HECToR Monthly Report, June 2009
Information on the utilisation, disk allocations, slowdowns and helpdesk statistics can be found in the associated SAFE monthly report.
Dates covered: 08:00 1 June 2009 to 08:00 1 July 2009
Number of hours: 720
Note: HECToR changed from a dual core to quad core configuration as of 19th June 09.
1: Availability
Scheduled down time: 108 hours 34 minutes. This includes downtime for Phase 2A upgrade.
Incidents
The following incidents were recorded:
| Severity | Number |
| 1 | 3 |
| 2 | 1 |
| 3 | 25 |
| 4 | 1 |
Of the four severity levels, level 1 corresponds to a contractual failure.
Out of the 25 SEV-3 Incidents, 25 were attributed to single node failures.
Details of severity level 1 incidents
| ID | Date | Description | Length | Attribution |
| Incident-1586 | 02/06/2009 | Link Inactive error | 01:26 | Cray |
| Incident-1641 | 12/06/2009 | OST21 hangup - lustre failure | 07:55 | Cray |
| Incident-1736 | 30/06/2009 | Link Inactive error | 01:56 | Cray |
MTBF and Serviceability
| Attribution | Failures | MTBF | UDT | Serviceability |
| Cray | 3 | 244 | 11:17:00 | 98.2% |
| Site | 0 | ∞ | 00:00:00 | 100% |
| External | 0 | ∞ | 00:00:00 | 100% |
| Other | 0 | ∞ | 00:00:00 | 100% |
| Overall | 3 | 244 | 11:17:00 | 98.2% |
- Note 1: Serviceability%= 100*(WCT-SDT-UDT)/(WCT-SDT)
- Note 2: MTBF (Mean Time Between Failures) is defined as 732/Number of failures.
Details of XT single node failures (Split by Architecture)
| Error Type | Dual Core | Quad Core |
| RX message header CRC Error | 2 | 1 |
| MCA bk0/bk2 error (Internal Opteron) | 3 | 1 |
| UME bk0/bk4 (Dimms) | 2 | 8 |
| Coldstart error (node failing to restart after reboot) | 5 | 1 |
| Software problem - kernel panic | 1 | 1 |
Note: During "coldstart" errors, no user jobs were affected.
Phase 2A Utilisation
The graph below illustrates the RAW AUs used during the Phase2A Upgrade in June.
Utilisation prior to the suspension of accounting on 19 June was 58%.
Utilisation following the suspension of accounting was 95%.
Note: The 'xclass' jobs were the acceptance test jobs run by the Cray Centre of Excellence.
2: Courses
This information is supplied by NAG Ltd| Title of Course | Dates | Available Places | Ordinary Attendees | Paying Attendees | CSE Staff | Total Attending |
| Introduction to MPI, University of Cambridge | 1 - 2 June 2009 2009 | 32 | 17 | 0 | 0 | 17 |
| Parallel Programming with MPI, Queens University of Belfast | 16 - 18 June 2009 | 24 | 12 | 0 | 0 | 12 |
3: Quality Tokens
| Date | Tokens Awarded | Comment |
| 24-Jun-2009 15:51:15 | * * * * * | Fast and effective support from helpdesk |
4: Hours Worked
| Group | Days worked | FTEs |
| USL | 93.2 | 6.0 |
| OSG | 73.7 | 4.1 |
5: Performance Metrics
Technology Provision
| Description | TSL | FSL | Value |
| Technology reliability | 85% | 98.5% | 98.2% |
| Technology throughput | 7000 hours | 8367 hours | 7345 hours |
| Capability job completion rate | 70% | 90% | 97.7 % |
| Technology MTBF | 100 hours | 126.4 hours | 244 hours |
Note: Technology throughput is calculated: 12*(732-UDT-SDT); 732 - annual average number of hours in a month
Note: MTBF is calculated as 732/number of failures
Service Provision
| Description | TSL | FSL | USL | Value |
| Percentage of non-in-depth queries resolved within one day | 85% | 97% | 99% | 99.3% |
| Number of SP FTEs | 7.3 | 8.0 | 8.7 | 10.1 |
| SP Serviceability | 80% | 99% | 99.5% | 100% |
