Re: [PATCH] scsi_execute_async() should add to the tail of the queue

2006-12-20 Thread Dan Aloni
Steven Hayter wrote: Dan Aloni wrote: Hello, scsi_execute_async() has replaced scsi_do_req() a few versions ago, but it also incurred a change of behavior. I noticed that over-queuing a SCSI device using that function causes I/Os to be starved from low-level queuing for no justified reason.

Re: [PATCH] scsi_execute_async() should add to the tail of the queue

2006-12-20 Thread Jeremy Linton
So instead of adding a parameter, we can make scsi_execute_async() decide for itself based on the SCSI command, with read/write I/Os taking the lowest priority. This seems like a bad idea, I can come up with a number of cases where the priority of a request would better be optimized by a higher

Re: [PATCH] scsi_execute_async() should add to the tail of the queue

2006-12-20 Thread Steven Hayter
Dan Aloni wrote: Hello, scsi_execute_async() has replaced scsi_do_req() a few versions ago, but it also incurred a change of behavior. I noticed that over-queuing a SCSI device using that function causes I/Os to be starved from low-level queuing for no justified reason. I think it makes muc

Re: [PATCH] scsi_execute_async() should add to the tail of the queue

2006-12-19 Thread Jon Escombe
Jens Axboe wrote: > On Tue, Dec 19 2006, Arjan van de Ven wrote: >> On Tue, 2006-12-19 at 10:35 +0200, Dan Aloni wrote: >>> Hello, >>> >>> scsi_execute_async() has replaced scsi_do_req() a few versions ago, >>> but it also incurred a change of behavior. I noticed that over-queuing >>> a SCSI devic

Re: [PATCH] scsi_execute_async() should add to the tail of the queue

2006-12-19 Thread Jens Axboe
On Tue, Dec 19 2006, Jon Escombe wrote: > Jens Axboe wrote: > > On Tue, Dec 19 2006, Arjan van de Ven wrote: > >> On Tue, 2006-12-19 at 10:35 +0200, Dan Aloni wrote: > >>> Hello, > >>> > >>> scsi_execute_async() has replaced scsi_do_req() a few versions ago, > >>> but it also incurred a change of b

Re: [PATCH] scsi_execute_async() should add to the tail of the queue

2006-12-19 Thread Jens Axboe
On Tue, Dec 19 2006, Arjan van de Ven wrote: > On Tue, 2006-12-19 at 10:35 +0200, Dan Aloni wrote: > > Hello, > > > > scsi_execute_async() has replaced scsi_do_req() a few versions ago, > > but it also incurred a change of behavior. I noticed that over-queuing > > a SCSI device using that functi

Re: [PATCH] scsi_execute_async() should add to the tail of the queue

2006-12-19 Thread Arjan van de Ven
On Tue, 2006-12-19 at 10:35 +0200, Dan Aloni wrote: > Hello, > > scsi_execute_async() has replaced scsi_do_req() a few versions ago, > but it also incurred a change of behavior. I noticed that over-queuing > a SCSI device using that function causes I/Os to be starved from > low-level queuing fo

Re: [PATCH] scsi_execute_async() should add to the tail of the queue

2006-12-19 Thread Dan Aloni
Arjan van de Ven wrote: On Tue, 2006-12-19 at 10:35 +0200, Dan Aloni wrote: Hello, scsi_execute_async() has replaced scsi_do_req() a few versions ago, but it also incurred a change of behavior. I noticed that over-queuing a SCSI device using that function causes I/Os to be starved from lo

[PATCH] scsi_execute_async() should add to the tail of the queue

2006-12-19 Thread Dan Aloni
Hello, scsi_execute_async() has replaced scsi_do_req() a few versions ago, but it also incurred a change of behavior. I noticed that over-queuing a SCSI device using that function causes I/Os to be starved from low-level queuing for no justified reason. I think it makes much more sense to per

[PATCH] scsi_execute_async() should add to the tail of the queue

2006-12-19 Thread Dan Aloni
Hello, scsi_execute_async() has replaced scsi_do_req() a few versions ago, but it also incurred a change of behavior. I noticed that over-queuing a SCSI device using that function causes I/Os to be starved from low-level queuing for no justified reason. I think it makes much more sense to per