Distributed Power (Full Day 2 includes CERN, Expedia, TapJoy and Telco Panel)
summary
Claim: distributed infrastructure wins when it reduces cost, speeds rollout and scales to science. Concrete outcomes: CERN runs 75,000 cores today with four Icehouse clouds, 100 PB of archive and a push to ~150,000 cores across sites by Q1 2015 using Puppet, Ceph, Elasticsearch and Nova Cells for scale and federation. Expedia runs three regions and 20,000+ instances from an OpenStack private cloud since 2013 for self‑service and public‑cloud bursting. Tapjoy builds a production cluster of 348 nodes (4 TB disk/node) cut over in June 2014 with zero downtime.
AI-written summary · about
chapters (9)
- 0:00Introduction and welcome
- 1:51Distributed power concept
- 11:26OpenStack in cloud computing
- 27:19CERN infrastructure journey
- 47:23Huawei OpenStack support
- 49:11Expedia cloud transformation
- 1:03:29TapJoy OpenStack deployment
- 1:19:03Telco panel on NFV
- 1:46:45Closing remarks and future outlook
related talks
19m10 years of OpenStack at CERN (From 0 to 300k cores)
16mKeynote: Awards Ceremony
18mScaling Bare Metal Provisioning with Nova and Ironic at CERN
44mLINE's Journey; Road to 4 Million Cores in t...
29mCeph, Xen, and CloudStack: Semper Melior
16mKeynote: Pooling Code, Keeping Control
30mOpenStack Works, so now what?
02mHighlights