DPDK patches and discussions
 help / color / mirror / Atom feed
From: Jerin Jacob <jerinjacobk@gmail.com>
To: Ruifeng Wang <ruifeng.wang@arm.com>
Cc: Jerin Jacob <jerinj@marvell.com>,
	Hemant Agrawal <hemant.agrawal@nxp.com>,
	 Ferruh Yigit <ferruh.yigit@intel.com>,
	Thomas Monjalon <thomas@monjalon.net>,
	 David Marchand <david.marchand@redhat.com>,
	dpdk-dev <dev@dpdk.org>, nd <nd@arm.com>,
	Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Subject: Re: [dpdk-dev] [PATCH 1/4] examples/l3fwd: tune prefetch for better performance
Date: Wed, 14 Apr 2021 00:20:56 +0530	[thread overview]
Message-ID: <CALBAE1PiXCypP1=d5t1L+JovQgh882AUWNtkV48Fka+evDYskQ@mail.gmail.com> (raw)
In-Reply-To: <20210318102550.59265-2-ruifeng.wang@arm.com>

On Thu, Mar 18, 2021 at 3:56 PM Ruifeng Wang <ruifeng.wang@arm.com> wrote:
>
> Packet header is prefetched before packet processing for better
> memory access performance. As L2 header will be updated by l3fwd,
> using of prefetch for store hint will set cache line to proper
> status and reduce cache maintenance overhead.

The code does read the cache line too. Right?

>
> With this change, 12.9% performance uplift was measured on N1SDP
> platform with MLX5 NIC.
>
> Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
>
> Signed-off-by: Ruifeng Wang <ruifeng.wang@arm.com>
> Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>


On the octeontx2 platform, It is 2% regression.

Looks like micro architecture-specific item of handing write hint on the memory
the area that does read and write.


I am testing the LPM lookup miss case.

My test command:
./build/examples/dpdk-l3fwd  -c 0x0100  -- -p 0x1 --config="(0,0,8)" -P



> ---
>  examples/l3fwd/l3fwd_lpm_neon.h | 10 +++++-----
>  1 file changed, 5 insertions(+), 5 deletions(-)
>
> diff --git a/examples/l3fwd/l3fwd_lpm_neon.h b/examples/l3fwd/l3fwd_lpm_neon.h
> index d6c0ba64a..ae8840694 100644
> --- a/examples/l3fwd/l3fwd_lpm_neon.h
> +++ b/examples/l3fwd/l3fwd_lpm_neon.h
> @@ -97,13 +97,13 @@ l3fwd_lpm_send_packets(int nb_rx, struct rte_mbuf **pkts_burst,
>
>         if (k) {
>                 for (i = 0; i < FWDSTEP; i++) {
> -                       rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[i],
> +                       rte_prefetch0_write(rte_pktmbuf_mtod(pkts_burst[i],
>                                                 struct rte_ether_hdr *) + 1);
>                 }
>
>                 for (j = 0; j != k - FWDSTEP; j += FWDSTEP) {
>                         for (i = 0; i < FWDSTEP; i++) {
> -                               rte_prefetch0(rte_pktmbuf_mtod(
> +                               rte_prefetch0_write(rte_pktmbuf_mtod(
>                                                 pkts_burst[j + i + FWDSTEP],
>                                                 struct rte_ether_hdr *) + 1);
>                         }
> @@ -124,17 +124,17 @@ l3fwd_lpm_send_packets(int nb_rx, struct rte_mbuf **pkts_burst,
>                 /* Prefetch last up to 3 packets one by one */
>                 switch (m) {
>                 case 3:
> -                       rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[j],
> +                       rte_prefetch0_write(rte_pktmbuf_mtod(pkts_burst[j],
>                                                 struct rte_ether_hdr *) + 1);
>                         j++;
>                         /* fallthrough */
>                 case 2:
> -                       rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[j],
> +                       rte_prefetch0_write(rte_pktmbuf_mtod(pkts_burst[j],
>                                                 struct rte_ether_hdr *) + 1);
>                         j++;
>                         /* fallthrough */
>                 case 1:
> -                       rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[j],
> +                       rte_prefetch0_write(rte_pktmbuf_mtod(pkts_burst[j],
>                                                 struct rte_ether_hdr *) + 1);
>                         j++;
>                 }
> --
> 2.25.1
>

  reply	other threads:[~2021-04-13 18:51 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-03-18 10:25 [dpdk-dev] [PATCH 0/4] l3fwd improvements Ruifeng Wang
2021-03-18 10:25 ` [dpdk-dev] [PATCH 1/4] examples/l3fwd: tune prefetch for better performance Ruifeng Wang
2021-04-13 18:50   ` Jerin Jacob [this message]
2021-04-13 20:00     ` Honnappa Nagarahalli
2021-05-19  7:52     ` Ruifeng Wang
2021-03-18 10:25 ` [dpdk-dev] [PATCH 2/4] examples/l3fwd: eliminate unnecessary calculations Ruifeng Wang
2021-04-13 18:40   ` Jerin Jacob
2021-03-18 10:25 ` [dpdk-dev] [PATCH 3/4] examples/l3fwd: eliminate unnecessary reloads in loop Ruifeng Wang
2021-04-13 17:43   ` Jerin Jacob
2021-04-14  6:02     ` Ruifeng Wang
2021-03-18 10:25 ` [dpdk-dev] [PATCH 4/4] examples/l3fwd: make data struct to be memory efficient Ruifeng Wang
2021-04-13 19:06   ` Jerin Jacob
2021-04-21  5:22     ` Hemant Agrawal
2021-04-26 10:55       ` Walsh, Conor
2021-04-27  1:19         ` Ruifeng Wang
2021-04-13  8:24 ` [dpdk-dev] [PATCH 0/4] l3fwd improvements Ruifeng Wang
2021-04-13 17:33   ` Jerin Jacob
2021-04-16  9:39 ` Ling, WeiX
2021-06-01  7:56 ` [dpdk-dev] [PATCH v2 0/3] " Ruifeng Wang
2021-06-01  7:56   ` [dpdk-dev] [PATCH v2 1/3] examples/l3fwd: reorganize code for better performance Ruifeng Wang
2021-06-06 18:34     ` Jerin Jacob
2021-06-01  7:56   ` [dpdk-dev] [PATCH v2 2/3] examples/l3fwd: eliminate unnecessary calculations Ruifeng Wang
2021-06-01  7:56   ` [dpdk-dev] [PATCH v2 3/3] examples/l3fwd: eliminate unnecessary reloads in loop Ruifeng Wang
2021-06-06 18:39     ` Jerin Jacob
2021-06-10  6:57 ` [dpdk-dev] [PATCH v3 0/2] l3fwd improvements Ruifeng Wang
2021-06-10  6:57   ` [dpdk-dev] [PATCH v3 1/2] examples/l3fwd: eliminate unnecessary calculations Ruifeng Wang
2021-06-10  6:57   ` [dpdk-dev] [PATCH v3 2/2] examples/l3fwd: eliminate unnecessary reloads in loop Ruifeng Wang
2021-07-05  8:36   ` [dpdk-dev] [PATCH v3 0/2] l3fwd improvements David Marchand

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='CALBAE1PiXCypP1=d5t1L+JovQgh882AUWNtkV48Fka+evDYskQ@mail.gmail.com' \
    --to=jerinjacobk@gmail.com \
    --cc=david.marchand@redhat.com \
    --cc=dev@dpdk.org \
    --cc=ferruh.yigit@intel.com \
    --cc=hemant.agrawal@nxp.com \
    --cc=honnappa.nagarahalli@arm.com \
    --cc=jerinj@marvell.com \
    --cc=nd@arm.com \
    --cc=ruifeng.wang@arm.com \
    --cc=thomas@monjalon.net \
    /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).