A Measurement Study on the Impact of Routing Events on End-to-End Internet Path Performance Feng Wang 1, Zhuoqing Morley Mao 2 Jia Wang 3, Lixin Gao 1, Randy Bush 4 1 University of Massachusetts, Amherst 2 University of Michigan 3 AT&T Labs-Research 4 Internet Initiative Japan Presentation modified with permission Presenter: Young-Rae Kim Date: Feb. 24, 2009 Table of Contents Background Motivation Open Question Our Work Methodology How Routing Failure Occur Summary Conclusion R-BGP Appendix Background : Border Gate Protocol(BGP) The Border Gateway Protocol(BGP) is the core routing protocol of the Internet. It maintains a table of IP networks or prefixes which designate network reachability among autonomous systems(AS). Most Internet users do not use BGP directly. However, most ISP must use BGP to establish routing between one another. Background : Border Gateway Protocol (BGP) Beacons BGP Beacons are for research purposes to improve our understanding of BGP dynamics. A BGP Beacon is an unused prefix which has a well-defined schedule for announcement and withdrawal. Given the known schedule of announcements and withdrawals, we can study the dynamics of BGP using publicly available BGP update data. Background : MRAI timer MRAI (Minimum Route Advertisement Interval) timer is specified in BGP. This timer acts to rate-limit updates, on a per-destination basis. BGP(BGP-4) suggests values of 30s and 5s for this interval for external BGP(eBGP) and internal BGP(iBGP) respectively. The MRAI serves to suppress messages which BGP would otherwise send out to describe transitory states, and so allow BGP to converge with significantly fewer messages sent. Background : Internet Control Message Protocol (ICMP) Chiefly used by networked computers OS to send error messages (i.e. indicating that a requested service is not available or that host or router could not be reached.) It differs in purpose from TCP/UDP in that it is typically not used to send and receive data between end systems. ICMP can be used directly by user using ping and trace routes. Motivation Real-time services have made high availability of end-to- end Internet paths of paramount importance. low packet loss rate, low delay, high network availability, and fast reaction time Internet path failures are widespread [ Labovitz:98, Markopoulou:04,Feamster:03 ]. can last as long as 10 minutes Degraded end-to-end path performance is correlated with routing dynamics. Open Questions How routing changes result in degraded end-to-end path performance? What kinds of routing dynamics cause the degraded end-to- end performance? How factors such as topological properties, or routing policies affect performance degradation? Our Work Study end-to-end performance under realistic topologies. Investigate several metrics to characterize the end-to- end loss, delay, and out-of-order packets. Characterize the kinds of routing changes that impact end-to-end path performance. Analyze the impact of topology, routing policies, MRAI timer and iBGP configurations on end-to-end path performance. Methodology A multi-homed prefix BGP Beacon prefix: /24 Controlled Routing Changes Failover events: Beacon changes from the state of having both providers to the state of having only a single provider. Recovery events: Beacon changes from the state of having a single provider for connectivity to the state of having both providers. Provider 1 Beacon Provider 2Provider 1Provider 2 Provider 1Provider 2 Beacon Failover event Recovery event Active Probing From 37 PlanetLab hosts to the Beacon host (a host within the Beacon prefix) Back-to-back traceroutes Back-to-back pings UDP probing (50msec interval) Data plane performance metrics Internet Provider 2 Beacon host Provider 1 host B host A host C metrics Active probing traceroutepingUDP probing Pack loss Delay Out-of-order Packet Loss Loss burst: consecutive UDP probing packets lost during a routing change event. FailoverRecovery Correlating Packet Loss with Routing Failures ICMP replies temporary loss of reachability (!N or !H) forwarding loops (exceeded TTL) Routing failures temporary loss of reachability and transient routing loops Correlate loss bursts with ICMP messages time window [-1 sec, 1 sec] Underestimate the number of loss bursts due to routing failures missing ICMP packets. An Example planet02.csc.ncsu.edu experiences packet loss on July 30, 2005 Loss Bursts due to Routing Failures Failover events: 76% packets lost Recovery events: 26% packets lost Failover Recovery How Routing Failures Occur (Failover)? R1 Beacon R4R5 R6 R2R3 Provider 1Provider 2 Peer link Prefer-customer routing policy: routes received from a providers customers are always preferred over those received from its peers. AS 0 Customer link How Routing Failures Occur (Failover)? (contd.) R1 Beacon R4R5 R6 R2R3 Provider 1 Provider 2 Peer link R7R9 Provider No-valley routing policy: peers do not transit traffic from one peer to another. AS 0 Peer link R8 How Routing Failures Occur? (Recovery) R1 R2R4 R3 0 Beacon path (0) Path (0) Withdraw (2 0) 5. R1 regains its connection to the Beacon 1. Path 0 R3 recovery. 2. R3 sends the path to R2 3. R2 sends a withdrawal to R1 4. R3 sends the recovery path to R1 iBGP constraint: a route received from an iBGP router cannot be transited to another iBGP router Provider 1 Provider 2 AS 0 Summary During failover and recovery events Routing changes impact packet loss significantly. Multiple loss bursts are observed in 60% of events. Routing changes can lead to long packet round-trip delays and reordering. Loss bursts explained by routing failures last longer than those unidentified ones. Loss bursts caused by forwarding loops last longer than those caused by loop-free routing failures. Conclusions During failover and recovery events routing failures contribute to end-to-end packet loss significantly. Routing policies, iBGP configuration and MRAI timer values play a major role in causing packet loss during routing events. Degraded end-to-end performance can be experienced by a diverse set of hosts when there is a routing change. Accommodate routing redundancy may eliminate majority of identified path failures. Resilient Border Gate Protocol (R-BGP) The End Thanks! Location of Lost Bursts (Failover events) Location of the first lost bursts caused by routing failures. From ISP 2s BGP updates: Routing failures do occur and are not visible from ICMP messages due to short duration. From another ASs BGP updates, and Oregon RouteView Routing failures are cascaded to other ASes. ClassISP 1ISP 2Other tier1Non tier-1 Failover 192%05%3% Failover 209%73%18% Location of Lost Bursts (Recovery events) Location of the first lost bursts caused by routing failures. BGP updates from ISP 2 12 withdrawals over 724 recovery events ClassISP 1ISP 2Other tier1Non tier-1 Failover 190%N/A0%10% Failover 2N/A0%59%41% Representativeness Connectivity of Destination Prefixes SS: Single-homed prefixes via a single upstream link SM: Single-homed prefixes via multiple upstream links MS: Multi-homed prefixes via a single upstream link MM: Multi-homed prefixes via multiple upstream links Routing tables from one tier-1 ISP on January 15, 2006 classSSSMMSMM percentage48%6%29%17% Representativeness (contd.) Multi-homed destination prefixes ISP 2ISP 3 ISP 1 destination Customer link Peer link Representativeness (contd.) Multi-homed destination prefixes with multi-upstream links ISP 2 ISP 1 ISP 2 Loss Burst Length loss burst length can be as long as 480 packets for failover events, and 180 packets for recovery events Loss burst length Failover eventsRecovery events Multiple Loss Bursts Multiple loss bursts after the injection of a withdrawal message or an announcement. Failover Recovery Methodology Evaluation Our measurement is not significantly biased by ICMP blocking The number of ICMP messages in the absence of routing change (0.6%). ICMP messages from 68 ASes, and 53% of them belong to 10 tier-1 ASes. 52% of ISP1 s routers, and 95% of ISP2 s routers generate ICMP messages.