[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20180118153205.ipl6yzdfqqoohzbs@linux-x5ow.site>
Date: Thu, 18 Jan 2018 16:32:05 +0100
From: Johannes Thumshirn <jthumshirn@...e.de>
To: Christoph Hellwig <hch@....de>
Cc: Sagi Grimberg <sagi@...mberg.me>,
Keith Busch <keith.busch@...el.com>,
Linux Kernel Mailinglist <linux-kernel@...r.kernel.org>,
Hannes Reinecke <hare@...e.de>,
Linux NVMe Mailinglist <linux-nvme@...ts.infradead.org>
Subject: Re: [PATCH v3 1/2] nvme: add tracepoint for nvme_setup_cmd
On Thu, Jan 18, 2018 at 04:21:34PM +0100, Christoph Hellwig wrote:
> On Wed, Jan 17, 2018 at 11:53:35AM +0100, Johannes Thumshirn wrote:
> > +nvme-core-y := trace.o core.o
>
> trace.o should be conditional on CONFIG_TRACEPOINTS.
Doesn't do too much of a difference for me if CONFIG_TRACEPOINTS=n but if you
insist I can do it of cause.
> > +TRACE_EVENT(nvme_setup_cmd,
> > + TP_PROTO(struct nvme_command *cmd),
> > + TP_ARGS(cmd),
> > + TP_STRUCT__entry(
> > + __field(__u8, opcode)
> > + __field(__u8, flags)
> > + __field(__u16, cid)
> > + __field(__le32, nsid)
> > + __field(__le64, metadata)
> > + __field_struct( struct nvme_command, cmnd )
>
> This still copies the whole SQE. I think that is way to much to
> copy, especially given that you also copy many of the fields separately
> as well.
it's not that much, but ok.
Will be sending out a v4 tomorrow.
--
Johannes Thumshirn Storage
jthumshirn@...e.de +49 911 74053 689
SUSE LINUX GmbH, Maxfeldstr. 5, 90409 Nürnberg
GF: Felix Imendörffer, Jane Smithard, Graham Norton
HRB 21284 (AG Nürnberg)
Key fingerprint = EC38 9CAB C2C4 F25D 8600 D0D0 0393 969D 2D76 0850
Powered by blists - more mailing lists