HECToR Monthly Report, May 2010

Information on the utilisation, disk allocations, slowdowns and helpdesk statistics can be found in the associated SAFE monthly report.

Dates covered: 08:00 1 May 2010 to 08:00 1 June 2010
Number of hours: 744

1: Availability

Scheduled down time: 22 hours 48 minutes.

Incidents

The following incidents were recorded:

SeverityNumber
15
22
326
40

Of the four severity levels, level 1 corresponds to a contractual failure.

Out of the 26 SEV-3 Incidents, 26 were attributed to single node failure events.

Details of severity level 1 incidents

,
ID Date Description Length Attribution
Incident-3431 02/05/2010 Cabinet emergency power down due to a power supply failure 04:54 Cray
Incident-3491 10/05/2010 Link inactive. Two modules replaced. 01:39 Cray
Incident-3566 18/05/2010 Link inactive. Two modules replaced. 00:59 Cray
Incident-3601 26/05/2010 Unplanned shutdown immediately prior to maintenance. User error executing script. 00:05 Cray
Incident-3631 31/05/2010 High speed network congestion. External lustre image removed. 02:12 Cray

MTBF and Serviceability

AttributionFailuresMTBFUDTServiceability
Cray514609:49:0098.6%
Site000:00:00100%
External000:00:00100%
Other000:00:00100%
Overall514609:49:0098.6%
  • 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 single node failures

Error Type Number
RX message header CRC Error 12
RX message CRC Error 7
RX packet sequence number error 1
MCA bk0 error (internal Opteron cache error) 2
UME bk4 (bk0 DIMMS) 2
Software/application related error 1
Heartbeat error 1

2: Courses

This information is supplied by NAG Ltd
Title of Course Dates Available Places Ordinary Attendees Paying Attendees CSE Staff Total Attending
Exploiting Parallel CASTEP on Large-scale HPC, NAG Manchester 17-18 May 2010 20 11 0 2 13
Parallel IO, NAG Oxford 19 May 2010 12 2 0 2 4
Advanced Computational Methods, University of Southampton Every Thursday in May (6,13,20,27) 20 9 MSc students (i.e. those being assessed) + 5 other attendees 0 0 14 (The numbers vary a bit from week to week)

3: Quality Tokens

Date Tokens Awarded Comment Consortium
11-May-2010 11:12:17 Que time is far too long as accounting is off! e05
11-May-2010 11:13:35 Jobs are taking too long to go on, whilst accounting is switched off!! e05
27-May-2010 08:47:09 Amount of queuing time ridiculous n02

4: Hours Worked

GroupDays workedFTEs
USL100.35.65
OSG83.1 4.61

5: Performance Metrics

Technology Provision

Description TSL FSL Value
Technology reliability 85% 98.5% 98.6%
Technology throughput 7000 hours 8367 hours 8393 hours
Capability job completion rate 70% 90% 94.3
Technology MTBF 100 hours 126.4 hours 146

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% 98.5%
Number of SP FTEs 7.3 8.0 8.7 10.3
SP Serviceability 80% 99% 99.5% 100%