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 4/4] examples/l3fwd: make data struct to be memory efficient
Date: Wed, 14 Apr 2021 00:36:03 +0530
Message-ID: <CALBAE1Pdj5Kq+6Qt=DaFKKg20Aj-s7wD8ywOBMCY1=W1qXd-hA@mail.gmail.com> (raw)
In-Reply-To: <20210318102550.59265-5-ruifeng.wang@arm.com>

On Thu, Mar 18, 2021 at 3:56 PM Ruifeng Wang <ruifeng.wang@arm.com> wrote:
>
> There are some holes in data struct lcore_conf. The holes are
> due to alignment requirement.
>
> For struct lcore_rx_queue, there is no need to make every element
> of this type to be cache line aligned, because the data is not
> shared between cores.
>
> Member len of struct mbuf_table can be moved out. So data can be
> packed and there will be no need to load an extra cache line when
> mbuf table is empty.
>
> The change showed slight performance improvement on N1SDP platform.
>
> Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
>
> Signed-off-by: Ruifeng Wang <ruifeng.wang@arm.com>

This change alone is OK in the octeontx2 platform.(No difference in performance)
combining with 3/4 shows some regression. Probably is due to prefetch
or 128B cache line tuning specifics.


> ---
>  examples/l3fwd/l3fwd.h        | 12 ++++++------
>  examples/l3fwd/l3fwd_common.h |  4 ++--
>  examples/l3fwd/l3fwd_em.c     |  6 +++---
>  examples/l3fwd/l3fwd_lpm.c    |  6 +++---
>  4 files changed, 14 insertions(+), 14 deletions(-)
>
> diff --git a/examples/l3fwd/l3fwd.h b/examples/l3fwd/l3fwd.h
> index 2cf06099e..f3a301e12 100644
> --- a/examples/l3fwd/l3fwd.h
> +++ b/examples/l3fwd/l3fwd.h
> @@ -57,22 +57,22 @@
>  #define HASH_ENTRY_NUMBER_DEFAULT      4
>
>  struct mbuf_table {
> -       uint16_t len;
>         struct rte_mbuf *m_table[MAX_PKT_BURST];
>  };
>
>  struct lcore_rx_queue {
>         uint16_t port_id;
>         uint8_t queue_id;
> -} __rte_cache_aligned;
> +};
>
>  struct lcore_conf {
> -       uint16_t n_rx_queue;
>         struct lcore_rx_queue rx_queue_list[MAX_RX_QUEUE_PER_LCORE];
> -       uint16_t n_tx_port;
>         uint16_t tx_port_id[RTE_MAX_ETHPORTS];
>         uint16_t tx_queue_id[RTE_MAX_ETHPORTS];
> +       uint16_t tx_mbuf_len[RTE_MAX_ETHPORTS];
>         struct mbuf_table tx_mbufs[RTE_MAX_ETHPORTS];
> +       uint16_t n_rx_queue;
> +       uint16_t n_tx_port;
>         void *ipv4_lookup_struct;
>         void *ipv6_lookup_struct;
>  } __rte_cache_aligned;
> @@ -122,7 +122,7 @@ send_single_packet(struct lcore_conf *qconf,
>  {
>         uint16_t len;
>
> -       len = qconf->tx_mbufs[port].len;
> +       len = qconf->tx_mbuf_len[port];
>         qconf->tx_mbufs[port].m_table[len] = m;
>         len++;
>
> @@ -132,7 +132,7 @@ send_single_packet(struct lcore_conf *qconf,
>                 len = 0;
>         }
>
> -       qconf->tx_mbufs[port].len = len;
> +       qconf->tx_mbuf_len[port] = len;
>         return 0;
>  }
>
> diff --git a/examples/l3fwd/l3fwd_common.h b/examples/l3fwd/l3fwd_common.h
> index 7d83ff641..05e03dbfc 100644
> --- a/examples/l3fwd/l3fwd_common.h
> +++ b/examples/l3fwd/l3fwd_common.h
> @@ -183,7 +183,7 @@ send_packetsx4(struct lcore_conf *qconf, uint16_t port, struct rte_mbuf *m[],
>  {
>         uint32_t len, j, n;
>
> -       len = qconf->tx_mbufs[port].len;
> +       len = qconf->tx_mbuf_len[port];
>
>         /*
>          * If TX buffer for that queue is empty, and we have enough packets,
> @@ -258,7 +258,7 @@ send_packetsx4(struct lcore_conf *qconf, uint16_t port, struct rte_mbuf *m[],
>                 }
>         }
>
> -       qconf->tx_mbufs[port].len = len;
> +       qconf->tx_mbuf_len[port] = len;
>  }
>
>  #endif /* _L3FWD_COMMON_H_ */
> diff --git a/examples/l3fwd/l3fwd_em.c b/examples/l3fwd/l3fwd_em.c
> index 9996bfba3..1970e0376 100644
> --- a/examples/l3fwd/l3fwd_em.c
> +++ b/examples/l3fwd/l3fwd_em.c
> @@ -662,12 +662,12 @@ em_main_loop(__rte_unused void *dummy)
>
>                         for (i = 0; i < qconf->n_tx_port; ++i) {
>                                 portid = qconf->tx_port_id[i];
> -                               if (qconf->tx_mbufs[portid].len == 0)
> +                               if (qconf->tx_mbuf_len[portid] == 0)
>                                         continue;
>                                 send_burst(qconf,
> -                                       qconf->tx_mbufs[portid].len,
> +                                       qconf->tx_mbuf_len[portid],
>                                         portid);
> -                               qconf->tx_mbufs[portid].len = 0;
> +                               qconf->tx_mbuf_len[portid] = 0;
>                         }
>
>                         prev_tsc = cur_tsc;
> diff --git a/examples/l3fwd/l3fwd_lpm.c b/examples/l3fwd/l3fwd_lpm.c
> index d338590b9..e62139a0e 100644
> --- a/examples/l3fwd/l3fwd_lpm.c
> +++ b/examples/l3fwd/l3fwd_lpm.c
> @@ -220,12 +220,12 @@ lpm_main_loop(__rte_unused void *dummy)
>
>                         for (i = 0; i < n_tx_p; ++i) {
>                                 portid = qconf->tx_port_id[i];
> -                               if (qconf->tx_mbufs[portid].len == 0)
> +                               if (qconf->tx_mbuf_len[portid] == 0)
>                                         continue;
>                                 send_burst(qconf,
> -                                       qconf->tx_mbufs[portid].len,
> +                                       qconf->tx_mbuf_len[portid],
>                                         portid);
> -                               qconf->tx_mbufs[portid].len = 0;
> +                               qconf->tx_mbuf_len[portid] = 0;
>                         }
>
>                         prev_tsc = cur_tsc;
> --
> 2.25.1
>

  reply	other threads:[~2021-04-13 19:06 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
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 [this message]
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='CALBAE1Pdj5Kq+6Qt=DaFKKg20Aj-s7wD8ywOBMCY1=W1qXd-hA@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

DPDK patches and discussions

This inbox may be cloned and mirrored by anyone:

	git clone --mirror https://inbox.dpdk.org/dev/0 dev/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 dev dev/ https://inbox.dpdk.org/dev \
		dev@dpdk.org
	public-inbox-index dev

Example config snippet for mirrors.
Newsgroup available over NNTP:
	nntp://inbox.dpdk.org/inbox.dpdk.dev


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git