Presentation is loading. Please wait.

Presentation is loading. Please wait.

Virtualised Worker Nodes Where are we? What next? Tony Cass GDB 2012 12/12/12.

Similar presentations


Presentation on theme: "Virtualised Worker Nodes Where are we? What next? Tony Cass GDB 2012 12/12/12."— Presentation transcript:

1 Virtualised Worker Nodes Where are we? What next? Tony Cass GDB 2012 12/12/12

2 Tony.Cass@ CERN.ch The HEPiX virtualisation working group  The HEPiX virtualisation working group was formed to facilitate the instantiation of user-generated virtual machine images at HEPiX (and WLCG) sites.  Users were expressing such a wish in 2008/9, but sites were worried about issues such as uncontrolled root access and the maintenance of the traceability logs required by Grid security policies. 2 This, at least, is still an issue.

3 Tony.Cass@ CERN.ch Image endorsement  The HEPiX VWG developed a policy that introduced the concept of image endorsers: people who would guarantee that generated images could be used safely at sites.  Amongst other things, such images would –have no embedded user credentials, and –enable sites to contextualise the images to enable the required logging and make other necessary customisations. »Sites agree, however, not to modify the software environment of the image.  Sites are free to trust (or not) specific image endorsers but, if they do trust someone in this role, it is expected that any images endorsed by this person can be used at that site without the need for inspection or manual approval.  The HEPiX VWG policy became the basis of an approved JSPG policy document, “Policy Trusted Virtual Machines”. 3

4 Tony.Cass@ CERN.ch Current Status  The endorsement policy is agreed.  Technical arrangements have been defined for –image contextualisation »these are compatible with EC2/OpenNebula/OpenStack –exchange of information between the site infrastructure and a running virtual machine »e.g. remaining lifetime, that the virtual machine can be terminated, …  A framework for image endorsers to publish and distribute images has been developed. –This has been integrated with StratusLab’s marketplace at LAL and is being integrated with OpenStack Glance at CERN.  CERNVM images are compatible with the HEPiX VWG policies –and there has been a security review of the underlying technology. 4 Many thanks to Owen, Michel, Belmiro & Ulrich HEPiX vwg model (and s/w) endorsed by the EGI federated cloud task force.

5 Tony.Cass@ CERN.ch Job done then. What now? 5

6 CERN IT Department CH-1211 Genève 23 Switzerland www.cern.ch/it How this could be used Central Task Queue Site A Site B Site C Shared Image Repository (VMIC) User VO service Instance requests Commercial cloud Payload pull Image maintainer Cloud bursting Slide courtesy of Ulrich Schwickerath

7 CERN IT Department CH-1211 Genève 23 Switzerland www.cern.ch/i t A Vision for Virtualisation in WLCG Tony Cass WLCG GDB, 9/9/9

8 CERN IT Department CH-1211 Genève 23 Switzerland www.cern.ch/i t Goals Enable experiments/users to choose environment for job execution. Ensure sites have control/traceability over resource usage. Virtualisation Vision- 8

9 CERN IT Department CH-1211 Genève 23 Switzerland www.cern.ch/i t Approach Step-by-step: Build on – established successes – established trust But end goal in view. Prepare for this now with – technical agreements/developments – user behaviour (especially explicit statement of resource requirements) Virtualisation Vision- 9

10 CERN IT Department CH-1211 Genève 23 Switzerland www.cern.ch/i t Approach Five steps Steps 1-3 – realistic – relatively uncontroversial(?) – achievable by end-2010? Steps 4 & 5 – kite-flying – probably controversial – interesting Virtualisation Vision- 10

11 CERN IT Department CH-1211 Genève 23 Switzerland www.cern.ch/i t Step 1 Users can choose between virtual images created at sites. Not really any different from now; could be rephrased “sites provide virtual machines for job execution, not real hardware”. Key issue is (full) understanding of resource requirements – OS type, memory, (range of) #cores,... Virtualisation Vision- 11 Not done. Sites may be using virtual machines but this is transparent to users. And I’m not sure we’re any nearer a negotiation on core needs. Let’s just forget this step now.

12 CERN IT Department CH-1211 Genève 23 Switzerland www.cern.ch/i t Step 2 Distribution of virtual machine images between sites (or from CERN...). – Image limited to minimalist operating system (SL4/5/6...) Requires – transparent process for image generation guaranteeing content – mechanism for sites to hook into local monitoring and batch scheduling. – trusted and verifiable method of image distribution Virtualisation Vision- 12 HEPiX Not done but could be.

13 CERN IT Department CH-1211 Genève 23 Switzerland www.cern.ch/i t Step 3 Distributed virtual image includes experiment software environment – So users can choose ATLAS version X on OS Y. Requires “transparent process for image generation” to be extended to include experiment software. – Snapshot of experiment build servers at CERN? Removes need for pilot jobs to verify (or create) correct environment. Virtualisation Vision- 13 CVMFS delivers this.

14 CERN IT Department CH-1211 Genève 23 Switzerland www.cern.ch/i t What about CernVM? Instantiation of CernVM machines being discussed between IT and PH teams; could be an option at CERN. But scalability and verifiability of CernVM distribution for widespread use as remote batch image is far from evident. – Not excluded, but more likely after successful experience with static images. Virtualisation Vision- 14 We took too long (not) testing static images! This works…

15 CERN IT Department CH-1211 Genève 23 Switzerland www.cern.ch/i t Step 4 Distributed virtual image includes client to connect directly to experiment pilot job framework (Dirac, PanDA). Initially with virtual machine images instantiated according to jobs arriving at sites. Later, sites instantiate virtual machines according to observed load and local policy – Lots of busy ATLAS machines? Start more... Requires some way for pilot job frameworks to know (remaining) lifetime of virtual machine. – VM unlikely to be updated (security patches...), so lifetime will be limited. Virtualisation Vision- 15 Let’s work on this now Let’s work on this together now from cvmfs

16 Tony.Cass@ CERN.ch Step 4 issues  Moving credentials into VM images  What role for pilot factories?  Can we avoid queues of virtual machine instantiation requests at sites?  How to streamline (minimise…) communications between sites and experiments? …… 16

17 Let the discussion begin!

18 CERN IT Department CH-1211 Genève 23 Switzerland www.cern.ch/i t Step 5 Experiment pilot job frameworks replaced by commercial/public domain schedulers. – Virtual LSF cluster for ATLAS – Virtual SGE cluster for CMS –... Virtualisation Vision- 18 SLURM today?

19


Download ppt "Virtualised Worker Nodes Where are we? What next? Tony Cass GDB 2012 12/12/12."

Similar presentations


Ads by Google