Re: queue_nr_requests needs to be selective

[Andrew Morton]

"Jeff V. Merkey" wrote:
> 
> The issue here is that it sleeps too much
> and what's really happening and that we are forcing 8 disk drives
> toshare 64/128 request buffers rather than provide each physical disk
> with what it really needs.

OK.  So would it suffice to make queue_nr_requests an argument to
a new blk_init_queue()?

-	blk_init_queue(q, sci_request);
+	blk_init_queue_ng(q, sci_request, 1024);

-