface are always
> faster in io/s (like 10 - 50x faster) compared to single spindles of
> high-RPM SAS, and some of them are faster for streaming write
> throughput as well.

It depends on your application and your drives. High end SSDs might be
blazingly fast but we are talking about some consumer drive here. And
these tend to be somewhat slow in practice.

Currently if you replace a consumer SATA drive with a consumer SSD in
a Windows box the performance drop is sharp.

If that is because it does not like weird IO patterns or because it is
simply not so fast doing aggressive caching in the OS should work
around either flaw. Sure, Windows is very poor at handling disk IO but
the disk firmware should hide implementation details from the OS.

Thanks

Michal


Home | Main Index | Thread Index | Old Index