The scale of cloud services keeps increasing over time, significantly introducing huge challenges in system manageability and reliability. Designing coordination services in cloud is the right track to solve the above problems. However, existing coordination services (e.g., Chubby and ZooKeeper) only perform well in read-intensive scenario and small ensemble scales. To this end, we propose Giraffe, a scalable distributed coordination service. There are three important contributions in our design. (1) Giraffe organizes coordination servers using interior-node-disjoint trees for better scalability. (2) Giraffe employs a novel Paxos protocol for strong consistency and fault-tolerance. (3) Giraffe supports hierarchical data organization and in-memory storage for high throughput and low latency. We evaluate Giraffe on a high performance computing test-bed. The experimental results show that Giraffe gains much better write performance than ZooKeeper when server ensemble is large. Giraffe is nearly 300% faster than ZooKeeper on update operations when ensemble size is 50 servers. Experiments also show that Giraffe reacts and recovers more quickly than ZooKeeper against node failures.

Software bugs affect system reliability. When a bug is exposed in the field, developers need to fix them. Unfortunately, the bug-fixing process can also introduce errors, which leads to buggy patches that further aggravate the damage to end users and erode software vendors' reputation.

Configuration errors (i.e., misconfigurations) are among the dominant causes of system failures. Their importance has inspired many research efforts on detecting, diagnosing, and fixing misconfigurations; such research would benefit greatly from a real-world characteristic study on misconfigurations. Unfortunately, few such studies have been conducted in the past, primarily because historical misconfigurations usually have not been recorded rigorously in databases.

Software bugs, such as concurrency, memory and semantic bugs, can significantly affect system reliability. Although much effort has been made to address this problem, there are still many bugs that cannot be detected, especially concurrency bugs due to the complexity of concurrent programs. Effective approaches for detecting these common bugs are therefore highly desired.

Bug reproduction is critically important for diagnosing a production-run failure. Unfortunately, reproducing a concurrency bug on multi-processors (e.g., multi-core) is challenging. Previous techniques either incur large overhead or require new non-trivial hardware extensions.

A global-scale low cost outdoor Internet access infrastructure is finally attainable. Emerging projects are leveraging the proliferation of private Wi-Fi networks to build a global-scale ubiquitous access infrastructure from autonomous, independently owned Internet connections at homes and other private properties. To ensure the trace ability and accountability required by the broadband ISPs and private owners of these Wi-Fi networks, reliable authentication and authorization are needed. This paper describes authentication on the edge, a localized and distributed authentication method for open Wi-Fi networks. Three main ideas are used to adapt to the variability and unreliability of these networks: the use of certificate-based authentication, the distribution of a segmented certificate revocation list to all entities and the self organization of access points into a social lookup network. These methods achieve the scalability needed for the overwhelming size and volume of a global network and increase resiliency against temporary failures in the infrastructure.