cvs commit: src/sys/sys mdioctl.h src/sys/dev/md md.csrc/sbin/mdconfig Makefile mdconfig.8 mdconfig.c

[Scott Long]

Brooks Davis wrote:
> On Fri, Sep 17, 2004 at 07:03:02PM +0200, Pawel Jakub Dawidek wrote:
> 
>>On Fri, Sep 17, 2004 at 10:29:47AM -0600, Scott Long wrote:
>>+> >Uhm, be aware that we are limited also to the size of individual
>>+> >swap disks.  31 bits of bytes/sectors/pages, not quite sure which.
>>+> >
>>+> 
>>+> 32 bits of pages, unless there is somewhere in the chain that the 
>>+> unsigned nature of the word is not being honored.
>>
>>Pages. It gives as maximum swap-backed device of 16TB. I tested it with
>>~15TB devices, so there is no signed/unsigned problem (which will limit
>>us to 8TB). Of course you can always (I hope) increase page size:)
> 
> 
> Given my quick read of the sunlabel format, there would be some value in
> 
>>16TB (17 would be sufficent) virtual disks.  Can we do a RAID0 of these
> 
> to get something that big?  I'm pretty sure sunlabel is limited to 14TB
> or 16TB so having something too big would be good for testing.
> 
> -- Brooks
> 

The 16TB limit comes not from md or from the block layer or disk layer
or whatnot, it comes from using 4k pages for swap backing and only being
about to address these pages using 32 bit numbers.  The important part
of the I/O path have already been converted (or are in the process of
being converted) to use 64 bit numbers.

Scott