SlideShare una empresa de Scribd logo

Influence of Online Games Traffic Multiplexing and Router Buffer on Subjective Quality

•
•
Jose Saldana
Jose Saldana

This document discusses the influence of online games, traffic multiplexing, and router buffer on subjective quality. It presents the results of tests on multiplexing gaming traffic using different period sizes and router buffer configurations. The key findings are: - Multiplexing can reduce bandwidth and packets per second by up to 30% and 35% respectively, at the cost of increased delay and jitter. - Larger period sizes and router buffers increase delay more than smaller configurations. Multiplexing is limited by the bandwidth of around 1400kbps. - Jitter also increases with multiplexing but is limited by the bandwidth, while smaller router buffers introduce less jitter and delay.

EducaciónTecnologíaEntretenimiento y humor
1 de 60
Descargar para leer sin conexión
INFLUENCE OF ONLINE GAMES TRAFFIC MULTIPLEXING AND ROUTER BUFFER ON SUBJECTIVE QUALITY GTC Communication Technologies Group Jose Saldana Julián Fernández-Navajas José Ruiz-Mas Eduardo Viruete Navarro Luis Casadesus University of Zaragoza, Spain
Index - I. Introduction II. Related Works III. Test Methodology IV. Tests and Results V. Conclusions
Index - I. Introduction II. Related Works III. Test Methodology IV. Tests and Results V. Conclusions
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Introduction - Online games are getting very popular in the last years - First Person Shooters are the ones with the tightest real-time requirements
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Introduction FPS use a client-server architecture Uplink bandwidth limit
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Introduction FPS use a client-server architecture Server processing capacity limit
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Introduction FPS use a client-server architecture Downlink bandwidth limit
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Introduction “Shooting around the corner” Jack Wang Wang
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Introduction “Shooting around the corner” Wang: Dead Jack Wang Wang
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Introduction “Shooting around the corner” Wang: Dead Jack ¡¡¡ #%$& !!! Wang
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Introduction Main Key Performance Indicators (KPI): - Delay - Jitter - Packet loss buffer Internet . . . Users Router Game & background traffic Game Server
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Introduction Access networks: low-end routers, with limitations in: - Bandwidth - Packets per second Different implementations buffer Internet . . . Users Router Game & background traffic Game Server
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Introduction Scenarios where many users share a connection: we can multiplex packets from different players, and compress headers
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Introduction By multiplexing, we can mitigate two problems: - Bandwidth - Packets per second … at the cost of adding: - Delay - Jitter
Index - I. Introduction II. Related Works III. Test Methodology IV. Tests and Results V. Conclusions
II. Related Works - Multiplexing real-time flows - Subjective quality evaluation - Influence of the router buffer
II. Related Works - Multiplexing real-time flows - Subjective quality evaluation - Influence of the router buffer
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Multiplexing real-time A multiplexer is introduced, and it also compresses headers delaymux delayrouter delaynetwork IP network router . . . MUX DEMUX Game Server Players IP TCM IP
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Multiplexing real-time First done for VoIP (RFC4170, “TCRTP”): payload payload ECRTP ... ECRTP RTP UDP IP PPP Mux PPP L2TP IP Adapted for non-RTP flows: Payload Payload Reduced Header ... UDP Reduced Header IP PPP Mux PPP L2TP IP
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Multiplexing real-time A period is defined, and all the packets arrived are compressed and multiplexed Native traffic ... Multiplexed traffic . . . PE PE PE PE ... ...
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Multiplexing real-time Efficiency improvement One IPv4/TCP packet 1500 bytes η=1460/1500=97% One IPv4/UDP/RTP packet of VoIP with two samples of 10 bytes η=20/60=33% One IPv4/UDP server-to-client packet of Counter Strike with 9 players η=160/188=85% Four IPv4/UDP client-to-server packets of Counter Strike η=61/89=68% One IPv4/TCM packet multiplexing four client-to-server Counter Strike packets η=244/293=83% saving
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Multiplexing real-time Significant savings (Counter Strike) Bandwidth Saving 35% 30% 25% BS 20% 15% 20 players 10% 15 players 10 players 5% 5 players 0% 5 10 15 20 25 30 period (ms) 35 40 45 50
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Multiplexing real-time Significant savings (Counter Strike) Packets per second 600 20 players 15 players 500 10 players 5 players pps 400 300 200 100 0 native 5 10 15 20 25 period (ms) 30 35 40 45 50
II. Related Works - Multiplexing real-time flows - Subjective quality evaluation - Influence of the router buffer
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Multiplexing real-time - E-Model: VoIP delay and packet loss - FPS games: different studies consider delay limits, and also packet loss limits - G-Model: MOS formula for Quake IV, adapted from E-Model: delay and jitter
II. Related Works - Multiplexing real-time flows - Subjective quality evaluation - Influence of the router buffer
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Multiplexing real-time - Buffer size - - Bandwidth-delay product Stanford model Tiny buffer Buffer implementation - - Byte sized Packet sized Buffer limitations - Maximum pps amount
Index - I. Introduction II. Related Works III. Test Methodology IV. Tests and Results V. Conclusions
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Test methodology - Simulation scenario: - - Traces of gaming traffic Background traffic RTT delay: sum of the delays delaymux delayrouter delaynetwork IP network router . . . MUX DEMUX Game Server Players IP TCM IP
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Test methodology Jitter: Multiplexing increases it stdevmux  PE / 12 Different added delays Native traffic ... Multiplexed traffic . . . PE PE PE PE ... ...
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Test methodology BW↓ Buffer jitter↓ PE ↑ Mux jitter↑ delaymux delayrouter delaynetwork IP network router . . . MUX DEMUX Game Server Players IP TCM IP
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Test methodology Jitter has to be added in a proper way (Network jitter is considered independent) stdevmuxrouter  stdevmux 2  stdevrouter2  cov mr stdevtotal  stdevmuxrouter2  stdevnetwork2 delaymux delayrouter delaynetwork IP network router . . . MUX DEMUX Game Server Players IP TCM IP
Index - I. Introduction II. Related Works III. Test Methodology IV. Tests and Results V. Conclusions
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results Buffer: Drop-tail, 2 Mbps byte-sized small big packet-sized 10 kB 100 kB 16 packets 166 packets Buffers are equivalent, considering average packet size = 600 bytes
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results Game: Quake IV, 20 players 64 pps 79.5 bytes Native: 40.7 kbps x 20 players = 814 kbps Multiplexed PE=5ms: 631 kbps Multiplexed PE=15ms: 605 kbps 395 bytes 1,118 bytes
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: delay byte-sized packet-sized RTT, Quake IV, 16pack, 166 pack RTT, Quake IV, 10kB, 100kB 600 600 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 500 500 400 ms 400 ms native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 300 300 200 200 100 100 0 0 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: delay byte-sized packet-sized RTT, Quake IV, 10kB, 100kB Bandwidth limit mux ≈1400 kbps 600 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 500 native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 500 400 ms 400 ms RTT, Quake IV, 16pack, 166 pack 600 300 300 200 200 100 100 0 0 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 400 Bandwidth limit native ≈ 1200 kbps 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: delay byte-sized packet-sized RTT, Quake IV, 16pack, 166 pack RTT, Quake IV, 10kB, 100kB 600 600 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 500 500 400 ms 400 ms native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 300 300 200 200 100 100 0 0 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 Buffer delay is constant 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 Buffer delay varies as packet size increases 2000
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: delay byte-sized packet-sized RTT, Quake IV, 16pack, 166 pack RTT, Quake IV, 10kB, 100kB 600 600 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 500 500 400 ms 400 ms native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 300 300 200 200 100 100 0 0 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 400 Small buffers introduce small delays 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: jitter byte-sized packet-sized jitter, Quake IV, 10kB, 100kB jitter, Quake IV, 16pack, 166 pack 140 140 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 120 100 native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 120 100 80 ms ms 80 60 60 40 40 20 20 0 0 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: jitter byte-sized packet-sized jitter, Quake IV, 10kB, 100kB jitter, Quake IV, 16pack, 166 pack Bandwidth limit mux ≈1400 kbps 140 140 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 120 100 native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 120 100 80 ms ms 80 60 60 40 40 20 20 0 0 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 400 600 Bandwidth limit native ≈ 1200 kbps 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: jitter byte-sized packet-sized jitter, Quake IV, 10kB, 100kB jitter, Quake IV, 16pack, 166 pack 140 140 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 120 100 native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack Average size of sent packets is bigger for packet-sized buffer, so jitter decreases 120 100 80 ms ms 80 60 60 40 40 20 20 0 0 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 Big packets have a bigger dropping probability 1800 2000 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 All packets have the same dropping probability 1800 2000
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: loss byte-sized packet-sized packet loss, Quake IV, 16pack, 166 pack packet loss, Quake IV, 10kB, 100kB 35% 35% native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 30% 30% 25% %packet loss %packet loss 25% native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 20% 15% 20% 15% 10% 10% 5% 5% 0% 0% 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: loss byte-sized packet-sized packet loss, Quake IV, 16pack, 166 pack packet loss, Quake IV, 10kB, 100kB 35% 35% native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 30% 30% 25% %packet loss %packet loss 25% native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 20% 15% 20% 15% 10% 10% 5% 5% 0% 0% 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 400 600 Small buffer starts loosing packets before reaching the limit 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: loss byte-sized packet-sized packet loss, Quake IV, 16pack, 166 pack packet loss, Quake IV, 10kB, 100kB 35% 35% native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 30% 30% 25% %packet loss %packet loss 25% native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 20% 15% 20% 15% 10% 10% 5% 5% 0% 0% 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 PE=15 obtains the worst results, because of packet size (1,118 bytes) 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: loss byte-sized packet-sized packet loss, Quake IV, 16pack, 166 pack packet loss, Quake IV, 10kB, 100kB 35% 35% native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 30% 30% 25% %packet loss %packet loss 25% native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 20% 15% 20% 15% 10% 10% 5% 5% 0% 0% 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 Worse results for packet-sized, because all the packets have the same discarding probability 1600 1800 2000
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: loss byte-sized packet-sized packet loss, Quake IV, 16pack, 166 pack packet loss, Quake IV, 10kB, 100kB 35% 35% native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 30% 30% 25% %packet loss %packet loss 25% native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 20% 15% 20% 15% 10% 10% 5% 5% 0% 0% 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 For packet-sized buffer, packet loss is significantly reduced when multiplexing 2000
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: MOS byte-sized packet-sized MOS, Quake IV, 16pack, 166 pack MOS, Quake IV, 10kB, 100kB 4.5 4 4 3.5 3.5 MOS 5 4.5 MOS 5 3 3 2.5 2.5 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 2 1.5 native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 2 1.5 1 1 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 MOS is based on delay and jitter 1800 2000
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: MOS byte-sized packet-sized MOS, Quake IV, 16pack, 166 pack MOS, Quake IV, 10kB, 100kB 4.5 4 4 3.5 3.5 MOS 5 4.5 MOS 5 3 3 2.5 2.5 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 2 1.5 native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 2 1.5 1 1 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 400 600 Small buffers: graphs go down, and grow a little when jitter peak goes down 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: MOS byte-sized packet-sized MOS, Quake IV, 16pack, 166 pack MOS, Quake IV, 10kB, 100kB 4.5 4 4 3.5 3.5 MOS 5 4.5 MOS 5 3 3 2.5 2.5 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 2 1.5 native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 2 1.5 1 1 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 Multiplexing allows more background traffic 1800 2000 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: MOS byte-sized packet-sized MOS, Quake IV, 16pack, 166 pack MOS, Quake IV, 10kB, 100kB 4.5 4 4 3.5 3.5 MOS 5 4.5 MOS 5 3 3 2.5 2.5 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 2 1.5 native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 2 1.5 1 1 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 Multiplexing results are worse than native 2000
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: MOS byte-sized byte-sized pps limit MOS, Quake IV, 10kB, 100kB MOS, Quake IV, 10kB, 100kB 4.5 4 4 3.5 3.5 MOS 5 4.5 MOS 5 3 2.5 3 2.5 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 2 1.5 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 2 1.5 1 1 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 2,000 pps (maximum 1,652 offered) 1800 2000
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: MOS byte-sized byte-sized pps limit MOS, Quake IV, 10kB, 100kB MOS, Quake IV, 10kB, 100kB 4.5 4 4 3.5 3.5 MOS 5 4.5 MOS 5 3 2.5 3 2.5 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 2 1.5 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 2 1.5 1 1 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 400 600 800 1000 1200 background traffic (kbps) This limitation has a very bad effect on MOS. Multiplexing alleviates it 1400 1600 1800 2000
Index - I. Introduction II. Related Works III. Test Methodology IV. Tests and Results V. Conclusions
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Conclusions - The mutual influence of the buffer router and multiplexing has been studied - Small buffers are more adequate to reduce delay and jitter - Packet-sized buffers increase packet loss, and multiplexing alleviates this
CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Conclusions - Multiplexing always saves bandwidth - In packet-sized buffers, multiplexing does not improve experienced quality - Multiplexing is very interesting when a limit in pps is present
THANK YOU GTC Communication Technologies Group jsaldana@unizar.es
Extra Slides

Recomendados

Bandwidth Efficiency Improvement for Online Games by the use of Tunneling, Co...
Bandwidth Efficiency Improvement for Online Games by the use of Tunneling, Co...Bandwidth Efficiency Improvement for Online Games by the use of Tunneling, Co...
Bandwidth Efficiency Improvement for Online Games by the use of Tunneling, Co...Jose Saldana
 
debugging openstack neutron /w openvswitch
debugging openstack neutron /w openvswitchdebugging openstack neutron /w openvswitch
debugging openstack neutron /w openvswitch어형 이
 
H2O - the optimized HTTP server
H2O - the optimized HTTP serverH2O - the optimized HTTP server
H2O - the optimized HTTP serverKazuho Oku
 
Teach your (micro)services talk Protocol Buffers with gRPC.
Teach your (micro)services talk Protocol Buffers with gRPC.Teach your (micro)services talk Protocol Buffers with gRPC.
Teach your (micro)services talk Protocol Buffers with gRPC.Mihai Iachimovschi
 
How happy they became with H2O/mruby and the future of HTTP
How happy they became with H2O/mruby and the future of HTTPHow happy they became with H2O/mruby and the future of HTTP
How happy they became with H2O/mruby and the future of HTTPIchito Nagata
 
Reorganizing Website Architecture for HTTP/2 and Beyond
Reorganizing Website Architecture for HTTP/2 and BeyondReorganizing Website Architecture for HTTP/2 and Beyond
Reorganizing Website Architecture for HTTP/2 and BeyondKazuho Oku
 
Taking Security Groups to Ludicrous Speed with OVS (OpenStack Summit 2015)
Taking Security Groups to Ludicrous Speed with OVS (OpenStack Summit 2015)Taking Security Groups to Ludicrous Speed with OVS (OpenStack Summit 2015)
Taking Security Groups to Ludicrous Speed with OVS (OpenStack Summit 2015)Thomas Graf
 
2015 FOSDEM - OVS Stateful Services
2015 FOSDEM - OVS Stateful Services2015 FOSDEM - OVS Stateful Services
2015 FOSDEM - OVS Stateful ServicesThomas Graf
 

Recomendados

Bandwidth Efficiency Improvement for Online Games by the use of Tunneling, Co...
Bandwidth Efficiency Improvement for Online Games by the use of Tunneling, Co...Bandwidth Efficiency Improvement for Online Games by the use of Tunneling, Co...
Bandwidth Efficiency Improvement for Online Games by the use of Tunneling, Co...Jose Saldana
 
debugging openstack neutron /w openvswitch
debugging openstack neutron /w openvswitchdebugging openstack neutron /w openvswitch
debugging openstack neutron /w openvswitch어형 이
 
H2O - the optimized HTTP server
H2O - the optimized HTTP serverH2O - the optimized HTTP server
H2O - the optimized HTTP serverKazuho Oku
 
Teach your (micro)services talk Protocol Buffers with gRPC.
Teach your (micro)services talk Protocol Buffers with gRPC.Teach your (micro)services talk Protocol Buffers with gRPC.
Teach your (micro)services talk Protocol Buffers with gRPC.Mihai Iachimovschi
 
How happy they became with H2O/mruby and the future of HTTP
How happy they became with H2O/mruby and the future of HTTPHow happy they became with H2O/mruby and the future of HTTP
How happy they became with H2O/mruby and the future of HTTPIchito Nagata
 
Reorganizing Website Architecture for HTTP/2 and Beyond
Reorganizing Website Architecture for HTTP/2 and BeyondReorganizing Website Architecture for HTTP/2 and Beyond
Reorganizing Website Architecture for HTTP/2 and BeyondKazuho Oku
 
Taking Security Groups to Ludicrous Speed with OVS (OpenStack Summit 2015)
Taking Security Groups to Ludicrous Speed with OVS (OpenStack Summit 2015)Taking Security Groups to Ludicrous Speed with OVS (OpenStack Summit 2015)
Taking Security Groups to Ludicrous Speed with OVS (OpenStack Summit 2015)Thomas Graf
 
2015 FOSDEM - OVS Stateful Services
2015 FOSDEM - OVS Stateful Services2015 FOSDEM - OVS Stateful Services
2015 FOSDEM - OVS Stateful ServicesThomas Graf
 
How to Speak Intel DPDK KNI for Web Services.
How to Speak Intel DPDK KNI for Web Services.How to Speak Intel DPDK KNI for Web Services.
How to Speak Intel DPDK KNI for Web Services.Naoto MATSUMOTO
 
Packet Framework - Cristian Dumitrescu
Packet Framework - Cristian DumitrescuPacket Framework - Cristian Dumitrescu
Packet Framework - Cristian Dumitrescuharryvanhaaren
 
7. protocols
7. protocols7. protocols
7. protocolsMarian Marinov
 
LinuxCon 2015 Linux Kernel Networking Walkthrough
LinuxCon 2015 Linux Kernel Networking WalkthroughLinuxCon 2015 Linux Kernel Networking Walkthrough
LinuxCon 2015 Linux Kernel Networking WalkthroughThomas Graf
 
Tcpdump
TcpdumpTcpdump
TcpdumpMohamed Gamel
 
Userspace networking
Userspace networkingUserspace networking
Userspace networkingStephen Hemminger
 
Introduction to tcp ip linux networking
Introduction to tcp ip linux networkingIntroduction to tcp ip linux networking
Introduction to tcp ip linux networkingSreenatha Reddy K R
 
Linux Networking Explained
Linux Networking ExplainedLinux Networking Explained
Linux Networking ExplainedThomas Graf
 
Course on TCP Dynamic Performance
Course on TCP Dynamic PerformanceCourse on TCP Dynamic Performance
Course on TCP Dynamic PerformanceJavier Arauz
 
7.protocols 2
7.protocols 27.protocols 2
7.protocols 2Marian Marinov
 
Lecture set 7
Lecture set 7Lecture set 7
Lecture set 7Gopi Saiteja
 
R bernardino hand_in_assignment_week_1
R bernardino hand_in_assignment_week_1R bernardino hand_in_assignment_week_1
R bernardino hand_in_assignment_week_1Raul Bernardino, BSc MSc
 
Client server
Client serverClient server
Client servermaryam1231
 
Network sockets
Network socketsNetwork sockets
Network socketsDenys Haryachyy
 
HTTP/2で 速くなるとき ならないとき
HTTP/2で 速くなるとき ならないときHTTP/2で 速くなるとき ならないとき
HTTP/2で 速くなるとき ならないときKazuho Oku
 
RTSP Analysis Wireshark
RTSP Analysis WiresharkRTSP Analysis Wireshark
RTSP Analysis WiresharkYoss Cohen
 
Troubleshooting TCP/IP
Troubleshooting TCP/IPTroubleshooting TCP/IP
Troubleshooting TCP/IPvijai s
 
OpenStack 2012 fall summit observation - Quantum/SDN
OpenStack 2012 fall summit observation - Quantum/SDNOpenStack 2012 fall summit observation - Quantum/SDN
OpenStack 2012 fall summit observation - Quantum/SDNTe-Yen Liu
 
DevConf 2014 Kernel Networking Walkthrough
DevConf 2014 Kernel Networking WalkthroughDevConf 2014 Kernel Networking Walkthrough
DevConf 2014 Kernel Networking WalkthroughThomas Graf
 
Comparison of Multiplexing Policies for FPS Games in terms of Subjective Quality
Comparison of Multiplexing Policies for FPS Games in terms of Subjective QualityComparison of Multiplexing Policies for FPS Games in terms of Subjective Quality
Comparison of Multiplexing Policies for FPS Games in terms of Subjective QualityJose Saldana
 
Alternative Network Deployments
Alternative Network DeploymentsAlternative Network Deployments
Alternative Network DeploymentsJose Saldana
 
Empirically Characterizing the Buffer Behaviour of Real Devices
Empirically Characterizing the Buffer Behaviour of Real DevicesEmpirically Characterizing the Buffer Behaviour of Real Devices
Empirically Characterizing the Buffer Behaviour of Real DevicesJose Saldana
 

Más contenido relacionado

La actualidad más candente

How to Speak Intel DPDK KNI for Web Services.
How to Speak Intel DPDK KNI for Web Services.How to Speak Intel DPDK KNI for Web Services.
How to Speak Intel DPDK KNI for Web Services.Naoto MATSUMOTO
 
Packet Framework - Cristian Dumitrescu
Packet Framework - Cristian DumitrescuPacket Framework - Cristian Dumitrescu
Packet Framework - Cristian Dumitrescuharryvanhaaren
 
LinuxCon 2015 Linux Kernel Networking Walkthrough
LinuxCon 2015 Linux Kernel Networking WalkthroughLinuxCon 2015 Linux Kernel Networking Walkthrough
LinuxCon 2015 Linux Kernel Networking WalkthroughThomas Graf
 
Introduction to tcp ip linux networking
Introduction to tcp ip linux networkingIntroduction to tcp ip linux networking
Introduction to tcp ip linux networkingSreenatha Reddy K R
 
Linux Networking Explained
Linux Networking ExplainedLinux Networking Explained
Linux Networking ExplainedThomas Graf
 
Course on TCP Dynamic Performance
Course on TCP Dynamic PerformanceCourse on TCP Dynamic Performance
Course on TCP Dynamic PerformanceJavier Arauz
 
HTTP/2で 速くなるとき ならないとき
HTTP/2で 速くなるとき ならないときHTTP/2で 速くなるとき ならないとき
HTTP/2で 速くなるとき ならないときKazuho Oku
 
RTSP Analysis Wireshark
RTSP Analysis WiresharkRTSP Analysis Wireshark
RTSP Analysis WiresharkYoss Cohen
 
Troubleshooting TCP/IP
Troubleshooting TCP/IPTroubleshooting TCP/IP
Troubleshooting TCP/IPvijai s
 
OpenStack 2012 fall summit observation - Quantum/SDN
OpenStack 2012 fall summit observation - Quantum/SDNOpenStack 2012 fall summit observation - Quantum/SDN
OpenStack 2012 fall summit observation - Quantum/SDNTe-Yen Liu
 
DevConf 2014 Kernel Networking Walkthrough
DevConf 2014 Kernel Networking WalkthroughDevConf 2014 Kernel Networking Walkthrough
DevConf 2014 Kernel Networking WalkthroughThomas Graf
 
Comparison of Multiplexing Policies for FPS Games in terms of Subjective Quality
Comparison of Multiplexing Policies for FPS Games in terms of Subjective QualityComparison of Multiplexing Policies for FPS Games in terms of Subjective Quality
Comparison of Multiplexing Policies for FPS Games in terms of Subjective QualityJose Saldana
 

La actualidad más candente (20)

How to Speak Intel DPDK KNI for Web Services.
How to Speak Intel DPDK KNI for Web Services.How to Speak Intel DPDK KNI for Web Services.
How to Speak Intel DPDK KNI for Web Services.
 
Packet Framework - Cristian Dumitrescu
Packet Framework - Cristian DumitrescuPacket Framework - Cristian Dumitrescu
Packet Framework - Cristian Dumitrescu
 
7. protocols
7. protocols7. protocols
7. protocols
 
LinuxCon 2015 Linux Kernel Networking Walkthrough
LinuxCon 2015 Linux Kernel Networking WalkthroughLinuxCon 2015 Linux Kernel Networking Walkthrough
LinuxCon 2015 Linux Kernel Networking Walkthrough
 
Tcpdump
TcpdumpTcpdump
Tcpdump
 
Userspace networking
Userspace networkingUserspace networking
Userspace networking
 
Introduction to tcp ip linux networking
Introduction to tcp ip linux networkingIntroduction to tcp ip linux networking
Introduction to tcp ip linux networking
 
Linux Networking Explained
Linux Networking ExplainedLinux Networking Explained
Linux Networking Explained
 
Course on TCP Dynamic Performance
Course on TCP Dynamic PerformanceCourse on TCP Dynamic Performance
Course on TCP Dynamic Performance
 
7.protocols 2
7.protocols 27.protocols 2
7.protocols 2
 
Lecture set 7
Lecture set 7Lecture set 7
Lecture set 7
 
R bernardino hand_in_assignment_week_1
R bernardino hand_in_assignment_week_1R bernardino hand_in_assignment_week_1
R bernardino hand_in_assignment_week_1
 
Client server
Client serverClient server
Client server
 
Network sockets
Network socketsNetwork sockets
Network sockets
 
HTTP/2で 速くなるとき ならないとき
HTTP/2で 速くなるとき ならないときHTTP/2で 速くなるとき ならないとき
HTTP/2で 速くなるとき ならないとき
 
RTSP Analysis Wireshark
RTSP Analysis WiresharkRTSP Analysis Wireshark
RTSP Analysis Wireshark
 
Troubleshooting TCP/IP
Troubleshooting TCP/IPTroubleshooting TCP/IP
Troubleshooting TCP/IP
 
OpenStack 2012 fall summit observation - Quantum/SDN
OpenStack 2012 fall summit observation - Quantum/SDNOpenStack 2012 fall summit observation - Quantum/SDN
OpenStack 2012 fall summit observation - Quantum/SDN
 
DevConf 2014 Kernel Networking Walkthrough
DevConf 2014 Kernel Networking WalkthroughDevConf 2014 Kernel Networking Walkthrough
DevConf 2014 Kernel Networking Walkthrough
 
Comparison of Multiplexing Policies for FPS Games in terms of Subjective Quality
Comparison of Multiplexing Policies for FPS Games in terms of Subjective QualityComparison of Multiplexing Policies for FPS Games in terms of Subjective Quality
Comparison of Multiplexing Policies for FPS Games in terms of Subjective Quality
 

Destacado

Alternative Network Deployments
Alternative Network DeploymentsAlternative Network Deployments
Alternative Network DeploymentsJose Saldana
 
Empirically Characterizing the Buffer Behaviour of Real Devices
Empirically Characterizing the Buffer Behaviour of Real DevicesEmpirically Characterizing the Buffer Behaviour of Real Devices
Empirically Characterizing the Buffer Behaviour of Real DevicesJose Saldana
 
Το μουσείο του μέλλοντος
Το μουσείο του μέλλοντοςΤο μουσείο του μέλλοντος
Το μουσείο του μέλλοντοςΗΡΩ ΧΑΤΖΑΣΚΟΥ
 
Menu restaurant higia lunch (4)
Menu restaurant higia lunch (4)Menu restaurant higia lunch (4)
Menu restaurant higia lunch (4)Asclepios9
 
Menu à la Carte - Restaurante Mozart - English
Menu à la Carte - Restaurante Mozart - EnglishMenu à la Carte - Restaurante Mozart - English
Menu à la Carte - Restaurante Mozart - EnglishGrupoForte
 
Bar-BoF session about Simplemux at IETF93, Prague
Bar-BoF session about Simplemux at IETF93, PragueBar-BoF session about Simplemux at IETF93, Prague
Bar-BoF session about Simplemux at IETF93, PragueJose Saldana
 
,Dana info=www.blackwell synergy.com+j.1601-1546.2005.00129
,Dana info=www.blackwell synergy.com+j.1601-1546.2005.00129,Dana info=www.blackwell synergy.com+j.1601-1546.2005.00129
,Dana info=www.blackwell synergy.com+j.1601-1546.2005.00129ibugesic1234
 

Destacado (7)

Alternative Network Deployments
Alternative Network DeploymentsAlternative Network Deployments
Alternative Network Deployments
 
Empirically Characterizing the Buffer Behaviour of Real Devices
Empirically Characterizing the Buffer Behaviour of Real DevicesEmpirically Characterizing the Buffer Behaviour of Real Devices
Empirically Characterizing the Buffer Behaviour of Real Devices
 
Το μουσείο του μέλλοντος
Το μουσείο του μέλλοντοςΤο μουσείο του μέλλοντος
Το μουσείο του μέλλοντος
 
Menu restaurant higia lunch (4)
Menu restaurant higia lunch (4)Menu restaurant higia lunch (4)
Menu restaurant higia lunch (4)
 
Menu à la Carte - Restaurante Mozart - English
Menu à la Carte - Restaurante Mozart - EnglishMenu à la Carte - Restaurante Mozart - English
Menu à la Carte - Restaurante Mozart - English
 
Bar-BoF session about Simplemux at IETF93, Prague
Bar-BoF session about Simplemux at IETF93, PragueBar-BoF session about Simplemux at IETF93, Prague
Bar-BoF session about Simplemux at IETF93, Prague
 
,Dana info=www.blackwell synergy.com+j.1601-1546.2005.00129
,Dana info=www.blackwell synergy.com+j.1601-1546.2005.00129,Dana info=www.blackwell synergy.com+j.1601-1546.2005.00129
,Dana info=www.blackwell synergy.com+j.1601-1546.2005.00129
 

Similar a Influence of Online Games Traffic Multiplexing and Router Buffer on Subjective Quality

The Effect of Router Buffer Size on Subjective Gaming Quality Estimators base...
The Effect of Router Buffer Size on Subjective Gaming Quality Estimators base...The Effect of Router Buffer Size on Subjective Gaming Quality Estimators base...
The Effect of Router Buffer Size on Subjective Gaming Quality Estimators base...Jose Saldana
 
The Utility of Characterizing Packet Loss as a Function of Packet Size in Com...
The Utility of Characterizing Packet Loss as a Function of Packet Size in Com...The Utility of Characterizing Packet Loss as a Function of Packet Size in Com...
The Utility of Characterizing Packet Loss as a Function of Packet Size in Com...Jose Saldana
 
Can We Multiplex ACKs without Harming the Performance of TCP?
Can We Multiplex ACKs without Harming the Performance of TCP?Can We Multiplex ACKs without Harming the Performance of TCP?
Can We Multiplex ACKs without Harming the Performance of TCP?Jose Saldana
 
BISmark : the broadband internet service benchmark
BISmark : the broadband internet service benchmarkBISmark : the broadband internet service benchmark
BISmark : the broadband internet service benchmarkNaLUG
 
Challenges and experiences with IPTV from a network point of view
Challenges and experiences with IPTV from a network point of viewChallenges and experiences with IPTV from a network point of view
Challenges and experiences with IPTV from a network point of viewbrouer
 
Introducing the CrossLink Programmable ASSP
Introducing the CrossLink Programmable ASSPIntroducing the CrossLink Programmable ASSP
Introducing the CrossLink Programmable ASSPLatticeSemiconductor
 
Yet another json rpc library (mole rpc)
Yet another json rpc library (mole rpc)Yet another json rpc library (mole rpc)
Yet another json rpc library (mole rpc)Viktor Turskyi
 
CHEP2012_Upgrade_CMS_Event_Builder_AP_21052011
CHEP2012_Upgrade_CMS_Event_Builder_AP_21052011CHEP2012_Upgrade_CMS_Event_Builder_AP_21052011
CHEP2012_Upgrade_CMS_Event_Builder_AP_21052011Andrea PETRUCCI
 
TCP & UDP Streaming Comparison and a Study on DCCP & SCTP Protocols
TCP & UDP Streaming Comparison and a Study on DCCP & SCTP ProtocolsTCP & UDP Streaming Comparison and a Study on DCCP & SCTP Protocols
TCP & UDP Streaming Comparison and a Study on DCCP & SCTP ProtocolsPeter SHIN
 
Introduction to DPDK
Introduction to DPDKIntroduction to DPDK
Introduction to DPDKKernel TLV
 
Jawdat NGN IDNOG v1.0 public
Jawdat NGN IDNOG v1.0 publicJawdat NGN IDNOG v1.0 public
Jawdat NGN IDNOG v1.0 publicHimawan Nugroho
 
JAWDAT NGN IDNOG v1.0 (public)[COPY]
JAWDAT NGN IDNOG v1.0 (public)[COPY]JAWDAT NGN IDNOG v1.0 (public)[COPY]
JAWDAT NGN IDNOG v1.0 (public)[COPY]Mahadiputra S
 
03 (IDNOG01) NGN Next Generation Networks by Himawan Nugroho
03 (IDNOG01) NGN Next Generation Networks by Himawan Nugroho03 (IDNOG01) NGN Next Generation Networks by Himawan Nugroho
03 (IDNOG01) NGN Next Generation Networks by Himawan NugrohoIndonesia Network Operators Group
 
High Performance Networking Leveraging the DPDK and Growing Community
High Performance Networking Leveraging the DPDK and Growing CommunityHigh Performance Networking Leveraging the DPDK and Growing Community
High Performance Networking Leveraging the DPDK and Growing Community6WIND
 
Traffic Optimization for TCP-based Massive Multiplayer Online Games
Traffic Optimization for TCP-based Massive Multiplayer Online GamesTraffic Optimization for TCP-based Massive Multiplayer Online Games
Traffic Optimization for TCP-based Massive Multiplayer Online GamesJose Saldana
 
DPDK Summit - 08 Sept 2014 - 6WIND - High Perf Networking Leveraging the DPDK...
DPDK Summit - 08 Sept 2014 - 6WIND - High Perf Networking Leveraging the DPDK...DPDK Summit - 08 Sept 2014 - 6WIND - High Perf Networking Leveraging the DPDK...
DPDK Summit - 08 Sept 2014 - 6WIND - High Perf Networking Leveraging the DPDK...Jim St. Leger
 
eProsima RPC over DDS - OMG June 2013 Berlin Meeting
eProsima RPC over DDS - OMG June 2013 Berlin MeetingeProsima RPC over DDS - OMG June 2013 Berlin Meeting
eProsima RPC over DDS - OMG June 2013 Berlin MeetingJaime Martin Losa
 
Optimization of Low-efficiency Traffic in OpenFlow Software Defined Networks
Optimization of Low-efficiency Traffic in OpenFlow Software Defined NetworksOptimization of Low-efficiency Traffic in OpenFlow Software Defined Networks
Optimization of Low-efficiency Traffic in OpenFlow Software Defined NetworksJose Saldana
 
Chapter7 multimedia
Chapter7 multimediaChapter7 multimedia
Chapter7 multimediaKhánh Ghẻ
 

Similar a Influence of Online Games Traffic Multiplexing and Router Buffer on Subjective Quality (20)

The Effect of Router Buffer Size on Subjective Gaming Quality Estimators base...
The Effect of Router Buffer Size on Subjective Gaming Quality Estimators base...The Effect of Router Buffer Size on Subjective Gaming Quality Estimators base...
The Effect of Router Buffer Size on Subjective Gaming Quality Estimators base...
 
The Utility of Characterizing Packet Loss as a Function of Packet Size in Com...
The Utility of Characterizing Packet Loss as a Function of Packet Size in Com...The Utility of Characterizing Packet Loss as a Function of Packet Size in Com...
The Utility of Characterizing Packet Loss as a Function of Packet Size in Com...
 
Can We Multiplex ACKs without Harming the Performance of TCP?
Can We Multiplex ACKs without Harming the Performance of TCP?Can We Multiplex ACKs without Harming the Performance of TCP?
Can We Multiplex ACKs without Harming the Performance of TCP?
 
BISmark : the broadband internet service benchmark
BISmark : the broadband internet service benchmarkBISmark : the broadband internet service benchmark
BISmark : the broadband internet service benchmark
 
Challenges and experiences with IPTV from a network point of view
Challenges and experiences with IPTV from a network point of viewChallenges and experiences with IPTV from a network point of view
Challenges and experiences with IPTV from a network point of view
 
Simplify Networking for Containers
Simplify Networking for ContainersSimplify Networking for Containers
Simplify Networking for Containers
 
Introducing the CrossLink Programmable ASSP
Introducing the CrossLink Programmable ASSPIntroducing the CrossLink Programmable ASSP
Introducing the CrossLink Programmable ASSP
 
Yet another json rpc library (mole rpc)
Yet another json rpc library (mole rpc)Yet another json rpc library (mole rpc)
Yet another json rpc library (mole rpc)
 
CHEP2012_Upgrade_CMS_Event_Builder_AP_21052011
CHEP2012_Upgrade_CMS_Event_Builder_AP_21052011CHEP2012_Upgrade_CMS_Event_Builder_AP_21052011
CHEP2012_Upgrade_CMS_Event_Builder_AP_21052011
 
TCP & UDP Streaming Comparison and a Study on DCCP & SCTP Protocols
TCP & UDP Streaming Comparison and a Study on DCCP & SCTP ProtocolsTCP & UDP Streaming Comparison and a Study on DCCP & SCTP Protocols
TCP & UDP Streaming Comparison and a Study on DCCP & SCTP Protocols
 
Introduction to DPDK
Introduction to DPDKIntroduction to DPDK
Introduction to DPDK
 
Jawdat NGN IDNOG v1.0 public
Jawdat NGN IDNOG v1.0 publicJawdat NGN IDNOG v1.0 public
Jawdat NGN IDNOG v1.0 public
 
JAWDAT NGN IDNOG v1.0 (public)[COPY]
JAWDAT NGN IDNOG v1.0 (public)[COPY]JAWDAT NGN IDNOG v1.0 (public)[COPY]
JAWDAT NGN IDNOG v1.0 (public)[COPY]
 
03 (IDNOG01) NGN Next Generation Networks by Himawan Nugroho
03 (IDNOG01) NGN Next Generation Networks by Himawan Nugroho03 (IDNOG01) NGN Next Generation Networks by Himawan Nugroho
03 (IDNOG01) NGN Next Generation Networks by Himawan Nugroho
 
High Performance Networking Leveraging the DPDK and Growing Community
High Performance Networking Leveraging the DPDK and Growing CommunityHigh Performance Networking Leveraging the DPDK and Growing Community
High Performance Networking Leveraging the DPDK and Growing Community
 
Traffic Optimization for TCP-based Massive Multiplayer Online Games
Traffic Optimization for TCP-based Massive Multiplayer Online GamesTraffic Optimization for TCP-based Massive Multiplayer Online Games
Traffic Optimization for TCP-based Massive Multiplayer Online Games
 
DPDK Summit - 08 Sept 2014 - 6WIND - High Perf Networking Leveraging the DPDK...
DPDK Summit - 08 Sept 2014 - 6WIND - High Perf Networking Leveraging the DPDK...DPDK Summit - 08 Sept 2014 - 6WIND - High Perf Networking Leveraging the DPDK...
DPDK Summit - 08 Sept 2014 - 6WIND - High Perf Networking Leveraging the DPDK...
 
eProsima RPC over DDS - OMG June 2013 Berlin Meeting
eProsima RPC over DDS - OMG June 2013 Berlin MeetingeProsima RPC over DDS - OMG June 2013 Berlin Meeting
eProsima RPC over DDS - OMG June 2013 Berlin Meeting
 
Optimization of Low-efficiency Traffic in OpenFlow Software Defined Networks
Optimization of Low-efficiency Traffic in OpenFlow Software Defined NetworksOptimization of Low-efficiency Traffic in OpenFlow Software Defined Networks
Optimization of Low-efficiency Traffic in OpenFlow Software Defined Networks
 
Chapter7 multimedia
Chapter7 multimediaChapter7 multimedia
Chapter7 multimedia
 

Más de Jose Saldana

Pint of science Patinete as a Service
Pint of science Patinete as a ServicePint of science Patinete as a Service
Pint of science Patinete as a ServiceJose Saldana
 
Mejorar tu empleabilidad como ingeniero
Mejorar tu empleabilidad como ingenieroMejorar tu empleabilidad como ingeniero
Mejorar tu empleabilidad como ingenieroJose Saldana
 
POUZ Universidad de Zaragoza - Telecomunicación 2º y 3º
POUZ Universidad de Zaragoza - Telecomunicación 2º y 3ºPOUZ Universidad de Zaragoza - Telecomunicación 2º y 3º
POUZ Universidad de Zaragoza - Telecomunicación 2º y 3ºJose Saldana
 
Cómo se conectan los ordenadores y los móviles
Cómo se conectan los ordenadores y los móvilesCómo se conectan los ordenadores y los móviles
Cómo se conectan los ordenadores y los móvilesJose Saldana
 
La bala que dobló la esquina: el problema de los videojuegos online
La bala que dobló la esquina: el problema de los videojuegos onlineLa bala que dobló la esquina: el problema de los videojuegos online
La bala que dobló la esquina: el problema de los videojuegos onlineJose Saldana
 
Entretenimiento online. Una perspectiva cristiana
Entretenimiento online. Una perspectiva cristianaEntretenimiento online. Una perspectiva cristiana
Entretenimiento online. Una perspectiva cristianaJose Saldana
 
¿Por qué el WiFi se va y se viene?
¿Por qué el WiFi se va y se viene?¿Por qué el WiFi se va y se viene?
¿Por qué el WiFi se va y se viene?Jose Saldana
 
Wi-5: Advanced Features for Low-cost Wi-Fi APs
Wi-5: Advanced Features for Low-cost Wi-Fi APsWi-5: Advanced Features for Low-cost Wi-Fi APs
Wi-5: Advanced Features for Low-cost Wi-Fi APsJose Saldana
 
Header compression and multiplexing in LISP
Header compression and multiplexing in LISPHeader compression and multiplexing in LISP
Header compression and multiplexing in LISPJose Saldana
 
Simplemux traffic optimization
Simplemux traffic optimizationSimplemux traffic optimization
Simplemux traffic optimizationJose Saldana
 
Online games: a real-time problem for the network
Online games: a real-time problem for the networkOnline games: a real-time problem for the network
Online games: a real-time problem for the networkJose Saldana
 
Improving Network Efficiency with Simplemux
Improving Network Efficiency with SimplemuxImproving Network Efficiency with Simplemux
Improving Network Efficiency with SimplemuxJose Saldana
 
GAIA and Alternative Networks
GAIA and Alternative NetworksGAIA and Alternative Networks
GAIA and Alternative NetworksJose Saldana
 
Simplemux: a generic multiplexing protocol
Simplemux: a generic multiplexing protocolSimplemux: a generic multiplexing protocol
Simplemux: a generic multiplexing protocolJose Saldana
 
The Effect of Multiplexing Delay on MMORPG TCP Traffic Flows
The Effect of Multiplexing Delay on MMORPG TCP Traffic FlowsThe Effect of Multiplexing Delay on MMORPG TCP Traffic Flows
The Effect of Multiplexing Delay on MMORPG TCP Traffic FlowsJose Saldana
 
Online games traffic characterization and network support
Online games traffic characterization and network supportOnline games traffic characterization and network support
Online games traffic characterization and network supportJose Saldana
 
The problem of using a best-effort network for online games
The problem of using a best-effort network for online gamesThe problem of using a best-effort network for online games
The problem of using a best-effort network for online gamesJose Saldana
 
Influence of the Distribution of TCRTP Multiplexed Flows on VoIP Conversation...
Influence of the Distribution of TCRTP Multiplexed Flows on VoIP Conversation...Influence of the Distribution of TCRTP Multiplexed Flows on VoIP Conversation...
Influence of the Distribution of TCRTP Multiplexed Flows on VoIP Conversation...Jose Saldana
 
Evaluation of Multiplexing and Buffer Policies Influence on VoIP Conversation...
Evaluation of Multiplexing and Buffer Policies Influence on VoIP Conversation...Evaluation of Multiplexing and Buffer Policies Influence on VoIP Conversation...
Evaluation of Multiplexing and Buffer Policies Influence on VoIP Conversation...Jose Saldana
 

Más de Jose Saldana (20)

Pint of science Patinete as a Service
Pint of science Patinete as a ServicePint of science Patinete as a Service
Pint of science Patinete as a Service
 
Mejorar tu empleabilidad como ingeniero
Mejorar tu empleabilidad como ingenieroMejorar tu empleabilidad como ingeniero
Mejorar tu empleabilidad como ingeniero
 
POUZ Universidad de Zaragoza - Telecomunicación 2º y 3º
POUZ Universidad de Zaragoza - Telecomunicación 2º y 3ºPOUZ Universidad de Zaragoza - Telecomunicación 2º y 3º
POUZ Universidad de Zaragoza - Telecomunicación 2º y 3º
 
Cómo se conectan los ordenadores y los móviles
Cómo se conectan los ordenadores y los móvilesCómo se conectan los ordenadores y los móviles
Cómo se conectan los ordenadores y los móviles
 
La bala que dobló la esquina: el problema de los videojuegos online
La bala que dobló la esquina: el problema de los videojuegos onlineLa bala que dobló la esquina: el problema de los videojuegos online
La bala que dobló la esquina: el problema de los videojuegos online
 
Entretenimiento online. Una perspectiva cristiana
Entretenimiento online. Una perspectiva cristianaEntretenimiento online. Una perspectiva cristiana
Entretenimiento online. Una perspectiva cristiana
 
¿Por qué el WiFi se va y se viene?
¿Por qué el WiFi se va y se viene?¿Por qué el WiFi se va y se viene?
¿Por qué el WiFi se va y se viene?
 
Wi-5: Advanced Features for Low-cost Wi-Fi APs
Wi-5: Advanced Features for Low-cost Wi-Fi APsWi-5: Advanced Features for Low-cost Wi-Fi APs
Wi-5: Advanced Features for Low-cost Wi-Fi APs
 
Header compression and multiplexing in LISP
Header compression and multiplexing in LISPHeader compression and multiplexing in LISP
Header compression and multiplexing in LISP
 
Simplemux traffic optimization
Simplemux traffic optimizationSimplemux traffic optimization
Simplemux traffic optimization
 
Online games: a real-time problem for the network
Online games: a real-time problem for the networkOnline games: a real-time problem for the network
Online games: a real-time problem for the network
 
Improving Network Efficiency with Simplemux
Improving Network Efficiency with SimplemuxImproving Network Efficiency with Simplemux
Improving Network Efficiency with Simplemux
 
GAIA and Alternative Networks
GAIA and Alternative NetworksGAIA and Alternative Networks
GAIA and Alternative Networks
 
Simplemux: a generic multiplexing protocol
Simplemux: a generic multiplexing protocolSimplemux: a generic multiplexing protocol
Simplemux: a generic multiplexing protocol
 
TCM-TF 2014
TCM-TF 2014TCM-TF 2014
TCM-TF 2014
 
The Effect of Multiplexing Delay on MMORPG TCP Traffic Flows
The Effect of Multiplexing Delay on MMORPG TCP Traffic FlowsThe Effect of Multiplexing Delay on MMORPG TCP Traffic Flows
The Effect of Multiplexing Delay on MMORPG TCP Traffic Flows
 
Online games traffic characterization and network support
Online games traffic characterization and network supportOnline games traffic characterization and network support
Online games traffic characterization and network support
 
The problem of using a best-effort network for online games
The problem of using a best-effort network for online gamesThe problem of using a best-effort network for online games
The problem of using a best-effort network for online games
 
Influence of the Distribution of TCRTP Multiplexed Flows on VoIP Conversation...
Influence of the Distribution of TCRTP Multiplexed Flows on VoIP Conversation...Influence of the Distribution of TCRTP Multiplexed Flows on VoIP Conversation...
Influence of the Distribution of TCRTP Multiplexed Flows on VoIP Conversation...
 
Evaluation of Multiplexing and Buffer Policies Influence on VoIP Conversation...
Evaluation of Multiplexing and Buffer Policies Influence on VoIP Conversation...Evaluation of Multiplexing and Buffer Policies Influence on VoIP Conversation...
Evaluation of Multiplexing and Buffer Policies Influence on VoIP Conversation...
 

Último

Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104misteraugie
 
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in DelhiRussian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhikauryashika82
 
Key note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfKey note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfAdmir Softic
 
Paris 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activityParis 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activityGeoBlogs
 
Unit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptxUnit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptxVishalSingh1417
 
Z Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphZ Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphThiyagu K
 
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxSOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxiammrhaywood
 
Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111Sapana Sha
 
General AI for Medical Educators April 2024
General AI for Medical Educators April 2024General AI for Medical Educators April 2024
General AI for Medical Educators April 2024Janet Corral
 
Class 11th Physics NEET formula sheet pdf
Class 11th Physics NEET formula sheet pdfClass 11th Physics NEET formula sheet pdf
Class 11th Physics NEET formula sheet pdfAyushMahapatra5
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfciinovamais
 
microwave assisted reaction. General introduction
microwave assisted reaction. General introductionmicrowave assisted reaction. General introduction
microwave assisted reaction. General introductionMaksud Ahmed
 
APM Welcome, APM North West Network Conference, Synergies Across Sectors
APM Welcome, APM North West Network Conference, Synergies Across SectorsAPM Welcome, APM North West Network Conference, Synergies Across Sectors
APM Welcome, APM North West Network Conference, Synergies Across SectorsAssociation for Project Management
 
Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)eniolaolutunde
 
Q4-W6-Restating Informational Text Grade 3
Q4-W6-Restating Informational Text Grade 3Q4-W6-Restating Informational Text Grade 3
Q4-W6-Restating Informational Text Grade 3JemimahLaneBuaron
 
Web & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdfWeb & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdfJayanti Pande
 
Grant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingGrant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingTechSoup
 
Interactive Powerpoint_How to Master effective communication
Interactive Powerpoint_How to Master effective communicationInteractive Powerpoint_How to Master effective communication
Interactive Powerpoint_How to Master effective communicationnomboosow
 
Sports & Fitness Value Added Course FY..
Sports & Fitness Value Added Course FY..Sports & Fitness Value Added Course FY..
Sports & Fitness Value Added Course FY..Disha Kariya
 

Último (20)

Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104
 
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in DelhiRussian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
 
Key note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfKey note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdf
 
INDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptx
INDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptxINDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptx
INDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptx
 
Paris 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activityParis 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activity
 
Unit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptxUnit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptx
 
Z Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphZ Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot Graph
 
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxSOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
 
Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111
 
General AI for Medical Educators April 2024
General AI for Medical Educators April 2024General AI for Medical Educators April 2024
General AI for Medical Educators April 2024
 
Class 11th Physics NEET formula sheet pdf
Class 11th Physics NEET formula sheet pdfClass 11th Physics NEET formula sheet pdf
Class 11th Physics NEET formula sheet pdf
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdf
 
microwave assisted reaction. General introduction
microwave assisted reaction. General introductionmicrowave assisted reaction. General introduction
microwave assisted reaction. General introduction
 
APM Welcome, APM North West Network Conference, Synergies Across Sectors
APM Welcome, APM North West Network Conference, Synergies Across SectorsAPM Welcome, APM North West Network Conference, Synergies Across Sectors
APM Welcome, APM North West Network Conference, Synergies Across Sectors
 
Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)
 
Q4-W6-Restating Informational Text Grade 3
Q4-W6-Restating Informational Text Grade 3Q4-W6-Restating Informational Text Grade 3
Q4-W6-Restating Informational Text Grade 3
 
Web & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdfWeb & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdf
 
Grant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingGrant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy Consulting
 
Interactive Powerpoint_How to Master effective communication
Interactive Powerpoint_How to Master effective communicationInteractive Powerpoint_How to Master effective communication
Interactive Powerpoint_How to Master effective communication
 
Sports & Fitness Value Added Course FY..
Sports & Fitness Value Added Course FY..Sports & Fitness Value Added Course FY..
Sports & Fitness Value Added Course FY..
 

Influence of Online Games Traffic Multiplexing and Router Buffer on Subjective Quality

  • 1.
  • 2. INFLUENCE OF ONLINE GAMES TRAFFIC MULTIPLEXING AND ROUTER BUFFER ON SUBJECTIVE QUALITY GTC Communication Technologies Group Jose Saldana Julián Fernández-Navajas José Ruiz-Mas Eduardo Viruete Navarro Luis Casadesus University of Zaragoza, Spain
  • 3. Index - I. Introduction II. Related Works III. Test Methodology IV. Tests and Results V. Conclusions
  • 4. Index - I. Introduction II. Related Works III. Test Methodology IV. Tests and Results V. Conclusions
  • 5. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Introduction - Online games are getting very popular in the last years - First Person Shooters are the ones with the tightest real-time requirements
  • 6. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Introduction FPS use a client-server architecture Uplink bandwidth limit
  • 7. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Introduction FPS use a client-server architecture Server processing capacity limit
  • 8. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Introduction FPS use a client-server architecture Downlink bandwidth limit
  • 9. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Introduction “Shooting around the corner” Jack Wang Wang
  • 10. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Introduction “Shooting around the corner” Wang: Dead Jack Wang Wang
  • 11. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Introduction “Shooting around the corner” Wang: Dead Jack ¡¡¡ #%$& !!! Wang
  • 12. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Introduction Main Key Performance Indicators (KPI): - Delay - Jitter - Packet loss buffer Internet . . . Users Router Game & background traffic Game Server
  • 13. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Introduction Access networks: low-end routers, with limitations in: - Bandwidth - Packets per second Different implementations buffer Internet . . . Users Router Game & background traffic Game Server
  • 14. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Introduction Scenarios where many users share a connection: we can multiplex packets from different players, and compress headers
  • 15. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Introduction By multiplexing, we can mitigate two problems: - Bandwidth - Packets per second … at the cost of adding: - Delay - Jitter
  • 16. Index - I. Introduction II. Related Works III. Test Methodology IV. Tests and Results V. Conclusions
  • 17. II. Related Works - Multiplexing real-time flows - Subjective quality evaluation - Influence of the router buffer
  • 18. II. Related Works - Multiplexing real-time flows - Subjective quality evaluation - Influence of the router buffer
  • 19. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Multiplexing real-time A multiplexer is introduced, and it also compresses headers delaymux delayrouter delaynetwork IP network router . . . MUX DEMUX Game Server Players IP TCM IP
  • 20. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Multiplexing real-time First done for VoIP (RFC4170, “TCRTP”): payload payload ECRTP ... ECRTP RTP UDP IP PPP Mux PPP L2TP IP Adapted for non-RTP flows: Payload Payload Reduced Header ... UDP Reduced Header IP PPP Mux PPP L2TP IP
  • 21. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Multiplexing real-time A period is defined, and all the packets arrived are compressed and multiplexed Native traffic ... Multiplexed traffic . . . PE PE PE PE ... ...
  • 22. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Multiplexing real-time Efficiency improvement One IPv4/TCP packet 1500 bytes η=1460/1500=97% One IPv4/UDP/RTP packet of VoIP with two samples of 10 bytes η=20/60=33% One IPv4/UDP server-to-client packet of Counter Strike with 9 players η=160/188=85% Four IPv4/UDP client-to-server packets of Counter Strike η=61/89=68% One IPv4/TCM packet multiplexing four client-to-server Counter Strike packets η=244/293=83% saving
  • 23. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Multiplexing real-time Significant savings (Counter Strike) Bandwidth Saving 35% 30% 25% BS 20% 15% 20 players 10% 15 players 10 players 5% 5 players 0% 5 10 15 20 25 30 period (ms) 35 40 45 50
  • 24. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Multiplexing real-time Significant savings (Counter Strike) Packets per second 600 20 players 15 players 500 10 players 5 players pps 400 300 200 100 0 native 5 10 15 20 25 period (ms) 30 35 40 45 50
  • 25. II. Related Works - Multiplexing real-time flows - Subjective quality evaluation - Influence of the router buffer
  • 26. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Multiplexing real-time - E-Model: VoIP delay and packet loss - FPS games: different studies consider delay limits, and also packet loss limits - G-Model: MOS formula for Quake IV, adapted from E-Model: delay and jitter
  • 27. II. Related Works - Multiplexing real-time flows - Subjective quality evaluation - Influence of the router buffer
  • 28. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Multiplexing real-time - Buffer size - - Bandwidth-delay product Stanford model Tiny buffer Buffer implementation - - Byte sized Packet sized Buffer limitations - Maximum pps amount
  • 29. Index - I. Introduction II. Related Works III. Test Methodology IV. Tests and Results V. Conclusions
  • 30. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Test methodology - Simulation scenario: - - Traces of gaming traffic Background traffic RTT delay: sum of the delays delaymux delayrouter delaynetwork IP network router . . . MUX DEMUX Game Server Players IP TCM IP
  • 31. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Test methodology Jitter: Multiplexing increases it stdevmux  PE / 12 Different added delays Native traffic ... Multiplexed traffic . . . PE PE PE PE ... ...
  • 32. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Test methodology BW↓ Buffer jitter↓ PE ↑ Mux jitter↑ delaymux delayrouter delaynetwork IP network router . . . MUX DEMUX Game Server Players IP TCM IP
  • 33. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Test methodology Jitter has to be added in a proper way (Network jitter is considered independent) stdevmuxrouter  stdevmux 2  stdevrouter2  cov mr stdevtotal  stdevmuxrouter2  stdevnetwork2 delaymux delayrouter delaynetwork IP network router . . . MUX DEMUX Game Server Players IP TCM IP
  • 34. Index - I. Introduction II. Related Works III. Test Methodology IV. Tests and Results V. Conclusions
  • 35. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results Buffer: Drop-tail, 2 Mbps byte-sized small big packet-sized 10 kB 100 kB 16 packets 166 packets Buffers are equivalent, considering average packet size = 600 bytes
  • 36. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results Game: Quake IV, 20 players 64 pps 79.5 bytes Native: 40.7 kbps x 20 players = 814 kbps Multiplexed PE=5ms: 631 kbps Multiplexed PE=15ms: 605 kbps 395 bytes 1,118 bytes
  • 37. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: delay byte-sized packet-sized RTT, Quake IV, 16pack, 166 pack RTT, Quake IV, 10kB, 100kB 600 600 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 500 500 400 ms 400 ms native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 300 300 200 200 100 100 0 0 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000
  • 38. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: delay byte-sized packet-sized RTT, Quake IV, 10kB, 100kB Bandwidth limit mux ≈1400 kbps 600 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 500 native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 500 400 ms 400 ms RTT, Quake IV, 16pack, 166 pack 600 300 300 200 200 100 100 0 0 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 400 Bandwidth limit native ≈ 1200 kbps 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000
  • 39. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: delay byte-sized packet-sized RTT, Quake IV, 16pack, 166 pack RTT, Quake IV, 10kB, 100kB 600 600 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 500 500 400 ms 400 ms native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 300 300 200 200 100 100 0 0 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 Buffer delay is constant 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 Buffer delay varies as packet size increases 2000
  • 40. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: delay byte-sized packet-sized RTT, Quake IV, 16pack, 166 pack RTT, Quake IV, 10kB, 100kB 600 600 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 500 500 400 ms 400 ms native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 300 300 200 200 100 100 0 0 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 400 Small buffers introduce small delays 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000
  • 41. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: jitter byte-sized packet-sized jitter, Quake IV, 10kB, 100kB jitter, Quake IV, 16pack, 166 pack 140 140 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 120 100 native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 120 100 80 ms ms 80 60 60 40 40 20 20 0 0 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000
  • 42. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: jitter byte-sized packet-sized jitter, Quake IV, 10kB, 100kB jitter, Quake IV, 16pack, 166 pack Bandwidth limit mux ≈1400 kbps 140 140 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 120 100 native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 120 100 80 ms ms 80 60 60 40 40 20 20 0 0 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 400 600 Bandwidth limit native ≈ 1200 kbps 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000
  • 43. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: jitter byte-sized packet-sized jitter, Quake IV, 10kB, 100kB jitter, Quake IV, 16pack, 166 pack 140 140 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 120 100 native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack Average size of sent packets is bigger for packet-sized buffer, so jitter decreases 120 100 80 ms ms 80 60 60 40 40 20 20 0 0 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 Big packets have a bigger dropping probability 1800 2000 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 All packets have the same dropping probability 1800 2000
  • 44. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: loss byte-sized packet-sized packet loss, Quake IV, 16pack, 166 pack packet loss, Quake IV, 10kB, 100kB 35% 35% native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 30% 30% 25% %packet loss %packet loss 25% native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 20% 15% 20% 15% 10% 10% 5% 5% 0% 0% 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000
  • 45. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: loss byte-sized packet-sized packet loss, Quake IV, 16pack, 166 pack packet loss, Quake IV, 10kB, 100kB 35% 35% native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 30% 30% 25% %packet loss %packet loss 25% native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 20% 15% 20% 15% 10% 10% 5% 5% 0% 0% 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 400 600 Small buffer starts loosing packets before reaching the limit 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000
  • 46. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: loss byte-sized packet-sized packet loss, Quake IV, 16pack, 166 pack packet loss, Quake IV, 10kB, 100kB 35% 35% native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 30% 30% 25% %packet loss %packet loss 25% native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 20% 15% 20% 15% 10% 10% 5% 5% 0% 0% 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 PE=15 obtains the worst results, because of packet size (1,118 bytes) 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000
  • 47. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: loss byte-sized packet-sized packet loss, Quake IV, 16pack, 166 pack packet loss, Quake IV, 10kB, 100kB 35% 35% native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 30% 30% 25% %packet loss %packet loss 25% native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 20% 15% 20% 15% 10% 10% 5% 5% 0% 0% 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 Worse results for packet-sized, because all the packets have the same discarding probability 1600 1800 2000
  • 48. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: loss byte-sized packet-sized packet loss, Quake IV, 16pack, 166 pack packet loss, Quake IV, 10kB, 100kB 35% 35% native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 30% 30% 25% %packet loss %packet loss 25% native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 20% 15% 20% 15% 10% 10% 5% 5% 0% 0% 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 For packet-sized buffer, packet loss is significantly reduced when multiplexing 2000
  • 49. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: MOS byte-sized packet-sized MOS, Quake IV, 16pack, 166 pack MOS, Quake IV, 10kB, 100kB 4.5 4 4 3.5 3.5 MOS 5 4.5 MOS 5 3 3 2.5 2.5 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 2 1.5 native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 2 1.5 1 1 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 MOS is based on delay and jitter 1800 2000
  • 50. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: MOS byte-sized packet-sized MOS, Quake IV, 16pack, 166 pack MOS, Quake IV, 10kB, 100kB 4.5 4 4 3.5 3.5 MOS 5 4.5 MOS 5 3 3 2.5 2.5 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 2 1.5 native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 2 1.5 1 1 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 400 600 Small buffers: graphs go down, and grow a little when jitter peak goes down 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000
  • 51. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: MOS byte-sized packet-sized MOS, Quake IV, 16pack, 166 pack MOS, Quake IV, 10kB, 100kB 4.5 4 4 3.5 3.5 MOS 5 4.5 MOS 5 3 3 2.5 2.5 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 2 1.5 native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 2 1.5 1 1 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 Multiplexing allows more background traffic 1800 2000 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000
  • 52. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: MOS byte-sized packet-sized MOS, Quake IV, 16pack, 166 pack MOS, Quake IV, 10kB, 100kB 4.5 4 4 3.5 3.5 MOS 5 4.5 MOS 5 3 3 2.5 2.5 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 2 1.5 native 16pack PE=5ms 16pack PE=15ms 16pack native 166pack PE=5ms 166pack PE=15ms 166pack 2 1.5 1 1 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 Multiplexing results are worse than native 2000
  • 53. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: MOS byte-sized byte-sized pps limit MOS, Quake IV, 10kB, 100kB MOS, Quake IV, 10kB, 100kB 4.5 4 4 3.5 3.5 MOS 5 4.5 MOS 5 3 2.5 3 2.5 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 2 1.5 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 2 1.5 1 1 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 2,000 pps (maximum 1,652 offered) 1800 2000
  • 54. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Tests and Results: MOS byte-sized byte-sized pps limit MOS, Quake IV, 10kB, 100kB MOS, Quake IV, 10kB, 100kB 4.5 4 4 3.5 3.5 MOS 5 4.5 MOS 5 3 2.5 3 2.5 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 2 1.5 native 10kB PE=5ms 10kB PE=15ms 10kB native 100kB PE=5ms 100kB PE=15ms 100kB 2 1.5 1 1 0 200 400 600 800 1000 1200 background traffic (kbps) 1400 1600 1800 2000 0 200 400 600 800 1000 1200 background traffic (kbps) This limitation has a very bad effect on MOS. Multiplexing alleviates it 1400 1600 1800 2000
  • 55. Index - I. Introduction II. Related Works III. Test Methodology IV. Tests and Results V. Conclusions
  • 56. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Conclusions - The mutual influence of the buffer router and multiplexing has been studied - Small buffers are more adequate to reduce delay and jitter - Packet-sized buffers increase packet loss, and multiplexing alleviates this
  • 57. CCNC 2012. DENVECT Workshop. Las Vegas Jan 14, 2012 Conclusions - Multiplexing always saves bandwidth - In packet-sized buffers, multiplexing does not improve experienced quality - Multiplexing is very interesting when a limit in pps is present
  • 59.