Despite the growing market penetration, today's high-end virtual reality (VR) systems remain tethered, which not only limits users' VR experience but also creates a safety hazard. In this paper, we perform a systematic design study of the “elephant in the room” facing the VR industry - is it feasible to enable high-quality VR apps on untethered mobile devices such as smartphones? Our quantitative, performance-driven design study makes two contributions. First, we show that the QoE achievable for high-quality VR applications on today's mobile hardware and wireless networks via local rendering or offloading is about 10X away from the acceptable QoE, yet waiting for future mobile hardware or next-generation wireless networks (e.g., 5G) is unlikely to help, because of power limitation and the higher CPU utilization needed for processing packets under higher data rate. Second, we present Furion, a VR framework that enables high-quality, immersive mobile VR on today's mobile devices and wireless networks. Furion exploits a key insight about the VR workload that foreground interactions and background environment have contrasting predictability and rendering workload, and employs a split renderer architecture running on both the phone and the server. Supplemented with video compression, use of panoramic frames, parallel decoding on multiple cores on the phone, and view-based bitrate adaptation we demonstrate Furion can support high-quality VR apps on today's smartphones over WiFi, with under 14 ms latency and 60 FPS (the phone display refresh rate).

Cloud computing platforms enable applications to offer low-latency services to users by deploying data storage in multiple geo-distributed data centers. In this paper, through benchmark measurements on Amazon AWS and Microsoft Azure together with an analysis of a large-scale dataset collected from a major cloud CDN provider, we identify the high tail latency problem in cloud CDNs, which can substantially undermine the efficacy of cloud CDNs. One crucial idea to reduce the tail latency is to send requests in parallel to multiple clouds in cloud CDNs. However, since application providers often have a budget for using cloud services, deciding how many chunks to download from each cloud and when to download chunks in a cost-efficient manner still remain as open problems in our concerned scenario. To address the problem, we present TailCutter, a workload scheduling framework that aims at optimizing the tail latency while meeting cost constraints given by application providers. Specifically, we formulate the tail latency minimization (TLM) problem in cloud CDNs and design the receding horizon control based maximum tail minimization algorithm (RHC-based MTMA) to efficiently solve the TLM problem in practice. We implement TailCutter across multiple data centers of Amazon AWS and Microsoft Azure. Extensive evaluations using a large-scale real-world data trace (collected from a major ISP) illustrate that TailCutter can reduce up to 58.9% of the 100th-percentile user-perceived latency, as compared with alternative solutions under the cost constraint.

In this paper, we perform a systematic design study of the "elephant in the room" facing the VR industry -- is it feasible to enable high-quality VR apps on untethered mobile devices such as smartphones? Our quantitative, performance-driven design study makes two contributions. First, we show that the QoE achievable for high-quality VR applications on today's mobile hardware and wireless networks via local rendering or offloading is about 10X away from the acceptable QoE, yet waiting for future mobile hardware or next-generation wireless networks (e.g. 5G) is unlikely to help, because of power limitation and the higher CPU utilization needed for processing packets under higher data rate. Second, we present Furion, a VR framework that enables high-quality, immersive mobile VR on today's mobile devices and wireless networks. Furion exploits a key insight about the VR workload that foreground interactions and background environment have contrasting predictability and rendering workload, and employs a split renderer architecture running on both the phone and the server. Supplemented with video compression, use of panoramic frames, and parallel decoding on multiple cores on the phone, we demonstrate Furion can support high-quality VR apps on today's smartphones over WiFi, with under 14ms latency and 60 FPS (the phone display refresh rate).

Mobile cloud storage services have gained phenomenal success in recent few years. In this paper, we identify, analyze, and address the synchronization (sync) inefficiency problem of modern mobile cloud storage services. Our measurement results demonstrate that existing commercial sync services fail to make full use of available bandwidth, and generate a large amount of unnecessary sync traffic in certain circumstances even though the incremental sync is implemented. For example, a minor document editing process in Dropbox may result in sync traffic 10 times that of the modification. These issues are caused by the inherent limitations of the sync protocol and the distributed architecture. Based on our findings, we propose QuickSync, a system with three novel techniques to improve the sync efficiency for mobile cloud storage services, and build the system on two commercial sync services. Our experimental results using representative workloads show that QuickSync is able to reduce up to 73.1 percent sync time in our experiment settings.

Cloud computing platforms enable applications to offer low latency access to user data by offering storage services in several geographically distributed data centers. In this paper, we identify the high tail latency problem in cloud CDN via analyzing a large-scale dataset collected from 783,944 users in a major cloud CDN. We find that the data downloading latency in cloud CDN is highly variable, which may significantly degrade the user experience of applications. To address the problem, we present TailCutter, a workload scheduling mechanism that aims at optimizing the tail latency while meeting the cost constraint given by application providers. We further design the Maximum Tail Minimization Algorithm (MTMA) working in TailCutter mechanism to optimally solve the Tail Latency Minimization (TLM) problem in polynomial time. We implement TailCutter across data centers of Amazon S3 and Microsoft Azure. Our extensive evaluation using large-scale real world data traces shows that TailCutter can reduce up to 68% 99th percentile user-perceived latency in comparison with alternative solutions under cost constraints.

Mobile cloud storage services have gained phenomenal success in recent few years. In this paper, we identify, analyze and address the synchronization (sync) inefficiency problem of modern mobile cloud storage services. Our measurement results demonstrate that existing commercial sync services fail to make full use of available bandwidth, and generate a large amount of unnecessary sync traffic in certain circumstance even though the incremental sync is implemented. These issues are caused by the inherent limitations of the sync protocol and the distributed architecture. Based on our findings, we propose QuickSync, a system with three novel techniques to improve the sync efficiency for mobile cloud storage services, and build the system on two commercial sync services. Our experimental results using representative workloads show that QuickSync is able to reduce up to 52.9% sync time in our experiment settings.