[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CACGkMEt9Vokeh6n8DKdBcqLRKVEXvNzM+-Zwad5eeMHvOdxXPw@mail.gmail.com>
Date: Tue, 18 Jun 2024 08:53:42 +0800
From: Jason Wang <jasowang@...hat.com>
To: Jiri Pirko <jiri@...nulli.us>
Cc: netdev@...r.kernel.org, davem@...emloft.net, edumazet@...gle.com,
kuba@...nel.org, pabeni@...hat.com, mst@...hat.com,
xuanzhuo@...ux.alibaba.com, virtualization@...ts.linux.dev, ast@...nel.org,
daniel@...earbox.net, hawk@...nel.org, john.fastabend@...il.com,
dave.taht@...il.com, kerneljasonxing@...il.com, hengqi@...ux.alibaba.com
Subject: Re: [PATCH net-next v2] virtio_net: add support for Byte Queue Limits
On Mon, Jun 17, 2024 at 5:18 PM Jiri Pirko <jiri@...nulli.us> wrote:
>
> Mon, Jun 17, 2024 at 04:34:26AM CEST, jasowang@...hat.com wrote:
> >On Thu, Jun 13, 2024 at 1:09 AM Jiri Pirko <jiri@...nulli.us> wrote:
> >>
> >> From: Jiri Pirko <jiri@...dia.com>
> >>
> >> Add support for Byte Queue Limits (BQL).
> >>
> >> Tested on qemu emulated virtio_net device with 1, 2 and 4 queues.
> >> Tested with fq_codel and pfifo_fast. Super netperf with 50 threads is
> >> running in background. Netperf TCP_RR results:
> >>
> >> NOBQL FQC 1q: 159.56 159.33 158.50 154.31 agv: 157.925
> >> NOBQL FQC 2q: 184.64 184.96 174.73 174.15 agv: 179.62
> >> NOBQL FQC 4q: 994.46 441.96 416.50 499.56 agv: 588.12
> >> NOBQL PFF 1q: 148.68 148.92 145.95 149.48 agv: 148.2575
> >> NOBQL PFF 2q: 171.86 171.20 170.42 169.42 agv: 170.725
> >> NOBQL PFF 4q: 1505.23 1137.23 2488.70 3507.99 agv: 2159.7875
> >> BQL FQC 1q: 1332.80 1297.97 1351.41 1147.57 agv: 1282.4375
> >> BQL FQC 2q: 768.30 817.72 864.43 974.40 agv: 856.2125
> >> BQL FQC 4q: 945.66 942.68 878.51 822.82 agv: 897.4175
> >> BQL PFF 1q: 149.69 151.49 149.40 147.47 agv: 149.5125
> >> BQL PFF 2q: 2059.32 798.74 1844.12 381.80 agv: 1270.995
> >> BQL PFF 4q: 1871.98 4420.02 4916.59 13268.16 agv: 6119.1875
> >>
> >> Signed-off-by: Jiri Pirko <jiri@...dia.com>
> >> ---
> >> v1->v2:
> >> - moved netdev_tx_completed_queue() call into __free_old_xmit(),
> >> propagate use_napi flag to __free_old_xmit() and only call
> >> netdev_tx_completed_queue() in case it is true
> >> - added forgotten call to netdev_tx_reset_queue()
> >> - fixed stats for xdp packets
> >> - fixed bql accounting when __free_old_xmit() is called from xdp path
> >> - handle the !use_napi case in start_xmit() kick section
> >> ---
> >> drivers/net/virtio_net.c | 50 +++++++++++++++++++++++++---------------
> >> 1 file changed, 32 insertions(+), 18 deletions(-)
> >>
> >> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> >> index 61a57d134544..5863c663ccab 100644
> >> --- a/drivers/net/virtio_net.c
> >> +++ b/drivers/net/virtio_net.c
> >> @@ -84,7 +84,9 @@ struct virtnet_stat_desc {
> >>
> >> struct virtnet_sq_free_stats {
> >> u64 packets;
> >> + u64 xdp_packets;
> >> u64 bytes;
> >> + u64 xdp_bytes;
> >> };
> >>
> >> struct virtnet_sq_stats {
> >> @@ -506,29 +508,33 @@ static struct xdp_frame *ptr_to_xdp(void *ptr)
> >> return (struct xdp_frame *)((unsigned long)ptr & ~VIRTIO_XDP_FLAG);
> >> }
> >>
> >> -static void __free_old_xmit(struct send_queue *sq, bool in_napi,
> >> +static void __free_old_xmit(struct send_queue *sq, struct netdev_queue *txq,
> >> + bool in_napi, bool use_napi,
> >> struct virtnet_sq_free_stats *stats)
> >> {
> >> unsigned int len;
> >> void *ptr;
> >>
> >> while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) {
> >> - ++stats->packets;
> >> -
> >> if (!is_xdp_frame(ptr)) {
> >> struct sk_buff *skb = ptr;
> >>
> >> pr_debug("Sent skb %p\n", skb);
> >>
> >> + stats->packets++;
> >> stats->bytes += skb->len;
> >> napi_consume_skb(skb, in_napi);
> >> } else {
> >> struct xdp_frame *frame = ptr_to_xdp(ptr);
> >>
> >> - stats->bytes += xdp_get_frame_len(frame);
> >> + stats->xdp_packets++;
> >> + stats->xdp_bytes += xdp_get_frame_len(frame);
> >> xdp_return_frame(frame);
> >> }
> >> }
> >> + if (use_napi)
> >> + netdev_tx_completed_queue(txq, stats->packets, stats->bytes);
> >> +
> >> }
> >
> >I wonder if this works correctly, for example NAPI could be enabled
> >after queued but before sent. So __netdev_tx_sent_queue() is not
> >called before.
>
> How is that possible? Napi weight can't change when link is up. Or am I
> missing something?
Something like this:
1) packet were queued
2) if down
3) enable NAPI
4) if up
5) packet were sent
?
Thanks
>
> >
> >Thanks
> >
>
Powered by blists - more mailing lists