An official website of the United States government
It has been long observed that communication between a client and a content server using overlay detours may result in substantially better performance than a native path offered by IP routing. Yet the use of detours has been limited to distributed platforms such as Akamai. This paper poses a question - how can clients practically take advantage of overlay detours without modification to content servers (which are obviously outside clients' control)? We have posited elsewhere that the emergence of gigabit-to-the-home access networks would precipitate a new home network appliance, which would maintain permanent presence on the Internet for the users and have general computing and storage capabilities. Given such an appliance, our vision is that Internet users may form cooperatives in which members agree to serve as waypoints points to each other to improve each other's Internet experience. To make detours transparent to the server, we leverage MPTCP, which normally allows a device to communicate with the server on several network interfaces in parallel but we use it to communicate through external waypoint hosts. The waypoints then mimic MPTCP's subflows to the server, making the server oblivious to the overlay detours as long as it supports MPTCP.
more »
« less
Towards client-side active measurements without application control
Monitoring performance and availability are critical to operating successful content distribution networks. Internet measurements provide the data needed for traffic engineering, alerting, and network diagnostics. While there are significant benefits to performing end-user active measurements, these capabilities are limited to a small number of content providers with application control. In this work, we present a solution to the long-standing problem of issuing active measurements from clients without requiring application control, e.g., injecting JavaScript to the content served. Our approach uses server-side programmable features of the Network Error Logging specification that allow a CDN to induce a browser connection to an HTTPS server of the CDN's choosing without application control.
more »
« less
- Award ID(s):
- 2003257
- PAR ID:
- 10346329
- Date Published:
- Journal Name:
- ACM SIGCOMM Computer Communication Review
- Volume:
- 52
- Issue:
- 1
- ISSN:
- 0146-4833
- Page Range / eLocation ID:
- 20 to 27
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Edge Computing is a new computing paradigm where applications operate at the network edge, providing low-latency services with augmented user and data privacy. A desirable goal for edge computing is pervasiveness, that is, enabling any capable and authorized entity at the edge to provide desired edge services--pervasive edge computing (PEC). However, efficient access control of users receiving services and edge servers handling user data, without sacrificing performance is a challenge. Current solutions, based on "always-on" authentication servers in the cloud, negate the latency benefits of services at the edge and also do not preserve user and data privacy. In this paper, we present APECS, an advanced access control framework for PEC, which allows legitimate users to utilize any available edge services without need for communication beyond the network edge. The APECS framework leverages multi-authority attribute-based encryption to create a federated authority, which delegates the authentication and authorization tasks to semi-trusted edge servers, thus eliminating the need for an "always-on" authentication server in the cloud. Additionally, APECS prevents access to encrypted content by unauthorized edge servers. We analyze and prove the security of APECS in the Universal Composability framework and provide experimental results on the GENI testbed to demonstrate the scalability and effectiveness of APECS.more » « less
-
Modern datacenter applications are concurrent, so they require synchronization to control access to shared data. Requests can contend for different combinations of locks, depending on application and request state. In this paper, we show that locks, especially blocking synchronization, can squander throughput and harm tail latency, even when the CPU is underutilized. Moreover, the presence of a large number of contention points, and the unpredictability in knowing which locks a request will require, make it difficult to prevent contention through overload control using traditional signals such as queueing delay and CPU utilization. We present Protego, a system that resolves these problems with two key ideas. First, it contributes a new admission control strategy that prevents compute congestion in the presence of lock contention. The key idea is to use marginal improvements in observed throughput, rather than CPU load or latency measurements, within a credit-based admission control algorithm that regulates the rate of incoming requests to a server. Second, it introduces a new latency-aware synchronization abstraction called Active Synchronization Queue Management (ASQM) that allows applications to abort requests if delays exceed latency objectives. We apply Protego to two real-world applications, Lucene and Memcached, and show that it achieves up to 3.3x more goodput and 12.2x lower 99th percentile latency than the state-of-the-art overload control systems while avoiding congestion collapse.more » « less
-
Balakrishnan, Mahesh; Ghobadi, Manya (Ed.)Modern datacenter applications are concurrent, so they require synchronization to control access to shared data. Requests can contend for different combinations of locks, depending on application and request state. In this paper, we show that locks, especially blocking synchronization, can squander throughput and harm tail latency, even when the CPU is underutilized. Moreover, the presence of a large number of contention points, and the unpredictability in knowing which locks a request will require, make it difficult to prevent contention through overload control using traditional signals such as queueing delay and CPU utilization. We present Protego, a system that resolves these problems with two key ideas. First, it contributes a new admission control strategy that prevents compute congestion in the presence of lock contention. The key idea is to use marginal improvements in observed throughput, rather than CPU load or latency measurements, within a credit-based admission control algorithm that regulates the rate of incoming requests to a server. Second, it introduces a new latency-aware synchronization abstraction called Active Synchronization Queue Management (ASQM) that allows applications to abort requests if delays exceed latency objectives. We apply Protego to two real-world applications, Lucene and Memcached, and show that it achieves up to 3.3x more goodput and 12.2x lower 99th percentile latency than the state-of-the-art overload control systems while avoiding congestion collapse.more » « less
-
Modern datacenter applications are concurrent, so they require synchronization to control access to shared data. Requests can contend for different combinations of locks, depending on application and request state. In this paper, we show that locks, especially blocking synchronization, can squander throughput and harm tail latency, even when the CPU is underutilized. Moreover, the presence of a large number of contention points, and the unpredictability in knowing which locks a request will require, make it difficult to prevent contention through overload control using traditional signals such as queueing delay and CPU utilization. We present Protego, a system that resolves these problems with two key ideas. First, it contributes a new admission control strategy that prevents compute congestion in the presence of lock contention. The key idea is to use marginal improvements in observed throughput, rather than CPU load or latency measurements, within a credit-based admission control algorithm that regulates the rate of incoming requests to a server. Second, it introduces a new latency-aware synchronization abstraction called Active Synchronization Queue Management (ASQM) that allows applications to abort requests if delays exceed latency objectives. We apply Protego to two real-world applications, Lucene and Memcached, and show that it achieves up to 3.3x more goodput and 12.2x lower 99th percentile latency than the state-of-the-art overload control systems while avoiding congestion collapse.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1145/3523230.3523234
