From: Thomas Monjalon <thomas@monjalon.net>
To: Slava Ovsiienko <viacheslavo@nvidia.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>,
Jerin Jacob <jerinjacobk@gmail.com>,
Raslan Darawsheh <rasland@nvidia.com>,
"david.marchand@redhat.com" <david.marchand@redhat.com>,
Maayan Kashani <mkashani@nvidia.com>
Subject: Re: [RFC 2/5] common/mlx5: introduce tracepoints for mlx5 drivers
Date: Tue, 27 Jun 2023 13:36:36 +0200 [thread overview]
Message-ID: <22210461.hxa6pUQ8Du@thomas> (raw)
In-Reply-To: <DM6PR12MB3753385C5A428FEC454481D4DF27A@DM6PR12MB3753.namprd12.prod.outlook.com>
27/06/2023 11:43, Slava Ovsiienko:
> From: Thomas Monjalon <thomas@monjalon.net>
> > 27/06/2023 10:19, Slava Ovsiienko:
> > > From: Thomas Monjalon <thomas@monjalon.net>
> > > > 27/06/2023 08:15, Slava Ovsiienko:
> > > > > From: Thomas Monjalon <thomas@monjalon.net>
> > > > > > 13/06/2023 18:01, Jerin Jacob:
> > > > > > > On Tue, Jun 13, 2023 at 9:29 PM Slava Ovsiienko
> > > > > > > <viacheslavo@nvidia.com>
> > > > > > wrote:
> > > > > > > > From: Jerin Jacob <jerinjacobk@gmail.com>
> > > > > > > > > On Tue, Jun 13, 2023 at 9:20 PM Slava Ovsiienko
> > > > > > > > > <viacheslavo@nvidia.com>
> > > > > > > > > wrote:
> > > > > > > > > >
> > > > > > > > > > Hi,
> > > > > > > > > >
> > > > > > > > > > <..snip..>
> > > > > > > > > > > >
> > > > > > > > > > > > mlx5_os_interrupt_handler_create; #
> > > > WINDOWS_NO_EXPORT
> > > > > > > > > > > > mlx5_os_interrupt_handler_destroy; #
> > > > > > > > > > > > WINDOWS_NO_EXPORT
> > > > > > > > > > > > +
> > > > > > > > > > > > + __rte_pmd_mlx5_trace_tx_entry;
> > > > > > > > > > > > + __rte_pmd_mlx5_trace_tx_exit;
> > > > > > > > > > > > + __rte_pmd_mlx5_trace_tx_wqe;
> > > > > > > > > > > > + __rte_pmd_mlx5_trace_tx_wait;
> > > > > > > > > > > > + __rte_pmd_mlx5_trace_tx_push;
> > > > > > > > > > > > + __rte_pmd_mlx5_trace_tx_complete;
> > > > > > > > > > >
> > > > > > > > > > > No need to expose these symbols. It is getting removed
> > > > > > > > > > > from rest of
> > > > > > DPDK.
> > > > > > > > > > > Application can do rte_trace_lookup() to get this address.
> > > > > > > > > > >
> > > > > > > > > > >
> > > > > > > > > > It is not for application, it is for PMD itself, w/o
> > > > > > > > > > exposing the symbols build
> > > > > > > > > failed.
> > > > > > > > >
> > > > > > > > > PMD is implementing this trace endpoints, not consuming
> > > > > > > > > this trace
> > > > > > point.
> > > > > > > > > Right? If so, Why to expose these symbols?
> > > > > > > >
> > > > > > > > As far as understand:
> > > > > > > > The tracepoint routines are defined in dedicated
> > > > > > > > common/mlx5_trace.c
> > > > > > file.
> > > > > > > > The tx_burst in mlx5 is implemented as template in header
> > > > > > > > file, and this template is used in multiple .c files under net/mlx5
> > filder.
> > > > > > > > So, common/mlx5 should expose its symbols to net/mlx5 to
> > > > > > > > allow successful linkage.
> > > > > > >
> > > > > > > OK. I missed the fact the these are in common code and net
> > > > > > > driver is depened on that.
> > > > > > > So changes makes sense.
> > > > > >
> > > > > > It does not make sense to me.
> > > > > > These are tracepoints for the ethdev driver.
> > > > > > Why declaring them in the common library?
> > > > >
> > > > > Just to gather all mlx5 traces in the single file, to see all
> > > > > available tracing
> > > > caps in single view.
> > > >
> > > > Better to not export them.
> > > >
> > > It is not about export, we have analyzing script over the trace data,
> > > and it would be better to see all the tracing routines gathered in one place.
> > I would prefer not to spread trace point definitions over the multiple source
> > files.
> >
> > You don't need to export trace symbols for using them.
> > It has been discussed already with Jerin that we prefer not exporting trace
> > symbols if it can be avoided. Here it can be avoided.
>
> Without exporting symbols defined in common/mlx5 we have link error for net/mlx5.
> So, do you insist on having dedicated mlx5_trace.c per /net/mlx5, common/mlx5, etc?
Yes please it looks better to have tracepoints close to their respective functions.
next prev parent reply other threads:[~2023-06-27 11:36 UTC|newest]
Thread overview: 76+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-04-20 10:07 [RFC 0/5] net/mlx5: introduce Tx datapath tracing Viacheslav Ovsiienko
2023-04-20 10:07 ` [RFC 1/5] app/testpmd: add trace dump command Viacheslav Ovsiienko
2023-04-20 10:13 ` Jerin Jacob
2023-04-20 10:08 ` [RFC 2/5] common/mlx5: introduce tracepoints for mlx5 drivers Viacheslav Ovsiienko
2023-04-20 10:11 ` Jerin Jacob
2023-06-13 15:50 ` Slava Ovsiienko
2023-06-13 15:53 ` Jerin Jacob
2023-06-13 15:59 ` Slava Ovsiienko
2023-06-13 16:01 ` Jerin Jacob
2023-06-27 0:39 ` Thomas Monjalon
2023-06-27 6:15 ` Slava Ovsiienko
2023-06-27 7:28 ` Thomas Monjalon
2023-06-27 8:19 ` Slava Ovsiienko
2023-06-27 9:33 ` Thomas Monjalon
2023-06-27 9:43 ` Slava Ovsiienko
2023-06-27 11:36 ` Thomas Monjalon [this message]
2023-04-20 10:08 ` [RFC 3/5] net/mlx5: add Tx datapath tracing Viacheslav Ovsiienko
2023-04-20 10:08 ` [RFC 4/5] net/mlx5: add comprehensive send completion trace Viacheslav Ovsiienko
2023-04-20 10:08 ` [RFC 5/5] net/mlx5: add Tx datapath trace analyzing script Viacheslav Ovsiienko
2023-06-09 15:28 ` [PATCH 0/5] net/mlx5: introduce Tx datapath tracing Viacheslav Ovsiienko
2023-06-09 15:28 ` [PATCH 1/5] app/testpmd: add trace dump command Viacheslav Ovsiienko
2023-06-09 15:28 ` [PATCH 2/5] common/mlx5: introduce tracepoints for mlx5 drivers Viacheslav Ovsiienko
2023-06-09 15:28 ` [PATCH 3/5] net/mlx5: add Tx datapath tracing Viacheslav Ovsiienko
2023-06-09 15:28 ` [PATCH 4/5] net/mlx5: add comprehensive send completion trace Viacheslav Ovsiienko
2023-06-09 15:28 ` [PATCH 5/5] net/mlx5: add Tx datapath trace analyzing script Viacheslav Ovsiienko
2023-06-13 16:58 ` [PATCH v2 0/5] net/mlx5: introduce Tx datapath tracing Viacheslav Ovsiienko
2023-06-13 16:58 ` [PATCH v2 1/5] app/testpmd: add trace save command Viacheslav Ovsiienko
2023-06-21 11:15 ` Ferruh Yigit
2023-06-23 8:00 ` Slava Ovsiienko
2023-06-23 11:52 ` Ferruh Yigit
2023-06-23 12:03 ` Jerin Jacob
2023-06-23 12:14 ` Slava Ovsiienko
2023-06-23 12:23 ` Ferruh Yigit
2023-06-13 16:58 ` [PATCH v2 2/5] common/mlx5: introduce tracepoints for mlx5 drivers Viacheslav Ovsiienko
2023-06-13 16:58 ` [PATCH v2 3/5] net/mlx5: add Tx datapath tracing Viacheslav Ovsiienko
2023-06-13 16:58 ` [PATCH v2 4/5] net/mlx5: add comprehensive send completion trace Viacheslav Ovsiienko
2023-06-13 16:58 ` [PATCH v2 5/5] net/mlx5: add Tx datapath trace analyzing script Viacheslav Ovsiienko
2023-06-20 12:00 ` [PATCH v2 0/5] net/mlx5: introduce Tx datapath tracing Raslan Darawsheh
2023-06-27 0:46 ` Thomas Monjalon
2023-06-27 11:24 ` Slava Ovsiienko
2023-06-27 11:34 ` Thomas Monjalon
2023-06-28 14:18 ` Robin Jarry
2023-06-29 7:16 ` Slava Ovsiienko
2023-06-29 9:08 ` Robin Jarry
2023-06-26 11:06 ` [PATCH] app/testpmd: add trace dump command Viacheslav Ovsiienko
2023-06-26 11:07 ` [PATCH v3] " Viacheslav Ovsiienko
2023-06-26 11:57 ` [PATCH v4] " Viacheslav Ovsiienko
2023-06-27 11:34 ` Ferruh Yigit
2023-06-27 11:39 ` Slava Ovsiienko
2023-06-27 11:58 ` Ferruh Yigit
2023-06-27 14:44 ` [PATCH] app/testpmd: add dump command help message Viacheslav Ovsiienko
2023-06-27 18:03 ` Ferruh Yigit
2023-06-28 9:54 ` [PATCH v2] " Viacheslav Ovsiienko
2023-06-28 13:18 ` Ferruh Yigit
2023-06-27 13:09 ` [PATCH v5] app/testpmd: add trace dump command Viacheslav Ovsiienko
2023-06-27 15:18 ` Ferruh Yigit
2023-06-28 11:09 ` [PATCH v3 0/4] net/mlx5: introduce Tx datapath tracing Viacheslav Ovsiienko
2023-06-28 11:09 ` [PATCH v3 1/4] net/mlx5: introduce tracepoints for mlx5 drivers Viacheslav Ovsiienko
2023-06-28 11:09 ` [PATCH v3 2/4] net/mlx5: add comprehensive send completion trace Viacheslav Ovsiienko
2023-06-28 11:09 ` [PATCH v3 3/4] net/mlx5: add Tx datapath trace analyzing script Viacheslav Ovsiienko
2023-06-28 11:09 ` [PATCH v3 4/4] doc: add mlx5 datapath tracing feature description Viacheslav Ovsiienko
2023-07-05 11:10 ` [PATCH v4 0/4] net/mlx5: introduce Tx datapath tracing Viacheslav Ovsiienko
2023-07-05 11:10 ` [PATCH v4 1/4] net/mlx5: introduce tracepoints for mlx5 drivers Viacheslav Ovsiienko
2023-07-05 11:10 ` [PATCH v4 2/4] net/mlx5: add comprehensive send completion trace Viacheslav Ovsiienko
2023-07-05 11:10 ` [PATCH v4 3/4] net/mlx5: add Tx datapath trace analyzing script Viacheslav Ovsiienko
2023-07-05 11:10 ` [PATCH v4 4/4] doc: add mlx5 datapath tracing feature description Viacheslav Ovsiienko
2023-07-05 15:31 ` [PATCH v5 0/4] net/mlx5: introduce Tx datapath tracing Viacheslav Ovsiienko
2023-07-05 15:31 ` [PATCH v5 1/4] net/mlx5: introduce tracepoints for mlx5 drivers Viacheslav Ovsiienko
2023-07-05 15:31 ` [PATCH v5 2/4] net/mlx5: add comprehensive send completion trace Viacheslav Ovsiienko
2023-07-05 15:31 ` [PATCH v5 3/4] net/mlx5: add Tx datapath trace analyzing script Viacheslav Ovsiienko
2023-07-05 15:31 ` [PATCH v5 4/4] doc: add mlx5 datapath tracing feature description Viacheslav Ovsiienko
2023-07-06 16:27 ` [PATCH v5 0/4] net/mlx5: introduce Tx datapath tracing Raslan Darawsheh
2023-07-11 15:15 ` [PATCH v6 0/2] " Viacheslav Ovsiienko
2023-07-11 15:15 ` [PATCH v6 1/2] net/mlx5: add Tx datapath trace analyzing script Viacheslav Ovsiienko
2023-07-11 15:15 ` [PATCH v6 2/2] doc: add mlx5 datapath tracing feature description Viacheslav Ovsiienko
2023-07-27 10:52 ` [PATCH v6 0/2] net/mlx5: introduce Tx datapath tracing Thomas Monjalon
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=22210461.hxa6pUQ8Du@thomas \
--to=thomas@monjalon.net \
--cc=david.marchand@redhat.com \
--cc=dev@dpdk.org \
--cc=jerinjacobk@gmail.com \
--cc=mkashani@nvidia.com \
--cc=rasland@nvidia.com \
--cc=viacheslavo@nvidia.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).