10k+
nodes scale. Focus area: resource over-subscription, multi-dimension resource support, global scheduling, placement constraint/node attributes.@IBM
BigInsights
project (A Hadoop based BigData Platform Offering by IBM)Education:
Want to know more? See my portfolio.
Beyond Experimental: Spark on Kubernetes. KubeConf North America, Detroit. Oct, 2022.
Next Level Spark on Kubernetes with Apache YuniKorn (Incubating). ApacheConf 2021, Oct, 2021.
Efficient Spark Scheduling on K8s with Apache YuniKorn. ApacheConf 2020, Oct 2020.
YARN to Kubernetes: How to tackle the challenages of resource management. Hadoop Meetup Shanghai, Sep 26, 2020. download pdf
Cloud-Native Spark Scheduling with YuniKorn Scheduler. Spark & AI Summit, June 2020.
Energize Multi-tenancy Flink on K8s with YuniKorn . Virtual Flink Forward Conference, San Francisco, Apr 24, 2020
Next Generation Scheduling: In Hybrid Cloud Environment for High Performance and Optimized Execution of Mixed Workloads. Dataworks Summit, Washington D.C. May 23, 2019
Open Hybrid Architecture: Running Stateful Containers on YARN. Hortonworks Tech Blog. Dec 17, 2018.
Apache Hadoop YARN: State of the Union. ArchSummit, Beijing, China. slides download. Dec 07, 2018.
Apache YARN 3.x in Alibaba. Dataworks Summit, San Jose, CA. Jun 21, 2018.
Success at Apache: the Chance to Influence the World. ASF “Success at Apache” Blog Series. Jun 04, 2018.
Apache Spark and DB2 with BLU Acceleration: Making ‘People Flow’ in Cities Measurable and Analyzable. IBM Insights Conference, Las Vegas. NV_ Oct 2015.
Apache Hadoop Fundamentals. School of Computer Science and Technology. Aug 15, 2012.
Get connected with LinkedIn: Link me!.