Ernest: Efficient Performance Prediction for Large-Scale Advanced Analytics - Venkataraman et al. 2016 With cloud computing environments such as Amazon EC2, users typically have a large number of choices in terms of the instance types and number of instances they can run their jobs on. Not surprisingly, the amount of memory per core, storage media, … Continue reading Ernest: Efficient Performance Prediction for Large-Scale Advanced Analytics
Month: March 2016
Diplomat: Using Delegations to Protect Community Repositories
Diplomat: Using Delegations to Protect Community Repositories - Kuppusamy et al. 2016 Community repositories, such as Docker Hub, Python Package Index (PyPI), RubyGems, and SourceForge provide an easy way for a developer to disseminate software... [they] are immensely popular and collectively serve more than a billion packages per year. Unfortunately, the popularity of these repositories … Continue reading Diplomat: Using Delegations to Protect Community Repositories
Polaris: Faster Page Loads Using Fine-Grained Dependency Tracking
Polaris: Faster Page Loads Using Fine-Grained Dependency Tracking - Netravali et al. 2016 Yesterday we looked at Shandian which promised faster web page load times, but required a modified client-side browser. Today we're sticking with the theme of reducing page load times with Polaris. Unlike Shandian, Polaris works with unmodified browsers, and in tests with … Continue reading Polaris: Faster Page Loads Using Fine-Grained Dependency Tracking
Speeding up Web Page Loads with Shandian
Speeding up Web Page Loads with Shandian - Wang et al. 2016 Despite its importance and various attempts to improve page load time (PLT), the end-to-end PLT for most pages is still a few seconds on desktops and more than ten seconds on mobile devices. Page load times are very important for user experience and … Continue reading Speeding up Web Page Loads with Shandian
Sieve: Cryptographically Enforced Access Control for User Data in Untrusted Clouds
Sieve: Cryptographically Enforced Access Control for User Data in Untrusted Clouds - Wang et al. 2016 Who owns your data? With cloud services, 'your' data is typically spread across multiple walled gardens, one per service. I'm reminded of a great line from "On the duality of resilience and privacy:" It is a truth universally acknowledged … Continue reading Sieve: Cryptographically Enforced Access Control for User Data in Untrusted Clouds
Cliffhanger: Scaling Performance Cliffs in Web Memory Caches
Cliffhanger: Scaling Performance Cliffs in Web Memory Caches - Cidon et al. 2016 Cliffhanger continues yesterday's theme of efficient cache allocation policies when sharing cache resources. The paper focuses on a shared memcached service, where memory is divided between a number of slabs (each slab storing items with sizes in a specific range - e.g. … Continue reading Cliffhanger: Scaling Performance Cliffs in Web Memory Caches
FairRide: Near-Optimal, Fair Cache Sharing
FairRide: Near-Optimal, Fair Cache Sharing - Pu et al. 2016 Yesterday we looked at a near-optimal packet scheduling algorithm (LSTF), today it's the turn of a near-optimal fair cache sharing algorithm. We're concerned with the scenario where a single cache resource is shared by multiple applications / users. Ideally we'd like three properties to hold: … Continue reading FairRide: Near-Optimal, Fair Cache Sharing
Universal Packet Scheduling
Universal Packet Scheduling - Mittal et al. 2015 (presented at NSDI '16) Is there a universal scheduling algorithm, such that simply by changing its configuration parameters, we can produce any desired schedule? In Universal Packet Scheduling, Mittal et al. show us that in theory there can be no Universal Packet Scheduling (UPS) algorithm which achieves … Continue reading Universal Packet Scheduling
Maglev: A Fast and Reliable Software Network Load Balancer
Maglev: A Fast and Reliable Software Network Load Balancer - Eisenbud et al. 2016 Maglev is Google's software load balancer used within all their datacenters. It offers greater scalability and availability than hardware load balancers, enables quick iteration, and is much easier to upgrade. Maglev is a just another distributed system running on the commodity … Continue reading Maglev: A Fast and Reliable Software Network Load Balancer
Distributed TensorFlow with MPI
Distributed TensorFlow with MPI - Vishnu et al. 2016 A short early release paper to close out the week this week, which looks at how to support machine learning and data mining (MLDM) with Google's TensorFlow in a distributed setting. The paper also contains some good background on TensorFlow itself as well as MPI - … Continue reading Distributed TensorFlow with MPI
the morning paper 