~/talk

Delivering Scalable Data Lake Analytics Solutions on Ceph with High Capacity Flash

Talkat Cephalocon Barcelona 2019 · 2019-05-19..05-20
links:none on file
slides:none on file

Discusses using Ceph-based data lake storage combined with high-capacity NVMe QLC NAND flash to meet petabyte-scale analytics needs, describing an all‑flash Ceph architecture and how it enables independent scaling of compute and storage. Presents performance benchmark results for analytics workloads (for example TPC-DS), provides best practices for deployment, and summarizes related work in the Ceph community.

AI-written summary · about

  1. 0:00Intro
  2. 2:35Hadoop/YARN Architecture
  3. 9:05NVM Express (NVMe)
  4. 13:00Challenges with Scaling Apache Hadoop
  5. 15:45Solution - Disaggregated Analytics with Ceph Object Storage
  6. 22:15QCT Lab Test Environment-System Configuration
  7. 24:11QCT Lab Test Environment - Setup
  8. 25:30Test Methodology
  9. 31:17Test Results - Hive (Hadoop/HDFS vs Hadoop/Ceph)
  10. 33:30Test Results - Presto (Hodoop/HDFS vs Hadoop/Ceph)
  11. 34:572019 Plans and Next Steps
  12. 41:01Summary
  13. 42:25Call to Action
~/search
type to search 6,249 conferences, 138,987 speakers and 185,172 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.