Difference between revisions of "Cloud & VM status"

From GridPP Wiki
Jump to: navigation, search
 
(16 intermediate revisions by 5 users not shown)
Line 1: Line 1:
This page will collect information from GridPP sites regarding their current deployment of job execution systems providing VMs, including Clouds. The information will help with wider considerations and strategy.  
+
This page will collect information from GridPP sites regarding their current deployment of job execution systems providing VMs, including Clouds. The information will help with wider considerations and strategy. The [http://www.gridpp.ac.uk/php/gridpp-dirac-sam.php?action=view GridPP DIRAC SAM] monitoring can be used to see the current state of many of these sites. There is a complementary page about [[Batch system status|batch system status]].
  
 
For sites with multiple VM Provider / VM Lifecycle Manager implementations, please create multiple rows.
 
For sites with multiple VM Provider / VM Lifecycle Manager implementations, please create multiple rows.
 
'''12March2015: please don't edit this page while I'm sorting out a first proper version of it. Thanks, Andrew'''
 
  
 
{|border="1" cellpadding="1"
 
{|border="1" cellpadding="1"
Line 23: Line 21:
 
|LHCb
 
|LHCb
 
|Others (specify)
 
|Others (specify)
 
  
 
|-
 
|-
 
|Birmingham
 
|Birmingham
|<span style="color:green">Vac</span>
+
|Vac
|<span style="color:green">Vac</span>
+
|Vac
|<span style="color:green">X</span>
+
|style="background-color:#CCFFCC"|X
|<span style="color:green"></span>
+
|
|<span style="color:black"></span>
+
|
|<span style="color:green"></span>
+
|
|<span style="color:black"></span>
+
|style="background-color:#CCFFCC"|X
|<span style="color:green"></span>
+
|
|<span style="color:green">Testing</span>
+
|
 
|
 
|
  
 
|-
 
|-
|Brunel
+
|Bristol
|<span>OpenVZ</span>
+
|
|<span></span>
+
|
|<span></span>
+
|
|<span></span>
+
|
|<span></span>
+
|
|<span></span>
+
|
|<span></span>
+
|
|<span></span>
+
|
|<span></span>
+
|
|<span></span>
+
|
  
 
|-
 
|-
|Imperial
+
|Brunel
|<span style="color:green">OpenStack</span>
+
|OpenVZ
|<span style="color:green">CloudScheduler</span>
+
|
|<span style="color:green"></span>
+
|
|<span style="color:green"></span>
+
|
|<span style="color:black">X</span>
+
|
|<span style="color:green"></span>
+
|
|<span style="color:green"></span>
+
|
|<span style="color:green"></span>
+
|
|<span style="color:green"></span>
+
|
 
|
 
|
  
 
|-
 
|-
|Imperial
+
|Cambridge
|<span style="color:green">OpenStack</span>
+
|
|<span style="color:green">Vcycle</span>
+
|
|<span style="color:green">X</span>
+
|
|<span style="color:green"></span>
+
|
|<span style="color:black">X</span>
+
|
|<span style="color:green">X</span>
+
|
|<span style="color:green">X</span>
+
|
|<span style="color:green"></span>
+
|
|<span style="color:green"></span>
+
|
 
|
 
|
  
  
 
|-
 
|-
|Lancaster
+
|CERN
|<span>Vac</span>
+
|OpenStack
|<span>Vac</span>
+
|Vcycle
|<span>X</span>
+
|style="background-color:#CCFFCC"|X
|<span></span>
+
|<span>X</span>
+
|<span>X</span>
+
|<span>X</span>
+
|<span></span>
+
|<span></span>
+
 
|
 
|
 +
|style="background-color:#CCFFCC"|X
 +
|style="background-color:#CCFFCC"|X
 +
|style="background-color:#CCFFCC"|X
 +
|
 +
|
 +
|Vcycle at Manchester
  
 
|-
 
|-
|Manchester
+
|Durham
|<span style="color:green">Torque/Maui (local)</span>
+
|<span style="color:green">Maui is unsupported. It had memory leaks. Robert wrote a patch and there was nowhere to feed it back into.</span>
+
|<span style="color:green">HTCondor</span>
+
|<span style="color:green">Currently CREAM, investigating ARC-CE</span>
+
|<span style="color:black">No</span>
+
|<span style="color:green">Yes</span>
+
|<span style="color:green">Vac in production</span>
+
 
|
 
|
 +
|
 +
|
 +
|
 +
|
 +
|
 +
|
 +
|
 +
|
 +
|
 +
  
 
|-
 
|-
|Oxford
+
|Edinburgh
|<span style="color:green">HTCondor (local)</span>
+
|
|<span style="color:green">None</span>
+
|
|<span style="color:green">No reason</span>
+
|
|<span style="color:green">ARC CE in production</span>
+
|
|<span style="color:green">Yes</span>
+
|
|<span style="color:green">Yes</span>
+
|
|<span style="color:green">OpenStack in production. Testing VAC</span>
+
|
 +
|
 +
|
 
|
 
|
 +
  
 
|-
 
|-
|RAL Tier-1
+
|Glasgow
|<span style="color:green">HTCondor</span>
+
|
|<span style="color:green">Condor Vacuum</span>
+
|
|<span style="color:green">X</span>
+
|
|<span style="color:green"></span>
+
|
|<span style="color:green">X</span>
+
|
|<span style="color:green">X</span>
+
|
|<span style="color:green">X</span>
+
|
|<span style="color:green"></span>
+
|
|<span style="color:green"></span>
+
|
 +
|
  
 
|-
 
|-
|RAL Tier-1
+
|Imperial
|<span style="color:green">OpenNebula</span>
+
|OpenStack
|<span style="color:green"></span>
+
|CloudScheduler
|<span style="color:green"></span>
+
|
|<span style="color:green"></span>
+
|
|<span style="color:green"></span>
+
|style="background-color:#CCFFCC"|X
|<span style="color:green"></span>
+
|
|<span style="color:green"></span>
+
|
|<span style="color:green"></span>
+
|
|<span style="color:green"></span>
+
|
 
|
 
|
  
 
|-
 
|-
|QMUL
+
|Imperial
|<span style="color:green">Gridengine (local)</span>
+
|OpenStack
|<span style="color:green">None</span>
+
|Vcycle
|<span style="color:green">Son of Gridengine</span>
+
|style="background-color:#CCFFCC"|X
|<span style="color:green">CREAM</span>
+
|
|<span style="color:black">No</span>
+
|style="background-color:#CCFFCC"|X
|<span style="color:green">Yes</span>
+
|style="background-color:#CCFFCC"|X
|<span style="color:green">Deploy cloudstack, find scalable solution to get our storage usable in the cloud</span>
+
|style="background-color:#CCFFCC"|X
 +
|
 
|
 
|
 +
|Vcycle at Manchester
  
 
|-
 
|-
|RHUL
+
|Lancaster
||<span style="color:green">Torque/Maui (local)</span>
+
|OpenStack (offsite)
|<span style="color:green">Torque/Maui support non-existent</span>
+
|
|<span style="color:green">Will follow the consensus</span>
+
|
|<span style="color:green">CREAM</span>
+
|
|<span style="color:black">No</span>
+
|style="background-color:#CCFFCC"|X
|<span style="color:green">Yes</span>
+
|
|<span style="color:green"></span>
+
|
 +
|
 +
|
 
|
 
|
 
  
 
|-
 
|-
|UCL
+
|Lancaster
|<span style="color:green"></span>
+
|Vac
|<span style="color:green"></span>
+
|Vac
|<span style="color:green"></span>
+
|style="background-color:#CCFFCC"|X
|<span style="color:green"></span>
+
|<span style="color:black">No</span>
+
|<span style="color:red">X</span>
+
|<span style="color:green"></span>
+
 
|
 
|
 
+
|style="background-color:#CCFFCC"|X
 
+
|style="background-color:#CCFFCC"|X
 +
|style="background-color:#CCFFCC"|X
 +
|
 +
|
 +
|Downtime for upgrade
  
 
|-
 
|-
|Liverpool <span style="color:blue">(Single core cluster)</span>
+
|Liverpool
|<span style="color:green">Torque Maui (local)</span>
+
|Vac
|<span style="color:green">Poor Support, Maui intrinsically broken</span>
+
|Vac
|<span style="color:green"> </span>
+
|style="background-color:#CCFFCC"|X
|<span style="color:green">Cream</span>
+
|style="background-color:#CCFFCC"|X
|<span style="color:black">No</span>
+
|style="background-color:#CCFFCC"|X
|<span style="color:green">NO</span>
+
|
|<span style="color:green">None</span>
+
|style="background-color:#CCFFCC"|X
 +
|
 +
|style="background-color:#CCFFCC"|X
 
|
 
|
  
  
 +
|-
 +
|Manchester
 +
|Vac
 +
|Vac
 +
|style="background-color:#CCFFCC"|X
 +
|
 +
|style="background-color:#CCFFCC"|X
 +
|style="background-color:#CCFFCC"|X
 +
|style="background-color:#CCFFCC"|X
 +
|
 +
|style="background-color:#CCFFCC"|X
 +
|
  
 
|-
 
|-
|Sheffield
+
|Oxford
|<span style="color:green">Torque/Maui (local)</span>
+
|OpenStack
|<span style="color:green">Torque/Maui support non-existent</span>
+
|CloudScheduler
|<span style="color:green">HTCondor is in testing mode</span>
+
|<span style="color:green">CREAM CE, ACR CE is in test</span>
+
|<span style="color:black">No</span>
+
|<span style="color:green">Yes</span>
+
|<span style="color:green"></span>
+
 
|
 
|
 
+
|
 +
|
 +
|
 +
|
 +
|
 +
|
 +
|decommissioned
  
 
|-
 
|-
|Durham
+
|Oxford
|<span style="color:green">SLURM (local)</span>
+
|Vac
|<span style="color:green"></span>
+
|Vac
|<span style="color:green">No reason</span>
+
|style="background-color:#CCFFCC"|X
|<span style="color:green">ARC CE</span>
+
|style="background-color:#CCFFCC"|X
|<span style="color:black">No</span>
+
|style="background-color:#CCFFCC"|X
|<span style="color:green">Yes</span>
+
|style="background-color:#CCFFCC"|X
|<span style="color:green">N/A</span>
+
|style="background-color:#CCFFCC"|X
 +
|
 +
|style="background-color:#CCFFCC"|X
 
|
 
|
  
  
 
|-
 
|-
|Edinburgh
+
|QMUL
|<span style="color:green">Gridengine</span>
+
|CloudStack
|<span style="color:green">None</span>
+
|
|<span style="color:green">No reason</span>
+
|
|<span style="color:green">Cream CE for standard production, ARC CE for exploratory HPC work</span>
+
|
|<span style="color:black">No</span>
+
|
|<span style="color:green">Yes</span>
+
|
|<span style="color:green"></span>
+
|
 +
|
 
|
 
|
 +
|Also looking at cloud storage
  
  
 
|-
 
|-
|Glasgow
+
|RAL PPD
|<span style="color:green"> HTcondor (local), Torque/Maui (local)</span>
+
|
|<span style="color:green">Becomes unresponsive at times of high load or nodes being un-contactable.</span>
+
|
|<span style="color:green">Investigating HTCondor/SoGE/SLURM as a replacement.</span>
+
|
|<span style="color:green">ARC, Cream</span>
+
|
|<span style="color:green">Yes</span>
+
|
|<span style="color:green">Yes</span>
+
|
|<span style="color:green">N/A</span>
+
|
 +
|
 +
|
 
|
 
|
  
 
|-
 
|-
|Birmingham
+
|RAL Tier-1
||<span style="color:green">Torque/Maui</span>
+
|HTCondor
|<span style="color:green">Maui sometimes fails to see new jobs and so nothing is scheduled</span>
+
|Condor Vacuum
|<span style="color:green">HTCondor</span>
+
|style="background-color:#CCFFCC"|X
|<span style="color:green">CREAM</span>
+
|
|<span style="color:black">No</span>
+
|style="background-color:#CCFFCC"|X
|<span style="color:green">No</span>
+
|style="background-color:#CCFFCC"|X
|<span style="color:green">Testing Vac setup</span>
+
|style="background-color:#CCFFCC"|X
 +
|
 +
|
 
|
 
|
 
  
 
|-
 
|-
|Bristol
+
|RAL Tier-1
|<span style="color:green">HTCondor (shared), torque + maui (local)</span>
+
|OpenNebula
|<span style="color:green">None</span>
+
|
|<span style="color:green">No reason</span>
+
|
|<span style="color:green">ARC & CREAM CEs</span>
+
|
|<span style="color:black">No</span>
+
|
|<span style="color:red">X</span>
+
|
|<span style="color:green"></span>
+
|
 +
|
 +
|
 
|
 
|
  
  
 
|-
 
|-
|Cambridge
+
|RHUL
|<span style="color:green">Torque/Maui (local)</span>
+
|
|<span style="color:green">Torque/Maui support non-existent</span>
+
|
|<span style="color:green">Will follow the consensus</span>
+
|
|<span style="color:green">CREAM CE</span>
+
|
|<span style="color:black">No</span>
+
|
|<span style="color:green">Yes</span>
+
|
|<span style="color:green">None at present</span>
+
|
 +
|
 +
|
 
|
 
|
 
 
  
  
 
|-
 
|-
|RAL PPD
+
|Sheffield
|<span style="color:green">HTCondor</span>
+
|
|<span style="color:green">None</span>
+
|
|<span style="color:green">No reason</span>
+
|
|<span style="color:green">ARC CE</span>
+
|
|<span style="color:green">Yes</span>
+
|
|<span style="color:green">Yes</span>
+
|
|<span style="color:green"></span>
+
|
 +
|
 +
|
 
|
 
|
  
Line 286: Line 319:
 
|-
 
|-
 
|Sussex
 
|Sussex
|<span style="color:green">(Shared) Gridengine - (Univa Grid Engine)</span>
+
|
|<span style="color:green">None</span>
+
|
|<span style="color:green">No reason</span>
+
|
|<span style="color:green">CREAMCE</span>
+
|
|<span style="color:orange">Looking into it</span>
+
|
|<span style="color:green">Yes</span>
+
|
|<span style="color:green"></span>
+
|
 +
|
 +
|
 
|
 
|
  
 +
 +
|-
 +
|UCL
 +
|Vac
 +
|Vac
 +
|style="background-color:#CCFFCC"|X
 +
|
 +
|
 +
|
 +
|style="background-color:#CCFFCC"|X
 +
|
 +
|style="background-color:#CCFFCC"|X
 +
|
  
 
|}
 
|}
  
 
[[Category:Cloud & VM]]
 
[[Category:Cloud & VM]]
 +
[[Category:Sites Status]]

Latest revision as of 09:57, 27 June 2017

This page will collect information from GridPP sites regarding their current deployment of job execution systems providing VMs, including Clouds. The information will help with wider considerations and strategy. The GridPP DIRAC SAM monitoring can be used to see the current state of many of these sites. There is a complementary page about batch system status.

For sites with multiple VM Provider / VM Lifecycle Manager implementations, please create multiple rows.

Site VM Provider VM Lifecycle Manager Experiment/VO APEL accounting Notes
GridPP DIRAC ALICE ATLAS CMS LHCb Others (specify)
Birmingham Vac Vac X X
Bristol
Brunel OpenVZ
Cambridge


CERN OpenStack Vcycle X X X X Vcycle at Manchester
Durham


Edinburgh


Glasgow
Imperial OpenStack CloudScheduler X
Imperial OpenStack Vcycle X X X X Vcycle at Manchester
Lancaster OpenStack (offsite) X
Lancaster Vac Vac X X X X Downtime for upgrade
Liverpool Vac Vac X X X X X


Manchester Vac Vac X X X X X
Oxford OpenStack CloudScheduler decommissioned
Oxford Vac Vac X X X X X X


QMUL CloudStack Also looking at cloud storage


RAL PPD
RAL Tier-1 HTCondor Condor Vacuum X X X X
RAL Tier-1 OpenNebula


RHUL


Sheffield


Sussex


UCL Vac Vac X X X