search for: pakcets

We should alloc big buffers also when guest can receive UFO pakcets to let the big packets be fit into guest rx buffer. Fixes 5c5167515d80f78f6bb538492c423adcae31ad65 (virtio-net: Allow UFO feature to be set and advertised.) Cc: Rusty Russell <rusty at rustcorp.com.au> Cc: Michael S. Tsirkin <mst at redhat.com> Cc: Sridhar Samudrala <sri at us.ibm....

We should alloc big buffers also when guest can receive UFO pakcets to let the big packets be fit into guest rx buffer. Fixes 5c5167515d80f78f6bb538492c423adcae31ad65 (virtio-net: Allow UFO feature to be set and advertised.) Cc: Rusty Russell <rusty at rustcorp.com.au> Cc: Michael S. Tsirkin <mst at redhat.com> Cc: Sridhar Samudrala <sri at us.ibm....

On 2016-06-17 10:50 AM, Rizwan Ishaq wrote: > 1) does 960 means number of samples in the (20msec frame)? (fs=48KHz) That's correct. > 2) The raw opus packet (i.e OPUS payload), how can I convert it to an > playable format? You can pass the payload section of the RTP packets directly to an opus decoder to convert to PCM float or integer samples. To save it in a file other audio

Hi, I have application, where I am reciving the RTP packets, which has OPUS payload. >From the RTP packets I got following information: (12 byes Header) tells about the version, payload time, time stamp, srsc, etc. The rest of the packet is OPUS payload (raw format), The TOC byte from OPUS payload tells its 20ms frame, even the time stamp different of 960 means 20 msec frame. Questions: 1)

On 02/12/2014 07:59 PM, Michael S. Tsirkin wrote: > On Wed, Feb 12, 2014 at 01:43:28PM +0800, Jason Wang wrote: >> > We should alloc big buffers also when guest can receive UFO >> > pakcets. Otherwise the big packets will be truncated when mergeable rx >> > buffer is disabled. > Not truncated, they will be dropped. > Why dropped? We enable the ufo on tap0 if VIRTIO_NET_F_GUEST_UFO is negotiated. So skb was queued on the receive queue. But since the receive buffer is sm...

On 02/12/2014 07:59 PM, Michael S. Tsirkin wrote: > On Wed, Feb 12, 2014 at 01:43:28PM +0800, Jason Wang wrote: >> > We should alloc big buffers also when guest can receive UFO >> > pakcets. Otherwise the big packets will be truncated when mergeable rx >> > buffer is disabled. > Not truncated, they will be dropped. > Why dropped? We enable the ufo on tap0 if VIRTIO_NET_F_GUEST_UFO is negotiated. So skb was queued on the receive queue. But since the receive buffer is sm...

We should alloc big buffers also when guest can receive UFO pakcets. Otherwise the big packets will be truncated when mergeable rx buffer is disabled. Fixes 5c5167515d80f78f6bb538492c423adcae31ad65 (virtio-net: Allow UFO feature to be set and advertised.) Cc: Rusty Russell <rusty at rustcorp.com.au> Cc: Michael S. Tsirkin <mst at redhat.com> Cc: Sridh...

We should alloc big buffers also when guest can receive UFO pakcets. Otherwise the big packets will be truncated when mergeable rx buffer is disabled. Fixes 5c5167515d80f78f6bb538492c423adcae31ad65 (virtio-net: Allow UFO feature to be set and advertised.) Cc: Rusty Russell <rusty at rustcorp.com.au> Cc: Michael S. Tsirkin <mst at redhat.com> Cc: Sridh...

On Fri, Feb 21, 2014 at 01:08:04PM +0800, Jason Wang wrote: > We should alloc big buffers also when guest can receive UFO > pakcets to let the big packets be fit into guest rx buffer. s/pakcets/packets/ s/be fit/fit/ otherwise: Acked-by: Michael S. Tsirkin <mst at redhat.com> > > Fixes 5c5167515d80f78f6bb538492c423adcae31ad65 > (virtio-net: Allow UFO feature to be set and advertised.) > > Cc: Rusty...

Some deivces do not free the old tx skbs immediately after it has been sent (usually in tx interrupt). One such example is virtio-net which optimizes for virt and only free the possible old tx skbs during the next packet sending. This would lead the pktgen to wait forever in the refcount of the skb if no other pakcet will be sent afterwards. Solving this issue by introducing a new flag

Some deivces do not free the old tx skbs immediately after it has been sent (usually in tx interrupt). One such example is virtio-net which optimizes for virt and only free the possible old tx skbs during the next packet sending. This would lead the pktgen to wait forever in the refcount of the skb if no other pakcet will be sent afterwards. Solving this issue by introducing a new flag

.... socketio > 2. Capable to generate "answer-sdp" and return backing using same > signaling gateway. (make sure that ICE are gathered & included in the > anwer-sdp) > 3. For WebRTC, media server MUST support DTSL/SRTP to capture, trancode > and forward encrypted RTP/RTCP pakcets > > I don't know if icecast2 has such functionalities built-in. It currently > accepts PUT requests only on HTTP. > > ?You can install STUN server side by side with icecast2 on a separate > port.? > > ?I think a gateway (a middle media server) can capture opus/etc. orien...

On Wed, Feb 12, 2014 at 01:43:28PM +0800, Jason Wang wrote: > We should alloc big buffers also when guest can receive UFO > pakcets. Otherwise the big packets will be truncated when mergeable rx > buffer is disabled. Not truncated, they will be dropped. > Fixes 5c5167515d80f78f6bb538492c423adcae31ad65 > (virtio-net: Allow UFO feature to be set and advertised.) > > Cc: Rusty Russell <rusty at rustcorp.com.au&...

On Thu, Feb 13, 2014 at 11:02:13AM +0800, Jason Wang wrote: > On 02/12/2014 07:59 PM, Michael S. Tsirkin wrote: > > On Wed, Feb 12, 2014 at 01:43:28PM +0800, Jason Wang wrote: > >> > We should alloc big buffers also when guest can receive UFO > >> > pakcets. Otherwise the big packets will be truncated when mergeable rx > >> > buffer is disabled. > > Not truncated, they will be dropped. > > > > Why dropped? We enable the ufo on tap0 if VIRTIO_NET_F_GUEST_UFO is > negotiated. So skb was queued on the receive queue. But...

...re greately improved according to the test result. The throughput were kept or improved when transfter with large packets. But we get regression with small packet (<1500) transmission/receiving. According to the satistics, TCP tends batch less when mq is enabled which means much more but smaller pakcets were sent/received whcih lead much higher cpu utilization and degradate the throughput. In the future, either tuning of TCP or automatic switch bettwen mq and sq is needed. Test environment: - Intel(R) Xeon(R) CPU E5620 @ 2.40GHz, 8 cores 2 numa nodes - Two directed connected 82599 - Host/Guest ke...

...re greately improved according to the test result. The throughput were kept or improved when transfter with large packets. But we get regression with small packet (<1500) transmission/receiving. According to the satistics, TCP tends batch less when mq is enabled which means much more but smaller pakcets were sent/received whcih lead much higher cpu utilization and degradate the throughput. In the future, either tuning of TCP or automatic switch bettwen mq and sq is needed. Test environment: - Intel(R) Xeon(R) CPU E5620 @ 2.40GHz, 8 cores 2 numa nodes - Two directed connected 82599 - Host/Guest ke...