> Pavel,
>
> The architecture of the RAID drivers is extremely primitive,
Jeff,
This is just to note that I take personal offence from the *extremely
primitive* description. The current RAID architecture supports:
1. Compatibility with *every* block device driver -- every block device
can be part of the RAID array, be it SCSI, IDE, whatever.
2. Compatibility with *every* file system, which just sees the
RAID array as any other block device.
The above two features are achieved especially because the RAID code
sits just at the request queueing layer, above the drivers but below
the buffer/page cache and filesystems.
In addition, the RAID subsysystem provides the designed redundancy,
good performance, and support for hot rebuilding. The RAID-5 code,
for example, includes "full stripe" write optimization, read-modify-write
cycles, completion-write cycles, maintains an internal cache, etc.
Perhaps primitive, but clearly not an *extremely primitive* architecture.
Regards,
Gadi
> and
> limiting, and does not handle hotixing or distributed cases. There are
> dependencies on NWFS for controlling th mirroring. At present, the
> buffer cache does not support a logical semantic. It's true we could
> "stand on our heads" and map something very unnatural to what's there,
> but there are still issues and problems with the buffer cache and how it
> acts. There are also config issues. NWFS style allows end users to
> configure and use mirroring on Linux without needing a degree in
> astro-physics to understand how to set it up.
>
> We basically need a smarter cache than what's there. Eventually, Linux
> will evolve there (Since the page cache already resembles what's in NT).
>
> Jeff
>
>
> Pavel Machek wrote:
> >
> > Hi!
> >
> > > Which is exactly what we have concluded. We probably should provide
> > > some input into 2.5 for our needs. We would be happy to put in the
> > > subsystems we require. The benefit to Linux would be a built in fault
> > > tolerant redirector within the cache (which is useful for this and
> > > distributed support -- time to start thinking about this). This would
> > > allow all of the Linux file systems to support multi-segmented
> > > mirroring and fault tolerant failover without the RAID drivers.
> >
> > What is problem with the RAID drivers?
> > Pavel
> > --
> > I'm really pavel@ucw.cz. Look at http://195.113.31.123/~pavel. Pavel
> > Hi! I'm a .signature virus! Copy me into your ~/.signature, please!
> >
> > -
> > To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> > the body of a message to majordomo@vger.rutgers.edu
> > Please read the FAQ at http://www.tux.org/lkml/
>
> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.rutgers.edu
> Please read the FAQ at http://www.tux.org/lkml/
>
>
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/