1+1=3: Combining Object Storage with Other Data Services

דובר:
Michael Factor - COLLOQUIUM LECTURE
תאריך:
יום שלישי, 24.4.2018, 14:30
מקום:
חדר 337 טאוב.
השתייכות:
IBM Research - Haifa
מארח:
Yuval Filmus

AI, Cognitive, Analytics, IoT all run on data. This data is needed by data scientists, line of business, developers, CDOs and others. Without data, in fact, one can do very little that is interesting or of value. Object storage, the default storage for the PBs and EBs of unstructured data in clouds, has brought huge efficiencies to storing and managing data. In this presentation, we will provide an overview of object storage, using IBM's Cloud Object Storage (formerly Cleversafe) as an example. In particular, we will describe the differences between object storage and more traditional big data storage solution. Motivated by a real application scenario, we will then discuss some innovative, high performance, integrations between object storage and other services such as Apache Spark or Apache Kafka, showing how the sum total is greater than the parts and enabling getting value from data.
Short Bio:
=========
Dr Factor is an IBM Fellow with a focus on cloud data, storage and systems. He has a B.Sc., Valedictorian (1984) in Computer Science from Union College, Schenectady, NY. M.Sc. (1988), M.Phil. (1989) and Ph.D. (1990) in Computer Science from Yale University. Since graduating, Dr. Factor has worked at the IBM Research -- Haifa.
His current main focus area is cloud data and storage where he is leading IBM in integrating cloud data services. He takes a leading role in cloud-related research in his lab including topics such as cloud data stores and their ecosystem, data infrastructure support for analytics, data organzation, data security and governance, next generation storage systems, and cloud delivery of data stores. In the past, he worked on archiving and long term digital preservation, storage power, advanced storage functions and storage system architectures, where he was an architect of advanced copy functions for IBM's DS family of storage subsystems. Prior to that, Dr. Factor was the manager of Distributed and Clustered Systems in HRL. Other areas where Dr. Factor has worked include the cluster VM for Java, the XML File System, the IBM iSeries Integrated File System and the Web server for the 1996 Atlanta Olympics.
Dr. Factor was a past chair of the SYSTORsteering committee and was the program committee co-chair for both SYSTOR 2009 and MSST2010: Research Track and has served on numerous program committees.
Dr. Factor also worked with Prof. Dan Tsafrir and Prof Assaf Schuster to co-advise students at the Technion, Israel Institute of Technology. Prior students include Gala Yadgar, who works on Karma, Multilevel Cache Management Based on Application Hints and Konstantin Shagin, who worked on JavaSplit, Fault Tolerant High-Performance Parallel Computing with Java.
 

בחזרה לאינדקס האירועים