Do you mean in terms of debug after a failure? I can resubmit the patch with 
the scsi_sense_hdr buffer still in place. I just wanted to keep the first draft 
simple to get the concept across. 

Todd Brandt
Linux Kernel Developer OTC, Hillsboro OR
https://opensource.intel.com/linux-wiki/ToddBrandt


________________________________________
From: linux-scsi-ow...@vger.kernel.org [linux-scsi-ow...@vger.kernel.org] on 
behalf of Oliver Neukum [oneu...@suse.de]
Sent: Friday, August 02, 2013 5:42 AM
To: Brandt, Todd E
Cc: linux-...@vger.kernel.org; linux-scsi@vger.kernel.org
Subject: Re: [PATCH] Hard disk S3 resume time optimization

On Thu, 2013-08-01 at 23:40 +0000, Brandt, Todd E wrote:
> This patch is a potential way to reduce the S3 resume time for SATA drives. 
> Essentially this patch removes the hard disk resume time from the total 
> system resume time, with the disks still taking as long to come back online 
> but in the background.
>
> The major bottleneck is in the ata port resume which sends out a wakeup 
> command and then waits up to several seconds for the port to resume. This 
> patch changes the ata_port_resume_common function to be non blocking. The 
> other bottleneck is in the scsi disk resume code, which issues a a command to 
> startup the disk with blk_execute_rq, which then waits for the command to 
> finish (which also depends on the ata port being fully resumed). The patch 
> switches the sd_resume function to use blk_execute_rq_nowait instead (the 
> underlying code is identical to sd_resume, but is changed to non-blocking).

But how do we know the command has succeeded?

        Regards
                Oliver


--
To unsubscribe from this list: send the line "unsubscribe linux-scsi" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line "unsubscribe linux-scsi" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Reply via email to