A common pitfall when hosting applications in today's cloud environments is that virtual servers often experience varying execution speeds due to the interference from co-located virtual servers degrading the tail sojourn times specified in service level agreements. Motivated by the significance of tail sojourn times for cloud clusters, we develop a model of N parallel virtual server queues, each of which processes jobs in a processor sharing fashion under varying execution speeds governed by Markov-modulated processes. We derive the tail distribution of the workloads for each server and the approximation for the tail sojourn times based on large deviation analysis. Furthermore, we optimize the cluster sizes that fulfill the requirements of target tail sojourn times. Extensive simulation experiments show very good matches to the derived analysis in a variety of scenarios, i.e., large numbers of servers experiencing a high number of different execution speeds, under various traffic intensities, workload variations and cluster sizes. Finally, we apply our proposed analysis to estimating the tail sojourn times of a Wikipedia system hosted in a private cloud, and the testbed results strongly confirm the applicability and accuracy of our analysis.@en

With the rapid growth of social media and Internet-of-Things, real-time processing of big data has become a core operation in various business areas. It is of paramount importance that big-data analyses are executed timely with specified accuracy guarantees. However, workloads in the wild are highly bursty with skewed contents and often present the conundrum of meeting latency and accuracy requirements simultaneously. In this paper we propose AccStream, which selectively samples and processes data tuples and blocks on emerging batch streaming platforms with a special focus on analysis of aggregation, e.g., counts, and top-k. AccStream dynamically learns the latency model of analysis jobs via on-line probing technique and employs sample theory to determine the lower limit of data so as to fulfill given accuracy targets. A unique feature of AccStream ensuring strong latency-accuracy fulfillment even under conflicts is the hybrid windowing that trades off data freshness via a combination of tumbling and rolling windows. We evaluate the prototype of AccStream on Spark Streaming, analyzing Twitter data. Our extensive results confirm that AccStream is able to achieve the latency and accuracy target against a wide range of conditions, i.e., slow and fast dynamic load intensities and content skewnesses, even when facing conflicting latency and accuracy targets. All in all, the effectiveness of AccStream in delivering timely, accurate, and (partial) fresh streaming analytics lies in shedding the adequate amount of input data at the right time and place.

@en

Message exchange is a central activity in distributed computing frameworks. Nevertheless, past research has paid little attention on profiling techniques and tools for endpoint communication. In this paper, we fill this gap by introducing a new fine-grained profiler for endpoints and communication between them in distributed systems. Our tool aids efficient analysis, optimization, and tuning of endpoint communication in distributed frameworks. The paper presents an overview of our profiler, discusses employed profiling techniques and collected metrics, and shows preliminary results in profiling a well-known distributed computing framework.

@en

Real-time processing of big data is becoming one of the core operations in various areas, such as social networks and anomaly detection. Thanks to the rich information of the data, multiple queries can be executed to analyse the data and discover a variety of business values. It is very typical that a cluster infrastructure running for example a Spark Streaming data stream processing system would execute multiple queries simultaneously. To enable multiple queries being answered from the same data concurrently, it is important to effectively allocate the CPU-cores of the underlying infrastructure to the queries, meanwhile adhering to the latency constraints of the individual queries. In this paper, we consider the problem of allocating CPU-cores in a Spark Streaming infrastructure in the context of two types of queries, namely primary and optional, that are associated with high-and low-priority analysis, respectively. We develop a controller, iBLOC, that adjusts the block sizes of streaming jobs on the fly and the parallelism level of jobs, according to the input data rates and the query priorities. Our evaluation shows that we can achieve significant CPU-core savings from the primary query type such that multiple queries can run together without impairing their latency constraints, in comparison to a static block-sizing scheme.

@en

Big-data applications are becoming the core of today's business operations, featuring complex data structures and high task fan-out. According to the publicly available Google trace, more than 40% of big-data jobs do not reach successful completion. Interestingly, a significant portion of tasks of such failed jobs undergo multiple types of repetitive failed executions and consume a non-negligible amount of resources. To conserve resources for big-data clusters, it is imperative to capture such failed tasks of failed jobs, a very challenging problem due to multiple types of failures associated with tasks and highly uneven tasks distribution. In this paper, we develop an on-line two-level Neural Network (NN) model which can accurately untangle the complex dependencies among tasks and jobs, and predict their execution classes in an extremely dynamic and heterogeneous system. Our proposed NN model predicts first the job class, and secondly three classes of failed tasks of failed jobs, based on a sliding learning window. Furthermore, we develop resource conservation policies that terminate failed tasks of failed jobs after a grace period that is derived from prediction confidences and task execution times. Overall, evaluating our results on a Google cluster trace, we are able to accurately capture failures of failures at big-data clusters, mitigate false negative tasks to 1%, and efficiently save system resources, achieving significant reductions of CPU, memory and disk consumption - as high as 49%.

@en

Concurrent execution of multiple applications leads to varying partial utilization of shared resources. Understanding system behavior in these conditions is essential for making concurrent execution efficient. Unfortunately, anticipating behavior of shared resources at partial utilization in complex systems is difficult, realistic experiments that reproduce and examine such behavior are therefore needed. To facilitate experiments at partial utilization, we present a tool that accurately controls the processor utilization of arbitrary concurrent workloads, either establishing constant partial load or replaying a variable load trace. We validate the ability of the tool to enforce the configured partial utilization on multiple platforms, and use the tool to collect novel information on system behavior at partial utilization levels. In detail, our experiments show how to examine the complex relationship between utilization and throughput, useful for tasks such as performance debugging or system dimensioning, and we show this relationship for the DaCapo benchmarks. Further, we show that CPU pinning (a technique used to improve workload isolation) can benefit from dynamic response to system utilization, improving system efficiency with partial utilization. Finally, we show that the overhead of virtualization also changes with partial utilization and CPU allocation.@en

Nowadays, numerous programming languages and frameworks offer concurrency based on the actor model. Among the actor libraries for the Java Virtual Machine, Akka is the most used one, as it is employed in various parallel and distributed applications and frameworks. Unfortunately, despite the spread of actors libraries, Akka in particular, existing profiling tools are not very effective at identifying performance drawbacks in applications using actors. In this tool paper, we aim at filling this gap by presenting AkkaProf, a profiling tool for Akka actors. AkkaProf provides detailed metrics on actor utilization and on the communication between them, two fundamental aspects of actor-based applications that are overlooked by other profilers. AkkaProf aids performance analysis in several applications and frameworks in both parallel and distributed environments.

@en

As modern service systems are pressured to provide competitive prices via cost-effective capacity planning, especially in the paradigm of cloud computing, service level agreements (SLAs) end up becoming ever more sophisticated, i.e., fulfilling targets of different percentiles of response times. However, it is no mean feat to predict even the average response times of real systems, or even abstracted queueing systems that typically simplify system details, and it gets even more complicated when trying to manage SLAs defined by various percentiles of response times. To efficiently capture these different percentiles, we first develop a novel and autonomic methodology - termed Burst Based Simulation, which combines burst profiling on real systems with complex, state-dependent simulations. Moreover, based on our methodology, we construct an analysis on SLA management: the prediction of SLA violations given a certain request pattern. We evaluate our approach on two types of service systems, virtualized and bare-metal, with wide ranges of SLAs and traffic loads. Our evaluation results show that our methodology is able to achieve an average error below 15% when predicting different response time percentiles, and accurately capture SLA violations.

@en

To operate systems cost-effectively, cloud providers not only multiplex applications on the shared infrastructure but also dynamically allocate available resources, such as power and cores. Data intensive applications based on the MapReduce paradigm rapidly grow in popularity and importance in the Cloud. Such big data applications typically have high fan-out of components and workload dynamics. It is no mean feat to deploy and further optimize application performance within (stringent) resource budgets. In this paper, we develop a novel solution, OptiCA, that eases the deployment of big data applications on cloud and the control of application components so that desired performance metrics can be best achieved for any given resource budgets, in terms of core capacities. The control algorithm of OptiCA distributes the available core budget across co-executed applications and components, based on their 'effective' demands obtained through non-intrusive profiling. Our proposed solution is able to achieve robust performance, i.e., with very minor degradation, in cases where resource budget decreases rapidly.

@en