Li Zha’s research while affiliated with Chinese Academy of Sciences and other places

This paper presents CirroData, a high-performance SQL-on-Hadoop system designed for Big Data analytics workloads. As a home-grown enterprise-level online analytical processing (OLAP) system with more than seven-year research and development (R&D) experiences, we share our design details to the community about how to achieve high performance in CirroData. Multiple optimization techniques have been discussed in the paper. The effectiveness and the efficiency of all these techniques have been proved by our customers’ daily usage. Benchmark-level studies, as well as several real application case studies of CirroData, have been presented in this paper. Our evaluations show that CirroData can outperform various types of counterpart database systems in the community, such as “Spark+Hive”, “Spark+HBase”, Impala, DB-X/Y, Greenplum, HAWQ, and others. CirroData can achieve up to 4.99x speedup compared with Greenplum, HAWQ, and Spark in the standard TPC-H queries. Application-level evaluations demonstrate that CirroData outperforms “Spark+Hive” and “Spark+HBase” by up to 8.4x and 38.8x, respectively. In the meantime, CirroData achieves the performance speedups for some application workloads by up to 20x, 100x, 182.5x, 92.6x, and 55.5x as compared with Greenplum, DB-X, Impala, DB-Y, and HAWQ, respectively.

Deep Learning has recently been gaining popularity. From the micro-architecture field to the upper-layer end applications, a lot of research work has been proposed in the literature to advance the knowledge of Deep Learning. Deep Learning Benchmarking is one of such hot spots in the community. There are a bunch of Deep Learning benchmarks available in the community already and new ones keep coming as well. However, we find that not many survey works are available to give an overview of these useful benchmarks in the literature. We also find few discussions on what has been done for Deep Leaning Benchmarking in the community and what are still missing. To fill this gap, this paper attempts to provide a survey on multiple high-impact Deep Learning Benchmarks with training and inference support. We share some of our insightful observations and discussions on these benchmarks. In this paper, we believe the community still needs more benchmarks to capture different perspectives, while these benchmarks need a way for converging to a standard.

In recent years, most Web 2.0/3.0 applications have been built on top of distributed systems which allow data to be modeled as Distributed Ordered Tables (DOTs) such as Apache HBase. To analyze the stored data, SQL-like range queries over a DOT are fundamental requirements. However, range queries over existing DOT implementations are highly inefficient. Several secondary index techniques have been proposed to alleviate this issue, but they introduce additional overhead while creating and updating the index. Moreover, index techniques introduce several additional challenges for DOTs, particularly, network communication and thread models for concurrent request processing. In this paper, we first characterize the performance of index techniques on DOTs from a networking perspective. We then propose an RDMA-based high-performance communication framework which uses HBase as the underlying DOT implementation to accelerate these techniques. We propose several thread models for our RDMA-based design and compare their performance. We design a parallel insert operation to reduce index creation overhead. We also design several benchmarks to evaluate DOT-based systems. Experimental evaluations with state-of-the-art index techniques (CCIndex and Apache Phoenix) show that our design can reduce the insert overhead for secondary indices to just 23%. Evaluation with TPC-H queries demonstrates an increase in query throughput by up to 2x, while application evaluation with real-world workloads and data (100M records) provided by AdMaster Inc. show up to 35% reduction in execution time.

Given a message, cascade prediction aims to predict the individuals who will potentially retweet it. Most existing methods either exploit demographical, structural, and temporal features for prediction, or explicitly rely on particular information diffusion models. Recently, researchers attempt to design fully data-driven methods for cascade prediction (i.e., without requiring human-defined features or information diffusion models), directly leveraging historical cascades to learn interpersonal proximity and then making prediction based on the learned proximity. One widely-used method to represent interpersonal proximity is social embedding, i.e., each individual is embedded into a low-dimensional latent metric space. One challenging problem is to design cost-effective method to learn social embedding from cascades. In this paper, we propose a position-aware asymmetric embedding method to effectively learn social embedding for cascade prediction. Different from existing methods where individuals are embedded into a single latent space, our method embeds each individual into two latent spaces: a latent influence space and a latent susceptibility space. Furthermore, our method employs the occurrence position of individuals in cascades to improve the learning efficiency of social embedding. We validate the proposed method on a dataset extracted from Sina Weibo. Experimental results demonstrate that the proposed model outperforms state-of-the-art social embedding methods at both learning efficiency and prediction accuracy.

In the original MapReduce model, reduce tasks need to fetch output data of map tasks in the manner of “pull”. However, reduce tasks which are occupying reduce slots cannot start executing until all the corresponding map tasks are completed. It forms the dependence between map and reduce tasks, which is called the coupled relationship in this paper. The coupled relationship leads to two problems: reduce slot hoarding and underutilized network bandwidth. Meanwhile, storing the result data is costly especially when the system has replications, which leads to the inefficient storage problem. We propose an uncoupled data process and transfer model in order to address these problems. Four core techniques, including weighted mapping, data pushing, partial data backup, and data compression are introduced and applied in Apache Hadoop, the mainstream open-source implementation of MapReduce model. This work has been practiced in Baidu, the biggest search engine company in China. A real-world application for web data processing shows that our model can improve the system throughput by 29.5 %, reduce the total wall time by 22.8 %, provide a weighted wall time acceleration of 26.3 %, and reduce the result data stored in disk by 70 %. What’s more, the implementation of this model is transparent to users and compatible with the original Hadoop.

Cloud database usually refers to a database based on the cloud computing technology. However, as far as we know, pre-existing solutions of cloud database cannot integrate the data from multi-sourced heterogeneous databases, only supplying an isolated homogeneous database cluster. This paper presents a new implementation approach for cloud database: Sea Base, which integrates various data types into a unified one, based on the CCEVP(Cloud Computing-based Effective-Virtual-Physical) model. The results of our experiments show that Sea Base is feasible and practical.

MPI has been widely used in High Performance Computing. In contrast, such efficient communication support is lacking in the field of Big Data Computing, where communication is realized by time consuming techniques such as HTTP/RPC. This paper takes a step in bridging these two fields by extending MPI to support Hadoop-like Big Data Computing jobs, where processing and communication of a large number of key-value pair instances are needed through distributed computation models such as MapReduce, Iteration, and Streaming. We abstract the characteristics of key-value communication patterns into a bipartite communication model, which reveals four distinctions from MPI: Dichotomic, Dynamic, Data-centric, and Diversified features. Utilizing this model, we propose the specification of a minimalistic extension to MPI. An open source communication library, DataMPI, is developed to implement this specification. Performance experiments show that DataMPI has significant advantages in performance and flexibility, while maintaining high productivity, scalability, and fault tolerance of Hadoop.