Re: Bio pool & scsi scatter gather pool usage

Alan Cox (alan@lxorguk.ukuu.org.uk)
Fri, 19 Apr 2002 16:57:49 +0100 (BST)


> Just looking at how my disks ended up partitioned not many of them are
> even on 4K boundaries, so any sort of concat built on them would
> have a boundary case which required such a split - I think, still
> working on my caffine intake this morning.

Alignment and concatenation are different things altogether. On the whole I
can blast 64K chunks on a 512 byte alignment out of my controllers. The
partitioning doesn't bother me too much. Do we even want to consider a
device that cannot hit its own sector size boundary ?

Oh and the unusual block size stuff seems to be quite easy for the bottom
layers. The horror lurks up higher. Most file systems can't cope (doesn't
matter too much), isofs can be mixed block size (bletch) but the killer
seems to be how you mmap a file on a device with 2326 byte sectors sanely..
(Just say no ?)
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/