DPDK patches and discussions
 help / color / mirror / Atom feed
From: Jerin Jacob <jerinjacobk@gmail.com>
To: "Mattias Rönnblom" <mattias.ronnblom@ericsson.com>,
	"Richardson, Bruce" <bruce.richardson@intel.com>
Cc: Jerin Jacob <jerinj@marvell.com>,
	dev@dpdk.org,  Peter Nilsson J <peter.j.nilsson@ericsson.com>
Subject: Re: [PATCH 1/2] eventdev: add bulk type event ring operations
Date: Tue, 2 May 2023 16:02:33 +0530	[thread overview]
Message-ID: <CALBAE1My+MiCrcszZL8RZMBfNssu254j4D58=9PCziX-Ki0GFg@mail.gmail.com> (raw)
In-Reply-To: <CALBAE1MDzqD+9kp4iPX2t7sUQteSKGdUnK4+YV3xGSUs5P+NTw@mail.gmail.com>

On Tue, Apr 4, 2023 at 12:33 PM Jerin Jacob <jerinjacobk@gmail.com> wrote:
>
> On Mon, Apr 3, 2023 at 6:49 PM Mattias Rönnblom
> <mattias.ronnblom@ericsson.com> wrote:
> >
> > Introduce bulk enqueue and dequeue operations into the
> > <rte_event_ring.h> API, to supplement the already-existing burst
> > calls.
> >
> > Signed-off-by: Mattias Rönnblom <mattias.ronnblom@ericsson.com>
>
> Looks good to me.
> As the original author adding @Richardson, Bruce  for review.


Acked-by: Jerin Jacob <jerinj@marvell.com>

Series applied to dpdk-next-net-eventdev/for-main. Thanks


>
>
> > ---
> >  lib/eventdev/rte_event_ring.h | 74 +++++++++++++++++++++++++++++++++++
> >  1 file changed, 74 insertions(+)
> >
> > diff --git a/lib/eventdev/rte_event_ring.h b/lib/eventdev/rte_event_ring.h
> > index 7efa64444b..f9cf19ae16 100644
> > --- a/lib/eventdev/rte_event_ring.h
> > +++ b/lib/eventdev/rte_event_ring.h
> > @@ -67,6 +67,80 @@ rte_event_ring_free_count(const struct rte_event_ring *r)
> >         return rte_ring_free_count(&r->r);
> >  }
> >
> > +
> > +/**
> > + * Enqueue several objects on a ring.
> > + *
> > + * This function calls the multi-producer or the single-producer
> > + * version depending on the default behavior that was specified at
> > + * ring creation time (see flags).
> > + *
> > + * @param r
> > + *   pointer to the event ring
> > + * @param events
> > + *   pointer to an array of struct rte_event objects
> > + * @param n
> > + *   The number of events in the array to enqueue
> > + * @param free_space
> > + *   if non-NULL, returns the amount of space in the ring after the
> > + *   enqueue operation has completed
> > + * @return
> > + *   the number of objects enqueued, either 0 or n
> > + */
> > +static __rte_always_inline unsigned int
> > +rte_event_ring_enqueue_bulk(struct rte_event_ring *r,
> > +                           const struct rte_event *events,
> > +                           unsigned int n, uint16_t *free_space)
> > +{
> > +       unsigned int num;
> > +       uint32_t space;
> > +
> > +       num = rte_ring_enqueue_bulk_elem(&r->r, events,
> > +                                        sizeof(struct rte_event), n,
> > +                                        &space);
> > +
> > +       if (free_space != NULL)
> > +               *free_space = space;
> > +
> > +       return num;
> > +}
> > +
> > +/**
> > + * Dequeue a set of events from a ring
> > + *
> > + * Note: this API does not work with pointers to events, rather it copies
> > + * the events themselves to the destination ``events`` buffer.
> > + *
> > + * @param r
> > + *   pointer to the event ring
> > + * @param events
> > + *   pointer to an array to hold the struct rte_event objects
> > + * @param n
> > + *   number of events that can be held in the ``events`` array
> > + * @param available
> > + *   if non-null, is updated to indicate the number of events remaining in
> > + *   the ring once the dequeue has completed
> > + * @return
> > + *   the number of objects dequeued, either 0 or n
> > + */
> > +static __rte_always_inline unsigned int
> > +rte_event_ring_dequeue_bulk(struct rte_event_ring *r,
> > +                            struct rte_event *events,
> > +                            unsigned int n, uint16_t *available)
> > +{
> > +       unsigned int num;
> > +       uint32_t remaining;
> > +
> > +       num = rte_ring_dequeue_bulk_elem(&r->r, events,
> > +                                        sizeof(struct rte_event), n,
> > +                                        &remaining);
> > +
> > +       if (available != NULL)
> > +               *available = remaining;
> > +
> > +       return num;
> > +}
> > +
> >  /**
> >   * Enqueue a set of events onto a ring
> >   *
> > --
> > 2.34.1
> >

      reply	other threads:[~2023-05-02 10:33 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-04-03 13:13 Mattias Rönnblom
2023-04-03 13:13 ` [PATCH 2/2] event/dsw: replace burst with bulk enqueue Mattias Rönnblom
2023-04-04  7:03 ` [PATCH 1/2] eventdev: add bulk type event ring operations Jerin Jacob
2023-05-02 10:32   ` Jerin Jacob [this message]

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='CALBAE1My+MiCrcszZL8RZMBfNssu254j4D58=9PCziX-Ki0GFg@mail.gmail.com' \
    --to=jerinjacobk@gmail.com \
    --cc=bruce.richardson@intel.com \
    --cc=dev@dpdk.org \
    --cc=jerinj@marvell.com \
    --cc=mattias.ronnblom@ericsson.com \
    --cc=peter.j.nilsson@ericsson.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).