Difference between revisions of "Meetings/Storlets"

Revision as of 11:39, 26 January 2016

Meeting Time: Every Wednesday at 13:00 UTC in #openstack-storlets

Agenda:

Austing talk.
Swift Hackathon
bugs.

Austin:

We currently have the following abstract
- Title: From Analytic to Image Processing in Swift with Openstack Storlets
- Openstack Stolets is an emerging Openstack project aimed at pushing down data centric compute jobs to the object store. Storlets offer a server-less programming model enabling developers to quickly develop and deploy data path computations without worrying about the underlying platform details.
- Storlets facilitate several interesting use cases such as:
  - Performing image processing in the storage, allowing to process large objects without downloading it.
  - Spark analytic push down to the store, saving on both bandwidth and memory in the analytic cluster.
  - Data obfuscation and anonymization at the source. Thus, preventing sensitive data from ever leaving the store.
- In this talk we will present the project, discuss and demonstrate the use cases and present a PoC about an effective architecture for image processing using Storlets done at NTT.

Swift Hackathon

The purpose of the session is to update the community on what's happening in the openstack-storlets project and get feedback on number of subjects (the intention is not to discuss pushing the middleware to Swift at this point).
- Updates:
  - Unit tests (Thanks NTT)
    - storlets GET flow: https://review.openstack.org/#/c/263533/
    - storlets PUT flow: https://review.openstack.org/#/c/264520/
    - uploading storlets/dependency: https://review.openstack.org/#/c/264638/
  - Copy semantics (I got a working prototype)
  - Storlets samples (thumbnail extraction, more to come), what else?
- Points for discussion:
  - Adding a non voting gate job for testing Storlets
  - Use footers for adding metadata
    - How to pass header information like Content-Type to storlet applications
  - Resource limitation
    - Should we the max number about containers or processes running on one node?
    - Can we stop unnecessary containers/processes?
  - To-be-fixed thing in swift
    - chunked transferring stuff: https://review.openstack.org/#/c/256201/

@@ Line 6: / Line 6: @@
 * bugs.
-'''Austin'''
+'''Austin:'''
 * We currently have the following abstract
 ** Title: From Analytic to Image Processing in Swift with Openstack Storlets
 ** Openstack Stolets is an emerging Openstack project aimed at pushing down data centric compute jobs to the object store. Storlets offer a server-less programming model enabling developers to quickly develop and deploy data path computations without worrying about the underlying platform details.
+** Storlets facilitate several interesting use cases such as:
-Storlets facilitate several interesting use cases such as:
+*** Performing image processing in the storage, allowing to process large objects without downloading it.
-. Performing image processing in the storage, allowing to process large objects without downloading it.
+*** Spark analytic push down to the store, saving on both bandwidth and memory in the analytic cluster.
-. Spark analytic push down to the store, saving on both bandwidth and memory in the analytic cluster.
+*** Data obfuscation and anonymization at the source. Thus, preventing sensitive data from ever leaving the store.
-. Data obfuscation and anonymization at the source. Thus, preventing sensitive data from ever leaving the store.
+** In this talk we will present the project, discuss and demonstrate the use cases and present a PoC about an effective architecture for image processing using Storlets done at NTT.
-In this talk we will present the project, discuss and demonstrate the use cases and present a PoC about an effective architecture for image processing using Storlets done at NTT.
 '''Swift Hackathon'''
@@ Line 36: / Line 35: @@
 *** To-be-fixed thing in swift
 **** chunked transferring stuff: https://review.openstack.org/#/c/256201/
-** https://review.openstack.org/#/c/261397/
-* Session in Openstack Hackathon
-***** anything else in master?
-**** more?
-* Next Openstack Summit
-** Here is a first shot at a talk abstract:
-*** Title: From Analytic to Image Processing in Swift with Openstack Storlets
-*** Openstack Stolets is an emerging project aimed at pushing down data centric compute jobs to the object store. In this talk we will present the project, discuss and demonstrate use cases varying from spark analytic push down to image processing and present a PoC about an effective system architecture for image processing using Storlets done at NTT.