Hakan Hacigümüs

Efficient Execution of Aggregation Queries over Encrypted Relational Databases

Encryption is a common method to assure privacy of stored data. In many practical situations, decrypting data before applying logic compromises privacy. The challenge is to come up with logic transformation techniques and result-mapping methods so that the exact result of applying logic to data-in-the-clear is obtained by applying the transformed logic to encrypted data and mapping the result produced. In the scope of relational aggregation queries and in the presence of logical predicates, we show how to support needed transformations and mappings.

Intelligent management of virtualized resources for database systems in cloud environment

In a cloud computing environment, resources are shared among different clients. Intelligently managing and allocating resources among various clients is important for system providers, whose business model relies on managing the infrastructure resources in a cost-effective manner while satisfying the client service level agreements (SLAs). In this paper, we address the issue of how to intelligently manage the resources in a shared cloud database system and present SmartSLA, a cost-aware resource management system. SmartSLA consists of two main components: the system modeling module and the resource allocation decision module. The system modeling module uses machine learning techniques to learn a model that describes the potential profit margins for each client under different resource allocations. Based on the learned model, the resource allocation decision module dynamically adjusts the resource allocations in order to achieve the optimum profits. We evaluate SmartSLA by using the TPC-W benchmark with workload characteristics derived from real-life systems. The performance results indicate that SmartSLA can successfully compute predictive models under different hardware resource allocations, such as CPU and memory, as well as database specific resources, such as the number of replicas in the database systems. The experimental results also show that SmartSLA can provide intelligent service differentiation according to factors such as variable workloads, SLA levels, resource costs, and deliver improved profit margins.

Query optimization in encrypted database systems

To ensure the privacy of data in the relational databases, prior work has given techniques to support data encryption and execute SQL queries over the encrypted data. However, the problem of how to put these techniques together in an optimum manner was not addressed, which is equivalent to having an RDBMS without a query optimizer. This paper models and solves that optimization problem.

Predicting query execution time: Are optimizer cost models really unusable?

Predicting query execution time is useful in many database management issues including admission control, query scheduling, progress monitoring, and system sizing. Recently the research community has been exploring the use of statistical machine learning approaches to build predictive models for this task. An implicit assumption behind this work is that the cost models used by query optimizers are insufficient for query execution time prediction. In this paper we challenge this assumption and show while the simple approach of scaling the optimizers estimated cost indeed fails, a properly calibrated optimizer cost model is surprisingly effective. However, even a well-tuned optimizer cost model will fail in the presence of errors in cardinality estimates. Accordingly we investigate the novel idea of spending extra resources to refine estimates for the query plan after it has been chosen by the optimizer but before execution. In our experiments we find that a well calibrated query optimizer model along with cardinality estimation refinement provides a low overhead way to provide estimates that are always competitive and often much better than the best reported numbers from the machine learning approaches.

Ensuring the Integrity of Encrypted Databases in the Database-as-a-Service Model

In the database-as-a-service model, a service provider hosts the clients’ data and allows access to the data through the Internet. Database-as-a-service model offers considerable benefits to organizations with data management needs by allowing them to outsource their data management infrastructures. Yet, the model introduces many significant challenges, in particular that of data privacy and security. Ensuring the integrity of the database, which is hosted by a service provider, is a critical and challenging problem in this context. We propose an encrypted database integrity assurance scheme, which allows the owner of the data to ensure the integrity of the database hosted at the service provider site, in addition to the security of the stored data against malicious attacks.

iCBS: incremental cost-based scheduling under piecewise linear SLAs

In a cloud computing environment, it is beneficial for the cloud service provider to offer differentiated services among different customers, who often have different cost profiles. Therefore, cost-aware scheduling of queries is important. A practical cost-aware scheduling algorithm must be able to handle the highly demanding query volumes in the scheduling queues to make online scheduling decisions very quickly. We develop such a highly efficient cost-aware query scheduling algorithm, called iCBS. iCBS takes the query costs derived from the service level agreements (SLAs) between the service provider and its customers into account to make cost-aware scheduling decisions. iCBS is an incremental variation of an existing scheduling algorithm, CBS. Although CBS exhibits an exceptionally good cost performance, it has a prohibitive time complexity. Our main contributions are (1) to observe how CBS behaves under piecewise linear SLAs, which are very common in cloud computing systems, and (2) to efficiently leverage these observations and to reduce the online time complexity from O(N) for the original version CBS to O(log2 N) for iCBS.

MISO: souping up big data query processing with a multistore system

Multistore systems utilize multiple distinct data stores such as Hadoops HDFS and an RDBMS for query processing by allowing a query to access data and computation in both stores. Current approaches to multistore query processing fail to achieve the full potential benefits of utilizing both systems due to the high cost of data movement and loading between the stores. Tuning the physical design of a multistore, i.e., deciding what data resides in which store, can reduce the amount of data movement during query processing, which is crucial for good multistore performance. In this work, we provide what we believe to be the first method to tune the physical design of a multistore system, by focusing on which store to place data. Our method, called MISO for MultISstore Online tuning, is adaptive, lightweight, and works in an online fashion utilizing only the by-products of query processing, which we term as opportunistic views. We show that MISO significantly improves the performance of ad-hoc big data query processing by leveraging the specific characteristics of the individual stores while incurring little additional overhead on the stores.

PMAX: tenant placement in multitenant databases for profit maximization

There has been a great interest in exploiting the cloud as a platform for database as a service. As with other cloud-based services, database services may enjoy cost efficiency through consolidation: hosting multiple databases within a single physical server. Aggressive consolidation, however, may hurt the service quality, leading to SLA violation penalty, which in turn reduces the total business profit, called SLA profit. In this paper, we consider the problem of tenant placement in the cloud for SLA profit maximization, which, as will be shown in the paper, is strongly NP-hard. We propose SLA profit-aware solutions for database tenant placement based on our model for expected penalty computation for multitenant servers. Specifically, we present two approximation algorithms, which have constant approximation ratios, and we further discuss improving the quality of tenant placement using a dynamic programming algorithm. Extensive experiments based on TPC-W workload verified the performance of the proposed approaches.

Efficient key updates in encrypted database systems

In this paper, we investigate efficient key updates in encrypted database environments. We study the issues in the context of database-as-a-service (DAS) model that allows organizations to outsource their data management infrastructures to a database service provider. In the DAS model, a service provider employs data encryption techniques to ensure the privacy of hosted data. The security of encryption techniques relies on the confidentiality of the encryption keys. The dynamic nature of the encrypted database in the DAS model adds complexity and raises specific requirements on the key management techniques. Key updates are particularly critical because of their potential impact on overall system performance and resources usage. In this paper, we propose specialized techniques and data structures to efficiently implement the key updates along with the other key management functions to improve the systems’ concurrency performance in the DAS model.

CloudDB: One Size Fits All Revived

We present a data management platform in the cloud, CloudDB. The guiding principle of CloudDB’s design is establishing data independence for the applications that need to use diverse underlying data stores that are optimized for varying workload needs and characteristics. The applications should not have to be aware of the physical organization of the data and how the data is accessed. Ideally, an application only needs a logical specification of the data access layer and the data access requests are handled in a declarative way. CloudDB hosts variety of specialized databases that deliver high performance, scalability, and cost efficiency for varying application needs. CloudDB’s API layer is designed in such a way to give data independence to the higher level applications. The goal is to let the clients use just a simple, standard, and uniform language API to access data management functions as a service.