Re: [PATCH] ide write barrier support

[Daniel Phillips]

On Monday 27 October 2003 11:29, Lars Marowsky-Bree wrote:
> On 2003-10-26T23:06:53,
>
>    Daniel Phillips <phillips@xxxxxxxx> said:
> > Not entirely within the multipath virtual device, that's the problem.
> > If it could stay somehow all within one device driver then ok, but
> > since we want to build this modularly, as a device mapper target,
> > there are API issues.
>
> Are you seeing problems with the write-ordering properties of
> multipathing? If so, what is the issue with handling them in the DM
> target once?

No, no problem.  A multipath write barrier can be handled by blocking incoming 
writes in the target and waiting for all outstanding writes to complete.  I'd 
prefer to let the write barrier flow down the pipe to the SCSI disk if I 
could, but there are technical challenges.  Mainly I need to know if an 
ordered write is able to read its buffer into the drive's cache while it is 
waiting for preceding commands to complete; if so it would be worth putting 
the effort into developing the flow-through scheme.

Regards,

Daneil

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/