Categories
Uncategorized

new conference paper: Anycast Polarization in The Wild

Our new paper “Anycast Polarization in The Wild” will appear at the 2024 Conference on Passive and Active Measurements (PAM 2024).

From the abstract:

The left figure shows the impacts of polarization. The Dallas, USA site for a CDN is receiving traffic from all over the world due to polarization. The red dots indicate high latency from Europe and Asia, even if Europe and India have anycast sites in their continent. We show this type of polarization is not uncommon. The right figure shows how a change in the routing configuration can improve the polarization problem. We can see almost no red dots from Europe and Asia continents.

IP anycast is a commonly used method to associate users with services provided across multiple sites, and if properly used, it can provide efficient access with low latency. However, prior work has shown that polarization can occur in global anycast services, where some users of that service are routed to an anycast site on another continent, adding 100 ms or more latency compared to a nearby site. This paper describes the causes of polarization in real-world anycast and shows how to observe polarization in third-party anycast services. We use these methods to look for polarization and its causes in 7986 known anycast prefixes. We find that polarization occurs in more than a quarter of anycast prefixes, and identify incomplete connectivity to Tier-1 transit providers and route leakage by regional ISPs as common problems. Finally, working with a commercial CDN, we show how small routing changes can often address polarization, improving latency for 40% of clients, by up to 54%.

This paper is a joint work by ASM Rizvi from USC/ISI and Akamai Technologies, Tingshan Huang from Akamai Technologies, Rasit Esrefoglu from Akamai Technologies, and John Heidemann from USC/ISI. ASM Rizvi and John Heidemann’s work was partially supported by DARPA under Contract No. HR001120C0157. John Heidemann’s work was also partially supported by the NFS projects CNS-2319409, CRI-8115780, and CNS-1925737. ASM Rizvi’s work was begun while on an internship at Akamai.

Categories
Uncategorized

USC/Viterbi and ISI news about “Anycast Agility” paper

USC Viterbi and ISI both posted a news article about our paper “Anycast Agility: Network Playbooks to Fight DDoS”.

Please see our blog entry for the abstract and the full technical paper for the real details, but their posts are very accessible. And with the hacker in the hoodie, you know it’s serious :-)

The canonical hacker in the hoodie, testifying to serious security work.
Categories
Anycast BGP Internet

new paper “Anycast Agility: Network Playbooks to Fight DDoS” at USENIX Security Symposium 2022

We will publish a new paper titled “Anycast Agility: Network Playbooks to Fight DDoS” by A S M Rizvi (USC/ISI), Leandro Bertholdo (University of Twente), João Ceron (SIDN Labs), and John Heidemann (USC/ISI) at the 31st USENIX Security Symposium in Aug. 2022.

A sample anycast playbook for a 3-site anycast deployment. Different routing configurations provide different traffic mixes. From [Rizvi22a, Table 5].

From the abstract:

IP anycast is used for services such as DNS and Content Delivery Networks (CDN) to provide the capacity to handle Distributed Denial-of-Service (DDoS) attacks. During a DDoS attack service operators redistribute traffic between anycast sites to take advantage of sites with unused or greater capacity. Depending on site traffic and attack size, operators may instead concentrate attackers in a few sites to preserve operation in others. Operators use these actions during attacks, but how to do so has not been described systematically or publicly. This paper describes several methods to use BGP to shift traffic when under DDoS, and shows that a response playbook can provide a menu of responses that are options during an attack. To choose an appropriate response from this playbook, we also describe a new method to estimate true attack size, even though the operator’s view during the attack is incomplete. Finally, operator choices are constrained by distributed routing policies, and not all are helpful. We explore how specific anycast deployment can constrain options in this playbook, and are the first to measure how generally applicable they are across multiple anycast networks.

Dataset used in this paper are listed at https://ant.isi.edu/datasets/anycast/anycast_against_ddos/index.html, and the software used in our work is at https://ant.isi.edu/software/anygility. They are provided as part of Call for Artifacts.

Acknowledgments: A S M Rizvi and John Heidemann’s work on this paper is supported, in part, by the DHS HSARPA Cyber Security Division via contract number HSHQDC-17-R-B0004-TTA.02-0006-I. Joao Ceron and Leandro Bertholdo’s work on this paper is supported by Netherlands Organisation for scientific research (4019020199), and European Union’s Horizon 2020 research and innovation program (830927). We would like to thank our anonymous reviewers for their valuable feedback. We are also grateful to the Peering and Tangled admins who allowed us to run measurements. We thank Dutch National Scrubbing Center for sharing DDoS data with us. We also thank Yuri Pradkin for his help to release our datasets.

Categories
Uncategorized

new conference paper “Anycast in Context: A Tale of Two Systems” at SIGCOMM 2021

We published a new paper “Anycast in Context: A Tale of Two Systems” by Thomas Koch, Ke Li, Calvin Ardi*, Ethan Katz-Bassett, Matt Calder**, and John Heidemann* (of Columbia, where not otherwise indicated, *USC/ISI, and **Microsoft and Columbia) at ACM SIGCOMM 2021.

From the abstract:

Anycast is used to serve content including web pages and DNS, and anycast deployments are growing. However, prior work examining root DNS suggests anycast deployments incur significant inflation, with users often routed to suboptimal sites. We reassess anycast performance, first extending prior analysis on inflation in the root DNS. We show that inflation is very common in root DNS, affecting more than 95% of users. However, we then show root DNS latency hardly matters to users because caching is so effective. These findings lead us to question: is inflation inherent to anycast, or can inflation be limited when it matters? To answer this question, we consider Microsoft’s anycast CDN serving latency-sensitive content. Here, latency matters orders of magnitude more than for root DNS. Perhaps because of this need, only 35% of CDN users experience any inflation, and the amount they experience is smaller than for root DNS. We show that CDN anycast latency has little inflation due to extensive peering and engineering. These results suggest prior claims of anycast inefficiency reflect experiments on a single application rather than anycast’s technical potential, and they demonstrate the importance of context when measuring system performance.

Tom also blogged about this work at APNIC.

Categories
Publications Students

congratulations to Lan Wei for her new PhD

I would like to congratulate Dr. Lan Wei for defending her PhD in September 2020 and completing her doctoral dissertation “Anycast Stability, Security and Latency in The Domain Name System (DNS) and Content Deliver Networks (CDNs)” in December 2020.

From the abstract:

Clients’ performance is important for both Content-Delivery Networks (CDNs) and the Domain Name System (DNS). Operators would like the service to meet expectations of their users. CDNs providing stable connections will prevent users from experiencing downloading pause from connection breaks. Users expect DNS traffic to be secure without being intercepted or injected. Both CDN and DNS operators care about a short network latency, since users can become frustrated by slow replies.


Many CDNs and DNS services (such as the DNS root) use IP anycast to bring content closer to users. Anycast-based services announce the same IP address(es) from globally distributed sites. In an anycast infrastructure, Internet routing protocols will direct users to a nearby site naturally. The path between a user and an anycast site is formed on a hop-to-hop basis—at each hop} (a network device such as a router), routing protocols like Border Gateway Protocol (BGP) makes the decision about which next hop to go to. ISPs at each hop will impose their routing policies to influence BGP’s decisions. Without globally knowing (also unable to modify) the distributed information of BGP routing table of every ISP on the path, anycast infrastructure operators are unable to predict and control in real-time which specific site a user will visit and what the routing path will look like. Also, any change in routing policy along the path may change both the path and the site visited by a user. We refer to such minimal control over routing towards an anycast service, the uncertainty of anycast routing. Using anycast spares extra traffic management to map users to sites, but can operators provide a good anycast-based service without precise control over the routing?


This routing uncertainty raises three concerns: routing can change, breaking connections; uncertainty about global routing means spoofing can go undetected, and lack of knowledge of global routing can lead to suboptimal latency. In this thesis, we show how we confirm the stability, how we confirm the security, and how we improve the latency of anycast to answer these three concerns. First, routing changes can cause users to switch sites, and therefore break a stateful connection such as a TCP connection immediately. We study routing stability and demonstrate that connections in anycast infrastructure are rarely broken by routing instability. Of all vantage points (VPs), fewer than 0.15% VP’s TCP connections frequently break due to timeout in 5s during all 17 hours we observed. We only observe such frequent TCP connection break in 1 service out of all 12 anycast services studied. A second problem is DNS spoofing, where a third-party can intercept the DNS query and return a false answer. We examine DNS spoofing to study two aspects of security–integrity and privacy, and we design an algorithm to detect spoofing and distinguish different mechanisms to spoof anycast-based DNS. We show that DNS spoofing is uncommon, happening to only 1.7% of all VPs, although increasing over the years. Among all three ways to spoof DNS–injections, proxies, and third-party anycast site (prefix hijack), we show that third-party anycast site is the least popular one. Last, diagnosing poor latency and improving the latency can be difficult for CDNs. We develop a new approach, BAUP (bidirectional anycast unicast probing), which detects inefficient routing with better routing replacement provided. We use BAUP to study anycast latency. By applying BAUP and changing peering policies, a commercial CDN is able to significantly reduce latency, cutting median latency in half from 40ms to 16ms for regional users.

Lan defended her PhD when USC was on work-from-home due to COVID-19; she is the third ANT student with a fully on-line PhD defense.

Categories
Papers Publications

New paper “Bidirectional Anycast/Unicast Probing (BAUP): Optimizing CDN Anycast” at IFIP TMA 2020

We published a new paper “Bidirectional Anycast/Unicast Probing (BAUP): Optimizing CDN Anycast” by Lan Wei (University of Southern California/ ISI), Marcel Flores (Verizon Digital Media Services), Harkeerat Bedi (Verizon Digital Media Services), John Heidemann (University of Southern California/ ISI) at Network Traffic Measurement and Analysis Conference 2020.

From the abstract:

IP anycast is widely used today in Content Delivery Networks (CDNs) and for Domain Name System (DNS) to provide efficient service to clients from multiple physical points-of-presence (PoPs). Anycast depends on BGP routing to map users to PoPs, so anycast efficiency depends on both the CDN operator and the routing policies of other ISPs. Detecting and diagnosing
inefficiency is challenging in this distributed environment. We propose Bidirectional Anycast/Unicast Probing (BAUP), a new approach that detects anycast routing problems by comparing anycast and unicast latencies. BAUP measures latency to help us identify problems experienced by clients, triggering traceroutes to localize the cause and suggest opportunities for improvement. Evaluating BAUP on a large, commercial CDN, we show that problems happens to 1.59% of observers, and we find multiple opportunities to improve service. Prompted by our work, the CDN changed peering policy and was able to significantly reduce latency, cutting median latency in half (40 ms to 16 ms) for regions with more than 100k users.

The data from this paper is publicly available from RIPE Atlas, please see paper reference for measurement IDs.

Categories
DNS Internet

B-root’s new sites reduce latency

B-Root, one of the 13 root DNS servers, deployed three new sites in January 2020, doubling its footprint and adding its first sites in Asia and Europe. How did this growth lower latency to users? We looked at B-Root deployment with Verfploter to answer this question. The end result was that new sites in Asia and Europe allowed users there to resolve DNS names with B-Root with lower latency (see the catchment map below). For more details please review our anycast catchment page.

B-root added 3 new sites in Singapore, Washington, DC, and Amsterdam to their three existing 3 sites in Los Angeles, Chile, and Miami. The graph below shows anycast catchments after these sites were deployed (each color in the pie charts shows traffic to a different site).

Categories
Announcements Projects

new project “Plannning for Anycast as Anti-DDoS” (PAADDoS)

We are happy to announce a new project Plannning for Anycast as Anti-DDoS (PAADDoS).

The PAADDoS project’s goal is to defend against large-scale DDoS attacks by making anycast-based capacity more effective than it is today.

We will work toward this goal by (1) developing tools to map anycast catchments and baseline load, (2) develop methods to plan changes and their effects on catchments, (3) develop tools to estimate attack load and assist anycast reconfiguration during an attack. and (4) evaluate and integration of these tools with traditional DoS defenses.

We expect these innovations to improve service resilience in the face of DDoS attacks. Our tools will improve anycast agility during an attack, allowing capacity to be used effectively.

PAADDoS is a joint effort of the ANT Lab involving USC/ISI (PI: John Heidemann) and the Design and Analysis of Communication Systems group at the University of Twente (PI: Aiko Pras).

PAADDoS is supported by the DHS HSARPA Cyber Security Division via contract number HSHQDC-17-R-B0004-TTA.02-0006-I, and by NWO.

Categories
DNS Papers Publications

new conference paper “When the Dike Breaks: Dissecting DNS Defenses During DDoS” at ACM IMC 2018

We have published a new paper “When the Dike Breaks: Dissecting DNS Defenses During DDoS” in the ACM Internet Measurements Conference (IMC 2018) in Boston, Mass., USA.

From the abstract:

Caching and retries protect half of clients even with 90% loss and an attack twice the cache duration. (Figure 7c from [Moura18b].)

The Internet’s Domain Name System (DNS) is a frequent target of Distributed Denial-of-Service (DDoS) attacks, but such attacks have had very different outcomes—some attacks have disabled major public websites, while the external effects of other attacks have been minimal. While on one hand the DNS protocol is relatively simple, the \emph{system} has many moving parts, with multiple levels of caching and retries and replicated servers. This paper uses controlled experiments to examine how these mechanisms affect DNS resilience and latency, exploring both the client side’s DNS \emph{user experience}, and server-side traffic. We find that, for about 30\% of clients, caching is not effective. However, when caches are full they allow about half of clients to ride out server outages that last less than cache lifetimes, Caching and retries together allow up to half of the clients to tolerate DDoS attacks longer than cache lifetimes, with 90\% query loss, and almost all clients to tolerate attacks resulting in 50\% packet loss. While clients may get service during an attack, tail-latency increases for clients. For servers, retries during DDoS attacks increase normal traffic up to $8\times$. Our findings about caching and retries help explain why users see service outages from some real-world DDoS events, but minimal visible effects from others.

Datasets from this paper are available at no cost and are listed at https://ant.isi.edu/datasets/dns/#Moura18b_data.

 

Categories
Publications Technical Report

new technical report “Back Out: End-to-end Inference of Common Points-of-Failure in the Internet (extended)”

We released a new technical report “Back Out: End-to-end Inference of Common Points-of-Failure in the Internet (extended)”, ISI-TR-724, available at https://www.isi.edu/~johnh/PAPERS/Heidemann18b.pdf.

From the abstract:

Clustering (from our event clustering algorithm) of 2014q3 outages from 172/8, showing 7 weeks including the 2014-08-27 Time Warner outage.

Internet reliability has many potential weaknesses: fiber rights-of-way at the physical layer, exchange-point congestion from DDOS at the network layer, settlement disputes between organizations at the financial layer, and government intervention the political layer. This paper shows that we can discover common points-of-failure at any of these layers by observing correlated failures. We use end-to-end observations from data-plane-level connectivity of edge hosts in the Internet. We identify correlations in connectivity: networks that usually fail and recover at the same time suggest common point-of-failure. We define two new algorithms to meet these goals. First, we define a computationally-efficient algorithm to create a linear ordering of blocks to make correlated failures apparent to a human analyst. Second, we develop an event-based clustering algorithm that directly networks with correlated failures, suggesting common points-of-failure. Our algorithms scale to real-world datasets of millions of networks and observations: linear ordering is O(n log n) time and event-based clustering parallelizes with Map/Reduce. We demonstrate them on three months of outages for 4 million /24 network prefixes, showing high recall (0.83 to 0.98) and precision (0.72 to 1.0) for blocks that respond. We also show that our algorithms generalize to identify correlations in anycast catchments and routing.

Datasets from this paper are available at no cost and are listed at https://ant.isi.edu/datasets/outage/, and we expect to release the software for this paper in the coming months (contact us if you are interested).