AdminPage

Management of the whole cluster

• elog
• How to properly switch off the cluster
• How to properly put the cluster on

CMS Services

• Phedex
• Heartbeat
• LoadTest
• FroNTier
• ProdAgent
• instructions to commit siteconf to git

Grid Configuration Issues

• Update the certificates of all our machines
• Issues with cream and how to solve them
• PBS TMPDIR
• APEL(OBSOLETE)
• BDII
• FTS
• SL4 x86_64 WNs(OBSOLETE)
• CE overloaded
• RB
• IPMI
• Upgrade CA certificates (OBSOLETE)
• Shutting down the cluster
• Software Area Switch
• Kernel mandatory updates for critical vulnerabilities
• Argus server and glexec on the workernodes
• Apel gap publishing
• Update IGTF CA certificates

Files section

• dCache
  • Find obsolete files
  • dCache admin mode
  • find size of a directory on dcache
  • dCache Pool Postinstallation steps
  • Adapt max mover
  • scripts to see on what pools files in a directory reside and to move them to other pools
• Procedure for removal of old user files on pnfs
• Retrieve lost files from datasets
• Storage Consistency

Status and Monitoring

• List of reserved WNs
• Todo-list
• Monitoring
• Plans/Schedule
• Grid Troubleshooting link
• Incident Reports
• How to put the software back
• What to do when a WN sends a "bad_wn.pl" email to grid_admin ?
• Nagios Installation at IIHE
• How to restart DCache

Info

• General info
• Installing CMSSW
• Installing CRAB
• System Benchmarks
• T2B Trac config info
• Hardware information
• Network Setup
• Setup Monitoring of LSI Disk Controler on Sunfire V20z Server
• LDAP authentication system for the replication between UCL and IIHE sites (OBSOLETE)
• IIHE Grid-admin survival guide
• Solaris 10
• Adding an SSD card and configuring RAID, zpools, filesystems and shares on the new Solaris fileserver
• Linux tricks for admins
• How to implement local PBS submission with CRAB ?(OBSOLETE)
• How to create an account for a CMS user from UCL ?(OBSOLETE)
• Deploying OS errata(OBSOLETE)
• Howto benchmark a node with HEPSPEC06
• Install a new dCache pool
• Backup of the users home dirs on Jefke
• Migration of mon and its Web services
• HOWTO restart a nagios test manually
• Compile and install ROOT
• Clean creamdb
• Reboot campaign for the workernodes :
  • Reboot after a kernel update
  • Reboot after an OS upgrade
  • Force reboot a WN with hanging nfs: echo 1 > /proc/sys/kernel/sysrq ;echo b > /proc/sysrq-trigger
  • Force shutdown a WN with hanging nfs: echo 1 > /proc/sys/kernel/sysrq ;echo o > /proc/sysrq-trigger
• Central management of all the admin scripts with Git
• Help page for all iihe scripts
• Configuration of a proxy for CVMFS
  • How to recover CVMFS
• How to test NFS Performance
• Alternatives to Tetex
• A new easy method to update kernel on the workernodes
• About automatic mail sending from the cluster
• T2B Trac access configuration
• Surviving to RHEL7
• Experimental : Securing profiles with Kerberos
• Migration of T2B Wiki from Trac to MediaWiki
• Message Of The Day (motd)
• Support of Long-tail of Science
• Querying BDII
• Machine private certificate with EL7
• Cluster usage accounting statistics
• Singularity container creation

Quattor

• FAQ - Aide-mémoire - Howtos
• Manage repositories with quattor
• How to build an RPM from a tag in Github
• Working in CB9 (Quattor release >= 14.2)
• How to add a new version of quattor in our scdb
• Quattor and FreeIPA
• Hard disks management
• How to use metaconfig (with examples)
• Aquilon

• BEgrid wiki(OBSOLETE)
• Test things(OBSOLETE)
• Lemon installation(OBSOLETE)
• Pointers to more in-depth information on quattor(OBSOLETE)
• Adding a new machine to the cluster(OBSOLETE)
• Automatic generation of hardware and profile templates for new workernodes(OBSOLETE: use script create_wn)
• Installation of a Quattor deployment server release 13.1(OBSOLETE: see quattor template for aii server)
• How to add a new OS to the Quattor Repository(OBSOLETE)
• How to migrate workernodes from CB8 to CB9(HISTORICAL)
• Howto build a new pysvn on a SL63 AII server(HISTORICAL)

FreeIPA

• Fix IPA client certificates

KVM virtualization

• Virtualization of the new CREAM-CE on dom02 with KVM
• Installation of the new virtualization server dom04
• Easy creation of virtual machines
• Monitoring the KVM vHosts with Ganglia

T2B Cloud

• Transforming the KVM hypervisors farm into an OpenNebula cloud
• Working in the T2B cloud
• Migrate one DB from sqlite to mysql
• Backup of the T2B Cloud
• Dealing with iPXE

Clouds for users

• VUB-ULB cloud
• BEgrid cloud (part of FedCloud)

gUSE/WS-PGRADE portal

• Portal installation
• Portal configuration
• Portal operations

Migration to EMI-3

• BEgrid facilities - Part 1
• BEgrid facilities - Part 2

XEN

• Manage XEN
• Xen and Quattor

CEPH

• Understanding Ceph
• Installing Ceph with Quattor
• Experiments with Ceph
• Operating a Ceph cluster

Logstash / Elasticsearch / Kibana (ELK)

machine: log10 | interface | index manager

• Forwarding a log with rsyslog to logstash using quattor
• Parsing the logs with logstash

Network

• Bonding of 2 interfaces + tagging of 2 vlans on the bond (PRIV+PUB)|
• Managing the Huawei CE8850-32CQ-EI 100G switch

HTCondor clusters

• Testing local submission
• Testing grid submission
• HTCondor cheat sheet
• HTCondor Python binding