RE: [PATCH V2 net-next 1/1] hv_netvsc: Use the xmit_more skb flag to optimize signaling the host

From: KY Srinivasan
Date: Tue May 05 2015 - 20:08:52 EST




> -----Original Message-----
> From: Eric Dumazet [mailto:eric.dumazet@xxxxxxxxx]
> Sent: Thursday, April 30, 2015 9:37 PM
> To: KY Srinivasan
> Cc: davem@xxxxxxxxxxxxx; netdev@xxxxxxxxxxxxxxx; linux-
> kernel@xxxxxxxxxxxxxxx; devel@xxxxxxxxxxxxxxxxxxxxxx; olaf@xxxxxxxxx;
> apw@xxxxxxxxxxxxx; jasowang@xxxxxxxxxx
> Subject: Re: [PATCH V2 net-next 1/1] hv_netvsc: Use the xmit_more skb flag
> to optimize signaling the host
>
> On Thu, 2015-04-30 at 16:29 -0700, K. Y. Srinivasan wrote:
> > Based on the information given to this driver (via the xmit_more skb flag),
> > we can defer signaling the host if more packets are on the way. This will
> help
> > make the host more efficient since it can potentially process a larger batch
> of
> > packets. Implement this optimization.
> >
> > Signed-off-by: K. Y. Srinivasan <kys@xxxxxxxxxxxxx>
> > ---
> > v2: Fixed up indentation based on feedback from David Miller.
> >
> > drivers/net/hyperv/netvsc.c | 20 ++++++++++++--------
> > 1 files changed, 12 insertions(+), 8 deletions(-)
> >
> > diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
> > index 2e8ad06..5fdc5e1 100644
> > --- a/drivers/net/hyperv/netvsc.c
> > +++ b/drivers/net/hyperv/netvsc.c
> > @@ -743,6 +743,7 @@ static inline int netvsc_send_pkt(
> > u64 req_id;
> > int ret;
> > struct hv_page_buffer *pgbuf;
> > + u32 vmbus_flags =
> VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED;
> >
> > nvmsg.hdr.msg_type = NVSP_MSG1_TYPE_SEND_RNDIS_PKT;
> > if (packet->is_data_pkt) {
> > @@ -772,19 +773,22 @@ static inline int netvsc_send_pkt(
> > if (packet->page_buf_cnt) {
> > pgbuf = packet->cp_partial ? packet->page_buf +
> > packet->rmsg_pgcnt : packet->page_buf;
> > - ret = vmbus_sendpacket_pagebuffer(out_channel,
> > - pgbuf,
> > - packet->page_buf_cnt,
> > - &nvmsg,
> > - sizeof(struct
> nvsp_message),
> > - req_id);
> > + ret = vmbus_sendpacket_pagebuffer_ctl(out_channel,
> > + pgbuf,
> > + packet->page_buf_cnt,
> > + &nvmsg,
> > + sizeof(struct
> > + nvsp_message),
> > + req_id,
> > + vmbus_flags,
> > + !packet->xmit_more);
> > } else {
> > - ret = vmbus_sendpacket(
> > + ret = vmbus_sendpacket_ctl(
> > out_channel, &nvmsg,
> > sizeof(struct nvsp_message),
> > req_id,
> > VM_PKT_DATA_INBAND,
> > -
> VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
> > + vmbus_flags, !packet->xmit_more);
> > }
> >
> > if (ret == 0) {
>
> This might be problematic, if queue is stopped ( netif_tx_stop_queue())
>
> You need to force a kick if we are about to stop the queue :
>
> Random example : commit ddd0ca5d60b350bbfbfb60b25885a9779ce6d6c7

Thanks Eric; I will fix and resend.

Regards,

K. Y
>
>

N‹§²æ¸›yú²X¬¶ÇvØ–)Þ{.nlj·¥Š{±‘êX§¶›¡Ü}©ž²ÆzÚj:+v‰¨¾«‘êZ+€Êzf£¢·hšˆ§~†­†Ûÿû®w¥¢¸?™¨è&¢)ßf”ùy§m…á«a¶Úÿ 0¶ìå