[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20180626150106.GB6628@localhost.localdomain>
Date: Tue, 26 Jun 2018 09:01:06 -0600
From: Keith Busch <keith.busch@...ux.intel.com>
To: Johannes Thumshirn <jthumshirn@...e.de>
Cc: Christoph Hellwig <hch@....de>, Sagi Grimberg <sagi@...mberg.me>,
Keith Busch <keith.busch@...el.com>,
Linux Kernel Mailinglist <linux-kernel@...r.kernel.org>,
Linux NVMe Mailinglist <linux-nvme@...ts.infradead.org>
Subject: Re: [PATCH] nvme: trace: add disk name to tracepoints
On Tue, Jun 26, 2018 at 03:51:41PM +0200, Johannes Thumshirn wrote:
> @@ -655,9 +655,9 @@ blk_status_t nvme_setup_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
> cmd->common.command_id = req->tag;
> nvme_req(req)->ctrl = ctrl;
> if (ns)
> - trace_nvme_setup_nvm_cmd(req->q->id, cmd);
> + trace_nvme_setup_nvm_cmd(req, cmd, ns->disk->disk_name);
Not related to your patch, but I did notice that the req->q->id isn't
really useful here since that's not the hardware context identifier.
That's just some ida assigned software identifier. For the admin command
completion trace, it's actually a little confusing to see the qid in the
trace.
Powered by blists - more mailing lists