DPDK patches and discussions
 help / color / mirror / Atom feed
From: Thomas Monjalon <thomas@monjalon.net>
To: Stephen Hemminger <stephen@networkplumber.org>
Cc: Tom Barbette <barbette@kth.se>,
	dev@dpdk.org, bruce.richardson@intel.com,
	john.mcnamara@intel.com, Ferruh Yigit <ferruh.yigit@intel.com>,
	Andrew Rybchenko <arybchenko@solarflare.com>,
	Shahaf Shuler <shahafs@mellanox.com>,
	Yongseok Koh <yskoh@mellanox.com>
Subject: Re: [dpdk-dev] [PATCH v2 0/3] Add rte_eth_read_clock API
Date: Wed, 27 Mar 2019 15:48:36 +0100	[thread overview]
Message-ID: <1643873.36pbUZ63Oi@xps> (raw)
In-Reply-To: <20190327074112.427c4758@shemminger-XPS-13-9360>

27/03/2019 15:41, Stephen Hemminger:
> On Wed, 27 Mar 2019 07:19:32 +0100
> Tom Barbette <barbette@kth.se> wrote:
> 
> > Some NICs allow to timestamp packets, but do not support the full
> > PTP synchronization process. Hence, the value set in the mbuf
> > timestamp field is only the raw value of an internal clock.
> > 
> > To make sense of this value, one at least needs to be able to query
> > the current hardware clock value. As with the TSC, from there
> > a frequency can be derieved by querying multiple time the current value of the
> > internal clock with some known delay between the queries (example
> > provided in the API doc).
> > 
> > This patch series adds support for MLX5.
> > 
> > An example app is provided in the rxtx_callback application.
> > It has been updated to display, on top of the software latency
> > in cycles, the total latency since the packet was received in hardware.
> > The API is used to compute a delta in the TX callback. The raw amount of
> > ticks is converted to cycles using a variation of the technique describe above.
> > 
> > Aside from offloading timestamping, which relieve the
> > software from a few operations, this allows to get much more precision
> > when studying the source of the latency in a system.
> > Eg. in our 100G, CX5 setup the rxtx callback application shows
> > SW latency is around 74 cycles (TSC is 3.2Ghz), but the latency
> > including NIC processing, PCIe, and queuing is around 196 cycles.
> > 
> > One may think at first this API is overlapping with te_eth_timesync_read_time.
> > rte_eth_timesync_read_time is clearly identified as part of a set of functions
> > to use PTP synchronization.
> > The device raw clock is not "sync" in any way. More importantly, the returned
> > value is not a timeval, but an amount of ticks. We could have a cast-based
> > solution, but on top of being an ugly solution, some people seeing the timeval
> > type of rte_eth_timesync_read_time could use it blindly.
> > 
> > Change in v2:
> >   - Rebase on current master
> > 
> > Tom Barbette (3):
> >   rte_ethdev: Add API function to read dev clock
> >   mlx5: Implement support for read_clock
> >   rxtx_callbacks: Add support for HW timestamp
> 
> I like this approach but would like to see the same API supported
> on multiple devices.
> 
> The current timestamp API is a mess because not all devices behave the
> same way. Trying to write an application that uses timestamping is therefore
> very difficult.

So what do you suggest?

  parent reply	other threads:[~2019-03-27 14:48 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-03-27  6:19 Tom Barbette
2019-03-27  6:19 ` Tom Barbette
2019-03-27  6:19 ` [dpdk-dev] [PATCH v2 1/3] rte_ethdev: Add API function to read dev clock Tom Barbette
2019-03-27  6:19   ` Tom Barbette
2019-04-02 17:46   ` Ferruh Yigit
2019-04-02 17:46     ` Ferruh Yigit
2019-04-02 19:24     ` Tom Barbette
2019-04-02 19:24       ` Tom Barbette
2019-03-27  6:19 ` [dpdk-dev] [PATCH v2 2/3] mlx5: Implement support for read_clock Tom Barbette
2019-03-27  6:19   ` Tom Barbette
2019-04-02 17:47   ` Ferruh Yigit
2019-04-02 17:47     ` Ferruh Yigit
2019-04-02 18:26   ` Ferruh Yigit
2019-04-02 18:26     ` Ferruh Yigit
2019-04-02 19:05     ` Tom Barbette
2019-04-02 19:05       ` Tom Barbette
2019-04-03  5:28   ` Shahaf Shuler
2019-04-03  5:28     ` Shahaf Shuler
2019-03-27  6:19 ` [dpdk-dev] [PATCH v2 3/3] rxtx_callbacks: Add support for HW timestamp Tom Barbette
2019-03-27  6:19   ` Tom Barbette
2019-04-02 18:22   ` Ferruh Yigit
2019-04-02 18:22     ` Ferruh Yigit
2019-04-02 19:39     ` Tom Barbette
2019-04-02 19:39       ` Tom Barbette
2019-03-27 14:41 ` [dpdk-dev] [PATCH v2 0/3] Add rte_eth_read_clock API Stephen Hemminger
2019-03-27 14:41   ` Stephen Hemminger
2019-03-27 14:48   ` Thomas Monjalon [this message]
2019-03-27 14:48     ` Thomas Monjalon
2019-03-27 14:54   ` Wiles, Keith
2019-03-27 14:54     ` Wiles, Keith
2019-03-27 16:08     ` Tom Barbette
2019-03-27 16:08       ` Tom Barbette

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=1643873.36pbUZ63Oi@xps \
    --to=thomas@monjalon.net \
    --cc=arybchenko@solarflare.com \
    --cc=barbette@kth.se \
    --cc=bruce.richardson@intel.com \
    --cc=dev@dpdk.org \
    --cc=ferruh.yigit@intel.com \
    --cc=john.mcnamara@intel.com \
    --cc=shahafs@mellanox.com \
    --cc=stephen@networkplumber.org \
    --cc=yskoh@mellanox.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).