As expected, the simplified accessors are faster.
for i in `seq 50`; do /usr/bin/time -f 'Wall time:%e' ./vringh_test --indirect --eventidx --parallel --fast-vringh; done 2>&1 | stats --trim-outliers:
Before:
Using CPUS 0 and 3
Guest: notified 0, pinged 39062-39063(39063)
Host: notified 39062-39063(39063), pinged 0
Wall time:1.760000-2.220000(1.789167)
After:
Using CPUS 0 and 3
Guest: notified 0, pinged 39037-39063(39062)
Host: notified 39037-39063(39062), pinged 0
Wall time:1.640000-1.810000(1.676875)
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
void *data,
gfp_t gfp);
+int virtqueue_add_outbuf(struct virtqueue *vq,
+ struct scatterlist sg[], unsigned int num,
+ void *data,
+ gfp_t gfp);
+
+int virtqueue_add_inbuf(struct virtqueue *vq,
+ struct scatterlist sg[], unsigned int num,
+ void *data,
+ gfp_t gfp);
+
void virtqueue_kick(struct virtqueue *vq);
void *virtqueue_get_buf(struct virtqueue *vq, unsigned int *len);
* user addr */
__kmalloc_fake = indirects + (xfers % RINGSIZE) * 4;
if (output)
- err = virtqueue_add_buf(vq, sg, num_sg, 0, dbuf,
- GFP_KERNEL);
+ err = virtqueue_add_outbuf(vq, sg, num_sg, dbuf,
+ GFP_KERNEL);
else
- err = virtqueue_add_buf(vq, sg, 0, num_sg, dbuf,
- GFP_KERNEL);
+ err = virtqueue_add_inbuf(vq, sg, num_sg,
+ dbuf, GFP_KERNEL);
if (err == -ENOSPC) {
if (!virtqueue_enable_cb_delayed(vq))