Re: [PATCH net-next 3/3] virtio-net: clean tx descriptors from rx napi

From: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
To: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Willem de Bruijn <willemb@google.com>,
	Network Development <netdev@vger.kernel.org>,
	David Miller <davem@davemloft.net>,
	virtualization@lists.linux-foundation.org
Subject: Re: [PATCH net-next 3/3] virtio-net: clean tx descriptors from rx napi
Date: Fri, 7 Apr 2017 16:59:58 -0400	[thread overview]
Message-ID: <CAF=yD-JmO7XVng74BubyDLyP5Yf7wSCdXJdza+hx-NkrhDoxrw__650.722781620239$1493076953$gmane$org@mail.gmail.com> (raw)
In-Reply-To: <20170407222616-mutt-send-email-mst@kernel.org>

On Fri, Apr 7, 2017 at 3:28 PM, Michael S. Tsirkin <mst@redhat.com> wrote:
> On Mon, Apr 03, 2017 at 01:02:13AM -0400, Willem de Bruijn wrote:
>> On Sun, Apr 2, 2017 at 10:47 PM, Michael S. Tsirkin <mst@redhat.com> wrote:
>> > On Sun, Apr 02, 2017 at 04:10:12PM -0400, Willem de Bruijn wrote:
>> >> From: Willem de Bruijn <willemb@google.com>
>> >>
>> >> Amortize the cost of virtual interrupts by doing both rx and tx work
>> >> on reception of a receive interrupt if tx napi is enabled. With
>> >> VIRTIO_F_EVENT_IDX, this suppresses most explicit tx completion
>> >> interrupts for bidirectional workloads.
>> >>
>> >> Signed-off-by: Willem de Bruijn <willemb@google.com>
>
> This is a popular approach, but I think this will only work well if tx
> and rx interrupts are processed on the same CPU and if tx queue is per
> cpu.  If they target different CPUs or if tx queue is used from multiple
> CPUs they will conflict on the shared locks.

Yes. As a result of this discussion I started running a few vcpu affinity tests.

The data is not complete. In particular, I don't have the data yet to
compare having tx and rx irq on the same cpu (0,0) vs on different
(0,2) for this patchset. Which is the relevant data to your point.

Initial results for unmodified upstream driver at {1, 10, 100}x
TCP_STREAM, for irq cpu affinity (rx,tx). Process is always pinned to cpu
1. This is a 4 vcpu system pinned by the host to 4 cores on the same
socket. The previously reported results were obtained with txq, rtx
and process on different vcpus (0,2). Running all on the same vcpu
lower cycle count considerably:

irq 0,0
1    throughput_Mbps=29767.14  391,488,924,526      cycles
10  throughput_Mbps=40808.64  424,530,251,896      cycles
100 throughput_Mbps=33475.13  414,622,071,167      cycles

irq 0,2
1   throughput_Mbps=30176.05  395,673,200,747      cycles
10 throughput_Mbps=40729.26  433,948,374,991      cycles
100 throughput_Mbps=33758.68 436,291,949,393      cycles

irq 1,1
1    throughput_Mbps=26635.20 269,071,002,844      cycles
10  throughput_Mbps=42385.05 299,945,944,516      cycles
100 throughput_Mbps=33580.98 283,272,895,507      cycles

With this patch set applied, cpu (1,1)

1     throughput_Mbps=34980.76  276,504,805,414      cycles
10   throughput_Mbps=42519.92 298,105,889,785      cycles
100 throughput_Mbps=35268.86 296,670,598,712      cycles

I will need to get data for (0,2) vs (0,0).

> This can even change dynamically as CPUs/queues are reconfigured.
> How about adding a flag and skipping the tx poll if there's no match?

I suspect that even with the cache invalidations this optimization
will be an improvement over handling all tx interrupts in the tx napi
handler. I will get the datapoint for that.

That said, we can make this conditional. What flag exactly do you
propose? Compare raw_smp_processor_id() in the rx softint with one
previously stored in the napi tx callback?