* [patch 0/2] blkparse extensions for PC requests
@ 2008-01-07 7:50 Christof Schmitt
2008-01-11 9:10 ` Jens Axboe
` (2 more replies)
0 siblings, 3 replies; 4+ messages in thread
From: Christof Schmitt @ 2008-01-07 7:50 UTC (permalink / raw)
To: linux-btrace
As a follow-up to the blktrace extension for SCSI generic device files, here
are two patches that extend the tracing of PC requests in blkparse. When
tracing I/O to SCSI tape drives, the I/O trace only contains PC requests. These
extensions allow to get some more data from these traces.
--
Christof Schmitt
^ permalink raw reply [flat|nested] 4+ messages in thread* Re: [patch 0/2] blkparse extensions for PC requests
2008-01-07 7:50 [patch 0/2] blkparse extensions for PC requests Christof Schmitt
@ 2008-01-11 9:10 ` Jens Axboe
2008-01-14 6:38 ` Christof Schmitt
2008-01-14 7:53 ` Jens Axboe
2 siblings, 0 replies; 4+ messages in thread
From: Jens Axboe @ 2008-01-11 9:10 UTC (permalink / raw)
To: linux-btrace
On Mon, Jan 07 2008, Christof Schmitt wrote:
> As a follow-up to the blktrace extension for SCSI generic device
> files, here are two patches that extend the tracing of PC requests in
> blkparse. When tracing I/O to SCSI tape drives, the I/O trace only
> contains PC requests. These extensions allow to get some more data
> from these traces.
Patches look fine, however should it just not default do this
accounting? But only print the status fields, if we actually saw a PC
request.
--
Jens Axboe
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [patch 0/2] blkparse extensions for PC requests
2008-01-07 7:50 [patch 0/2] blkparse extensions for PC requests Christof Schmitt
2008-01-11 9:10 ` Jens Axboe
@ 2008-01-14 6:38 ` Christof Schmitt
2008-01-14 7:53 ` Jens Axboe
2 siblings, 0 replies; 4+ messages in thread
From: Christof Schmitt @ 2008-01-14 6:38 UTC (permalink / raw)
To: linux-btrace
On Fri, Jan 11, 2008 at 10:10:35AM +0100, Jens Axboe wrote:
> Patches look fine, however should it just not default do this
> accounting? But only print the status fields, if we actually saw a PC
> request.
My intent was to not change the data shown in the current summary
output. But you are right, it makes more sense to simply output the PC
summary when a PC request has been seen. I will post an updated patch
that does this without the --pc flag.
Christof Schmitt
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [patch 0/2] blkparse extensions for PC requests
2008-01-07 7:50 [patch 0/2] blkparse extensions for PC requests Christof Schmitt
2008-01-11 9:10 ` Jens Axboe
2008-01-14 6:38 ` Christof Schmitt
@ 2008-01-14 7:53 ` Jens Axboe
2 siblings, 0 replies; 4+ messages in thread
From: Jens Axboe @ 2008-01-14 7:53 UTC (permalink / raw)
To: linux-btrace
On Mon, Jan 14 2008, Christof Schmitt wrote:
> On Fri, Jan 11, 2008 at 10:10:35AM +0100, Jens Axboe wrote:
> > Patches look fine, however should it just not default do this
> > accounting? But only print the status fields, if we actually saw a PC
> > request.
>
> My intent was to not change the data shown in the current summary
> output. But you are right, it makes more sense to simply output the PC
> summary when a PC request has been seen. I will post an updated patch
> that does this without the --pc flag.
Yep I think so. If you send a patch that does that, I'll apply it.
--
Jens Axboe
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2008-01-14 7:53 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2008-01-07 7:50 [patch 0/2] blkparse extensions for PC requests Christof Schmitt
2008-01-11 9:10 ` Jens Axboe
2008-01-14 6:38 ` Christof Schmitt
2008-01-14 7:53 ` Jens Axboe
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).