Date: Monday, 18 March 2024, Session II 1300-1500
Full client with Video: https://meetecho.ietf.org/conference/?group=maprg&short=maprg&item=1
Room: P1
IRTF Note Well: https://irtf.org/policies/irtf-note-well-2019-11.pdf
Overview and Status - Mirja/Dave (5 min)
Heads-up: Performance Evaluation of PDM Implementation using eBPF in TC versus Traditional Kernel Methods - Nalini Elkins (5 mins)
Heads-up: Putting the Spin Bit under the Microscope - Ike Kunze (10 mins)
Towards Improving Outage Detection with Multiple Probing Protocols - Manasvini Sethuraman (remote) (10 mins)
Watching Stars in Pixels: The Interplay of Traffic Shaping and YouTube Streaming QoE over GEO Satellite Networks - Jiamo Liu (remote) (15 mins)
IRRedicator: Pruning IRR with RPKI-Valid BGP Insights - Taejoong (tijay) Chung (remote) (15 mins)
Anycast Polarization in The Wild - ASM Rizvi (remote) (15 mins)
Measuring L4S & NQB Latency EQects in Real World Network Testing - Jason Livingood (10 mins)
Out in the Open: On the Implementation of Mobile App Filtering in India - Devashish Gosain (remote) (15 mins)
Nalini Elkins , Chinmaya Sharma , Amogh Umesh , Balajinaidu V , Mohit P. Tahiliani
RFC8250 describes an optional IPv6 Destination Option (DO) extension header embedded in each packet to provide sequence numbers and timing information as a basis for measurements. As kernel implementation can be complex and time-consuming, this session describes the implementation of the Performance and Diagnostic Metrics (PDM) extension header using eBPF in the Linux kernel's Traffic Control (TC) subsystem. The session also provides a performance analysis of the eBPF implementation in comparison to the traditional kernel implementation.
Ike Kunze
The spin bit is an explicit measurement signal that enables RTT estimations by passive observers.
While it is only an optional feature of QUIC, we have shown that it is indeed used in the wild on around 10% of domains that had QUIC support in our measurement study.
However, we also found that the RTT estimation is very inaccurate for a large share of those connections, raising the need for additional studies digging into the exact reasons of the observed inaccuracy.
In this talk, we will give a short overview of our continued work and present some early results, focusing on i) extensions of our web measurement pipeline, ii) a deeper dive into our web measurement results, and iii) additional testbed-based measurements for studying the spin bit in more detail.
Manasvini Sethuraman (Georgia Institute of Technology), Zachary Bischof (Georgia Institute of Technology), Alberto Dainotti (Georgia Institute of Technology)
Multiple systems actively monitor the IPv4 address space for outages, often through ICMP probing. In this work, we explore the potential benefits (in terms of increased coverage) of leveraging additional protocols for probing by analyzing Internet-wide scans conducted using transport layer (TCP/UDP) probes. Using several existing Internet-wide scan snapshots, we show that between 531k to 606k additional /24 blocks, which were originally too sparse to be monitored via ICMP probing alone, now have the potential to be monitored for outages. We also find that it is possible to improve the probing efficiency for 850k-970k blocks, of which, 106k-125k blocks were not observed in the previous two years of ICMP-based scans. We observe that the average percent of /24 blocks per AS that could potentially be reliably monitored for outages increases from 65% to 83%, spanning 28k ASes.
Jiamo Liu (University of California Santa Barbara), David Lerner (Viasat), Jae Chung (Viasat), Udit Paul (University of California Santa Barbara), Arpit Gupta (University of California Santa Barbara), Elizabeth M. Belding
Geosynchronous satellite (GEO) networks are an important Internet access option for users beyond terrestrial connectivity. However, unlike terrestrial networks, GEO networks exhibit high latency and, as a result, deploy TCP proxies and traffic shapers. Currently, it is unclear how the interplay between GEO networks' high latency, TCP proxies, and traffic shaping policies affects the quality of experience (QoE) for commonly used video applications. In this talk, I will share insights from a study conducted on a 1Mbps shaped production GEO network, focusing on the QoE for YouTube video streaming. Despite the network's shaped bandwidth being theoretically sufficient for the targeted video bitrate, the actual QoE falls significantly short of expectations. This discrepancy raises important questions about the efficacy of traffic shaping policies in GEO networks, especially when dealing with adaptive bitrate video streaming services. By investigating the reasons behind the observed discrepancies in expected versus actual network throughput, we showcase the nuanced interplay between protocol, traffic shaping and application-level optimizations. The findings underscore an important evaluation of current traffic shaping approaches in GEO networks, highlighting their challenges in effectively managing video streaming quality.
ASM Rizvi (University of Southern California / Information Sciences Institute / Akamai Technologies), Tingshan Huang (Akamai Technologies), Rasit Esrefoglu (Akamai Technologies), John Heidemann (University of Southern California / Information Sciences Institute)
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%.
Minhyeok Kang (Seoul National University), Weitong Li (Virginia Tech), Roland van Rijswijk-Deij (University of Twente), Ted "Taekyoung" Kwon (Seoul National University), Taejoong Chung (Virginia Tech)
Border Gateway Protocol (BGP) provides a way of exchanging routing information to help routers construct their routing tables. However, due to the lack of security considerations, BGP has been suffering from vulnerabilities such as BGP hijacking attacks. To mitigate these issues, two data sources have been used, Internet Routing Registry (IRR) and Resource Public Key Infrastructure (RPKI), to provide reliable mappings between IP prefixes and their authorized Autonomous Systems (ASes). Each of the data sources, however, has its own limitations. IRR has been well-known for its stale Route objects with outdated AS information since network operators do not have enough incentives to keep them up to date, and RPKI has been slowly deployed due to its operational complexities. In this paper, we measure the prevalent inconsistencies between Route objects in IRR and ROA objects in RPKI. We next characterize inconsistent and consistent Route objects, respectively, by focusing on their BGP announcement patterns. Based on this insight, we develop a technique that identifies stale Route objects by leveraging a machine learning algorithm and evaluate its performance. From real trace-based experiments, we show that our technique can offer advantages against the status quo by reducing the percentage of potentially stale Route objects from 72% to 40% (of the whole IRR Route objects). In this way, we achieve 93% of the accuracy of validating BGP announcements while covering 87% of BGP announcements.
Jason Livingood
The IETF’s TSVWG has standardized L4S (Low Latency, Low Loss, Scalable Throughput)1 and is finishing standardization of NQB (Non-Queue-Building Per Hop Behavior)2. These two standards describe how to implement dual-queue low latency networking, which can improve the working latency of interactive traQic flows.
Comcast has been conducting the world’s first field trials of these standards with hundreds of users and several application partners. They have collected interesting measurement data on the improvements that can be observed. This includes running “network responsiveness” tests using the in-development Responsiveness Under Working Conditions specification being developed by the IP Performance Measurement (IPPM) working group3. It also includes application layer latency statistics from two cloud gaming partners, as well as network layer statistics from a real-time communications application.
This data can be presented to quantify, from a variety of vantage points and layers, the potential benefits of the new L4S and NQB standards. This will therefore illustrate how these protocols function “in the wild” and may provide motivation for application providers and network operators to adopt L4S and NQB.
Devashish Gosain (BITS Pilani Goa Campus), Kartikey Singh (IIIT Delhi), Rishi Sharma (IIIT Delhi), Jithin S (IIIT Delhi), Sambuddho (IIIT Delhi)
In this paper, we present the first comprehensive study highlighting the evolving mobile app filtering within India. We study the recent mobile app blocking in India and describe in detail the mechanics involved. We analyzed 220 Chinese apps that were blocked due to official government orders. Our research reveals a novel three-tiered app censorship scheme, with each tier increasing the sophistication of censorship. After thoroughly analyzing the app censorship mechanisms, we present effective circumvention techniques to bypass the tiered app censorship. We were able to access all the blocked apps with the said techniques. We believe our analysis and findings from the case study of India will aid future research on mobile app filtering.