1-800-OVERLAYS: Using Overlay Networks to Improve VoIP Quality. Yair Amir, Claudiu Danilov, Stuart Goose, David Hedqvist, Andreas Terzis

Transcription

1 1-800-OVERLAYS: Using Overlay Networks to Improve VoIP Quality Yair Amir, Claudiu Danilov, Stuart Goose, David Hedqvist, Andreas Terzis

2 Voice over IP To call or not to call The Internet started as an overlay on top of the telephone network People expect high quality and reliable telephony While not impressed by constant good quality, users are easily disappointed by a few bad or dropped calls High quality calls demand predictable performance The best-effort service offered by the Internet was not designed to offer any quality guarantees Communication subject to dynamic loss, delay, jitter, path failures VoIP is interactive. Humans perceive delays at 100ms NOSSDAV

3 Quality Degradation with Loss PESQ - Average Normal 25% burst 50% burst 75% burst PSTN PESQ - 5 percentile Normal 25% burst 50% burst 75% burst Loss rate (%) Loss rate (%) 50ms network delay G.711 High quality voice codec PESQ Standardized measure of voice quality Internet characteristics in 2003 [Andersen et al, 03]: Average loss rate: 0.42% can be as high as 13% Conditional loss probability (burstiness): 66% NOSSDAV

4 Solution Highlights Use overlay networks to break end-to-end connections into multiple, shorter hops Localized real-time recovery on overlay links Retransmission is attempted only once Only if the packet is likely to arrive in time at destination Flexible routing avoids chronically congested paths Cost metric based on measured latency and loss rate of the links Link cost equivalent to the expected packet latency when retransmissions are considered NOSSDAV

5 Spines A generic overlay network research platform Spines builds an overlay router (daemon) on top of UDP, running as a regular user application Researchers can build protocols within its framework, experimenting with routing, link protocols, etc. Transparent API API similar to the socket interface, giving TCP, UDP and IP Multicast functionality A deployable platform Improving application performance over the Internet Enabling new services Open source ( NOSSDAV

6 The Spines Architecture Daemons create an overlay network on the fly Clients are identified by the IP address of their daemon and a port ID Clients feel they are working with UDP and TCP using their IP and port identifiers Up to several hundreds of daemons (locations). Each daemon can handle up to about 1000 clients NOSSDAV

7 Real-time Recovery Protocol Each node keeps a history of the packets forwarded in the last 100ms When the other end of a link detects a loss, requests a retransmission, and moves on If the upstream node still has the packet in the history, resends it Not a reliable protocol No blocking. No ACKs. No duplicates. loss 2 p 2 retr delay =3 T Δ Able to recover packets only for links shorter than 30 ms Overlay links are short! NOSSDAV

8 VoIP Quality Improvements PESQ - Average Spines Normal Spines 25% Spines 50% Spines 75% UDP Normal UDP 75% PESQ - 5 percentile Spines Normal Spines 25% Spines 50% Spines 75% UDP Normal UDP 75% Loss rate (%) Loss rate (%) Spines overlay 5 links of 10ms each 10 VoIP streams sending in parallel Loss on middle link C-D 1 0 m s 1 0 m s 1 0 m s 1 0 m s 1 0 m s A 1 0 M b p s B 1 0 M b p s C 1 0 M b p s D 1 0 M b p s E 1 0 M b p s F 50ms network delay NOSSDAV

9 Real-time Routing Metric Routing algorithm that takes into account retransmissions Which path maximizes the number of packets arriving at node E in under 100 ms? Finding the best path by computing loss and delay distribution on all the possible routes is very expensive Weight metric for links that approximates the best path A 1 0 m s, 2 % l o s s B C 2 0 m s, 1 % l o s s D? E Exp latency = 1 p T p 2 p 2 3 T Δ 2 p 2 T max NOSSDAV

10 Routing Simulation Evaluated different routing metrics on random topologies generated by BRITE [Medina et al, 01] On each topology, the nodes defining the diameter of the network (further appart) were chosen as sender and receiver Random loss rate from 0% to 5% on half of the links Optimizing Exp_latency metric compared with: hops: Number of hops in the path latency: Delay of the path loss: Cumulative loss on the path greedy: Dijkstra algorithm that computes delay distributions at each iteration and selects the partial path with maximum delivery ratio best path: Computed out of all the possible paths NOSSDAV

11 Routing Simulation (2) Avg. deliveryratio(%) best path explatency latency gredy hops los Avg.deliveryratio(%) explatency latency gredy hops los Networkdiameter(ms) Networkdiameter(ms) 15 nodes; 30 links 50 nodes; 100 links Each point in the graphs is an average over 1000 different topologies generated with BRITE Our simulator could not compute best path for topologies with more than 16 nodes in a timely manner NOSSDAV

12 Summary The voice quality is aversely affected by network conditions An overlay network approach breaks end-to-end connections into multiple, shorter hops Localized recovery on overlay links Takes care of sudden increases in loss Routing metric equivalent to the expected packet latency when retransmissions are considered Avoids long term congested paths NOSSDAV

13 Thanks! NOSSDAV

14 Additional Slides For the challenging questions from the audience NOSSDAV

15 Application-level Routing Scheduling expensive when competing with other processes Time-sensitive messaging systems should be run with high priority Spines overhead < 0.15ms when the overlay nodes run with real-time priority, even under a load of 10 Average packet delay (ms) VoIP streams Spines UDP M b p s L A N M b p s L A N A B C NOSSDAV

16 The Spines Architecture (2) Daemon-Client Interface Application Clien Reliable Session Session API Library Overlay Node Data Forwarder Routing Group State Link State State Flood Hello Protocol Reliable Datagram Overlay Link Real-time Data Link Best Data Effort Link Reliable Data Link Control Link Datalink (UDP/IP unicast) NOSSDAV

17 Packet Delay Distribution D e l a y ( m s ) U n i f o r m 2 5 % b u r s t 5 0 % b u r s t 7 5 % b u r s t D e l a y ( m s ) U n i f o r m P a c k e t s ( % ) P a c k e t s ( % ) 1 link, 10ms, 5% loss 2 concatenated links, 5% loss each Most of the packets arrive within network delay Retransmissions incur additional delay Small fraction of the packets are lost Burstiness affects retransmissions delay NOSSDAV

18 Related Work VoIP: Skype, Vonage, AT&T, etc. MPLS (Multi Protocol Label Switching) Pre-allocating resources (LSPs) in the Internet Packets follow established paths FEC (Forward Error Correction) Sending redundant information together with the data based on loss rate estimates Overlay Networks RON resilient routing using alternate paths XBone flexible routing using IP in IP tunneling OverQoS Link protocol that combines ARQ and FEC NOSSDAV