No abstract

As the distribution of video over the Internet is becoming mainstream, user expectation for higb quality is constantly increasing. In this context, it is crucial for content providers to understand if and bow video quality affects user engagement and bow to best invest tbeir resources to optimize video quality. Tbis paper is a first step toward addressing tbese questions. We use a unique dataset tbat spans different content types, including sbort video on demand (VoD), long VoD, and live content from popular video content providers. Using client-side instrumentation, we measure quality metrics sucb as tbe join time, buffering ratio, average bitrate, rendering quality, and rate of buffering events. We find tbat tbe percentage of time spent in buffering (buffering ratio) bas tbe largest impact on tbe user engagement across all types of content. However, tbe magnitude of tbis impact depends on tbe content type, witb live content being tbe most impacted. For example, a 1% increase in buffering ratio can reduce user engagement by more tban 3 min for a 90-min live video event.

Basal ganglia (BG) constitute a network of seven deep brain nuclei involved in a variety of crucial brain functions including: action selection, action gating, reward based learning, motor preparation, timing, etc. In spite of the immense amount of data available today, researchers continue to wonder how a single deep brain circuit performs such a bewildering range of functions. Computational models of BG have focused on individual functions and fail to give an integrative picture of BG function. A major breakthrough in our understanding of BG function is perhaps the insight that activities of mesencephalic dopaminergic cells represent some form of 'reward' to the organism. This insight enabled application of tools from 'reinforcement learning,' a branch of machine learning, in the study of BG function. Nevertheless, in spite of these bright spots, we are far from the goal of arriving at a comprehensive understanding of these 'mysterious nuclei.' A comprehensive knowledge of BG function has the potential to radically alter treatment and management of a variety of BG-related neurological disorders (Parkinson's disease, Huntington's chorea, etc.) and neuropsychiatric disorders (schizophrenia, obsessive compulsive disorder, etc.) also. In this article, we review the existing modeling literature on BG and hypothesize an integrative picture of the function of these nuclei.

Today's data centers deploy a variety of middleboxes (e.g., firewalls, load balancers and SSL offloaders) to protect, manage and improve the performance of the applications and services they run. Unfortunately, existing networks provide limited support for middleboxes. Administrators typically overload layer-2 path selection mechanisms to make sure that traffic traverses the desired sequence of middleboxes. These ad-hoc practices result in a data center network that is hard to configure, upgrade and maintain, wastes middlebox resources on unwanted traffic, and cannot guarantee middlebox traversal under network churn.To address these issues, we propose the policy-aware switching layer, or PLayer. The PLayer separates policies from reachability by allowing administrators to explicitly specify sequences of middleboxes. Middleboxes are connected to policy-aware switches, or pswitches, whose forwarding state is configured by a centralized controller according to the policy requirements. This way, the PLayer addresses the limitations of current middlebox deployments without modifying existing middleboxes or servers. To demonstrate the feasibility of our approach we implemented a prototype of the PLayer using the Click modular software router. Preliminary experimental results suggest that the PLayer is flexible, uses middleboxes efficiently, and ensures the correctness of middlebox traversal under churn.

Today's data centers deploy a variety of middleboxes (e.g., firewalls, load balancers and SSL offloaders) to protect, manage and improve the performance of the applications and services they run. Unfortunately, existing networks provide limited support for middleboxes. Administrators typically overload layer-2 path selection mechanisms to make sure that traffic traverses the desired sequence of middleboxes. These ad-hoc practices result in a data center network that is hard to configure, upgrade and maintain, wastes middlebox resources on unwanted traffic, and cannot guarantee middlebox traversal under network churn.To address these issues, we propose the policy-aware switching layer, or PLayer. The PLayer separates policies from reachability by allowing administrators to explicitly specify sequences of middleboxes. Middleboxes are connected to policy-aware switches, or pswitches, whose forwarding state is configured by a centralized controller according to the policy requirements. This way, the PLayer addresses the limitations of current middlebox deployments without modifying existing middleboxes or servers. To demonstrate the feasibility of our approach we implemented a prototype of the PLayer using the Click modular software router. Preliminary experimental results suggest that the PLayer is flexible, uses middleboxes efficiently, and ensures the correctness of middlebox traversal under churn.