Messages in this thread | | | Date | Tue, 23 Mar 1999 07:38:28 -0500 (EST) | From | Eric Youngdale <> | Subject | Re: disk head scheduling |
| |
Forgive me for jumping in late on this one - I have just one observation. It isn't clear to me that it would work well to have a single queue per device, at least in all cases. Some host adapters have limits (sometimes in hardware, not just a driver limitation) on the maximum number of outstanding commands, and it would take a bit of hacking to find a way to pick commands from multiple queues in order to prevent starvation. For host adapters that have no such limits, then a per-device queue would work just fine.
-Eric
On Tue, 23 Mar 1999, Rogier Wolff wrote:
> Linus Torvalds wrote: > > > > > > On Tue, 23 Mar 1999, Rogier Wolff wrote: > > > > > > > > This is what we do for block sizes, and it's a complete horror to maintain > > > > and debug. Even worse: it forces us to have 8-bit minor and major numbers > > > > forever. > > > > > > Nah! It is the device drivers responsibility to allocate enough > > > space. So if a new SCSI disk driver notices 20 disks, and therefore > > > wants 320 minors, it should allocate the array to be 320 entries. > > > > Umm.. > > > > What if we have sparse minor numbers? > > Let me start by saying I agree completely. You convinced me in one > go. > > Ehhmm. You're paraphrasing the paragraph that I had written below the > one you quoted. > > Roger. > > -- > ** R.E.Wolff@BitWizard.nl ** http://www.BitWizard.nl/ ** +31-15-2137555 ** > *-- BitWizard writes Linux device drivers for any device you may have! --* > ------ Microsoft gives you Windows, Linux gives you the whole house ------ > > > - > To unsubscribe from this list: send the line "unsubscribe linux-kernel" in > the body of a message to majordomo@vger.rutgers.edu > Please read the FAQ at http://www.tux.org/lkml/ >
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |