Jump to: navigation, search

Difference between revisions of "Large Scale SIG"

(4 intermediate revisions by 2 users not shown)
Line 7: Line 7:
 
   Thierry Carrez <thierry@openstack.org>
 
   Thierry Carrez <thierry@openstack.org>
  
The aim of the group is to facilitate running OpenStack at large scale, and help address some of the limitations operators encounter in large OpenStack clusters.
+
The aim of the group is to facilitate running OpenStack at large scale, answer questions that OpenStack operators have as they need to scale up and scale out, and help address some of the limitations operators encounter in large OpenStack clusters.
  
=== Short-term Objectives ===
+
=== Goals ===
* Scaling within one cluster, and instrumentation of the bottlenecks there (see https://etherpad.openstack.org/p/large-scale-sig-cluster-scaling)
+
==== Scaling with one cluster ====
* Document large scale configuration and tips &tricks (see https://etherpad.openstack.org/p/large-scale-sig-documentation)
+
Document the typical scaling issues. Push back the limits preventing scaling within one single cluster. Instrument the bottlenecks.
 +
 
 +
Resources:
 +
* Work tracker: https://etherpad.openstack.org/p/large-scale-sig-cluster-scaling
 +
* [[Large Scale Scaling Stories]]
 +
* Oslo-metrics spec: https://specs.openstack.org/openstack/oslo-specs/specs/ussuri/oslo-metrics.html
 +
 
 +
==== Meaningful monitoring ====
 +
How to get meaningful and actionable information about the state of your OpenStack deployments.
 +
 
 +
Resources:
 +
* Work tracker: https://etherpad.openstack.org/p/large-scale-sig-meaningful-monitoring
 +
 
 +
==== Document large scale configuration ====
 +
Produce a set of documentation and guidelines on how to configure OpenStack for large scale usage.
 +
 
 +
Resources:
 +
* Work tracker: https://etherpad.openstack.org/p/large-scale-sig-documentation
 +
* [[Large Scale Configuration Guidelines]]
  
 
=== Communications ===
 
=== Communications ===
Line 17: Line 35:
  
 
=== Meeting ===
 
=== Meeting ===
The Large Scale SIG meets on IRC typically every two weeks.  
+
The Large Scale SIG meets on IRC typically every two weeks. We rotate between an APAC/EU-friendly meeting time (8 UTC) and an EU/US-friendly meeting time (16 UTC).
See https://etherpad.openstack.org/p/large-scale-sig-meeting for details on the next meeting
+
See https://etherpad.openstack.org/p/large-scale-sig-meeting for details on the next meeting(s), and to propose meeting agenda items.
  
=== Past meeting summary and logs ===
+
=== Past meetings summary and logs ===
 
See http://eavesdrop.openstack.org/meetings/large_scale_sig/
 
See http://eavesdrop.openstack.org/meetings/large_scale_sig/
  
=== In-person meetings ===
+
=== Past and future events ===
 +
* Project Teams Gathering meetings Wednesday Oct 28 7UTC-8UTC and 16UTC-17UTC
 +
** Notes at https://etherpad.opendev.org/p/w-forum-scaling-stories
 +
* Open Infrastructure Summit, virtual, Oct 20, 2020 (forum session)
 +
* OpenDev (virtual), June 2020
 
* Open Infrastructure Summit, Shanghai, Nov 4, 2019 (forum session)
 
* Open Infrastructure Summit, Shanghai, Nov 4, 2019 (forum session)
 
** Notes at https://etherpad.openstack.org/p/PVG-large-scale-SIG
 
** Notes at https://etherpad.openstack.org/p/PVG-large-scale-SIG

Revision as of 15:07, 23 September 2020

Status: Active

Chairs:

 Belmiro Moreira <belmiro.moreira@cern.ch>
 Pengju Jiao <jiaopengju@cmss.chinamobile.com>
 Thierry Carrez <thierry@openstack.org>

The aim of the group is to facilitate running OpenStack at large scale, answer questions that OpenStack operators have as they need to scale up and scale out, and help address some of the limitations operators encounter in large OpenStack clusters.

Goals

Scaling with one cluster

Document the typical scaling issues. Push back the limits preventing scaling within one single cluster. Instrument the bottlenecks.

Resources:

Meaningful monitoring

How to get meaningful and actionable information about the state of your OpenStack deployments.

Resources:

Document large scale configuration

Produce a set of documentation and guidelines on how to configure OpenStack for large scale usage.

Resources:

Communications

The Large Scale SIG will use mostly asynchronous communications means: discussions on the openstack-discuss mailing-list using the [largescale-sig] prefix, and various etherpads. Occasionally we may leverage the #openstack-operators IRC channel for synchronous discussion.

Meeting

The Large Scale SIG meets on IRC typically every two weeks. We rotate between an APAC/EU-friendly meeting time (8 UTC) and an EU/US-friendly meeting time (16 UTC). See https://etherpad.openstack.org/p/large-scale-sig-meeting for details on the next meeting(s), and to propose meeting agenda items.

Past meetings summary and logs

See http://eavesdrop.openstack.org/meetings/large_scale_sig/

Past and future events