From: "Michael S. Tsirkin" <mst@redhat.com>
To: Heng Qi <hengqi@linux.alibaba.com>
Cc: netdev@vger.kernel.org, Jakub Kicinski <kuba@kernel.org>,
Eric Dumazet <edumazet@google.com>,
Paolo Abeni <pabeni@redhat.com>,
Vladimir Oltean <vladimir.oltean@nxp.com>,
"David S. Miller" <davem@davemloft.net>,
Jason Wang <jasowang@redhat.com>,
Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Subject: Re: [PATCH net-next v2 2/2] virtio-net: support dim profile fine-tuning
Date: Thu, 28 Mar 2024 03:27:04 -0400 [thread overview]
Message-ID: <20240328032636-mutt-send-email-mst@kernel.org> (raw)
In-Reply-To: <1711531146-91920-3-git-send-email-hengqi@linux.alibaba.com>
On Wed, Mar 27, 2024 at 05:19:06PM +0800, Heng Qi wrote:
> Virtio-net has different types of back-end device
> implementations. In order to effectively optimize
> the dim library's gains for different device
> implementations, let's use the new interface params
> to fine-tune the profile list.
>
> Signed-off-by: Heng Qi <hengqi@linux.alibaba.com>
> ---
> drivers/net/virtio_net.c | 54 ++++++++++++++++++++++++++++++++++++++++++++++--
> 1 file changed, 52 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index e709d44..9b6c727 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -57,6 +57,16 @@
>
> #define VIRTNET_DRIVER_VERSION "1.0.0"
>
> +/* This is copied from NET_DIM_RX_EQE_PROFILES in DIM library */
So maybe move it to a header and reuse?
> +#define VIRTNET_DIM_RX_PKTS 256
> +static struct dim_cq_moder rx_eqe_conf[] = {
> + {.usec = 1, .pkts = VIRTNET_DIM_RX_PKTS,},
> + {.usec = 8, .pkts = VIRTNET_DIM_RX_PKTS,},
> + {.usec = 64, .pkts = VIRTNET_DIM_RX_PKTS,},
> + {.usec = 128, .pkts = VIRTNET_DIM_RX_PKTS,},
> + {.usec = 256, .pkts = VIRTNET_DIM_RX_PKTS,}
> +};
> +
> static const unsigned long guest_offloads[] = {
> VIRTIO_NET_F_GUEST_TSO4,
> VIRTIO_NET_F_GUEST_TSO6,
> @@ -3584,7 +3594,10 @@ static void virtnet_rx_dim_work(struct work_struct *work)
> if (!rq->dim_enabled)
> continue;
>
> - update_moder = net_dim_get_rx_moderation(dim->mode, dim->profile_ix);
> + if (dim->profile_ix >= ARRAY_SIZE(rx_eqe_conf))
> + dim->profile_ix = ARRAY_SIZE(rx_eqe_conf) - 1;
> +
> + update_moder = rx_eqe_conf[dim->profile_ix];
> if (update_moder.usec != rq->intr_coal.max_usecs ||
> update_moder.pkts != rq->intr_coal.max_packets) {
> err = virtnet_send_rx_ctrl_coal_vq_cmd(vi, qnum,
> @@ -3627,6 +3640,34 @@ static int virtnet_should_update_vq_weight(int dev_flags, int weight,
> return 0;
> }
>
> +static int virtnet_update_profile(struct virtnet_info *vi,
> + struct kernel_ethtool_coalesce *kc)
> +{
> + int i;
> +
> + if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) {
> + for (i = 0; i < NET_DIM_PARAMS_NUM_PROFILES; i++)
> + if (kc->rx_eqe_profs[i].comps)
> + return -EINVAL;
> + } else {
> + for (i = 0; i < NET_DIM_PARAMS_NUM_PROFILES; i++) {
> + if (kc->rx_eqe_profs[i].usec != rx_eqe_conf[i].usec ||
> + kc->rx_eqe_profs[i].pkts != rx_eqe_conf[i].pkts ||
> + kc->rx_eqe_profs[i].comps)
> + return -EINVAL;
> + }
> +
> + return 0;
> + }
> +
> + for (i = 0; i < NET_DIM_PARAMS_NUM_PROFILES; i++) {
> + rx_eqe_conf[i].usec = kc->rx_eqe_profs[i].usec;
> + rx_eqe_conf[i].pkts = kc->rx_eqe_profs[i].pkts;
> + }
> +
> + return 0;
> +}
> +
> static int virtnet_set_coalesce(struct net_device *dev,
> struct ethtool_coalesce *ec,
> struct kernel_ethtool_coalesce *kernel_coal,
> @@ -3653,6 +3694,10 @@ static int virtnet_set_coalesce(struct net_device *dev,
> }
> }
>
> + ret = virtnet_update_profile(vi, kernel_coal);
> + if (ret)
> + return ret;
> +
> if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL))
> ret = virtnet_send_notf_coal_cmds(vi, ec);
> else
> @@ -3689,6 +3734,10 @@ static int virtnet_get_coalesce(struct net_device *dev,
> ec->tx_max_coalesced_frames = 1;
> }
>
> + if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL))
> + memcpy(kernel_coal->rx_eqe_profs, rx_eqe_conf,
> + sizeof(rx_eqe_conf));
> +
> return 0;
> }
>
> @@ -3868,7 +3917,8 @@ static int virtnet_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info)
>
> static const struct ethtool_ops virtnet_ethtool_ops = {
> .supported_coalesce_params = ETHTOOL_COALESCE_MAX_FRAMES |
> - ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_USE_ADAPTIVE_RX,
> + ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_USE_ADAPTIVE_RX |
> + ETHTOOL_COALESCE_RX_EQE_PROFILE,
> .get_drvinfo = virtnet_get_drvinfo,
> .get_link = ethtool_op_get_link,
> .get_ringparam = virtnet_get_ringparam,
> --
> 1.8.3.1
next prev parent reply other threads:[~2024-03-28 7:27 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-03-27 9:19 [PATCH net-next v2 0/2] ethtool: provide the dim profile fine-tuning channel Heng Qi
2024-03-27 9:19 ` [PATCH net-next v2 1/2] ethtool: provide customized dim profile management Heng Qi
2024-03-27 9:19 ` [PATCH net-next v2 2/2] virtio-net: support dim profile fine-tuning Heng Qi
2024-03-27 14:45 ` Alexander Lobakin
2024-03-28 0:32 ` Jakub Kicinski
2024-03-28 2:12 ` Xuan Zhuo
2024-03-28 16:48 ` Jakub Kicinski
2024-03-29 8:56 ` Heng Qi
2024-03-29 15:18 ` Jakub Kicinski
2024-03-28 2:26 ` Heng Qi
2024-03-28 2:02 ` Heng Qi
2024-03-28 7:27 ` Michael S. Tsirkin
2024-03-28 7:27 ` Michael S. Tsirkin [this message]
2024-03-28 7:51 ` Heng Qi
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=20240328032636-mutt-send-email-mst@kernel.org \
--to=mst@redhat.com \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=hengqi@linux.alibaba.com \
--cc=jasowang@redhat.com \
--cc=kuba@kernel.org \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=vladimir.oltean@nxp.com \
--cc=xuanzhuo@linux.alibaba.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).