|
|
||||
|
Bulletin 184 - 2008 December 23
The period from close of business on 24th December to the commencement of business on 2nd January will be a shutdown period for HPCCC and CSIRO ASC staff. Systems will be left running, but if there are problems, only essential and operational systems will be restored to service. Any problem reports sent to hpchelp@hpccc.gov.au or hpchelp@csiro.au may not be attended to until after the shutdown period. In addition, in periods of high temperatures, parts of some systems will be shutdown, and may not be restored to service until 2nd January or later. [ page top ] 2. Central Computing Facility cooling capacity In recent weeks, additional cooling capacity has been installed and brought into operation in the Bureau's Central Computing Facility (CCF). This has allowed the four SX-6s nodes, that had been down for many weeks, to be returned to service. [ page top ] 3. REQ System Milestone We recently reached the milestone of 10,000 requests into the HPCCC wreq request tracking system! The person to submit the 10,000th req was ...... (drum-roll) Wes Barris from CSIRO. At 23rd December, there were 149 open requests out of 10128 received. [ page top ] 4. CSIRO Data Store - high recent recall load, and tape transfers Over recent weeks, there has been a high load of file recalls on the CSIRO Data Store. Please use touch and dmget (see http://www.hpsc.csiro.au/userguides/ds/ and especially the section on the dmget command) to control the recall of files. Please do not copy files when a move will do - a copy will initiate a recall, and move does not. Please look at the traffic lights to see the current load, and click on the DMF 'more' button for extra information, and from there on the "DMF queue list" link to see the actual queue of requests. Over the holiday period, we will give higher priority to DMF system tasks than to user requests - in particular, the carrying out of writing one copy of all files to the new T10000A tape drives. This task is part of the process of coping with the ever-increasing storage demand. In general, the more data is stored, the worse the access becomes, as all devices have trade-offs between capacity and access times and i/o speeds. Delays in accessing offline files during this period will unfortunately increase. Removal of significant quantities of unwanted data is always appreciated. [ page top ] 5. CSIRO ASC Cluster outage Parts of the CSIRO cluster burnet (and burnet-old) will be down on the morning of 5th January, to allow the power feeds to some of the chassis to be re-configured. Job reservations will be set on the nodes to be shutdown during the outage, to prevent jobs starting whose finishing time would otherwise span the outage. (This work is being done to provide power to the CSIRO SL8500 tape library, but will result in parts of the cluster system being at higher risk of shutdown during power failures and re-configurations in the future.) [ page top ] 6. CSIRO ASC Software Upgrades The following have been recently installed:
[ page top ] 7. Seasons Greetings
---------------------------------------------------------------------------
. . . + . . .
. . # . .
. . ### . . .
. . "#:. .:##"##:. .:#" . .
. . "####"###"####" .
. "#:. .:#"###"#:. .:#" . . .
. "#########"#########" . .
. "#:. "####"###"####" .:#" . .
. . "#######""##"##""#######" .
."##"#####"#####"##" . .
. "#:. ... .:##"###"###"##:. ... .:#" .
. "#######"##"#####"##"#######" . .
. . "#####""#######""#####" . .
. " 000 " . .
. . . 000 . . .
.. .. ..................O000O........................ ...... ...
Seasons Greetings from the HPCCC and CSIRO ASC teams [ page top ]
|
|
Comments to: © Copyright 2010, CSIRO Australia Use of this web site and information available from it is subject to our Legal Notice and Disclaimer and Privacy Statement |