The Power of Explicit Congestion Notification Aleksandar Kuzmanovic - PowerPoint PPT Presentation

The Power of Explicit Congestion Notification Aleksandar Kuzmanovic Northwestern University http://www.cs.northwestern.edu/~akuzma/ http://www.cs.northwestern.edu/~akuzma/

Motivation Recent measurements [PF01,MPF04]: – 2000: 1.1% Web servers support ECN – 2004: the percent increased to 2.1% – Not a single packet was marked in the network ECN deployment 100% 50% ye year ar 239 2396 (Sigc Sigcomm omm # 41 # 411) 1) year 2000 2100 2200 2300 2400 2 A. Kuzmanovic A. Kuzmanovic The Power of ECN The Power of ECN

Background AQM Router FCFS scheduler Marker/ Client Server Dropper Active Queue Management (AQM): – Simultaneously achieves high throughput and low average delay – AQM algorithms can mark (instead of drop) packets – The router and both endpoints have to be ECN-enabled 3 A. Kuzmanovic A. Kuzmanovic The Power of ECN The Power of ECN

Negotiating ECN Capabilities (I) Client initiates ECN-capable communication by setting appropriate bits in the TCP SYN packet’s TCP header TCP header Server Client TCP SYN 4 A. Kuzmanovic A. Kuzmanovic The Power of ECN The Power of ECN

Negotiating ECN Capabilities (II) An ECN-capable server replies by setting appropriate bits in the SYN ACK packet’s TCP header TCP header Server Client TCP SYN SYN ACK Once the SYN ACK packet arrives, ECN negotiation is completed 5 A. Kuzmanovic A. Kuzmanovic The Power of ECN The Power of ECN

Barriers to Adoption of ECN reset Server Client TCP SYN router "Broken" firewall “Broken” firewalls and load balancers incorrectly reset TCP flows attempting to negotiate ECN – The problem addressed in RFC 3360 Consequences are devastating New incentives? 6 A. Kuzmanovic A. Kuzmanovic The Power of ECN The Power of ECN

ECN and TCP’s Control Packets Client Server TCP SYN SYN ACK HTTP REQ TCP SYN and SYN ACK packets are dropped during congestion Can significantly reduce end-to-end performance – RTO = 3 sec (+6 sec, +12 sec, etc.) Marking SYN packets? 7 A. Kuzmanovic A. Kuzmanovic The Power of ECN The Power of ECN

Marking TCP SYN Packets? Client Server TCP SYN SYN ACK packets: TCP SYN packets: – Security problems – No security obstacles – More relevant • Congestion likely to happen from servers to clients 8 A. Kuzmanovic A. Kuzmanovic The Power of ECN The Power of ECN

Marking SYN ACK Packets? Server Client TCP SYN SYN ACK SYN ACK packets (ECN+): TCP SYN packets: – No security obstacles – Security problems – More relevant • Congestion likely to happen from servers to clients 9 A. Kuzmanovic A. Kuzmanovic The Power of ECN The Power of ECN

Deployment Requirements Security – No novel security holes Performance improvements – Necessary to provide incentives to all involved parties Incremental deployability – What level of deployment is needed to achieve the above improvements? – What happens to those who do not apply the change? 10 A. Kuzmanovic A. Kuzmanovic The Power of ECN The Power of ECN

Simulation Scenario 100/622/1,000 Client Server Mbps 1 Gbps 1 Gbps responses AQM 90% objects Client Server downloaded in less than 0.5 sec requests Client pool Server pool Client Server Light and persistent congestion from servers to clients Web and general traffic mixes AQM algorithms: Random Early Detection (RED) (others in the paper) 11 A. Kuzmanovic A. Kuzmanovic The Power of ECN The Power of ECN

Outdated Implementation Drop/mark rate 100% max_p Average min_th max_th Queue Length RED’s dropping/marking rate as a function of the queue length RED (1993) – “This notification can consist of dropping or marking a packet.” RFC 3168 (2001) – Guidelines for setting ECN with RED Older RED versions still present (e.g., Linux) 12 A. Kuzmanovic A. Kuzmanovic The Power of ECN The Power of ECN

Dropping RED Drop/mark rate 100% operating point max_p Average min_th max_th Queue Length Reduced performance due to congestion 13 A. Kuzmanovic A. Kuzmanovic The Power of ECN The Power of ECN

Add ECN All SYN packets are dropped Drop/mark rate 100% operating point max_p Average min_th max_th Queue Length Outdated implementation can cause drastic performance degradations 14 A. Kuzmanovic A. Kuzmanovic The Power of ECN The Power of ECN

Add ECN+ SYN ACK packets are NOT dropped Drop/mark rate 100% operating point max_p Average min_th max_th Queue Length ECN+ systematically improves throughput and response times of all investigated AQM schemes 15 A. Kuzmanovic A. Kuzmanovic The Power of ECN The Power of ECN

Incremental Deployability Scenario x% clients: ECN ECN+ (100-x)%: no ECN at servers Server Client ECN at routers Client Server Client pool Server pool Client Server 16 A. Kuzmanovic A. Kuzmanovic The Power of ECN The Power of ECN

5% Deployment 5% ECN 95% no ECN Instant gains for ECN-enabled clients 17 A. Kuzmanovic A. Kuzmanovic The Power of ECN The Power of ECN

50% Deployment 50% ECN 50% no ECN Gradual degradation for clients not applying ECN 18 A. Kuzmanovic A. Kuzmanovic The Power of ECN The Power of ECN

95% Deployment 95% ECN Performance necessarily degraded 5% no ECN 19 A. Kuzmanovic A. Kuzmanovic The Power of ECN The Power of ECN

Testbed Experiments no ECN ECN Server ECN ECN+ responses (15 Mbps) Server Client 10 Mbps router requests 100 Mbps Server pool Server 20 A. Kuzmanovic A. Kuzmanovic The Power of ECN The Power of ECN

ECN and Flash Crowds Throughput Average Response (% of capacity) Time 44% 26 sec RED, no ECN Reasonable performance despite huge congestion RED, ECN 4.5 sec 56% RED, ECN+ 0.5 sec 99% 21 A. Kuzmanovic A. Kuzmanovic The Power of ECN The Power of ECN

Conclusions Security – No novel security holes Incremental deployability – Instant benefits for clients applying the change – Gradual degradation for those not applying the change Incentives – Providers, clients, and servers Implementation – Wrong or outdated implementation can significantly reduce deployment and performance 22 A. Kuzmanovic A. Kuzmanovic The Power of ECN The Power of ECN