archive mirror
 help / color / mirror / Atom feed
* Re: [dpdk-dev] [PATCH 00/39] adding eventmode helper library
@ 2019-06-25 10:33 Jerin Jacob Kollanukkaran
  2019-06-27  5:28 ` Anoob Joseph
  0 siblings, 1 reply; 21+ messages in thread
From: Jerin Jacob Kollanukkaran @ 2019-06-25 10:33 UTC (permalink / raw)
  To: Anoob Joseph, Mattias Rönnblom, Nikhil Rao,
	Erik Gabriel Carrillo, Abhinandan Gujjar, Bruce Richardson,
	Pablo de Lara
  Cc: Narayana Prasad Raju Athreya, dev, Lukas Bartosik,
	Pavan Nikhilesh Bhagavatula, Hemant Agrawal, Nipun Gupta,
	Harry van Haaren, Liang Ma

> -----Original Message-----
> From: Anoob Joseph
> Sent: Thursday, June 20, 2019 9:15 AM
> To: Mattias Rönnblom <>; Jerin Jacob
> Kollanukkaran <>; Nikhil Rao <>; Erik
> Gabriel Carrillo <>; Abhinandan Gujjar
> <>; Bruce Richardson
> <>; Pablo de Lara
> <>
> Cc: Narayana Prasad Raju Athreya <>;;
> Lukas Bartosik <>; Pavan Nikhilesh Bhagavatula
> <>; Hemant Agrawal <>;
> Nipun Gupta <>; Harry van Haaren
> <>; Liang Ma <>
> Subject: RE: [dpdk-dev] [EXT] Re: [PATCH 00/39] adding eventmode helper
> library
> > However, the flexibility and many of the parameters are there for a
> > reason (those there aren't should be deprecated). I would expect a
> > real-world application to tweak quite a few of them. I know our applications
> do.
> >
> > I worry I have is that if you put eventmode (in its current form)
> > forward as a generic framework, applications might start using it,
> > only to realize it's not flexible enough, and then eventmode is just
> > an extra layer, increasing rather than reducing complexity. Or even
> > worse, the application's developers are forced to do a big-bang switch
> > over to using the event and ethernet device APIs directly, in case
> > they can't patch DPDK to work around the eventmode- assumption-that-
> didn't-hold-for-them.
> >
> > You could always add flexibility to the framework (as you encounter a
> > need for it), but then it will grow in complexity as well.
> >
> > A less ambitious approach would be to instead do a properly
> > modularized, non-trivial eventdev example application, for the
> > applications to start off from, instead of a generic library.
> >
> > I would expect it to be very difficult to design a truly generic
> > application framework for eventdev-based applications. Such a
> > framework would tie everything that's needed in a non-trivial
> > application together. If successful, it would be a huge step toward
> > making DPDK an operating system for packet processing applications.
> [Anoob] The idea here is not to deprecate any event dev APIs. I do agree that all
> the configuration exposed by eventdev & adapters are required for various
> requirements in the real world applications. But the requirement to understand
> & use all this configuration is making the applications complicated and causes
> significant effort from anyone who would want to get started with event mode.
> The idea of helper is to allow an easy framework for applications to get started
> with eventmode, and then use various options from C/L or config file (both
> planned) to override the configuration as required. DPDK has components like
> crypto-scheduler which abstracts lot of configuration and simplify usage from
> application's perspective. This effort is on similar lines.
> My patchset is a followup to , wherein the
> approach of introducing a helper library for event mode was mooted. The initial
> patch proposed additions in one application, and that involved huge code
> additions just for doing the configuration.
> The helper library will be experimental while we add event-mode support for
> other applications like l3fwd & ipsec-secgw. I expect the helper library to be
> complete over the course of those applications also using the helper library.

I have only concern about moving this as library inside eventdev that till we have mature
version of helper library the eventdev library ABI will not stable(i.e .so file version needs
to be incremented as when a change needed). Which align with Mattias thoughts for
some other reason:. How about moving this code to
1) example/common or
2) to specific application itself, once at least two applications starts using it then move
to Eventdev library.


> >
> > What event devices have you tested with?
> [Anoob] Eventmode helper is tested with the following combinations,
>     1. event-octeontx event PMD & nicvf eth PMD
>     2. event-octeontx event PMD & eth-octeontx eth PMD

^ permalink raw reply	[flat|nested] 21+ messages in thread
* [dpdk-dev] [PATCH 00/39] adding eventmode helper library
@ 2019-06-03 17:32 Anoob Joseph
  2019-06-07  9:48 ` Jerin Jacob Kollanukkaran
  0 siblings, 1 reply; 21+ messages in thread
From: Anoob Joseph @ 2019-06-03 17:32 UTC (permalink / raw)
  To: Jerin Jacob, Nikhil Rao, Erik Gabriel Carrillo,
	Abhinandan Gujjar, Bruce Richardson, Pablo de Lara
  Cc: Anoob Joseph, Narayana Prasad, dev, Lukasz Bartosik,
	Pavan Nikhilesh, Hemant Agrawal, Nipun Gupta, Harry van Haaren,
	Mattias Rönnblom, Liang Ma

This series adds support for eventmode helper library and l2fwd-event

First 13 patches creates a new l2fwd application (l2fwd-event). Minor
code reorganization is done to faciliate seamless integration of

Next 22 patches adds eventmode helper library. This library abstracts
the configuration of event device & Rx-Tx event adapters. The library
can be extended to allow users to control all the configuration
exposed by adapters and eth device.

Last 4 patches implements eventmode in l2fwd-event application. With
event device and adapters, fine tuned threads (based on dev
capabilities) can be drafted to maximize performance. Eventmode
library facilitates this and l2fwd-event demonstrates this usage.

With the introduction of eventmode helper library, any poll mode
application can be converted to an eventmode application with simple
steps, enabling multi-core scaling and dynamic load balancing to
various example applications.

     ./l2fwd-event -- <EAL args> -- <l2fwd args> -- --transfer-mode 1

The above command would invoke eventmode and with the default conf
loaded, traffic on one port would be delivered to all enabled cores.

Planned features,
1. Eventmode helper library doesn't intialize ethdev. Since all
   applications already do this, eventmode helper would start
   from reconfiguring.
2. All features of eventdev and adapters can be exposed to the user
   using common CL arguments. The framework for achieving the same
   is already in place. It has to be extended to support more
3. Documentation is pending.

Created new app based on discussions,

Tested with nicvf eth PMD and event_octeontx event PMD on Marvell's
CN83XX platform.

Anoob Joseph (39):
  examples/l2fwd-event: create copy of l2fwd
  examples/l2fwd-event: move macros to common header
  examples/l2fwd-event: move structures to common header
  examples/l2fwd-event: move global vars to common header
  examples/l2fwd-event: move dataplane code to new file
  examples/l2fwd-event: remove unused header includes
  examples/l2fwd-event: move drain buffers to new function
  examples/l2fwd-event: optimize check for master core
  examples/l2fwd-event: move periodic tasks to new func
  examples/l2fwd-event: do timer updates only on master
  examples/l2fwd-event: move pkt send code to a new func
  examples/l2fwd-event: use fprintf in usage print
  examples/l2fwd-event: improvements to the usage print
  eventdev: add files for eventmode helper
  eventdev: add routines for logging eventmode helper
  eventdev: add eventmode CL options framework
  eventdev: allow application to set ethernet portmask
  eventdev: add framework for eventmode conf
  eventdev: add common initialize routine for eventmode devs
  eventdev: add eventdevice init for eventmode
  eventdev: add eventdev port-lcore link
  eventdev: add option to specify schedule mode for app stage
  eventdev: add placeholder for ethdev init
  eventdev: add Rx adapter init in eventmode
  eventdev: add routine to validate conf
  eventdev: add default conf for event devs field in conf
  eventdev: add default conf for Rx adapter conf
  eventdev: add default conf for event port-lcore link
  eventdev: add routines to display the eventmode conf
  eventdev: add routine to access eventmode link info
  eventdev: add routine to access event queue for eth Tx
  eventdev: add routine to launch eventmode workers
  eventdev: add Tx adapter support
  eventdev: add support for internal ports
  eventdev: display Tx adapter conf
  examples/l2fwd-event: add eventmode for l2fwd
  examples/l2fwd-event: add eventmode worker
  examples/l2fwd-event: add eventmode worker
  examples/l2fwd-event: add eventmode worker

 config/common_base                                 |    1 +
 examples/Makefile                                  |    1 +
 examples/l2fwd-event/Makefile                      |   57 +
 examples/l2fwd-event/l2fwd_common.h                |   63 +
 examples/l2fwd-event/l2fwd_worker.c                | 1121 +++++++++++++
 examples/l2fwd-event/l2fwd_worker.h                |   16 +
 examples/l2fwd-event/main.c                        |  585 +++++++
 examples/l2fwd-event/                   |   14 +
 lib/librte_eal/common/eal_common_log.c             |    1 +
 lib/librte_eal/common/include/rte_log.h            |    1 +
 lib/librte_eventdev/Makefile                       |    6 +-
 lib/librte_eventdev/                    |    3 +
 lib/librte_eventdev/       |    8 +
 lib/librte_eventdev/rte_eventmode_helper.c         | 1678 ++++++++++++++++++++
 lib/librte_eventdev/rte_eventmode_helper.h         |  241 +++
 .../rte_eventmode_helper_internal.h                |  144 ++
 lib/librte_eventdev/rte_eventmode_helper_prints.c  |  223 +++
 17 files changed, 4161 insertions(+), 2 deletions(-)
 create mode 100644 examples/l2fwd-event/Makefile
 create mode 100644 examples/l2fwd-event/l2fwd_common.h
 create mode 100644 examples/l2fwd-event/l2fwd_worker.c
 create mode 100644 examples/l2fwd-event/l2fwd_worker.h
 create mode 100644 examples/l2fwd-event/main.c
 create mode 100644 examples/l2fwd-event/
 create mode 100644 lib/librte_eventdev/rte_eventmode_helper.c
 create mode 100644 lib/librte_eventdev/rte_eventmode_helper.h
 create mode 100644 lib/librte_eventdev/rte_eventmode_helper_internal.h
 create mode 100644 lib/librte_eventdev/rte_eventmode_helper_prints.c


^ permalink raw reply	[flat|nested] 21+ messages in thread

end of thread, other threads:[~2019-07-04  3:35 UTC | newest]

Thread overview: 21+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2019-06-25 10:33 [dpdk-dev] [PATCH 00/39] adding eventmode helper library Jerin Jacob Kollanukkaran
2019-06-27  5:28 ` Anoob Joseph
2019-06-28  3:37   ` Jerin Jacob Kollanukkaran
2019-06-28  8:02     ` Mattias Rönnblom
2019-06-28  8:40     ` Thomas Monjalon
2019-06-28  9:07       ` Mattias Rönnblom
2019-06-28 11:34       ` [dpdk-dev] [EXT] " Anoob Joseph
2019-07-02 14:17         ` Anoob Joseph
2019-07-02 14:26           ` Jerin Jacob Kollanukkaran
2019-07-02 14:49             ` Bruce Richardson
2019-07-02 14:57             ` Thomas Monjalon
2019-07-02 16:18               ` Anoob Joseph
2019-07-02 17:38                 ` Mattias Rönnblom
2019-07-03  1:35                   ` Anoob Joseph
2019-07-03  8:51                     ` Thomas Monjalon
2019-07-03  9:37                       ` Anoob Joseph
2019-07-03 16:30                         ` Thomas Monjalon
2019-07-04  3:34                           ` Anoob Joseph
  -- strict thread matches above, loose matches on Subject: below --
2019-06-03 17:32 [dpdk-dev] " Anoob Joseph
2019-06-07  9:48 ` Jerin Jacob Kollanukkaran
2019-06-11 10:44   ` Mattias Rönnblom

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).