Accounting Review Summary and action list from the (pre)GDB Julia Andreeva CERN-IT WLCG MB 19th April 2016 1.

Slides:



Advertisements
Similar presentations
WLCG Monitoring Consolidation NEC`2013, Varna Julia Andreeva CERN IT-SDC.
Advertisements

LHC Experiment Dashboard Main areas covered by the Experiment Dashboard: Data processing monitoring (job monitoring) Data transfer monitoring Site/service.
Configuration Management Process and Environment MACS Review 1 February 5th, 2010 Roland Moser PR a-RMO, February 5 th, 2010 R. Moser 1 R. Gutleber.
Storage Accounting John Gordon, STFC GDB June 2012.
Enabling Grids for E-sciencE Overview of System Analysis Working Group Julia Andreeva CERN, WLCG Collaboration Workshop, Monitoring BOF session 23 January.
CERN IT Department CH-1211 Genève 23 Switzerland t Internet Services Job Monitoring for the LHC experiments Irina Sidorova (CERN, JINR) on.
1 Resource Provisioning Overview Laurence Field 12 April 2015.
Enabling Grids for E-sciencE System Analysis Working Group and Experiment Dashboard Julia Andreeva CERN Grid Operations Workshop – June, Stockholm.
Towards a Global Service Registry for the World-Wide LHC Computing Grid Maria ALANDES, Laurence FIELD, Alessandro DI GIROLAMO CERN IT Department CHEP 2013.
EGEE-III INFSO-RI Enabling Grids for E-sciencE Overview of STEP09 monitoring issues Julia Andreeva, IT/GS STEP09 Postmortem.
Julia Andreeva, CERN IT-ES GDB Every experiment does evaluation of the site status and experiment activities at the site As a rule the state.
1 Andrea Sciabà CERN Critical Services and Monitoring - CMS Andrea Sciabà WLCG Service Reliability Workshop 26 – 30 November, 2007.
WLCG infrastructure monitoring proposal Pablo Saiz IT/SDC/MI 16 th August 2013.
HLRmon accounting portal DGAS (Distributed Grid Accounting System) sensors collect accounting information at site level. Site data are sent to site or.
EMI INFSO-RI Accounting John Gordon (STFC) APEL PT Leader.
Report from the WLCG Operations and Tools TEG Maria Girone / CERN & Jeff Templon / NIKHEF WLCG Workshop, 19 th May 2012.
Automatic Resource & Usage Monitoring Steve Traylen/Flavia Donno CERN/IT.
XROOTD AND FEDERATED STORAGE MONITORING CURRENT STATUS AND ISSUES A.Petrosyan, D.Oleynik, J.Andreeva Creating federated data stores for the LHC CC-IN2P3,
Accounting Update John Gordon and Stuart Pullinger January 2014 GDB.
Julia Andreeva on behalf of the MND section MND review.
EGEE-III INFSO-RI Enabling Grids for E-sciencE EGEE and gLite are registered trademarks John Gordon SA1 Face to Face CERN, June.
APEL Cloud Accounting Status and Plans APEL Team John Gordon.
CERN IT Department CH-1211 Genève 23 Switzerland t CERN IT Monitoring and Data Analytics Pedro Andrade (IT-GT) Openlab Workshop on Data Analytics.
Global ADC Job Monitoring Laura Sargsyan (YerPhI).
HLRmon accounting portal The accounting layout A. Cristofori 1, E. Fattibene 1, L. Gaido 2, P. Veronesi 1 INFN-CNAF Bologna (Italy) 1, INFN-Torino Torino.
Experiment Support CERN IT Department CH-1211 Geneva 23 Switzerland t DBES Andrea Sciabà Ideal information system - CMS Andrea Sciabà IS.
Components Selection Validation Integration Deployment What it could mean inside EGI
Accounting Review Summary from the pre-GDB related to CPU (wallclock) accounting Julia Andreeva CERN-IT GDB 13th April
WLCG Accounting Task Force Update Julia Andreeva CERN GDB, 8 th of June,
EGI-InSPIRE RI EGI-InSPIRE EGI-InSPIRE RI Storage Accounting John Gordon, STFC OMB August 2013.
LCG Accounting Update John Gordon, CCLRC-RAL 10/1/2007.
Site notifications with SAM and Dashboards Marian Babik SDC/MI Team IT/SDC/MI 12 th June 2013 GDB.
Accounting Update John Gordon. Outline Multicore CPU Accounting Developments Cloud Accounting Storage Accounting Miscellaneous.
WLCG Resource Reporting 2 Laurence Field Cloud Status Document A few comments received Mainly minor text changes New final version (v1) has been generated.
The Grid Information System Maria Alandes Pradillo IT-SDC White Area Lecture, 4th June 2014.
Operations Coordination Team Maria Girone, CERN IT-ES GDB, 11 July 2012.
WLCG Accounting Task Force Introduction Julia Andreeva CERN 9 th of June,
GridPP37, Ambleside Adrian Coveney (STFC)
Bob Jones EGEE Technical Director
IT Service Transition – purpose and processes
Monitoring Evolution and IPv6
Main objectives To have by the end of August :
WLCG Workshop 2017 [Manchester] Operations Session Summary
Software Project Configuration Management
John Gordon STFC OMB 26 July 2011
Report from WLCG Workshop 2017: WLCG Network Requirements GDB - CERN 12th of July 2017
WLCG Data Steering Group
WLCG Resources Reporting
WLCG Accounting Task Force Update Julia Andreeva CERN IT on behalf of the WLCG Accounting Task Force GDB
Key Activities. MND sections
Benchmarking Changes and Accounting
POW MND section.
CREAM Status and Plans Massimo Sgaravatto – INFN Padova
GOCDB Update 27/05/ Me: Working on GOCDB 3 days a week
How to enable computing
Taming the protocol zoo
Proposal for obtaining installed capacity
Experiment Dashboard overviw of the applications
Advancements in Availability and Reliability computation Introduction and current status of the Comp Reports mini project C. Kanellopoulos GRNET.
WLCG Accounting Task Force Update Julia Andreeva CERN WLCG Workshop 08
Summary from last MB “The MB agreed that a detailed deployment plan and a realistic time scale are required for deploying glexec with setuid mode at WLCG.
Infrastructure Area EMI All Hands Summary.
WLCG dedicated accounting portal (proposal)
WLCG Collaboration Workshop;
Cloud Computing R&D Proposal
Solutions for federated services management EGI
Monitoring of the infrastructure from the VO perspective
Cloud Management Mechanisms
SISAI STATISTICAL INFORMATION SYSTEMS ARCHITECTURE AND INTEGRATION
New Types of Accounting Beyond CPU
Presentation transcript:

Accounting Review Summary and action list from the (pre)GDB Julia Andreeva CERN-IT WLCG MB 19th April

The goals of the accounting review We have quite some issues and open questions related to the accounting Effort is dispersed across various task forces and working groups (IS task force, benchmarking WG, cloud procurement work, WLCG resource reporting task force, etc…) Need to summarize issues we have, define an action plan and propose how we can better organize this work 2

Topics which were discussed CPU (wallclock) accounting Multicore accounting Accounting of the resources provided through cloud interfaces Accounting of the opportunistic resources Review of the EGI accounting portal and accounting reports generated by REBUS Storage space accounting. In particular what are our plans for no-srm storage 3

Conclusions and action list 4

Multicore accounting Seems to be in good shape Proper reporting of the number of cores is enabled at all T1 and most of T2. Corner cases to be followed up Main effort required for validation of the multicore information in the accounting portal Information can be crosschecked with CMS and ATLAS Dashboard where multicore accounting is available

Accounting of the resources provided through cloud interfaces (private clouds) The good start was the work done by the WLCG Resource Reporting Task Force. However, it looks like there is still a lot of effort required before we have production solutions for instrumenting our cloud resources for proper reporting With OpenStack we progress well thanks to work of the CERN IT-CM group. What about other platforms for cloud computing? Need to understand whether other WLCG sites apart from CERN work on it. If yes, need to streamline this effort. And collaborate with EGI.

Accounting of the cloud resources provided by commercial clouds Work on accounting of the commercial clouds is in progress and is driven by the CERN IT CM group and in the scope of CERN cloud procurement activity. Currently no actions are required.

Accounting of the opportunistic resources Some of the experiments believe that it would be nice to have a capability to expose usage of the opportunistic resources in the accounting portal These resources are already accounted in the experiment-specific systems which can expose accounting information though APIs The proposal is to evaluate a possibility to inject information of usage of the opportunistic resources in APEL, the same way it is done for OSG accounting info which is injected from GRATIA.

Review of the accounting portal and accounting reports Agreed that though available capacity is required for operations, it does not need to be a part of the accounting reports Agreed that manual fixes of the accounting numbers for the accounting reports should be avoided and if accounting data is not properly reported to APEL the problem should be fixed there instead Agreed that WLCG needs a dedicated simplified instance of the accounting UI, which provides customized menus and contains ONLY metrics required by WLCG Agreed that we use GGUS for reporting bugs and submitting requests to APEL and accounting portal developers Agreed that better coordination between APEL/accounting portal developers and WLCG represented by the WLCG operations team is required, in particular in what concerns validation of the accounting portal (in terms of functionality) and checking of the trustworthiness of the provided information.

Some more proposed and agreed changes on the accounting reports and accounting portal In the reports - use a consistent metric with the one in which pledges are expressed wallclock HS06 instead of CPU HS06. In the reports - use the same unit HEPSPEC06 days both for T1 and T2 reports. On the portal - add a simple metric ‘Elapsed time multiplied by number of cores’ in order to easily crosscheck information with the experiment specific accounting systems On the portal - mandatory views for the WLCG resources T1,T2, (for all of the formal WLCG sites) and a Country one that includes all sites contributing time to any LHC experiment 10

Some highlights regarding REBUS REBUS is used for pledges, installed (available) capacities and generation of the accounting reports Accounting reports are constructed taking data from REBUS itself and accounting data from the accounting portal The functionality of REBUS might be reviewed if the new WLCG configuration system is accepted. REBUS can be turned into a service for report generation taking data via APIs from various external sources 11

Proposal for setting up the CPU accounting Task Force The goals are : - to agree with all stakeholders on the content of the accounting portal and accounting reports (metrics, units, aggregation in terms of time and set of attributes like site, VO, country, etc…); - coordinate with APEL and accounting portal development team and follow up on the progress - validate the new version of the portal, ideally a dedicated customized UI for WLCG, and make sure that the requirements of the stakeholders are addressed - validate accounting data, ensure that it is correct in the APEL repository so that manual fixes could be avoided - follow up on whether/ how we enable injection of the opportunistic resources into APEL and accounting portal - In case CRIC is accepted as a WLCG central configuration system, re-evaluate role and functionality of REBUS which can be turned into a simpler service responsible for pledges and report generation - assess the situation with accounting of the pledged resources provided through private clouds, understand whether we have all components in place to properly account such resources, make sure that they are correctly publishing to APEL. In case this requires substantial development, testing and evaluation effort, this can be a question of launching its own dedicated task force

Storage space accounting There are two main use cases for storage space accounting which experiments currently deal with: Very detailed space accounting with a possibility of the full storage dump. Implies experiment-specific requirements and data organization High level space accounting (few numbers : total/used/free per VO and where/if possible with some level of details for high level quotas) As much as WLCG infrastructure is concerned the second objective is more important and looks to be easier to address in a common way

Steps towards generic WLCG storage space accounting Agree with the experiments on high level accounting requirements (second use case on the previous slide) Agree with the experiments on the common format of the ‘space usage record’ (second use case on the previous slide) Inspect solutions we have for various storage implementations in order to generate ‘space usage records’. Whether we have solutions for all storage implementations which are currently in use? Whether these implementations are optimal? Work with storage providers in order to enable generation of the required space usage records Understand how we collect, store and visualize storage space accounting information, possible alternatives: -Work with EGI in order to enable this info in APEL and accounting portal -Investigate WLCG-specific solution, possibly based on ATLAS space accounting Dashboard 14

How we organize work on storage space accounting This work was started by the WLCG operations. Discussions were held with ATLAS, CMS and LHCb Further effort can be organized in a form of a dedicated task force or working group Another possibility would be to handle this work under the umbrella of the WLCG storage providers working group, which is needed not just for this task In whatever form this work is organized, the goal is to assess the possibility to have a WLCG solution for high level space accounting which is not based on SRM - evaluate existing solutions in the experiments - agree on common formats for space usage records - collaborate with storage providers and experts in the experiments at sites in order to enable usage record generation scripts for various storage implementation and make sure that there are shared in the community - collaborate with APEL development team to understand data collection and exposure through the EGI accounting - assess other scenarios for data collection and aggregation ( WLCG-specific repository) - based on this assessment come up with the proposed architecture and estimation of the required development effort