Serverless computing emerges as a new paradigm to build cloud applications, in which developers write small functions that react to cloud infrastructure events, and cloud providers maintain all resources and schedule the functions in containers. Serverless computing thus enables developers to focus on their core business logic and leave server management and scaling to cloud providers. Unfortunately, existing serverless computing systems suffer from a key limitation that deprives them of enjoying significant speedups. Specifically, they treat each cloud function as a black box and are blind to which data the function reads or writes, therefore missing potentially huge optimization opportunities, such as caching data and colocating functions. We present Lambdata, a novel serverless computing system that enables developers to declare a cloud function's data intents, including both data read and data written. Once data intents are made explicit, Lambdata performs a variety of optimizations to improve speed, including caching data locally and scheduling functions based on code and data locality. Our evaluation of Lambdata shows that it achieves an average speedup of 1.51x on the turnaround time of practical workloads and reduces monetary cost by 16.5%.

Web applications are getting ubiquitous every day because they offer many useful services to consumers and businesses. Many of these web applications are quite storage-intensive. Cloud computing offers attractive and economical choices for meeting their storage needs. Unfortunately, it remains challenging for developers to best leverage them to minimize cost. This paper presents Grandet, an extensible storage system that significantly reduces storage cost for web applications deployed in the cloud. Grandet provides both a key-value interface and a file system interface, supporting a broad spectrum of web applications. Under the hood, it supports multiple heterogeneous stores and unifies them by placing each data object at the store deemed most economical. We implemented Grandet on Amazon Web Services and evaluated Grandet on a diverse set of four popular open-source web applications. Our results show that Grandet reduces their cost by an average of 42.4%, and it is fast, scalable, and easy to use. The source code of Grandet is at http://columbia.github.io/grandet.

Mobile apps bring unprecedented levels of convenience, yet they are often buggy, and their bugs offset the convenience the apps bring. A key reason for buggy apps is that they must handle a vast variety of system and user actions such as being randomly killed by the OS to save resources, but app developers, facing tough competitions, lack time to thoroughly test these actions. AppDoctor is a system for efficiently and effectively testing apps against many system and user actions, and helping developers diagnose the resultant bug reports. It quickly screens for potential bugs using approximate execution, which runs much faster than real execution and exposes bugs but may cause false positives. From the reports, AppDoctor automatically verifies most bugs and prunes most false positives, greatly saving manual inspection effort. It uses action slicing to further speed up bug diagnosis. We implement AppDoctor in Android. It operates as a cloud of physical devices or emulators to scale up testing. Evaluation on 53 out of 100 most popular apps in Google Play and 11 of the most popular open-source apps shows that, AppDoctor effectively detects 72 bugs---including two bugs in the Android framework that affect all apps---with quick checking sessions, speeds up testing by 13.3 times, and vastly reduces diagnosis effort.

To provide fault tolerance for cloud storage, recent studies propose to stripe data across multiple cloud vendors. However, if a cloud suffers from a permanent failure and loses all its data, we need to repair the lost data with the help of the other surviving clouds to preserve data redundancy. We present a proxy-based storage system for fault-tolerant multiple-cloud storage called NCCloud, which achieves cost-effective repair for a permanent single-cloud failure. NCCloud is built on top of a network-coding-based storage scheme called the functional minimum-storage regenerating (FMSR) codes, which maintain the same fault tolerance and data redundancy as in traditional erasure codes (e.g., RAID-6), but use less repair traffic and, hence, incur less monetary cost due to data transfer. One key design feature of our FMSR codes is that we relax the encoding requirement of storage nodes during repair, while preserving the benefits of network coding in repair. We implement a proof-of-concept prototype of NCCloud and deploy it atop both local and commercial clouds. We validate that FMSR codes provide significant monetary cost savings in repair over RAID-6 codes, while having comparable response time performance in normal cloud storage operations such as upload/download.

Alias analysis is perhaps one of the most crucial and widely used analyses, and has attracted tremendous research efforts over the years. Yet, advanced alias analyses are extremely difficult to get right, and the bugs in these analyses are one key reason that they have not been adopted to production compilers. This paper presents NeonGoby, a system for effectively detecting errors in alias analysis implementations, improving their correctness and hopefully widening their adoption. NeonGoby detects the worst type of bugs where the alias analysis claims that two pointers never alias, but they actually alias at runtime. NeonGoby works by dynamically observing pointer addresses during the execution of a test program and then checking these addresses against an alias analysis for errors. It is explicitly designed to (1) be agnostic to the alias analysis it checks for maximum applicability and ease of use and (2) detect alias analysis errors that manifest on real-world programs and workloads. It emits no false positives as long as test programs do not have undefined behavior per ANSI C specification or call external functions that interfere with our detection algorithm. It reduces performance overhead using a practical selection of techniques. Evaluation on three popular alias analyses and real-world programs Apache and MySQL shows that NeonGoby effectively finds 29 alias analysis bugs with zero false positives and reasonable overhead; the most serious four bugs have been patched by the developers. To enable alias analysis builders to start using NeonGoby today, we have released it open-source at https://github.com/columbia/neongoby, along with our error detection results and proposed patches.

Parallel programs are known to be difficult to analyze. A key reason is that they typically have an enormous number of execution interleavings, or schedules. Static analysis over all schedules requires over-approximations, resulting in poor precision; dynamic analysis rarely covers more than a tiny fraction of all schedules. We propose an approach called schedule specialization to analyze a parallel program over only a small set of schedules for precision, and then enforce these schedules at runtime for soundness of the static analysis results. We build a schedule specialization framework for C/C++ multithreaded programs that use Pthreads. Our framework avoids the need to modify every analysis to be schedule-aware by specializing a program into a simpler program based on a schedule, so that the resultant program can be analyzed with stock analyses for improved precision. Moreover, our framework provides a precise schedule-aware def-use analysis on memory locations, enabling us to build three highly precise analyses: an alias analyzer, a data-race detector, and a path slicer. Evaluation on 17 programs, including 2 real-world programs and 15 popular benchmarks, shows that analyses using our framework reduced may-aliases by 61.9%, false race reports by 69%, and path slices by 48.7%; and detected 7 unknown bugs in well-checked programs.

We can now outsource data backups off-site to third-party cloud storage services so as to reduce data management costs. However, we must provide security guarantees for the outsourced data, which is now maintained by third parties. We design and implement FADE, a secure overlay cloud storage system that achieves fine-grained, policy-based access control and file assured deletion. It associates outsourced files with file access policies, and assuredly deletes files to make them unrecoverable to anyone upon revocations of file access policies. To achieve such security goals, FADE is built upon a set of cryptographic key operations that are self-maintained by a quorum of key managers that are independent of third-party clouds. In particular, FADE acts as an overlay system that works seamlessly atop today's cloud storage services. We implement a proof-of-concept prototype of FADE atop Amazon S3, one of today's cloud storage services. We conduct extensive empirical studies, and demonstrate that FADE provides security protection for outsourced data, while introducing only minimal performance and monetary cost overhead. Our work provides insights of how to incorporate value-added security features into today's cloud storage services.