Per-Ake Larson

SCOPE: easy and efficient parallel processing of massive data sets

Companies providing cloud-scale services have an increasing need to store and analyze massive data sets such as search logs and click streams. For cost and performance reasons, processing is typically done on large clusters of shared-nothing commodity machines. It is imperative to develop a programming model that hides the complexity of the underlying system but provides flexibility by allowing users to extend functionality to meet a variety of requirements. In this paper, we present a new declarative and extensible scripting language, SCOPE (Structured Computations Optimized for Parallel Execution), targeted for this type of massive data analysis. The language is designed for ease of use with no explicit parallelism, while being amenable to efficient parallel execution on large clusters. SCOPE borrows several features from SQL. Data is modeled as sets of rows composed of typed columns. The select statement is retained with inner joins, outer joins, and aggregation allowed. Users can easily define their own functions and implement their own versions of operators: extractors (parsing and constructing rows from a file), processors (row-wise processing), reducers (group-wise processing), and combiners (combining rows from two inputs). SCOPE supports nesting of expressions but also allows a computation to be specified as a series of steps, in a manner often preferred by programmers. We also describe how scripts are compiled into efficient, parallel execution plans and executed on large clusters.

Hekaton: SQL server's memory-optimized OLTP engine

Hekaton is a new database engine optimized for memory resident data and OLTP workloads. Hekaton is fully integrated into SQL Server; it is not a separate system. To take advantage of Hekaton, a user simply declares a table memory optimized. Hekaton tables are fully transactional and durable and accessed using T-SQL in the same way as regular SQL Server tables. A query can reference both Hekaton tables and regular tables and a transaction can update data in both types of tables. T-SQL stored procedures that reference only Hekaton tables can be compiled into machine code for further performance improvements. The engine is designed for high con-currency. To achieve this it uses only latch-free data structures and a new optimistic, multiversion concurrency control technique. This paper gives an overview of the design of the Hekaton engine and reports some experimental results.

High-performance concurrency control mechanisms for main-memory databases

A database system optimized for in-memory storage can support much higher transaction rates than current systems. However, standard concurrency control methods used today do not scale to the high transaction rates achievable by such systems. In this paper we introduce two efficient concurrency control methods specifically designed for main-memory databases. Both use multiversioning to isolate read-only transactions from updates but differ in how atomicity is ensured: one is optimistic and one is pessimistic. To avoid expensive context switching, transactions never block during normal processing but they may have to wait before commit to ensure correct serialization ordering. We also implemented a main-memory optimized version of single-version locking. Experimental results show that while single-version locking works well when transactions are short and contention is low performance degrades under more demanding conditions. The multiversion schemes have higher overhead but are much less sensitive to hotspots and the presence of long-running transactions.

Summary-based routing for content-based event distribution networks

Providing scalable distributed Web-based eventing services has been an important research topic. It is desirable to have an effective mechanism for the servers to summarize their filters for in-network preprocessing in order to optimize system performance. In this paper, we propose a summary-based routing mechanism and introduce the notion of imprecise summaries to provide a trade-off between routing overhead and event traffic. Our system uses similarity-based filter clustering to reduce overall event traffic and performs self-tuning summary precision selection to optimize throughput. We have implemented summary-based routing on top of an XML-based infrastructure that closely follows the proposed Web services standards. Measurements from the actual implementation validate our analytical and simulation results, and demonstrate the practical benefits of the proposed techniques.

SCOPE: parallel databases meet MapReduce

Companies providing cloud-scale data services have increasing needs to store and analyze massive data sets, such as search logs, click streams, and web graph data. For cost and performance reasons, processing is typically done on large clusters of tens of thousands of commodity machines. Such massive data analysis on large clusters presents new opportunities and challenges for developing a highly scalable and efficient distributed computation system that is easy to program and supports complex system optimization to maximize performance and reliability. In this paper, we describe a distributed computation system, Structured Computations Optimized for Parallel Execution (Scope), targeted for this type of massive data analysis. Scope combines benefits from both traditional parallel databases and MapReduce execution engines to allow easy programmability and deliver massive scalability and high performance through advanced optimization. Similar to parallel databases, the system has a SQL-like declarative scripting language with no explicit parallelism, while being amenable to efficient parallel execution on large clusters. An optimizer is responsible for converting scripts into efficient execution plans for the distributed computation engine. A physical execution plan consists of a directed acyclic graph of vertices. Execution of the plan is orchestrated by a job manager that schedules execution on available machines and provides fault tolerance and recovery, much like MapReduce systems. Scope is being used daily for a variety of data analysis and data mining applications over tens of thousands of machines at Microsoft, powering Bing, and other online services.

Memory allocation for long-running server applications

Prior work on dynamic memory allocation has largely neglected long-running server applications, for example, web servers and mail servers. Their requirements differ from those of one-shot applications like compilers or text editors. We investigated how to build an allocator that is not only fast and memory efficient but also scales well on SMP machines. We found that it is not sufficient to focus on reducing lock contention - higher speedups require a reduction in cache misses and bus traffic. We then designed and prototyped a new allocator, called LKmalloc, targeted for both traditional applications and server applications. LKmalloc uses several subheaps, each one with a separate set of free lists and memory arena. A thread always allocates from the same subheap but can free a block belonging to any subheap. A thread is assigned to a subheap by hashing on its thread ID. WC compared its performance with several other allocators on a server-like, simulated workload and found that it indeed scales well and is quite fast hut memory more efficiently.

Efficient exploitation of similar subexpressions for query processing

Complex queries often contain common or similar subexpressions, either within a single query or among multiple queries submitted as a batch. If so, query execution time can be improved by evaluating a common subexpression once and reusing the result in multiple places. However, current query optimizers do not recognize and exploit similar subexpressions, even within the same query. We present an efficient, scalable, and principled solution to this long-standing optimization problem. We introduce a light-weight and effective mechanism to detect potential sharing opportunities among expressions. Candidate covering subexpressions are constructed and optimization is resumed to determine which, if any, such subexpressions to include in the final query plan. The chosen subexpression(s) are computed only once and the results are reused to answer other parts of queries. Our solution automatically applies to optimization of query batches, nested queries, and maintenance of multiple materialized views. It is the first comprehensive solution covering all aspects of the problem: detection, construction, and cost-based optimization. Experiments on Microsoft SQL Server show significant performance improvements with minimal overhead.

Incorporating partitioning and parallel plans into the SCOPE optimizer

Massive data analysis on large clusters presents new opportunities and challenges for query optimization. Data partitioning is crucial to performance in this environment. However, data repartitioning is a very expensive operation so minimizing the number of such operations can yield very significant performance improvements. A query optimizer for this environment must therefore be able to reason about data partitioning including its interaction with sorting and grouping. SCOPE is a SQL-like scripting language used at Microsoft for massive data analysis. A transformation-based optimizer is responsible for converting scripts into efficient execution plans for the Cosmos distributed computing platform. In this paper, we describe how reasoning about data partitioning is incorporated into the SCOPE optimizer. We show how relational operators affect partitioning, sorting and grouping properties and describe how the optimizer reasons about and exploits such properties to avoid unnecessary operations. In most optimizers, consideration of parallel plans is an afterthought done in a postprocessing step. Reasoning about partitioning enables the SCOPE optimizer to fully integrate consideration of parallel, serial and mixed plans into the cost-based optimization. The benefits are illustrated by showing the variety of plans enabled by our approach.

Identifying hot and cold data in main-memory databases

Main memories are becoming sufficiently large that most OLTP databases can be stored entirely in main memory, but this may not be the best solution. OLTP workloads typically exhibit skewed access patterns where some records are hot (frequently accessed) but many records are cold (infrequently or never accessed). It is more economical to store the coldest records on secondary storage such as flash. As a first step towards managing cold data in databases optimized for main memory we investigate how to efficiently identify hot and cold data. We propose to log record accesses - possibly only a sample to reduce overhead - and perform offline analysis to estimate record access frequencies. We present four estimation algorithms based on exponential smoothing and experimentally evaluate their efficiency and accuracy. We find that exponential smoothing produces very accurate estimates, leading to higher hit rates than the best caching techniques. Our most efficient algorithm is able to analyze a log of 1B accesses in sub-second time on a workstation-class machine.

Dynamic Materialized Views

A conventional materialized view blindly materializes and maintains all rows of a view, even rows that are never accessed. We propose a more flexible materialization strategy aimed at reducing storage space and view maintenance costs. A dynamic materialized view selectively materializes only a subset of rows, for example, the most frequently accessed rows. One or more control tables are associated with the view and define which rows are currently materialized. The set of materialized rows can be changed dynamically, either manually or automatically by an internal cache manager using a feedback loop. Dynamic execution plans are generated to decide whether the view is applicable at run time. Experimental results in Microsoft SQL Server show that compared with conventional materialized views, dynamic materialized views greatly reduce storage requirements and maintenance costs while achieving better query performance with improved buffer pool efficiency.