While virtual machine (VM) migration is allowing data centers to rebalance workloads across physical machines, the promise of a maximally utilized infrastructure is yet to be realized. Part of the challenge is due to the inherent dependencies between VMs comprising a multi-tier application, which introduce complex load interactions between the underlying physical servers. For example, simply moving an overloaded VM to a (random) underloaded physical machine can inadvertently overload the network. We introduce AppAware-a novel, computationally efficient scheme for incorporating (1) inter-VM dependencies and (2) the underlying network topology into VM migration decisions. Using simulations, we show that our proposed method decreases network traffic by up to 81%compared to a well known alternative VM migration method that is not application-aware.

With the intense competition between cloud providers, oversubscription is increasingly important to maintain profitability. Oversubscribing physical resources is not without consequences: it increases the likelihood of overload. Memory overload is particularly damaging. Contrary to traditional views, we analyze current data center logs and realistic Web workloads to show that overload is largely transient: up to 88.1% of overloads last for less than 2 minutes. Regarding overload as a continuum that includes both transient and sustained overloads of various durations points us to consider mitigation approaches also as a continuum, complete with tradeoffs with respect to application performance and data center overhead. In particular, heavyweight techniques, like VM migration, are better suited to sustained overloads, whereas lightweight approaches, like network memory, are better suited to transient overloads. We present Overdriver, a system that adaptively takes advantage of these tradeoffs, mitigating all overloads within 8% of well-provisioned performance. Furthermore, under reasonable oversubscription ratios, where transient overload constitutes the vast majority of overloads, Overdriver requires 15% of the excess space and generates a factor of four less network traffic than a migration-only approach.

The recent explosion of the Internet and the World Wide Web has made digital libraries popular. Easy access to a digital library is provided by commercially available Web browsers, which provide a user-friendly interface. To retrieve documents of interest, the user is provided with a search interface that may only consist of one input field and one push button. Most users type in a single keyword, click the button, and hope for the best. The result of a query using this kind of search interface can consist of a large unordered set of documents, or a ranked list of documents based on the frequency of the keywords. Both lists can contain articles unrelated to the user's inquiry unless a sophisticated search was performed and the user knows exactly what to look for. More sophisticated algorithms for ranking the search results according to how well they meet the users' needs as expressed in the search input may help. However, what is desperately needed are software tools that can analyze the search result and manipulate large hierarchies of data graphically. In this article we describe the design of a language-independent document classification system being developed to help users of the Florida Center for Library Automation analyze search query results. Easy access through the Web is provided, as well as a graphical user interface to display the classification results. We also describe the use of this system to retrieve and analyze sets of documents from public Web sites.

A fundamental trend for servers in network-centric computing environments is to evolve from traditional database and transaction servers to information distribution and handling systems. In addition to documents written in the HyperText Markup Language (HTML), data stored in other forms can be retrieved through the Common Gateway Interface (CGI). A significant performance bottleneck is the initialization and setup phase for a CGI process to gain access to a backend server. In this paper, we describe the design and implementation of distributed Web server for CGI processes to acquire services efficiently. A Connection Manager Daemon (CMD) is developed to provide a number of cliettes, which are connected to backend servers to eliminate initialization costs for incoming requests. A Cache Manager is implemented to speedup response time in case of repeated requests. We also trace and monitor the Connection Manager Daemon as well as its clients using extended UTE (Unified Trace Environment) tools, and present its performance analysis and visualization. The platforms where we conduct this study include a single-node workstation, a cluster of workstations, and an IBM Scalable Parallel (SP) system.

In essence, the World Wide Web is a worldwide string of computer databases using a common information retrieval architecture. With the increasing popularity of the World Wide Web, more and more functions have been added to retrieve not only documents written in HTML (Hypertext Markup Language), but also those in other forms through the Common Gateway Interface (CGI), by constructing HTML documents dynamically. Dynamic construction of HTML documents for handling information such as digital libraries is slow and requires much more computer power. A significant performance bottleneck is the initialization and setup phase for a CGI process to gain access to the system containing the data. In this paper we describe the design and implementation of a Connection Manager Interface on IBM SP systems. The Connection Manager provides cliette processes to serve CGI requests and eliminates such bottlenecks. An IBM SP system is used for this emerging area to show that our design and implementation is flexible enough to take advantage of the High-Performance Switch in an IBM SP system. We trace and monitor this scalable Web services using UTE (Unified Trace Environment) tools, and present its performance analysis and visualization.

Stack simulation is a powerful cache analysis approach to generate the number of misses and write backs for various cache configurations in a single run. Unfortunately, none of the previous work on stack simulation has efficient stack algorithm for virtual address caches with real tags (VIR-type caches). In this paper, we devise an efficient stack simulation algorithm for analyzing VIR-type caches. Using markers with a valid range for synonym lines, our algorithm is able to keep track of stack distances for different cache configurations. In addition to cache miss ratios and write back ratios, our approach generates pseudonym frequency for all cache configurations under investigation.>

We present an integrated approach to deal with timestamp consistency, and trace based performance analysis techniques for distributed parallel applications. Our trace generation facility captures message passing and system events such as process dispatch with minimal trace overhead. Trace driven analysis tools are developed for post execution analysis, reporting information such as the time stolen by other processes in each node, and the observed message passing time and local wait time for each message. We then present our techniques to reduce total elapsed times based on observed message passing times and local wait times.

We propose efficient stack simulation algorithms for shared memory multiprocessor (MP) caches. A stack simulation algorithm for write-updated MP caches is first presented. It produces the number of write-updates as well as misses for all cache configurations in a single run. We then devise a new stack simulation algorithm for writeinvalidate MP caches. Our algorithm takes into account cross-invalidation among processors, and generates the number of invalidations as well as misses for all cache configurations in a single run. A cache simulator based on our algorithms for MP caches is developed and the results on sample traces are reported. Our results show that effi cient stack simulation is a powerful technique for multi processor cache analysis.

Parallel accesses to the table lookaside buffer (TLB) and cache array are crucial for high-performance computer systems, and the choice of cache types is one of the most important factors affecting cache performance. The authors classify caches according to both index and tag. Since both index and tag could be either virtual (V) or real (R), their classification results in four combinations or cache types. The real address caches with virtual tags for high-performance computer systems in this study are prediction-based, since index bins are generated from a small array and predictions could be false. As a result, they also discuss and evaluate real address MRU caches with real tags, and propose virtually indexed MRU caches with real tags. Each of the four cache types and MRU caches are discussed and evaluated using trace-driven simulation. The results show that a virtually indexed MRU cache with real tags is a good choice for high-performance computer systems.>

Efficient stack simulation has been successfully applied in physically indexed caches with physical or real tags to generate the number of misses and write backs for various cache configurations in a single run. The authors devise a stack simulation algorithm for virtually indexed caches with real tags. Using markers with a valid range for synonym lines, the algorithm is able to keep track of stack distances for various cache configurations. In addition to cache miss ratios and number of write backs, the algorithm reports pseudonym frequency for all cache configurations under investigation. A one-pass cache simulator based on the algorithm is developed, and its results on sample traces are reported.>