hongmei zhang institute of high energy physics beijing
play

Hongmei Zhang Institute of High Energy Physics, Beijing 1 2017-3-10 - PowerPoint PPT Presentation

Hongmei Zhang Institute of High Energy Physics, Beijing 1 2017-3-10 Experiments @ IHEP Computing environment The operation management platform The Billing System The Billing System Next Plan 2 2017-3-10 3 2017-3-10


  1. Hongmei Zhang Institute of High Energy Physics, Beijing 1 2017-3-10

  2.  Experiments @ IHEP  Computing environment  The operation management platform  The Billing System  The Billing System  Next Plan 2 2017-3-10

  3. 3 2017-3-10

  4.  BEPC:Beijing Electron ‐ Positron Collider  BESIII (Beijing Spectrometer III at BEPCII)  BESIII (Beijing Spectrometer III at BEPCII)  Produces ~100 TB/year raw data y  >3.5PB now  >5PB in five years  7000 Cores for data  7000 Cores for data process and physics analysis 4 2017-3-10

  5.  Daya Bay Reactor Neutrino Experiment  To measure the mixing angle θ 13  To measure the mixing angle θ 13  Produces ~200 TB/year (2011 ‐ 2018) 5 2017-3-10

  6.  Jiangmen Underground Neutrino Observatory (under construction)  Start to build in 2014, operational in 2019  Estimated to produce 2PB data/year for 10 years 6 2017-3-10

  7.  Large High Altitude Air Shower Observatory(under  L Hi h Altit d Ai Sh Ob t ( d construction)  located on the border of Sichuan and Yunnan Province  Expected to be operational in 2019 p p  ~1.2PB data/year * 10 Years  On ‐ site storage and computing resources. Data will be filtered and O it t d ti D t ill b filt d d compressed before transferring back to IHEP 7 2017-3-10

  8.  Circular Electron Positron Collider(Future Project)  Circular Electron Positron Collider(Future Project)  Next Generation Accelerator in China after BEPCII  Will complete its mission about 2021  Estimated to produce 200TB/year raw data for Higgs factory  Estimated to produce 200TB/year raw data for Higgs factory and >100PB/year for Z factory 8 2017-3-10

  9.  Experiments @ IHEP  Computing environment  The operation management platform  The Billing System  The Billing System  Next Plan 9 2017-3-10

  10. ~17000CPUcores 17000 CPU 5PBtapelibrary ~5PBdiskspace Powersupply&coolingsystem 10 2017-3-10

  11.  Local clusters  DIRAC ‐ based distributed L l l DIRAC b d di ib d computing system computing system  ~13,500 CPU cores 13,500 CPU cores  300 GPU cards  ~ 2,000 CPU cores  Grid site (WLCG)  IHEPCloud based on Openstack  1,200 CPU Cores  ~ 720 CPU cores 720 CPU cores  11 2017-3-10

  12.  Lustre as main disk storage  Capacity: 5.7 PB storage  Gluster system  734TB storage with replica feature  DPM & dCache  DPM & dCache  940TB, With SRM interface  HSM, with modified CASTOR  Capacity: 5 PB 12 2017-3-10

  13.  Low resources utilization rate L ili i  Less than 60% on average Less than 60% on average  Computing resources are non ‐ shared 13 2017-3-10

  14.  Experiments @ IHEP  Computing environment  The operation management platform  The Billing System  The Billing System  Next Plan 14 2017-3-10

  15.  Goal  Platform between users and resources  Manage & allocate all resources of IHEP data center & ll ll f d  Apply for & manage resources pp y g  Compute the bill  Promoting resource sharing  Share resources  Improve resource utilization p 15 2017-3-10

  16. Equipments Billing Sharing Jobs Files … Users Reports Monitoring DSS DSS Al Alerts t 16 2017-3-10

  17. Equipments APP Cabinets Fault Statistics 17 2017-3-10

  18.  Experiments @ IHEP  Computing environment  The operation management platform  The Billing System  The Billing System  Next Plan 18 2017-3-10

  19.  Objective(stage Ⅰ )  Support 3 computing resources  Support individual user & experimental group  Apply for resources  Apply for resources  Compute the bill  Features  Can be configured  Easy to be used  Easy to be used 19 2017-3-10

  20. Local HTCondor IHEP SSO HTCAccount BEPC Cloud BES BSRF IHEP Billing g O Openstack t k HXMT System ADS Web JUNO OpenstackAcc bill bill ount t CSNS HR etc. Dirac ARP ARP ( Academia Resource Planning ) Planning ) i ) DiracAccount Di A t Pl 20 2017-3-10

  21. Decorator BootStrap Utils Utils CKEditor CKFinder Spring MVC Message Layer zTree zTree Shiro Spring Log4j MyBatis Ehcache Alibaba Druid ( Database connection POOL ) Alibaba Druid ( Database connection POOL ) MySQL MySQL

  22. Application Instance Type Price Bill BIL LL Management Management SSO User Afs Group User Afs User Distribute User ARP User User Role Menu Log Base e Area Area Office Office Config Config monitor monitor Dictionary Dictionary 2017/3/22 22

  23. • Users select resources(instance type ,time) • Administrators allocate resources Apply Apply • Get bill from Account System automatically • Get bill from Account System automatically Account • Automatic settlement , export bill • Users can check the bill Compute 23 2017-3-10

  24. System Openstack Manager Manager BS. db Billing System Real data Users Novadb Keystonedb Gl Glancedb db Account. db Request and information dataflow ACCount System 24 2017-3-10

  25. 25 2017-3-10

  26. 26 2017/3/22

  27. Bill Cloud bill Dirac bill Cl Cluster bill t bill R Runing bill i bill 2017/3/22 27

  28. 28 2017-3-10

  29. 29 2017-3-10

  30.  Experiments @ IHEP  Computing environment  The operation management platform  The Billing System  The Billing System  Next Plan 30 2017-3-10

  31.  Support more resources  Storage, Database etc. St D t b t  Integrate monitoring system Integrate monitoring system  Mobile client 31 2017-3-10

  32. 32 Thanks ! k ! Th 2017-3-10

Recommend


More recommend