LCG Software Activities in India

1
LCG Software Activities in India

• Rajesh K.
• Computer Division
• BARC

2
DAE-CERN Collaboration on Grid Computing

• Agreement for collaboration in software
  development for LCG
• 5 year period 2003-2007 (inclusive)
• 50 FTE years
• Participating DAE institutes BARC, CAT, VECC,
  TIFR

3
Current Projects

• 3 projects currently underway in the area of Grid
  Monitoring and Fabric Management
• GRIDVIEW A visualization tool for LCG
• ELFMS Extremely Large Fabric Management System
• CC Tracker Computer Centre Tracker

4
GRIDVIEW Visualization Tool for LCG

• Visualization system for viewing monitoring
  information from the LCG
• Dashboard showing different status views for
  different kinds of information
• Site-wise
• VO-wise
• Etc.
• Intended for use in GOCs and ROCs but not
  restricted to that

5
Gridview

• Collects monitoring information from different
  monitoring tools from grid sites using R-GMA as
  transport
• Gridftp monitor
• SFT
• RB Logs etc.
• Archival of monitoring information in a central
  Oracle database at CERN
• Analysis of this data to generate summaries
• Visualization of summary data through Web
  interface and GUI

6
Gridview Architecture
7
Gridview Current

• GridFTP transfer monitoring
• In production use
• Display of network throughput and total data
  transferred
• Different host/destination
• VO-wise, Site-wise, Host-wise
• Current, Hourly, Daily, Monthly etc.
• Used during SC3 throughput tests

8
Gridview In development

• Job Status Monitoring
• Total number of jobs at grid sites in different
  states
• VO-wise, RB-wise distribution
• Site wise job failure rate, utilization etc.
• Grid Dashboard
• Pictorial representation of site status info on a
  world map

9
(No Transcript)
10
ELFMS Extremely Large Fabric Management System

• Participation in CERN Project on ELFMS
• ELFMS is used to manage and monitor thousands of
  nodes in the CERN computer centre and other LCG
  sites
• Contribution to development and support for ELFMS
  modules LEMON and QUATTOR

11
LEMON LHC Era MONitoring

• Lemon is a system designed to monitor performance
  metrics, exceptions status information of
  extremely large clusters
• At CERN it monitors 2000 nodes, 70 clusters
  with 150 metrics/host producing 1GB of data.
  Estimated to monitor up to 10000 nodes
• A variety of web based views of monitored data
  for Sysadmins, managers and users
• Highly modular architecture allows the
  integration of user developed sensors for
  monitoring site-specific metrics.

12
Contribution to LEMON project

• TCP based communication between agent and server
  instead of the current UDP based one.
• SSL encryption
• A light weight correlation engine to generate
  exception metrics and launch fault tolerant
  actuators in response to an undesired state. This
  sensor supports multiple metric correlation and
  mathematical operations between correlated metrics

13
Quattor

• Quattor is a tool suite providing automated
  installation, configuration and management of
  clusters and farms
• Highly suitable to install, configure and manage
  Grid computing clusters correctly and
  automatically
• At CERN, currently used to auto manage nodes
  gt2000 with heterogeneous hardware and software
  applications
• Centrally configurable reproducible
  installations, run time management for functional
  security updates to maximize availability

14
Contribution to Quattor project

• Testing all new releases Quattor outside CERN.
• Presently working in the SWRep (Software
  Repoisitory) part of Quattor.
• Changing SWRep framework from ssh to SOAP with
  ssl.

15
CC Tracker

• A tool to Visualize the CERN Computer Centre
• Simplifies management of the CERN Computer Centre
  for LHC scale operations
• Allows easy invocation of service management and
  operational interventions across sets of selected
  nodes

16
CC Tracker Functionality

• Visualize Computer Centre
• Physical View Display of all CC rooms with
  Racks, Disk cabinets, Tape silos, PDUs
• Logical View Display Domains, Clusters, Sub
  clusters hosts in hierarchical way
• Manage Hardware
• Add , Move, Rename Retire operations for a set
  of machines
• Change cluster, update kernel, update OS ,
  shutdown, reboot set desired state
• Manage Infrastructure
• Addition/deletion of Rack, Disk Cabinet, Tape
  Silo, PDU and Tape drive
• Updating properties (name, location)
• Check power consumption by rack, zone, room
  cluster
• Check cost by rack, zone, room cluster

17
CCTrackerLogical Physical view
18
Completed Projects

• SHIVA Problem Tracking System
• QoS Quality of Service Prediction for worker
  nodes
• RDBMS backend for POOL
• LCG-AliEn Storage Element Interface
• Test Suite for perl harnessing with AliEn

19
SHIVA Problem Tracking System

• General purpose bug tracking system for keeping
  track of bugs, feature and other issues in
  software development projects
• SHIVA accepts problem reports from users, routes
  them to troubleshooters and maintains archives of
  problems and solutions
• Generate reports and statistics
• Implement helpdesk systems for services
• Used as a problem tracker for SC3 related work

20
SHIVA Screenshot
21
QoS Predicting Quality of Service of Worker nodes

• Deriving a composite metric for quality of
  service offered by worker node
• QoS computed by a correlation engine which takes
  simple metrics such as load average, free memory
  and so on as input

22
RelationalStorageSvc for POOL

• Designed and Developed the Relational
  StorageSvc module prototype for POOL.
• Designed the prototype as a plugin in POOL
  framework.
• Provided solution for Remote Database
  connectivity.
• Implemented interfaces of the POOL Storage
  Manager for ORACLE backend.
• Demonstrated the Navigation,Storage and Retrieval
  of data using ORACLE and the ODBC connectivity
  option.
• Tested the cross technology referencing concept
  of POOL Storage Manager using ROOT and ORACLE,
  for primitive and referenced data types

Courtesy Anil Rawat, Centre for Advanced
Technology, Indore
23
RSSvcs place in POOL Architecture
Courtesy Anil Rawat, Centre for Advanced
Technology, Indore
24
LCG-AliEn Storage Element Interface

• Test Bed Installation for Grid Environment
• One central server and two Sites.
• Installation of Certification Authority Server
• Installation of GridFTP Library under AliEn
• The GridFTP daemon in.ftpd has been used as
  server and globus-url-copy has been used as
  client
• Development of AliEn-SE Interface via GridFTP
• These newly developed modules along with
  necessary GridFTP libraries and changes made in
  existing AliEn Code have been committed to CVS
  Server at CERN.

Courtesy Tapas Samanta, VECC, Kolkata
25
Quality Assurance and Test Environment for
AliEn-ARDA Prototype

• Exploration and Design of Test Scripts using
  perl.
• Implementation of Test Scripts for each
  Individual perl sub-module of AliEn.
• Individual perl sub-modules of AliEn code were
  tested for proper functionalities. It Generates a
  detailed report of the individual tests and
  maintains a log.
• Validation of Test-Scripts and Procedures.
• Testing Modules with perl Harnessing Environment.
• The Complete Suit was tested at CERN under perl
  Harnessing Environment for testing AliEn online
  and generating online consolidated report of the
  test.
• Inline Documentation to the extent possible.

Courtesy Tapas Samanta, VECC, Kolkata
26
Acknowledgements

• Gridview and Shiva team Phool Chand, Digamber
  Sonvane, Kislay Bhatt
• ELFMS, CC Tracker and Qos team R.S.Mundada,
  R.Sharma, D.Sarode. C.Murthy
• Anil Rawat, CAT, Indore
• T.Samanta, VECC, Kolkata
• Colleagues from IT Dept., CERN