Re: File Systems vs. Raw Devices

In article <2s2tai$a5n_at_ace.mid.net> rory_at_cronus (Rory Reynoldson) writes:
>hth (hhong_at_nova.umd.edu) wrote:
>: In article <1994May25.183843.15365_at_rossinc.com>,
>: Joel Gary <joelga_at_rossinc.com> wrote:
>: >In article <2rnj3g$npt_at_samba.oit.unc.edu> Harold.Bauer_at_launchpad.unc.edu (harold bauer) writes:
>: >
>: >> What are the performance gains (is there really a 50% gain in using
>: >> raw devices over file systems)?
>: >
>: >No, more like 10-15%, at least on BSD SunOS systems.
>
> Can't tell you on SunOS, but on the systems I've worked with
> we've seen much more than 50%.. (300% on HP-UX 8.0, about the
> same on SCO/Unisys SVR3). After about a year, we just started
> putting all Oracle databases on raw partitions by default.
>
> In my opinion, if a filesystem is going to have some OS type
> buffer cache, why have the OS and Oracle both caching? I can't
> take the caching away from Oracle, but I can take it away from
> Unix.

We don't disagree here, it just shows up the importance of testing for specific configurations/situations.

That HP-UX, a BSD filesystem, showed 300%, amazes me. I can only speculate about dueling caches... or testing methodology. ;-)

-- 
Joel Garry       joelga_at_amber.rossix.com       Compuserve 70661,1534
These are my opinions, not necessarily those of Ross Systems, Inc.
%DCL-W-SOFTONEDGEDONTPUSH, Software On Edge - Don't Push.