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

Wimpy virtual instances equipped with small numbers of cores and RAM are popular public and private cloud offerings because of their low cost for hosting applications. The challenge is how to run latency-sensitive applications using such instances, which trade off performance for cost. In this study, we analytically and experimentally show that simultaneously scaling resources at coarse granularity and workloads, i.e., submitting multiple query clones to different servers, at fine granularity can overcome the performance disadvantages of wimpy VM instances and achieve stringent latency targets that are even lower than the average execution times of wimpy servers. To such an end, we first derive a closed-form analysis for the latency under any given VM provisioning and query replication level, considering cloning policies that can (not) terminate outstanding clones with (without) an overhead. Validated on trace-driven simulations, our analysis is able to accurately predict the latency and efficiently search for the optimal number of VMs and clones. Secondly, we develop a dual elastic scaler, DuoScale, that dynamically scales VMs and clones according to the workload dynamics so as to achieve the target latency in a cost-effective manner. The effectiveness of DuoScale lies on the observation that the application performance only scales sub-linearly with increasing vertical or horizontal resource provisioning, i.e., resources per VM or number of VMs. We evaluate DuoScale against VM-only scaling strategies via extensive trace-driven simulations as well as experimental results on a cloud test-bed. Our results show that DuoScale is able to achieve the stringent target latency by using clones on wimpy VMs with cost savings up to 50%, compared to scaling brawny VMs that have better performance at a higher unit cost.

@en

Replicating redundant requests has been shown to be an effective mechanism to defend application performance from high capacity variability - the common pitfall in the cloud. While the prior art centers on single-tier systems, it still remains an open question how to design replication strategies for distributed multi-tier systems, where interference from neighboring workloads is entangled with complex tier interdependency. In this paper, we design a first of its kind PArtial REplication system, sPARE, that replicates and dispatches read-only workloads for multi-tier web applications, determining replication factors per tier. The two key components of sPARE are (i) the variability-aware replicator that coordinates the replication levels on all tiers via an iterative searching algorithm, and (ii) the replication-aware arbiter that uses a novel token-based arbitration algorithm (TAD) to dispatch requests in each tier. We evaluate sPARE on web serving and web searching applications, i.e., MediaWiki and Solr, deployed on our private cloud testbed. Our results based on various interference patterns and traffic loads show that sPARE is able to improve the tail latency of MediaWiki and Solr by a factor of almost 2.7x and 2.9x, respectively.

@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