Re: [PATCH 0/3] map multiple blocks in get_block() and mpage_readpages()

[Peter Staubach]

Badari Pulavarty wrote:

> Thanks. Only current issue Nathan raised is, he wants to see
> b_size change to u64 (instead of u32) to support really-huge-IO
> requests. Does this sound reasonable to you ?

I believe that the various read and write system calls impose a 32 bit limit
on the size of the i/o request, so you may need to look at that too.

Increasing the size of b_size would address a bug which exists when trying
to read more than 4GB from a block device which is greater than 4GB in size.
Currently, that bug is masked because the maximum system call size is
arbitrarily limited.

   Thanx...

      ps
-
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/