lguest: try to batch interrupts on network receive

Rather than triggering an interrupt every time, we only trigger an
interrupt when there are no more incoming packets (or the recv queue
is full).

However, the overhead of doing the select to figure this out is
measurable: 1M pings goes from 98 to 104 seconds, and 1G Guest->Host
TCP goes from 3.69 to 3.94 seconds.  It's close to the noise though.

I tested various timeouts, including reducing it as the number of
pending packets increased, timing a 1 gigabyte TCP send from Guest ->
Host and Host -> Guest (GSO disabled, to increase packet rate).

// time tcpblast -o -s 65536 -c 16k 192.168.2.1:9999 > /dev/null

Timeout		Guest->Host	Pkts/irq	Host->Guest	Pkts/irq
Before		11.3s		1.0		6.3s		1.0
0		11.7s		1.0		6.6s		23.5
1		17.1s		8.8		8.6s		26.0
1/pending	13.4s		1.9		6.6s		23.8
2/pending	13.6s		2.8		6.6s		24.1
5/pending	14.1s		5.0		6.6s		24.4

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>

diff --git a/Documentation/lguest/lguest.c b/Documentation/lguest/lguest.c
index 20f8253..6411079 100644 (file)
--- a/Documentation/lguest/lguest.c
+++ b/Documentation/lguest/lguest.c
@@ -769,6 +769,16 @@ static void net_output(struct virtqueue *vq)
        add_used(vq, head, 0);
 }
 
+/* Will reading from this file descriptor block? */
+static bool will_block(int fd)
+{
+       fd_set fdset;
+       struct timeval zero = { 0, 0 };
+       FD_ZERO(&fdset);
+       FD_SET(fd, &fdset);
+       return select(fd+1, &fdset, NULL, NULL, &zero) != 1;
+}
+
 /* This is where we handle packets coming in from the tun device to our
  * Guest. */
 static void net_input(struct virtqueue *vq)
@@ -781,10 +791,15 @@ static void net_input(struct virtqueue *vq)
        head = wait_for_vq_desc(vq, iov, &out, &in);
        if (out)
                errx(1, "Output buffers in net input queue?");
+
+       /* Deliver interrupt now, since we're about to sleep. */
+       if (vq->pending_used && will_block(net_info->tunfd))
+               trigger_irq(vq);
+
        len = readv(net_info->tunfd, iov, in);
        if (len <= 0)
                err(1, "Failed to read from tun.");
-       add_used_and_trigger(vq, head, len);
+       add_used(vq, head, len);
 }
 
 /* This is the helper to create threads. */