You are here: Foswiki>ATLAS Web>WebChanges (15 Nov 2006, TWikiContributor)Edit Attach

500 recent changes in ATLAS Web retrieved at 12:28 (GMT)

First batch node SN mapping node SN atlas1 2102311GGX10GB000034 atlas2 2102311GGX10GB000035 atlas3 2102311GGX10GB000036 atlas4 2102311...

r4 - 30 Jun 2020 - 15:02 by SvenRenas

ClusterInternalSSH

How to use dsh and password less ssh in between the nodes It's very easy to get password less ssh working in between the nodes, you just need a proper ssh keypair...

r4 - 12 Mar 2020 - 08:43 by HenningFehrmann

GridKaHOWTO

GridKaHOWTO Follow the whole process with the same user and the same browser! If you use Firefox, please ensure to use version ESR version 60 or 68 a...

r33 - 24 Sep 2019 - 07:34 by CarstenAulbert

PlannedWork

Planned downtimes This page summarizes planned/on going work within the Atlas cluster along with a few details. Usually, we will issue condor_off peaceful at lea...

r16 - 24 Aug 2019 - 16:02 by SvenRenas

WebHome

This is the public information on the ATLAS cluster operated by the Max Planck Institute for Gravitational Physics (also named Albert Einstein Insititute, AEI) si...

r56 - 25 Jul 2019 - 13:13 by CarstenAulbert

NetInstallViaiPXEInstall

Trying to get iPXE as the default method to netinstalls working (based on http://ipxe.org/howto/chainloading and https://doc.rogerwhittaker.org.uk/ipxe installati...

r4 - 11 Jul 2019 - 10:28 by CarstenAulbert

KernelRebuildPbuilder

Rebuilding Debian's kernel (loosely following https://kernel team.pages.debian.net/kernel handbook/ch common tasks.html#s common official) pbuilder environment I...

NEW - 09 Jul 2019 - 06:26 by CarstenAulbert

SpackTest

First steps with spack Please note this all this was tested on a extremely minimally installed server. I.e. just installing something like doxygen can take a very...

r2 - 28 Jun 2019 - 14:09 by CarstenAulbert

CreateHybridUSBImage

Create a hybrid USB Image The goal is to create an image file which can be copied onto a USB stick and booted both via legacy BIOS as well as UEFI. This document ...

r2 - 05 Jun 2019 - 09:16 by CarstenAulbert

SimpleZVolTesting

Simple ZFS ZVol testing creating baseline Create simple test data set in RAM: mkdir p /dev/shm/data for i in $(seq w 30); do dd if=/dev/null base64)" nosalt...

r3 - 01 Feb 2019 - 14:07 by HenningFehrmann

WebStatistics

Statistics for ATLAS Web Month: Topic views: Topic saves: File uploads: Most popular topic views: Top contributors for topic save and uploads: ...

NEW - 13 Jul 2018 - 12:49 by OliverBock

ZpoolTests2017

Simple zpool tests on w8501 raidz1 zpool created as 8*(2 1) raidz1: zpool status pool: srv state: ONLINE scan: none requested config: NAME ...

NEW - 22 Nov 2017 - 16:34 by CarstenAulbert

MonitoringMetrics

Detailed list of metrics we want to monitor Compute nodes (61) * CPU: user / nice / system / wait (4) * disk: * space available/free per locally defi...

NEW - 11 Sep 2017 - 13:15 by CarstenAulbert

MonitoringJessieAndBeyond

Monitoring for Jessie and Beyond What do we want/need to monitor (metrics/checks) A list of non exhaustive metrics and checks we we need/would like to have, e.g....

r23 - 11 Sep 2017 - 13:08 by CarstenAulbert

RadioServer

Atlas Radio Server Typical host names ra1 ra11 Spec table Chassis (3U Chassis) PSU Motherboard X8DT6 network Intel 82574L IPM...

NEW - 28 Apr 2017 - 09:36 by ChristianBeer

PrivateWeb

Webserver serving user content If you need a webserver to serve content from your $HOME to the world, please create the directory ~/WWW on Atlas if it does not ex...

r12 - 21 Feb 2017 - 15:37 by KarlWette

LowLatencyDataFlow

Low Latency Data Flow

NEW - 10 Nov 2016 - 08:26 by CarstenAulbert

AddNewHostSalt

How to add a new host (salt era) This example will use einstein12 as a sample machine which before was known as ra15. Before you begin, you need to have ssh agent...

r5 - 02 Nov 2016 - 10:08 by CarstenAulbert

JessieUpgrade

Cluster upgrade to Debian 8/Jessie We plan to use this page for keeping a record of where we are with respect to our full cluster upgrade to Debian Jessie. Curr...

r4 - 30 Sep 2016 - 12:38 by CarstenAulbert

FaiJessie

FAI Jessie set up 1 base install via old fai jessie 1 base minimal config via salt 1 echo 'deb http://repo.atlas.local/reprepro fai contrib' /etc/apt/...

NEW - 28 Sep 2016 - 14:13 by CarstenAulbert

DisableKM12ManuallyUseKM4

How to disable KM1/2 and use KM4 manually In order to disable KM1/2 and temporarily run with KM4 only, the following steps are needed (please monitor that each ch...

NEW - 26 Sep 2016 - 10:08 by CarstenAulbert

HSMFileSystemCheck

HSM file system check stats (last update: 2016 07 26T18:42Z) Planned steps (starting at 2016 07 26T11:00Z): 1 Issuing condor_hold to all jobs on all submit hos...

r5 - 26 Jul 2016 - 18:42 by CarstenAulbert

GitmasterMigration

How to migrate from gitmaster to gitlab This document explains how to migrate away from gitmaster.atlas.aei.uni hannover.de to the new gitlab.aei.uni hannover.de:...

r11 - 07 Jun 2016 - 05:22 by AlexPost

AptlyTrial

Aptly For the new LDG repo set , we are trying to use aptly as a potential successor to reprepro. The goals are: * support various Debian and Ubuntu releases ...

NEW - 12 May 2016 - 09:04 by CarstenAulbert

EatHDiskConfigTests2

Simple E@H disk layout tests Summary Table with timing results (time in seconds, lower is better): setup file # size/file kB zfs2lc128 zfs2l...

r3 - 08 Apr 2016 - 07:22 by CarstenAulbert

EatHDiskConfigTests

Simple E@H disk layout tests Summary Table with timing results (time in seconds, lower is better): setup md3log z2log/cache zfs3log/cache btrf...

r7 - 07 Apr 2016 - 11:09 by CarstenAulbert

FoswikiMigration

Foswiki Migration assumptions: * /old/ server * wiki.atlas.aei.uni hannover.de * /var/lib/foswiki * /new/ server * 10.20.60.82 * /va...

NEW - 29 Jan 2016 - 14:02 by CarstenAulbert

OraclePartExchange

Oracle Part Exchanges number date of return SR error disk size GB /PN DHL Tracking Auftragsnummer 2013 001 2013 10 07 x ...

r61 - 29 Oct 2015 - 09:31 by CarstenAulbert

LdrDataStatusAtlas

completeness status * type * * detector * * number of files at AEI * * number of files at CIT * * diff * * start time * * end time * * comments ...

r4 - 02 Oct 2015 - 12:45 by HenningFehrmann

GpfsQuestions

general questions are dual port 10GbaseT connectors possible Likely, will be clarified. are 40 GBits (QFSP ) possible Not clear yet. what is the meaning of a q...

r3 - 24 Aug 2015 - 08:48 by HenningFehrmann

VerifySAMTapeDriveOrdering

Checking drive ordering between SL3000 and SAM Following Doc Id 1006246.1 to verify drive ordering matches between SL3000 and SAM/Solaris preparation 1 Shut d...

r2 - 04 Aug 2015 - 11:37 by OliverBock

LllDD

llldd * TCP connection from CIT (or sites) to special receiver machine (possibly need root access for John Zweizig) possibly SL6???? * from there UDP multic...

NEW - 07 Jul 2015 - 19:01 by CarstenAulbert

CondorAccountingGroups

Condor Accounting Groups on Atlas In May 2015, LIGO introduced mandatory accounting groups for jobs running on the LIGO data grid (LDG). As Atlas is part of the L...

r3 - 29 Jun 2015 - 05:30 by CarstenAulbert

IntroductionGeneralPublic

What is ATLAS? ATLAS is a general purpose compute cluster, located in the Albert Einstein Institute for Gravitational Physics, in Hannover Germany, on the campus ...

r27 - 23 Jun 2015 - 07:37 by HenningFehrmann

CondorConfigUpdate2015

HTCondor configuration updates in 2015 (1) Using cgroups to softly enforce memory and core limits Reasoning In the past, we either relied on users' jobs to obey...

r5 - 22 May 2015 - 08:26 by CarstenAulbert

PeakPerformanceAtlas

Simple page about the peak performance of Atlas Components CPUs CPU single precision peak performance GFlops/s cores clock GHz Intel Xe...

r4 - 01 Dec 2014 - 13:13 by CarstenAulbert

DistributedFileSystemsBenchmark

Benchmarking distributed file systems stupid fast tests first, all using small compute nodes and use iozone r 32 s $((2**24 2**25)) i 0 i 1 i 2 i 8 O I S...

r8 - 03 Sep 2014 - 10:20 by CarstenAulbert

TypicalRebootOrderEinsteinAtHome

Cheat sheet for rebooting E@H machines in Hannover If the E@H machines need to be rebooted (e.g. kernel upgrade) here's the proper ordering: Isolated machines Th...

r3 - 29 Jul 2014 - 08:55 by BerndMachenschalk

SqlDumpEinsteinAtHome

SQLDump tests for Einstein@home On einstein db1 the following was found: # no compresion /usr/bin/mysqldump opt master data=2 EinsteinAtHome mbuffer /dev/nu...

NEW - 24 Jul 2014 - 11:38 by CarstenAulbert

CurrentSysOpTasks

This is just an unsorted, unfiltered list of current tasks and services all over the AEI (and beyond) which could be counted as SYSOP related. It is neither compl...

r2 - 23 Jul 2014 - 15:03 by OliverBock

ClusterGuide

Common guide lines for cluster usage This document describes common pitfalls and guide lines when using a large computing cluster. Some of the details are specifi...

NEW - 18 Jul 2014 - 10:16 by CarstenAulbert

ConfigurationManagement

Configuration Management (primer/summary/brainstormer) What's out there? These are not really meant for configuration mgmt (alone) and have their strengths somew...

r6 - 10 Jul 2014 - 18:07 by OliverBock

DistributedFilesystems

Distributed/clustered file systems This page should summarize what scenarios such file systems could fulfill within Atlas and what we expect from it. Properties s...

r5 - 30 Jun 2014 - 09:45 by OliverBock

HSMUpgradeJuly2014

HSM Upgrade July 2014 This is the proposed plan, small changes may be needed Move from x4270 to x4 2l Moving to new meta data server should result in more file s...

NEW - 26 Jun 2014 - 15:36 by CarstenAulbert

PlannedNextSteps

Planned steps for Atlas Update to Wheezy Steps to perform: * get new head nodes up and running * reinstall all old nodes a0101...a3842, gpu001...gpu0XX ...

NEW - 20 Jun 2014 - 08:59 by CarstenAulbert

LSCDirectoryStructure

Directory hierarchy for LSC files Storage structure for S4/S5/S6 data (past) In the past we used paths like these H/H1/RDS/C03/L1/H H1_RDS_C03_L1 822092472 60.gw...

r5 - 13 Jun 2014 - 09:59 by HenningFehrmann

ConfigurationPossibilitiesFCArray

Short overview on different configuration possibilities for FC arrays Our DDN FC array currently houses 600 disks (400 3 TB drives and 200 2 TB drives). DDN only ...

NEW - 23 May 2014 - 14:40 by CarstenAulbert

CoreSwitch

caption abbreviation explanation A left FS1000 B right FS1000 LC line card in EFX 1000 L leaf P port R rack s sun box ...

r72 - 04 Apr 2014 - 08:47 by HenningFehrmann

BCacheBenchmarking

Benchmarking bcache Evaluating if bcache can/should be used on our compute nodes. Benchmarking was performed with iozone (revision 3.397) with the command line io...

r2 - 28 Mar 2014 - 10:20 by CarstenAulbert

ManagementNetwork

HP switch mapping CC3E5FCF11D8 172.25.13.39 mgs039b CC3E5FCF4968 172.25.13.43 mgs043b CC3E5FCF3778 172.25.13.44 mgs044b CC3E5FCF2860 172.25.13.44 mgs045b CC3E5FCF...

r7 - 17 Mar 2014 - 14:07 by HenningFehrmann

HPDataNetConfiguration

basic configuration the default baud rate is 9600 first steps Use the serial console with a baud rate of 9600 and do system view interface Route Aggregation 1...

r12 - 06 Mar 2014 - 13:19 by HenningFehrmann

HSM6780CreateServiceDataFile

Create Service Data File for 6780 In case a hard drive is about to fail (or has already failed), Oracle support needs one special file collection, to create this,...

r3 - 24 Feb 2014 - 07:51 by CarstenAulbert

CompressionSizeEfficiency

Comparing efficiency and size of compressors With samfs and archive dumps being rather large, we needed a good compression scheme for these. We use a 101GB (1033...

r5 - 20 Feb 2014 - 14:10 by CarstenAulbert

HsmSolaris11Update

HSM upgrade Current status 2014 02 01T12:33Z: samfsdump/final backup stopped due to too many non archived files. Rushing to archive those as fast as possible. 20...

r12 - 05 Feb 2014 - 11:12 by CarstenAulbert

Solaris11FirstSteps

First steps with Solaris 11 I'm using the old x4440 machine, booting off a solaris 11 CD based on sol 11_1 text x86.iso. You must exit the grub countdown with ESC...

r4 - 12 Dec 2013 - 09:20 by CarstenAulbert

WorkEndOfYear2013

Infrastructure work at the end of 2013 work status planned dates move gpu001...gpu010 to rack 100 TBD 1952 2013 12 09 move gpu011...gpu02...

NEW - 09 Dec 2013 - 06:55 by CarstenAulbert

EinsteinAtHomeMachineHeadCount

Einstein@Home machine head count Please check this list to make migration and finding/cabling machines easier (racks used for these machines should be 79 (water c...

r9 - 02 Dec 2013 - 09:25 by CarstenAulbert

KernelBuilding

Building an atlas Kernel This assumes that a stable linux kernel source tree already exists on a machine (bob, /srv/kernel/linux stable), cloned via git clone git...

r4 - 05 Nov 2013 - 08:23 by CarstenAulbert

RackLayout2014

Rack layout for 2014 Row 1 rack number main usage 1 old 2008 compute nodes 2 old 2008 compute nodes 3 old 2008 compute nodes 4 ...

r2 - 04 Nov 2013 - 08:38 by CarstenAulbert

RackLayout

Rack layout which racks contained what and when

Basic information * rack rows are numbered 1 to 10 * Water cooled racks are numbered 1 to 102 * open ...

r2 - 01 Nov 2013 - 10:19 by CarstenAulbert

RackLayoutEmptyTemplate

Empty Table Template Row 1 rack number main usage 1 2 3 4 5 6 A 7 8 9 10 ...

r2 - 01 Nov 2013 - 10:17 by CarstenAulbert

RackLayoutEndOf2013

Rack layout at the end of 2013 Row 1 rack number main usage 1 compute nodes 2 compute nodes 3 compute nodes 4 compute nodes ...

r2 - 01 Nov 2013 - 10:16 by CarstenAulbert

DataNetwork2013

New networking set up for Atlas From 2008 till 2013 we used a flat networking structure, i.e. all computers on the data network were connected "directly" to the c...

r2 - 13 Oct 2013 - 14:11 by CarstenAulbert

NewsTicker

News Ticker for Atlas * 2013 09 03 Start moving hbeggenstein from s10 to HSM/C2 Main.CarstenAulbert 04 Sep 2013

NEW - 04 Sep 2013 - 09:21 by CarstenAulbert

GeneralOverview

For Users * General Introduction for Users * Useful Items * How ATLAS stores files * ErrorMessages and how to fix them (not updated) General Document...

r8 - 07 Jun 2013 - 09:35 by HenningFehrmann

EFX1000

Category:Network Category:WovenSystems This Page is about our ATLAS.CoreSwitch. You might also want to read the TRX page. Configuration access serial not wor...

r5 - 07 Jun 2013 - 09:35 by HenningFehrmann

WebPreferences

ATLAS Web Preferences The following settings are web preferences of the ATLAS web. These preferences overwrite the site level preferences in . and , and c...

r16 - 20 May 2013 - 14:52 by CarstenAulbert

EinsteinAtHomeBackfillWithCgroups

Using cgroups to push backfill into the background apt get update apt get y install boinc client libboinc app7 cgroup bin rsync a n0669:/etc/default/boinc clien...

NEW - 16 Apr 2013 - 20:10 by CarstenAulbert

LINDYCOMPowerSwitchLITE

LINDY COMPower Switch LITE 8 Main.AlexPost 11 May 2009: This document describes the use of the LINDY 8port Power Strip 32453. The easiest way to access the po...

r6 - 10 Apr 2013 - 08:48 by BerndMachenschalk

DebianLiveBuild

Create benchmark image with Debian live build apt get install live build lb config archives live.debian.net mkdir /srv/live default cd /srv/live default lb ...

NEW - 26 Mar 2013 - 10:02 by CarstenAulbert

TestUpload

testupload Main.SebastianGleicher 31 Jan 2013

NEW - 31 Jan 2013 - 13:28 by SebastianGleicher

WorkPlanShutdown20130115

Work planned for cluster shutdown on 2013 01 15 shutdown plan The following services will be shut down 1 all compute nodes possibly with the exception of "r...

NEW - 10 Jan 2013 - 08:03 by CarstenAulbert

EdacUtilsLabel

The proper labels for the /etc/edac/labels.db are: Vendor: Supermicro Model: PDSML DIMM 1A: 0.0.0, 0.1.0; DIMM 2A: 0.0.1, 0.1.1; DIMM 1B: 0.2.0, 0.3.0; ...

r2 - 10 Dec 2012 - 09:41 by CarstenAulbert

TestTopic12

test Main.CarstenAulbert 13 Nov 2012

r2 - 14 Nov 2012 - 10:39 by CarstenAulbert

EinsteinAtHomeDownloadserverRAID

Einstein@home RAID setup testing Over time the einstein abp1 download server (mostly BRP project) went through various updates to increase download throughput (ap...

NEW - 11 Sep 2012 - 06:18 by CarstenAulbert

BenchmarkCentral

Central benchmark page All our benchmark results should be linked from this page to help rediscovering already performed benchmarks. Ideally, a summary page will ...

r3 - 11 Sep 2012 - 05:40 by CarstenAulbert

AircoGericht

1.: Uns wurde gesagt, dass zu wartende Teile eine Gewährleistungsdauer von 2 Jahre habe. Nicht zu wartende Teile haben eine Gewährleistungsdauer von 5 Jahren. Dur...

r2 - 05 Jul 2012 - 12:44 by CarstenAulbert

CoolingIssuesSummary

Zusammenfassung Kühlprobleme hauptsächlich externe Aermec Kaltwassersätze Gerichtsverfahren Verlauf involvierte Firmen $ Airco : Anlagenbauer der Kältean...

r22 - 05 Jul 2012 - 11:25 by HenningFehrmann

KvmOnVM

generate a kvm environment on vm * login on vm * edit /srv/kvm/config/imagename.conf and add this or similar settings * NIC1=int * NIC2=ext ...

r6 - 02 Jul 2012 - 09:17 by HenningFehrmann

AddNewUser

AddNewUser How to add a new user All this is now done by atlas_adduser.pl from our git repo! The remaining stuff here is done for the fictitious user foo BAR, an...

r6 - 19 Jun 2012 - 09:08 by CarstenAulbert

Internal-serialnumbers

Serial Numbers and MACs of our X4500 Name S/N xge0 e1000g0 e1000g1 e1000g2 e1000g3 s01 0746AMT037 0:c:fc:0:3f:53 0:14:4f:a6:d1:f4 0:14:4f...

r9 - 14 May 2012 - 14:34 by HenningFehrmann

ZFSBenchmarkTest

ZFS Send/Receive Performance Testing Since we want to backup and move users' home file systems regularly between Thumpers we want to have as much speed as poss...

r20 - 24 Apr 2012 - 12:26 by CarstenAulbert

S01BenchmarkSSD

Testing different zpool layouts on Thumper Local testing with iozone Essentially the tests were made with a single iozone run per file system, zfs compression wa...

r9 - 24 Apr 2012 - 12:26 by CarstenAulbert

IozoneArecaMirror

Iozone on Areca server Command line iozone a g 16G O n 32K y 32 q 32 i 0 i 2 Disk layout The disk layout for the four test was in RAID1 or RAID10 mode o...

r4 - 24 Apr 2012 - 12:26 by CarstenAulbert

ChannelBondingBenchmark

Channelbonding Benchmark Monitoring CPU,Interupts,Traffic (eth0,eth1,bond0) via dstat T1, T2, T3 are Testnodes n1668, n1669, n1670 (1) netperf Setup * a) S0...

r3 - 24 Apr 2012 - 12:25 by CarstenAulbert

ZFSioZone

IOZone ZFS performance benchmark On s01 with a ZFS layout like this one: atlashome raidz2 c0t0d0 c1t0d0 c4t0d0 c6t0d0 c7t0d0 c0t1d...

r3 - 24 Apr 2012 - 12:25 by CarstenAulbert

MyricomBenchmarking

Myrycom Benchmarking We received two myricom NICs for evaluation 03:00.0 Ethernet controller: MYRICOM Inc. Myri 10G Dual Protocol NIC (10G PCIE 8A) These netperf ...

r2 - 24 Apr 2012 - 12:25 by CarstenAulbert

BenchmarksBonnieX4500

Measured performance with this command line bonnie s 32768 d /path/to/dir u 1000 The results are # data server locally store03,32G,76714,99,358710,47,160723,3...

r2 - 24 Apr 2012 - 12:24 by CarstenAulbert

FfsbFileSystemsComputeNodes

Testing different file systems on Atlas compute nodes We are using the attached ffsb profiles for testing, these are just a first shot at the problem, but might p...

r6 - 24 Apr 2012 - 12:24 by CarstenAulbert

FortinetSwitches

serial numbers, MAC addresses and IP addresse FS100 serial number MAC address IP address status QTFCFI7470011 00:1b:24:be:0b:00 10.25.0.1 ...

r2 - 20 Apr 2012 - 08:39 by HenningFehrmann

AtlasBoincCondor

Atlas Boinc Condor Scheduling As Condor's fetchwork does not seem to work with dynamic slots, we are working on our own "scheduling" system for BOINC Initial tho...

r7 - 16 Apr 2012 - 14:39 by CarstenAulbert

IntroductionUsers

Atlas basic usage guide First things first Be nice to others, others should be nice to you as well :) Please read this aloud: I will be nice to other users, and ...

r16 - 05 Apr 2012 - 17:22 by CarstenAulbert

MoveToSqueeze

Move from Debian Lenny to Debian Squeeze Changes * updated packages from upstream Debian * Condor 7.6 with dynamic slots on most execute machines (exceptio...

r9 - 05 Apr 2012 - 13:15 by CarstenAulbert

AtlasTour

Small tour of Atlas Atlas is a computer cluster situated in the basement of a university building near the Max Planck institute in Hannover. Since the ceiling is ...

r8 - 29 Mar 2012 - 13:21 by CarstenAulbert

DataServer2011

Atlas Data Server 2011 Typical host names from Delta (ra01) Spec table Chassis Supermicro 3U Chassis PSU Motherboard X8DT6 network ...

r7 - 27 Mar 2012 - 14:21 by KatharinaIsleif

ComputeNode2008

Atlas Compute Node 2008 These Supermicro based machines were bought from Pyramid in 2008. Typical host names n0001 n1680 Spec table Chassis SC811T 300B (1...

r10 - 27 Mar 2012 - 14:21 by KatharinaIsleif

GPU

Atlas Compute Node 2010 Typical host names from Sysgen (gpu001 gpu065) Spec table Chassis Sysgen 4U Chassis PSU Emacs PSL 6C00V Motherboard...

r6 - 27 Mar 2012 - 14:08 by KatharinaIsleif

DataServer2008

Atlas Data Server 2008 Typical host names d10 d30 Spec table Chassis 836TQ R800B (4U Chassis) PSU Motherboard X7DVL network Intel ...

r6 - 27 Mar 2012 - 09:02 by KatharinaIsleif

HeadNode2008

Atlas Head Node 2008 Typical host names atlas1, atlas2, atlas3, atlas4 Spec table Chassis 836TQ R800B (4U Chassis) PSU Motherboard X7DVL ...

r8 - 27 Mar 2012 - 09:01 by KatharinaIsleif

HeadNode2009

Atlas Head Node 2009 Typical host names titan1, titan2 Spec table Chassis Sysgen 1U Chassis PSU SanAce80 Motherboard H8DM8 2 network ...

r6 - 23 Mar 2012 - 09:54 by KatharinaIsleif

ComputeNode

Atlas Compute nodes Compute Node 2008 In 2008 we bought 1680 Supermicro based machines from Pyramid in 2008, getting a total of 6720 2.4GHz compute cores, 13TB R...

r10 - 21 Mar 2012 - 10:36 by KatharinaIsleif

TestTopic8

For Squeeze all need to be performed in a chroot, i.e. run cowbuilder update basepath /var/cache/pbuilder/base.squeeze.amd64.cow/ # prepare environment apt ...

r6 - 15 Mar 2012 - 14:01 by CarstenAulbert

ShutdownPriority

Shutdown priorities The following list puts priorities on computers, equipment and other items of interest. Computers in racks, which will stay powered up, should...

r4 - 15 Mar 2012 - 09:41 by CarstenAulbert

MainPage

Main Categories * 24 Hour Test * Hannover LSC LOC * Cluster * Globus Grid Software * Tips Tricks * Stundenzettel * Internal:Main Page...

r3 - 02 Mar 2012 - 14:12 by ArthurVarkentin

WhereShallIPutLogFiles

Where shall I put my (Condor) log files? As always, the correct answer is: It depends. You can put your log files in your home, e.g. assuming your user name is MY...

r3 - 10 Feb 2012 - 14:35 by ArthurVarkentin

WindowsCiscoVPNClient

Windows Cisco VPN Client How to connect to the 10.117.0.0 network of Max Plank Institute with VPN The Cicso VPN Client with the pcf file calls AEI 10NET.pfc can ...

r4 - 10 Feb 2012 - 14:35 by ArthurVarkentin

XfsRepair

Repair a xfs filesystem A XFS file system can become corrupted due to a power cut, a kernel bug or something else. To repair it, please use a recent version of xf...

r4 - 10 Feb 2012 - 14:35 by ArthurVarkentin

VirtualboxAndUSBOnGutsy

Virtualbox and USB on gutsy Getting USB support working in virtualbox under Ubuntu gutsy 0) for general important info for virtualbox on gutsy, see FAQ: #91;31 ...

r4 - 10 Feb 2012 - 14:35 by ArthurVarkentin

VerifyingSMIMEmail

How to verify a S/MIME signed email (X.509) * save the email into a file * check that the certificate authority for this sender is known in your system, e.g...

r4 - 10 Feb 2012 - 14:35 by ArthurVarkentin

VideoCaptureBox

Video capture box How to use the video capture box we got from Golm: Some good documenation how to use VLC for capturing multiple devices and creating a mosaic wi...

r4 - 10 Feb 2012 - 14:35 by ArthurVarkentin

SshPasswordLess

Ssh password less Three steps to passless ssh (without ssh agent) ... 1 Use ssh keygen to generate the key pair ssh keygen t rsa ! do NOT use passphrase, ju...

r4 - 10 Feb 2012 - 14:35 by ArthurVarkentin

SuseCiscoVPN

Suse Cisco VPN Installing Cisco VPN Client in Suse If you want to connect with your suse to an VPN network, it's very simple. Now we install an VPN Client and ma...

r4 - 10 Feb 2012 - 14:35 by ArthurVarkentin

SvnToGit

In order to convert existent SVN repositories to git there are a few simple steps to take. First of all you'll need the following tools (if not already available)...

r4 - 10 Feb 2012 - 14:35 by ArthurVarkentin

SolarisSNMP

* install netsnmp pkg get i netsmp * create a configuration file /opt/csw/share/snmp/snmpd.conf rocommunity public disk /atlashome 5% load 12 6 3 syslocati...

r2 - 10 Feb 2012 - 14:35 by ArthurVarkentin

SshFS

How to mount your Atlas home on your computer Using sshfs it is quite simple but could be a little bit on the slower side of life. Prerequisites: 1. Make sure...

r2 - 10 Feb 2012 - 14:35 by ArthurVarkentin

SendingAutoSMS

How to send automatic SMS messages (via host postfix) Create a temporary file which looks like this: To: 49123456789 This is the SMS text and then move the fil...

r2 - 10 Feb 2012 - 14:35 by ArthurVarkentin

SolarisFMADM

How to read failure information on Solaris and how to "repair" old faults. Using fmdump one can look at the past error logs, while fmadm faulty will display fault...

r4 - 10 Feb 2012 - 14:35 by ArthurVarkentin

SolarisInstallPostfix

Superseed sendmail with postfix on Solaris 10 1. update blastwave packages: pkgutil u 1. install postfix: pkgutil i postfix 1. disable sendmail: scvadm...

r2 - 10 Feb 2012 - 14:35 by ArthurVarkentin

RestartGEOSEGDB

Restart GEOSegDB if service does not work anymore * log into geosegdb either as root/suser/ldbd (x509 certs) * assume ldbd identity * run db2start * a...

r2 - 10 Feb 2012 - 14:35 by ArthurVarkentin

RunningOctaveScriptsOnATLAS

Some things to be aware of when running Octave scripts on ATLAS: Octave path searching When an Octave script calls a non built in function, Octave will look thro...

r6 - 10 Feb 2012 - 14:35 by ArthurVarkentin

SamQFSExportTapes

How to export/import tapes from SL3000 Export tapes Explanatory task: tapes from the secondary copy of a file system should be exported * Log into metadata se...

r5 - 10 Feb 2012 - 14:35 by ArthurVarkentin

RecoverDeletedFiles

How to recover a file you accidentally deleted? If you $HOME is on a ZFS file system 1 you can easily retrieve files you deleted from an automatic snapshot creat...

r2 - 10 Feb 2012 - 14:35 by ArthurVarkentin

RedmineUsage

This basic tutorial describes the correct usage of the Redmine bugtracker. After the login you will be redirected to your own page which can be customized by usig...

r4 - 10 Feb 2012 - 14:35 by ArthurVarkentin

RescueDataFromBrokenDisk

How to rescue data from a broken disk If a disk is "only" throwing errors, but is not entirely dead yet, dd might help, but can cause a lot of grief. This recipe ...

r2 - 10 Feb 2012 - 14:35 by ArthurVarkentin

ProtectWebpagesWithHTAccess

How to protect a web page with .htaccess If you happen to need to protect a web page but not only for LSC usage, you need to perform the following steps: * Cre...

r2 - 10 Feb 2012 - 14:35 by ArthurVarkentin

RAIDControllerSoftware

How To Talk To RAID Controller ARECA CLI Download the command line interface (CLI) at this mirror and run chmod a x on the binary.

r4 - 10 Feb 2012 - 14:35 by ArthurVarkentin

OracleHSMCollectEvidenceForProblems

Collect evidence data for an Oracle case (HSM) Based on based experience we should perform the following before restarting samd or even rebooting the machine: ...

r3 - 10 Feb 2012 - 14:35 by ArthurVarkentin

PortForwarding

using iptables A gateway with two network cards conntects a LAN with WAN. This document describes, how to forward ports of nodes in the LAN to ports of the gatewa...

r4 - 10 Feb 2012 - 14:35 by ArthurVarkentin

MatlabUnderCondor

Running compiled Matlab under Condor Problems Multiple users on the same node When running compiled Matlab codes under Condor, you need to be aware that the def...

r5 - 10 Feb 2012 - 14:35 by ArthurVarkentin

Netboot

Netboot This is a simple description how to boot over a network using kernel on the remote server. Server side configuration To proivde net boot capabilities, yo...

r4 - 10 Feb 2012 - 14:35 by ArthurVarkentin

Lvm

What is LVM ? Note: This may answer the question, why editing the /etc config files does nothing. If you don't have a backup, you can re create the equivalent of ...

r4 - 10 Feb 2012 - 14:35 by ArthurVarkentin

MatlabInterferingLibraryPath

Dangers when sourcing the Matlab runtime environment Problem When sourcing the Matlab runtime environment (currently /opt/matlab/2008a/MCR/MCRSetup_R2008a_glnxa6...

r4 - 10 Feb 2012 - 14:35 by ArthurVarkentin

MatlabRemoteConnectionMacOS

Problems with X11 when connecting with MacOS X to headnodes If you experience problems running X programs, e.g. Matlab (even in command line mode), you might be h...

r3 - 10 Feb 2012 - 14:35 by ArthurVarkentin

LocalSshConfig

Local ssh configuration You can create shortcuts as well as special settings for hosts you want to connect to in the file $HOME/.ssh/config. The following lines c...

r3 - 10 Feb 2012 - 14:35 by ArthurVarkentin

LscPackages

The following packages are currently available in our repository: Main.CarstenAulbert 21 Aug 2008

r5 - 10 Feb 2012 - 14:35 by ArthurVarkentin

LigoDataFind

Using ligo_data_find (successor to LSCdataFind) The command line arguments are basically the same as before with LSCdataFind. One new feature is the P or no pro...

r2 - 10 Feb 2012 - 14:35 by ArthurVarkentin

LiveSystem

We have a pxe bootable live system to examine a node without touching the system on the harddrive. It is basically a self made chroot environment. usage * st...

r5 - 10 Feb 2012 - 14:35 by ArthurVarkentin

JumpstartSolaris

Jumpstart Solaris How To clone our Solaris Sun boxes: Create flash archive flarcreate n "s01 flash" c R / x /atlashome /atlashome/carsten/s01.flar Our conf...

r4 - 10 Feb 2012 - 14:35 by ArthurVarkentin

KeepX509CertificateAliveAfterLogout

Keep your X.509 certificate alive after logging out of the cluster On some occasions one needs a valid grid proxy to access data, query the file database using LS...

r4 - 10 Feb 2012 - 14:35 by ArthurVarkentin

HowToComputerIsOffline

HOWTO: Guideline to repair an offline computer Evaluate current status (remotely) 1. Try to log in via data network 1. Try to log in via mgmt network 1....

r2 - 10 Feb 2012 - 14:35 by ArthurVarkentin

ILOMUpdate

HOWTO Update ILOM Firmware cf. ILOM Howto Update ILOM Firmware * Log in in ILOM CLI and type "version" to check * Download new Firmware versions http://w...

r8 - 10 Feb 2012 - 14:35 by ArthurVarkentin

HardwareRepair

Main.HenningFehrmann 24 Jul 2008 abstract This page contains detected symptoms and the corresponding hardware problems. It is based on experiences. See the list ...

r13 - 10 Feb 2012 - 14:35 by ArthurVarkentin

HardwareResources

ATLAS Hardware Resources And Photo Gallery This is about the hardware resources that ATLAS is based on and related photos Computer node There are 1680 Computer n...

r21 - 10 Feb 2012 - 14:35 by ArthurVarkentin

GsiSSHonwindows

How to use GSI enabled ssh on Windows * Get a certificate * fill out the request form at Webinterface of GridKa CA * in a few days you will receive...

r5 - 10 Feb 2012 - 14:35 by ArthurVarkentin

GsisshOpenSSLError

Why do I get an openssl related problem when logging into a machine? If you see something like this: GSSAPI Error: GSS Major Status: Authentication Failed GSS Min...

r2 - 10 Feb 2012 - 14:35 by ArthurVarkentin

GlobusURLCopy

How to use gridftp In general the remote site should be running a gsiftp server which will accept your user credentials (X.509 grid certificate). The full syntax ...

r4 - 10 Feb 2012 - 14:35 by ArthurVarkentin

GangliaMonitoring

How to monitor the current usage of LSC clusters or Atlas? There are two nice web pages summarizing these information. First of all there is watchtower which is a...

r3 - 10 Feb 2012 - 14:34 by ArthurVarkentin

Fdisk

What is fdisk? fdisk is a command line partition manager available for a lot of platforms. Usage general fdisk l Lists the partition table fdisk /dev/...

r4 - 10 Feb 2012 - 14:34 by ArthurVarkentin

FixBootArchiveSolaris

How to fix a Solaris boot archive After an update it might happen, that the bootarchive is invalid/damaged. To fix this, boot into the failsafe mode (usually seco...

r2 - 10 Feb 2012 - 14:34 by ArthurVarkentin

FoswikiReprepro

How to create a pulling foswiki set up with reprepro Assuming you are already in the location where the repository shall live, perform these magic steps: mkdir co...

r4 - 10 Feb 2012 - 14:34 by ArthurVarkentin

Dos

This explains how to get FreeDOS working with TCP/IP and ssh. The Problem Sometimes, it is necessary to flash the BIOS, the IPMI card or to set the BIOS. For som...

r4 - 10 Feb 2012 - 14:34 by ArthurVarkentin

FaiLennyClasses

RFC: Classes list for FAI/Lenny The Etch installation scheme with our FAI server used one class for each type of node (NODE_COMPUTE, STORAGE, ...) but this is som...

r4 - 10 Feb 2012 - 14:34 by ArthurVarkentin

DebianSqueezeVDT

Getting VDT up and running on Debian Squeeze Problem description As of 2010 03 12 there is a new openssl version in squeeze which is somewhat incompatible with t...

r4 - 10 Feb 2012 - 14:34 by ArthurVarkentin

Debootstrap

Debootstrap It is sufficient to read the man page. To debootstrap from local deb mirror: debootstrap distribution dest. directory http://192.168.0.1:9999/deb...

r3 - 10 Feb 2012 - 14:34 by ArthurVarkentin

DebianPackaging

This documentation will briefly summarize how to build packages. At the time of writing this, we focused on packages for Debian etch and lenny in i386 and amd64 v...

r11 - 10 Feb 2012 - 14:34 by ArthurVarkentin

DebianSourcePackage

This is a short explanation of how to create debian source package. Assume you want to build package x.y.tar.gz. 1. Rename that one to package x.y.orig.tar.gz. 2....

r3 - 10 Feb 2012 - 14:34 by ArthurVarkentin

CondorDagManHowTo

Brief Condor dagman HowTo This small article will not get into any depth what DAGs are and will also not explain the terminology of Condor's dagman, for this plea...

r2 - 10 Feb 2012 - 14:34 by ArthurVarkentin

ConserverDocumentation

Conserver Conserver is a server/client program enabling to pool console connections. The upstream page is at http://www.conserver.com/, in Debian the packages are...

r5 - 10 Feb 2012 - 14:34 by ArthurVarkentin

DebianPackageBuild

How to create a Debian package? Tutorials: * Debian packaging tutorial by Lars Wirzenius * Debian packaging tutorial * Debian New Maintainer Guide Bad st...

r5 - 10 Feb 2012 - 14:34 by ArthurVarkentin

CondorBoincDynamicSlots

Condor, BOINC and dynamic slots As Condor's dynamic slots don't yet mix with "fetch work", we build the system around a dedicated, cron based system running on a ...

r2 - 10 Feb 2012 - 14:34 by ArthurVarkentin

ClusterMonitoring

ClusterMonitoring Description We need to monitor frequently various values in the cluster. See Ticket here: https://n0.aei.uni hannover.de/tracking/issues/show/...

r48 - 10 Feb 2012 - 14:34 by ArthurVarkentin

CompilingTempo2OnUbuntuAMD64

Compiling tempo2 on Ubuntu AMD64 The pgplot packages shipped with ubuntu are not consistently compiled using fPIC, which results in an unusable cpgplot wrapper l...

r4 - 10 Feb 2012 - 14:34 by ArthurVarkentin

CleanLocalScratch

Clean the local scratch space Sometimes you want to get rid off all temporary stuff you left on any compute node (e.g. you just finished a big search, all results...

r5 - 10 Feb 2012 - 14:34 by ArthurVarkentin

CleaningHomeDirectory

Cleaning your $HOME Quick steps for those who have no time to spare 1. Locate directory which you don't need right now but which produced a lot of small Condo...

r13 - 10 Feb 2012 - 14:34 by ArthurVarkentin

BuildFarm

How to create a build farm. Installation/Preparation Install the necessary base packages sudo aptitude install pbuilder cowdancer reprepro rebuildd * pbuild...

r4 - 10 Feb 2012 - 14:34 by ArthurVarkentin

BuildMatlab

How to build Matlab Before Installation You need: matlab installation cd ( or iso image ), pbuilder, installation key, license file to activate the product, ping...

r4 - 10 Feb 2012 - 14:34 by ArthurVarkentin

Bind9

updating the DB If you want to add names to the db (e.g. /etc/bind9/atlas.local.db), please make sure to follow these steps: (1) Increase serial number by using t...

r4 - 10 Feb 2012 - 14:34 by ArthurVarkentin

BobPackaging

Packaging on Bob This page documents how to use git buildpackage to build packages local and on the server. Quick recipe (only builds on the server) * insta...

r12 - 10 Feb 2012 - 14:34 by ArthurVarkentin

BadBlocksXFS

Badblocks on XFS Essentially the same as for ext 23 as shown on the smartmontools homepage. Please follow this example: smartctl reports bad sector # smartctl ...

r7 - 10 Feb 2012 - 14:34 by ArthurVarkentin

BadblocksPatch

Using Badblocks for testing hdds on the nodes one normally uses $ badblocks v p10 /dev/sdb which checks the disk. if it makes 10 clean runs it will exit. but if...

r7 - 10 Feb 2012 - 14:34 by ArthurVarkentin

BackupSVN

How to backup (and restore) a SVN repository Backup First create a hotcopy somewhere where enough free space is available: mkdir /tmp/hotcopy svnadmin hotcopy ...

r4 - 10 Feb 2012 - 14:34 by ArthurVarkentin

BadBlockTesting

How to find bad blocks on hard drives Testing hard drives with bad blocks: 1 smartctl a /dev/sdb 1 badblocks b 512 p 1 t random s w /dev/sdb 1 smar...

r5 - 10 Feb 2012 - 14:34 by ArthurVarkentin

AutomaticEnvironmentSetup

Automatic environment setup Introduction After the upgrade to Debian Lenny, we finally offer the psosiblity to automatically set up your environment. This is bei...

r5 - 10 Feb 2012 - 14:34 by ArthurVarkentin

AutomatingTelnet

Automating telnet Here a quick and dirty bash script, showing how you could automate some configuration tasks to be done in a menu based telnet session. E.g. to d...

r4 - 10 Feb 2012 - 14:34 by ArthurVarkentin

Apache

Apache Limit access to certain directories: Add AllowOverride AuthConfig in your config section in httpd.conf or where you define your servers. In the limit...

r4 - 10 Feb 2012 - 14:34 by ArthurVarkentin

GlusterFSTesting

Testing GlusterFS with data servers Brainstorm for i in 0 1 2 3 4; do blkid /dev/md$i awk "{print \$2 \" /data\" $i 1 \" xfs rw 0 2\"}"; done Main.CarstenAul...

NEW - 19 Jan 2012 - 12:32 by CarstenAulbert

GSTLALDependencyPackage

Building the GSTLAL Dependency Package for Lenny Preperation phase Start in a fresh location by issuing the following commands: mkdir p gstlal/gst deps 1.0/pack...

r3 - 10 Jan 2012 - 20:49 by CarstenAulbert

BackupStatS07

anamaria s07 2 0.0 1.00x s08 0.0 2011 12 16T05:18:01 UTC anderson s07 71 0.0 1.98x s08 0.0 2011 12 16T05...

NEW - 16 Dec 2011 - 05:18 by CarstenAulbert

BackupStatS09

amergl s09 1.55x s10 0.7 2011 12 16T05:18:01 UTC ecm s09 1.66x s10 2273.3 2011 12 16T05:18:02 UTC ...

NEW - 16 Dec 2011 - 05:18 by CarstenAulbert

BackupStatS11

acmeyer s11 1 0.0 1.00x s12 0.0 2011 12 16T05:18:01 UTC apetit s11 35596 34.7 1.02x s12 30.2 2011 12 16T...

NEW - 16 Dec 2011 - 05:18 by CarstenAulbert

BackupStatS04

ajw s04 16457429 973.0 1.37x s05 613.0 2011 12 15T17:18:03 UTC akm2129 s04 1 0.0 1.00x s05 0.0 2011 12 1...

NEW - 15 Dec 2011 - 17:18 by CarstenAulbert

BackupStatS06

acorsi s06 1 0.0 1.00x s07 0.0 2011 12 15T17:18:05 UTC andonis s06 1 0.0 1.00x s07 0.0 2011 12 15T17:18:...

NEW - 15 Dec 2011 - 17:18 by CarstenAulbert

BackupStatS08

NONE s08 1 0.0 1.00x s09 0.0 2011 12 15T17:18:02 UTC Rory.smith s08 1628865 1402.1 4.61x s09 340.0 2011 ...

NEW - 15 Dec 2011 - 17:18 by CarstenAulbert

BackupStatS10

acsearle s10 122375 2.0 1.00x s11 1.1 2011 12 15T17:18:00 UTC amelatos s10 1 0.0 1.00x s11 0.0 2011 12 1...

NEW - 15 Dec 2011 - 17:18 by CarstenAulbert

BackupStatS12

benk s12 9258073 4586.8 1.03x s13 4126.7 2011 12 15T17:18:02 UTC cbc s12 323101 68.0 1.14x s13 41.2 2011...

NEW - 15 Dec 2011 - 17:18 by CarstenAulbert

RackNodeNumbering

Rack numbering We only count the cooled rack space with numbers, the open racks are "counted" with letters. Please look at the following diagram: Compute Nodes T...

r11 - 15 Dec 2011 - 11:43 by HenningFehrmann

BackupStatS05

Aje8 s05 1 0.0 1.00x s06 0.0 2011 12 15T05:18:04 UTC ale87 s05 1 0.0 1.00x s06 0.0 2011 12 15T05:18:06 U...

NEW - 15 Dec 2011 - 05:18 by CarstenAulbert

BackupStatD04

HOST: d04 available: 2.58TB used: 6.78TB files: 24989199 DONE

NEW - 09 Dec 2011 - 11:11 by UnknownUser

BackupStatD05

HOST: d05 available: 1.14TB used: 8.23TB files: 63203 DONE

NEW - 09 Dec 2011 - 11:11 by UnknownUser

BackupStatD06

HOST: d06 available: 6.94TB used: 2.43TB files: 52640 DONE

NEW - 09 Dec 2011 - 11:11 by UnknownUser

BackupStatD10

HOST: d10 available: 15.65TB used: 9.64TB files: 284890 DONE

NEW - 09 Dec 2011 - 11:11 by UnknownUser

BackupStatD11

HOST: d11 available: 15.65TB used: 9.63TB files: 284140 DONE

NEW - 09 Dec 2011 - 11:11 by UnknownUser

BackupStatD14

HOST: d14 available: 0.00TB used: 9.37TB files: 276869 DONE

NEW - 09 Dec 2011 - 11:11 by UnknownUser

BackupStatD15

HOST: d15 available: 0.00TB used: 9.37TB files: 276439 DONE

NEW - 09 Dec 2011 - 11:11 by UnknownUser

BackupStatD19

HOST: d19 available: 0.00TB used: 9.37TB files: 276313 DONE

NEW - 09 Dec 2011 - 11:11 by UnknownUser

BackupStatD21

HOST: d21 available: 0.00TB used: 9.37TB files: 169414 DONE

NEW - 09 Dec 2011 - 11:11 by UnknownUser

BackupStatD22

HOST: d22 available: 0.00TB used: 9.37TB files: 168579 DONE

NEW - 09 Dec 2011 - 11:11 by UnknownUser

BackupStatD24

HOST: d24 available: 0.00TB used: 9.37TB files: 168572 DONE

NEW - 09 Dec 2011 - 11:11 by UnknownUser

BackupStatD27

HOST: d27 available: 0.00TB used: 9.37TB files: 169635 DONE

NEW - 09 Dec 2011 - 11:11 by UnknownUser

BackupStatD30

HOST: d30 available: 1.87TB used: 7.49TB files: 12820263 DONE

NEW - 09 Dec 2011 - 11:11 by UnknownUser

BackupStatD01

HOST: d01 available: 0.96TB used: 8.41TB files: 5338566 DONE

NEW - 09 Dec 2011 - 11:11 by UnknownUser

BackupStatD07

HOST: d07 available: 7.10TB used: 2.27TB files: 59028 DONE

NEW - 09 Dec 2011 - 11:11 by UnknownUser

BackupStatD16

HOST: d16 available: 0.00TB used: 9.37TB files: 276919 DONE

NEW - 09 Dec 2011 - 11:11 by UnknownUser

BackupStatD18

HOST: d18 available: 0.00TB used: 9.37TB files: 276719 DONE

NEW - 09 Dec 2011 - 11:11 by UnknownUser

BackupStatD20

HOST: d20 available: 2.47TB used: 6.90TB files: 112397 DONE

NEW - 09 Dec 2011 - 11:11 by UnknownUser

BackupStatD25

HOST: d25 available: 0.00TB used: 9.37TB files: 169076 DONE

NEW - 09 Dec 2011 - 11:11 by UnknownUser

BackupStatD26

HOST: d26 available: 0.00TB used: 9.37TB files: 168077 DONE

NEW - 09 Dec 2011 - 11:11 by UnknownUser

BackupStatD09

HOST: d09 available: 4.04TB used: 5.33TB files: 88120 DONE

NEW - 09 Dec 2011 - 11:11 by UnknownUser

BackupStatD17

HOST: d17 available: 0.00TB used: 9.37TB files: 276361 DONE

NEW - 09 Dec 2011 - 11:11 by UnknownUser

BackupStatD28

HOST: d28 available: 0.00TB used: 9.37TB files: 169080 DONE

NEW - 09 Dec 2011 - 11:11 by UnknownUser

Cluster

Cluster HOWTOs * Configuration hints and examples Hardware * Hardware test configurations * ClusterNetwork * Testrack * BIOS * Cluster Hall ...

r2 - 25 Nov 2011 - 12:44 by CarstenAulbert

DebainStatusBobRepo

Current LSCsoft repo on bob Main.CarstenAulbert 21 Oct 2011

r2 - 25 Nov 2011 - 12:34 by CarstenAulbert

SpecialIPs

IP Scheme for Servers Special IPs This is an IP Scheme for special IPs. For an IP Scheme of the Management and Data Network, refer here. There are separate tabl...

r10 - 24 Nov 2011 - 14:54 by CarstenAulbert

BackupStatS03

EAH s03 2 0.0 1.00x s04 0.0 2011 11 12T05:18:01 UTC apearlma s03 1 0.0 1.00x s04 0.0 2011 11 12T05:18:02...

NEW - 12 Nov 2011 - 05:18 by CarstenAulbert

PhotoCollection

r9 - 02 Nov 2011 - 13:04 by HenningFehrmann

BackupStatS02

Cinthia1212 s02 1 0.0 1.00x s03 0.0 2011 10 28T16:18:06 UTC ahnitz s02 1 0.0 1.00x s03 0.0 2011 10 28T16...

NEW - 28 Oct 2011 - 16:18 by CarstenAulbert

Jumpstart

jumpstart A jumpstart server provides the information and configuration used to install other nodes. It serves tftp requests to provide a kernel and installatio...

r3 - 18 Oct 2011 - 14:39 by HenningFehrmann

CornellSpeedTest

Cornell Speed Test Very brief test pulling /dev/zero from gridftp1.cac.cornell.edu to atlas2:/dev/null (units are bytes for tcp blocksize and MByte/s for speeds):...

r3 - 14 Sep 2011 - 12:45 by CarstenAulbert

PackageMathematica

Preperation Start pbuilder/cowbuilder environment and copy the installer to / inside this environment. aptitude install menu xdg xdg utils mkdir p /usr/share/ico...

r3 - 14 Sep 2011 - 12:43 by CarstenAulbert

CowBuilderCreate

To simply create a nice cowbuilder environment for lenny within atlas just use: cowbuilder create distribution=lenny debootstrapopts arch=amd64 basepath /var...

r2 - 14 Sep 2011 - 12:42 by CarstenAulbert

ClusterRoomCleaningSchedule

Cluster room cleaning schedule This page is about keeping all cluster related rooms in an orderly state, if you have suggestions for modifications, please contact...

r4 - 14 Sep 2011 - 12:38 by CarstenAulbert

FaiInstallation

what happens before the FAI installation * client * server * provides * * admin action * NICs do a DHCP request (BIOS default ) DHCP server IP addre...

r12 - 14 Sep 2011 - 12:25 by CarstenAulbert

CleaningFormDraft

Main.AlexPost 05 Sep 2011 * WeeklySchedule.pdf: WeeklySchedule.pdf

r2 - 14 Sep 2011 - 12:22 by CarstenAulbert

FortinetTroubleShooting

This side contains a list of discovered network problems, corresponding tools and possible solution. Wrong MAC address port assignment symptom The node is not...

r16 - 25 Mar 2011 - 12:43 by HenningFehrmann

ServerIPLenny

IP Scheme for Servers (Lenny) This is an IP Scheme for Lenny Servers. For an IP Scheme of the Management and Data Network, refer here. For a scheme of Etch server...

r54 - 11 Feb 2011 - 10:29 by HenningFehrmann

ServerIPSqueeze

IP Scheme for Servers (Squeeze) This is an IP Scheme for Squeeze Servers. For an IP Scheme of the Management and Data Network, refer here. For a scheme of Etch se...

r35 - 03 Feb 2011 - 09:30 by HenningFehrmann

ServerIPetch

IP Scheme for Servers (Etch) This is an IP Scheme for Servers. For an IP Scheme of the Management and Data Network, refer here. For a scheme of Lenny Servers, re...

r12 - 28 Jan 2011 - 14:38 by ArthurVarkentin

IPScheme

IP Scheme The goal is to create a scheme which eases daily life. IP mapping should be more or less straightforward and extensible. For servers look at: * indi...

r84 - 28 Jan 2011 - 11:12 by HenningFehrmann

LSCSoftDebian

Overview of Topics on LSC Software packaging for Debian * Packaging Howto 1 * Packaging Howto 2 * How to build personal lal/lalapps on ATLAS * How to ...

r7 - 18 Jan 2011 - 06:23 by CarstenAulbert

ScratchSpaceScrubbing

Scrubbing local scratch space Scrubber Design Imagine a local partition which is quite crowded and needs to be cleaned. Cleaning should be performed based on fil...

r3 - 03 Jan 2011 - 10:14 by CarstenAulbert

AtlasServerSummary

Summary of Atlas Servers/Services If you want a quick overview, please refer to our server matrix page, otherwise just read on. External machines/services Head ...

r7 - 07 Dec 2010 - 09:28 by CarstenAulbert

AtlasServerMatrix

Atlas Server Matrix This matrix tries to summarize the current situation of Atlas, i.e. which server are available name cores freq RAM disk CE CS ...

r3 - 07 Dec 2010 - 06:37 by CarstenAulbert

HOWTOs

Collection of HowTos OS hangs Try to reset node. OS hangs, even after reset Possible causes 1. hdd broken look if everything is well wired, change hdd, ma...

r7 - 30 Mar 2010 - 12:47 by ArthurVarkentin

ServerStatus

How full are our servers? Sun Thumper ($HOME) Data servers (S5, S6, ...)

r3 - 16 Mar 2010 - 07:01 by CarstenAulbert

BrokenHardware

This page presents the list of faulty hardware. See and add symptoms. Please add dates here, when the problem occurred and when it was fixed. Henning or Carsten w...

r262 - 04 Mar 2010 - 17:02 by HolgerPetzholdt

LogcheckMailAndRelatedScripts

Logcheck mail locations, related scripts and other mail locations on postfix server Log mail location on postfixserver logadmin account 1. Normal logcheck mail...

r16 - 17 Feb 2010 - 12:39 by XiaomeiN

BackupStatusHome

Main.CarstenAulbert 22 Jan 2010

r4 - 28 Jan 2010 - 18:05 by CarstenAulbert

X4500-Case72065766

Case 72065766 Opened 2009 12 01 Synopsis After running zpool scrub on s13 a vdev was marked degraded due to excessive read errors. After exchanging the supposedl...

NEW - 01 Dec 2009 - 07:28 by CarstenAulbert

X4500

Sun Fire X4500 The Sun Fire X4500 Servers (nick named "Thumper") are the heart of our $HOME. All user data reside on these boxes. To ensure that there are as few ...

r28 - 01 Dec 2009 - 07:25 by CarstenAulbert

CustomPackageUpdateSensors

Quellpaket update sensors Binärpaket update sensors Description Updates the database if sensor values change This package provides the infrastructure. Dependen...

r2 - 25 Nov 2009 - 12:15 by AlexPost

CustomPackageComputerdb

Quellpaket computerdb Binärpaket computerdb Description The atlasdb/coputerdb to monitor the nodes. Dependencies ruby Maintainer Henning Perl Alexander Post ...

r2 - 25 Nov 2009 - 12:14 by AlexPost

CustomPackageRails

Quellpaket rails Binärpaket rails Description MVC ruby based framework geared for web application development Rails is a full stack, open source web framework i...

r2 - 25 Nov 2009 - 12:14 by AlexPost

CustomPackageScam

Source Package scam Binary Package scam Description: Simple Cluster Administration Management A Web application to manage and administer a cluster Dependenci...

r2 - 25 Nov 2009 - 12:14 by AlexPost

SunThumperBackup

Backup Strategy for users' $HOME Rolling snapshots Each thumper will loop over all users' file systems and create a new snapshot every 6 hours. Old snapshots wil...

NEW - 25 Nov 2009 - 09:32 by CarstenAulbert

CMCControlUnit

The CMC control units are used to monitor values of different sensors in the Rack or in the LCP. They can also be used to set critical values. As soon as a sensor...

r3 - 18 Nov 2009 - 13:29 by HenningPerl

LocalScratch

Local scratch on nodes local partitions Storing data locally on the nodes is possible everywhere. Please remember you are free to log into any node manually (rsh...

r4 - 08 Nov 2009 - 16:10 by CarstenAulbert

MassCp

Location The script is currently only placed on atlas1.atlas.aei.uni hannover.de. Syntax /usr/local/bin/masscp The script has to be started with the path informa...

NEW - 15 Sep 2009 - 10:26 by HenningFehrmann

ComputeNodeRack23

Table of contents Schema for compute node rack rack #23 height unit usage OS eth0 eth1 eth2 eth3 42 sysgen GPU01 Intel based ...

r8 - 08 Sep 2009 - 14:12 by CarstenAulbert

BenchmarkTests

Benchmarks Network Disk Performance ffsb We are also using ffsb to simulated different workloads. The following tests were performed so far: * Testing diffe...

r6 - 19 Aug 2009 - 14:00 by CarstenAulbert

MiroslavShaltev

Package table for stable: Package Version Etch i386 Etch amd64 Lenny i386 Lenny amd64 lue 1.13 1.13 3lscsoft3 1.13 3lscsoft3 e.c. e.c. ...

r11 - 02 Jul 2009 - 13:57 by MiroslavShaltev

DebianPackagingStatus

NOTE: these are the Debian PACKAGE MAINTAINER pages! If you are looking for USER instructions to install LSCSoft on Debian, please visit https://www.lsc group.p...

r81 - 02 Jul 2009 - 13:56 by MiroslavShaltev

BACnet

BACnet BACnet is a facility management protocol. The 'outside cooling' uses BACnet over IP. The Protocol is transmittet via UDP packets. BACnet4linux The BACnet4...

r2 - 24 Jun 2009 - 12:48 by JenniferSchenke

LinuxChannelbondingVLANworkaround

A introduction to Channelbonding can be found here. Description Why? Round robin is the only way to get more than the speed of a single interface for a single T...

r2 - 24 Jun 2009 - 10:52 by JenniferSchenke

ProCurveSwitch2900

ProCurve Switch 2900 Specification Visit http://www.hp.com/rnd/products/switches/ProCurve_Switch_2900_Series/overview.htm for more detailed information on the 29...

r2 - 23 Jun 2009 - 14:03 by JenniferSchenke

ProCurveSwitch1800

ProCurve Switch 1800 Specification Visit http://www.hp.com/rnd/products/switches/ProCurve_Switch_1800_Series/overview.htm for more detailed information on the 18...

r2 - 23 Jun 2009 - 13:59 by JenniferSchenke

Procfs

Procfs There is an excellent summary of the /proc file system available #91;2 #93;.

r2 - 23 Jun 2009 - 13:49 by JenniferSchenke

SMART

"S.M.A.R.T" is for "Self Monitoring, Analysis and Reporting Technology". The SMART protocols stores disk sensor values and event counters on a special area of the...

r5 - 23 Jun 2009 - 13:32 by JenniferSchenke

Scheduler

Currently Linux knows four different schedulers: CFQ CFQ, also known as "Complete Fair Queuing", is an I/O scheduler for the Linux kernel which was written by Je...

r2 - 23 Jun 2009 - 13:18 by JenniferSchenke

SNMP

SNMP http://en.wikipedia.org/wiki/Snmp Standard tools: snmpwalk, snmpget/set mrtg Maybe also: Nagios http://www.zenoss.com/ general Rack We are using SNMP to re...

r2 - 23 Jun 2009 - 12:52 by JenniferSchenke

Consoles

Root shell on tty9 On startup there is always an open root shell for maintenance on tty9. Feel free to use it carefully!. /var/log/messages on tty11 On tty11 you...

r2 - 23 Jun 2009 - 09:38 by JenniferSchenke

Hostnames

Hostnames * The name of a node is n abcd . where abcd is a number between 0001 and 1340. * The data server are called d ab where ab runs from 01 to 31. ...

r2 - 22 Jun 2009 - 13:58 by JenniferSchenke

ServicesOffered

Services we want/need to offer Please write down a list of services which we want/need to host along with the contact person who requested this and a brief descri...

r2 - 22 Jun 2009 - 13:51 by JenniferSchenke

Treiberkonzept

Treiberkonzept The university gets alerts and reacts acording to following scheme: smoke alert check the room and inform the MPI in the case of fire of dense s...

r2 - 22 Jun 2009 - 13:30 by JenniferSchenke

WovenSwitch

You can connect to the switch directly via the serial interface, using minicom . To disable tagging on all interfaces, enter (in Configure mode): switchport all...

r2 - 22 Jun 2009 - 13:19 by JenniferSchenke

CoreNetwork

outdated did not work. The core network consists of a WovenSystems EFX1000 with 144 10Gb/s network ports. Main.CarstenAulbert 02 Feb 2009 * EFX1000 front i...

r3 - 22 Jun 2009 - 13:02 by JenniferSchenke

RackSchemes

Rack schemes Our racks are equipped like this: row 5 4 3 2 1 rack type content rack type content rack...

r3 - 16 Jun 2009 - 10:23 by JenniferSchenke

CustomSoftwarePackages

List of software packages we maintain ourselves * lm sensors config atlas * update sensors * scam * rails * computerdb

r3 - 06 May 2009 - 08:45 by HenningPerl

CustomPackageLmSensorsConfigAtlas

lm sensors config atlas Description configuration for lm sensors for the atlas cluster Will install config file '/etc/sensors.conf' and add kernel modules to '/e...

r2 - 30 Apr 2009 - 17:13 by HenrikKroeger

ComputeNodeRack24

Management Rack #24 height unit usage 42 monitor 41 nis 40 postfix 39 atlasdb 38 nut 37 Meinberg GPS ...

r3 - 16 Apr 2009 - 07:08 by CarstenAulbert

EDACMemorySetup

EDAC memory setup On one of our file servers based on Supermicros X7DVL which has 6 memory seats labeled {1,2}{A,B,C}. Unfortunately, one needs two DIMMs (showing...

NEW - 14 Apr 2009 - 08:39 by CarstenAulbert

RackSchemesComputeNode

Schema for compute node rack height unit usage 42 compute node 41 compute node 40 compute node 39 compute node 38...

NEW - 06 Apr 2009 - 13:36 by CarstenAulbert

CableLabelling

Labeling the network cables Network cables are labeled according to this scheme: LABEL TYPE Mxx Management uplinks from Allied Telesys switch in rac...

NEW - 17 Feb 2009 - 13:29 by CarstenAulbert

OpenCloseIotest

Measuring open/close IO performance Local/NFS performance measured 2009 02 06 cycles/s h1 h2 h4 remarks local 59282 3586 603...

r4 - 16 Feb 2009 - 07:43 by CarstenAulbert

H2Problems

Problems with h2 h2 is the machine which was up first and thus users like it and feel homely there; h1 came later and takes a bit of the load, but the main load i...

r2 - 12 Feb 2009 - 08:41 by CarstenAulbert

GangliaPatch

A problem with the webinterface of the ganglia monitoring service is that really every single is shown at the first page. This can be really annoying in a big clu...

NEW - 11 Feb 2009 - 10:54 by HenrikKroeger

SunFireX4500

Sun Fire X4500 We have got a Sun Fire X4500 , a dual Opteron storage server with 48 SATA 500GB drives from Sun Microsystems. Installation It weights about 80kg...

r4 - 06 Feb 2009 - 14:22 by HenningFehrmann

SpecialNodes

Main.CarstenAulbert 08 Jan 2009 Special nodes The following nodes are considered special, please help to keep this list up to date! node name assigned job...

r2 - 31 Jan 2009 - 13:48 by MiroslavShaltev

WebTopicCreator

* Local VIEW_TEMPLATE = WebCreateNewTopic

r2 - 28 Jan 2009 - 16:30 by CarstenAulbert

DataSpray

Principle The node number a particular file lives on is determined by its filename: take the first six digits of the md5sum of the name, take this as a hex number...

r45 - 23 Jan 2009 - 10:58 by BerndMachenschalk

X4500-Case70469164

Main.CarstenAulbert 31 Dec 2008 After adding extra nodes in December 2008 we discovered that the SUN servers sent out a continuous stream of ARP requests into the...

NEW - 31 Dec 2008 - 09:35 by CarstenAulbert

Netconsole

Netconsole To enable netconsole on a node, just insert the 'netcosole' module as follows (just change node_ip): modprobe netconsole netconsole=4444@node_ip/eth1,5...

r2 - 16 Dec 2008 - 14:33 by HenningPerl

DebianLscsoftPersonalLal

This is how to build and install personal lal/lalapps on ATLAS both use the global available libmetaio8 lalapps uses the fresh installed personal lal Insi...

r2 - 02 Dec 2008 - 13:41 by MiroslavShaltev

BenchmarksBonnieHeadnode

Runnning bonnie on a head node in various configurations Headnode parts: * dual socket, quad core CPUs (E5342) * 16 GB RAM * Areca 1261ML * 4 or 8 H...

r14 - 02 Dec 2008 - 08:53 by CarstenAulbert

WebTopicViewTemplate

r2 - 17 Nov 2008 - 12:04 by HenningPerl

AptRepository

apt repository abstract The apt repository is local debian repository containing self made debian packages. installation call aptitude install reprepro instal...

r6 - 13 Nov 2008 - 14:36 by HenningFehrmann

Server

Abstract This documentation describes server, the corresponding functions and the location. Table of Server name location function * ip * FAI manage...

r2 - 31 Oct 2008 - 15:16 by HenningFehrmann

BackupOverview

All times given are in UTC, usage and backup sizes in full GByte. If the last backup was done within the past 48hrs the times are green, otherwise red. Main.Ca...

r2 - 27 Oct 2008 - 10:57 by CarstenAulbert

Condor

Condor Condor High Throughput Computing System is a software framework for managing workload on a cluster of computers. It is some kind of batch system, that di...

r2 - 22 Oct 2008 - 10:07 by MiroslavShaltev

CondorDAG

abstract CondorDAG stays for Directed Acyclic Graph Condor DAG is a scheme to start jobs in a particular order. The start of subsequent jobs depends on the exit c...

NEW - 21 Oct 2008 - 10:11 by HenningFehrmann

ClusterUpgrade

Main.HenningFehrmann 17 Oct 2008 Todo installing the new nodes We get 336 new nodes and fill all together 8 Racks EFX recabeling Each TRX has only three uplink...

r14 - 17 Oct 2008 - 14:19 by HenningFehrmann

X4500FreshInstall

Fresh install of a X4500 Files to add/overwrite to the default installation root root/.ssh root/.ssh/id_rsa # define local key root/.ssh/authorized_key...

r2 - 16 Oct 2008 - 12:08 by HenningFehrmann

MTAOnNodes

MTA on nodes Following are some MTA candidates for nodes nullmailer Nullmailer is a replacement MTA for hosts, which relay to a fixed set of smart relays. It is ...

r2 - 18 Sep 2008 - 08:47 by XiaomeiN

DriveFailure

What to do if a drive failure occurs? First signs A drive failure might be reported via fmdump or zpool status, e.g. # fmdump v Jul 16 22:18:52.7769 f52c874e 91...

r6 - 29 Aug 2008 - 12:29 by CarstenAulbert

DataServer

Main.CarstenAulbert 05 Jun 2008 Data Servers Currently we have 30 data servers up and running. Within the cluster you can get these file areas automounted via /a...

r11 - 26 Aug 2008 - 13:43 by CarstenAulbert

InstallMatlabManually

Manual Matlab install 1 Grab copy of the ISO file from AEI's internal fileserver (ToDo: where) 1 Mount image via loopback on computer where it should be ins...

r4 - 26 Aug 2008 - 07:52 by CarstenAulbert

Flar

flar A flar image contains the solaris system archive similar to tar balls. It can be used to make a system snapshot and install it on other machines. Generatio...

r2 - 25 Aug 2008 - 12:00 by HenningFehrmann

HomeFileSystem

$HOME file systems Where does the data live? We currently have 12 Sun Thumper X4500 which are used to store users' $HOME file systems. The users are distributed ...

NEW - 19 Aug 2008 - 09:56 by CarstenAulbert

X4500-diskUnconfigured

How to configure a replaced disk? Sometimes after replacing a disk the disk is in the following state: sata2/4 unknown connected un...

r2 - 14 Aug 2008 - 12:48 by CarstenAulbert

ClusterFileSystem

Cluster File Systems A long list of what file systems are available can be found on Wikipedia, for us these file systems seem to be interesting enough for further...

NEW - 11 Aug 2008 - 07:55 by CarstenAulbert

SunServerUserMapping

How to determine which user to put onto which Sun server The idea is pretty simple and should work well. From our 12 Sun servers currently set up for users, we wi...

r9 - 05 Aug 2008 - 06:50 by HenningFehrmann

InrushCurrentLimiter

We have got a power strip from Rittal and Bürger Elektroniks with build in inrush current limiter. For a single node the inrush current limiter works as it is sup...

r5 - 24 Jul 2008 - 10:54 by AlexPost

OscilloscopeUsage

In order to manage Issue #56 there is some basic knowledge required to use the TDS 3014B. So let's get started: It is highly recommended that you use the external...

r6 - 23 Jul 2008 - 09:08 by AlexPost

X4500-MTU9000-Neterion

Recover from Neterion NIC running at low MTU size Just run this: ifconfig xge0 unplumb # ifconfig xge1 unplumb cd /root/xge 2.0.7.6641 solbin/ ./install.sh jumbo ...

NEW - 18 Jul 2008 - 14:35 by CarstenAulbert

20080714

Working Schedule for UPS test on July 14th, 2008 The "Plan" This is a rough plan of actions which need to be performed on that day (all times are CEST=UTC 0200) ...

r19 - 11 Jul 2008 - 13:19 by CarstenAulbert

TechnicalBlurb

Technical stuff Cabling issues Head nodes Each head node has 6 network connections on its back ...

NEW - 10 Jul 2008 - 16:58 by CarstenAulbert

AvailableData

Data available via LDR Our LDR server is named ldr.aei.uni hannover.de (externally) and ldr.atlas.local (internally). You may need to use this environment variabl...

NEW - 10 Jul 2008 - 12:47 by CarstenAulbert

LDR

AEI/Han LDR box is 130.75.117.101 with user hanrobot. LDR is installed under /srv/LDR and before using it, you must source the appropriate files and also set the ...

r3 - 10 Jul 2008 - 12:38 by CarstenAulbert

X4500-usermappingscheme

User mapping scheme This is the first idea, it should already work nicely, but we may need to adjust it in the future. Initial user mapping We will start with 10...

NEW - 07 Jul 2008 - 10:19 by CarstenAulbert

X4500-Case38104140

Case38104140 Sun in principle acknowledged this error, but said this is Neterion's business. Neterion is working to reproduce this error. I love hotline ping pong...

r2 - 26 Jun 2008 - 15:17 by CarstenAulbert

ErrorMessageCondorHold

Condor Job on Hold How to get the output: condor_q awk '/ H / {print $1}' xargs n 1 condor_q long grep HoldReason Error: Failed to open file Error Message...

r3 - 26 Jun 2008 - 10:16 by CarstenAulbert

ErrorMessages

Error messages and their (likely) way of fixing them Hardware Software You can find a very short description of the symptoms here, for more information, follow ...

r2 - 26 Jun 2008 - 06:42 by CarstenAulbert

AtlasDistributedFiles

Though ATLAS has strong data servers, accessing files fon the local harddrive of the nodes is much faster, and given that you could read files in parallel accessi...

r4 - 25 Jun 2008 - 14:01 by OliverBock

ThumperSNMP

SNMP OIDs on SunFire X4500 Here some OIDs for Thumper Events: FAN front: OK=7 FAIL=5 enterprises.42.2.70.101.1.1.2.1.3.29 FAN 0 enterprises.42.2.70.101.1.1.2.1.3....

r6 - 25 Jun 2008 - 12:08 by SebastianGreschner

UsefulItems

Usefull tools making your life easier dsh the distributed/dancer shell Introduction The dancer shell is very usefull to run identical commands on the whole cl...

r3 - 18 Jun 2008 - 16:32 by CarstenAulbert

X4500_zpoolconfiguration

Possible zpool configurations In the standard setup there are two system disks (either on controller c5 or c6 depending if one installs the box via a USB device ...

r7 - 18 Jun 2008 - 12:14 by HenningFehrmann

X4500-system_disk_mirror

Mirroring system disks Right now jumpstart fails to create mirrored system on our thumpers (see according Case ID). Thus it is required to create the mirror after...

NEW - 18 Jun 2008 - 08:11 by CarstenAulbert

X4500-Case38101108

Case ID38101108 X4500 reboots infinitely when jumpstarting with mirror setup We encountered a problem, that when setting up a mirrored system disk during jumpst...

r2 - 13 Jun 2008 - 08:36 by CarstenAulbert

X4500_ZFS_NFS

Performance problems with X4500 using ZFS with NFSv3 When moving a large number of small files onto our X4500 boxes we found very bad performance numbers: Job ...

NEW - 12 Jun 2008 - 17:25 by CarstenAulbert

Condor-LocalConfiguration

This is the condor local configuration used on ATLAS global HOSTNAME=$(hostname) RELEASE_DIR=/opt/condor LOCAL_DIR=/local/condor.$(hostname) CONDOR_ADMIN=root@lo...

r2 - 12 Jun 2008 - 17:17 by CarstenAulbert

SunDocumentation

Here some links to useful Solaris documentation: Thumper * Sun Fire X4500 Server Administration Guide * Specifications ZFS * Manpage zfs * Tips for ...

r2 - 11 Jun 2008 - 11:42 by SebastianGreschner

DocumentationOnMakingFakeDataContainingSignalsFromPulsarsInTightBinaries

Documentation on making fake data containing signals from pulsars in tight binaries 1. REDIRECT Making fake data containing signals from pulsars in tight binar...

r2 - 06 Jun 2008 - 13:37 by ReinhardPrix

SSL

SSL We have now the Wiki as well as the trac system working with http over SSL. From now on, all traffic should be encrypted and one should be forwarded to port 4...

r2 - 28 May 2008 - 14:35 by HenningPerl

OpenSolaris

(Open)Solaris Solaris is an operating system desinged by Sun Microsystems. In 2004 it has been open sourced in the OpenSolaris project. * Solaris overview ...

NEW - 14 May 2008 - 22:47 by Sebastian

BooksForAEIHannover

Books for AEI Hannover Wishlist of books to order for AEI Hannover Library * Robert M. Wald, "General Relativity", Library * Sivia, Skilling, "Data Analysi...

NEW - 06 May 2008 - 14:41 by Repr

WikiEvaluationForPulgroup

Wiki Evaluation for pulgroup or getting away from the evil elog ... Motivation and overview There are various well known problems with our current pulgroup page...

NEW - 05 May 2008 - 07:54 by Repr

Rrdtool

useful tricks Print maximum number of errors (output from EFX, data is on c0 under /scr/EFX/RRD/db): ls err*rrd xargs i rrdtool graph /tmp/test DEF:err_r={}:e...

NEW - 23 Apr 2008 - 09:57 by Carsten

SMSWarningConditions

SMSWarningConditions This is also a todo list which needs to be implemented. A SMS is send out to a list of numbers whenever a email is send to sms #64;postfixser...

NEW - 22 Apr 2008 - 08:03 by Carsten

UPS

Hardware MGE Galaxy 6000 ups.mfr: MGE UPS SYSTEMS ups.model: Galaxy Single UPS ups.serial: 49EH29101 ups.date: 2008/03/24 ups.firmware: V1.GAU305S300IC303 ups.fi...

NEW - 20 Apr 2008 - 09:51 by Shaltev

Channelbonding

Category:Kernel Category:Network Finally the Channelbonding Documentation has been rewritten. I hope its new structure helps answering the questions! Some illustr...

NEW - 09 Apr 2008 - 12:21 by Carsten

FileStagingArea

File Staging Area File containing a list of missing Results from S5R1: /MI_missingS5R1a.txt.bz2 Einstein@Home Talk for APS 2008: /EinsteinAtHomeS4R2 G080189...

NEW - 02 Apr 2008 - 18:55 by Repr

Snmptrap

SNMPTRAPD In order to receive traps on has to install snmpd on a node. Edit the /etc/default/snmpd file and set the TRAPRUN flag to yes . You will find trap ...

NEW - 31 Mar 2008 - 08:11 by Fehrmann

ToDoUS

PLEASE DO NOT REMOVE ANY ITEM FROM THIS LIST. IF IT IS COMPLETE, THEN PLEASE MOVE IT TO THE END OF THE LIST UNDER "DONE". TO DO ClusterRoom Order fan trays ...

NEW - 26 Mar 2008 - 13:28 by Carsten

ToDoRittal

ToDoRittal * Steckdosenleisten blockieren horizontale HE * 6 Rackbeschriftungen sind falsch herum * 2 Rackbeschriftungen fehlen * LCP CMC software um Lü...

NEW - 19 Mar 2008 - 15:56 by Fehrmann

MeinbergGPSNTP

Configuration settings Change the configuration by using setup when logged in via ssh Increase ARP cache for this box The box comes with Linux kernel defaults, i...

NEW - 17 Mar 2008 - 14:35 by Carsten

FlatFstatMetric

Flat Fstat Metric LOGBOOK 15:48, 16 March 2008 (CET) Problematic result of old FstatMetric code is seen by running compareMetrics.m, and plotting the result usi...

NEW - 16 Mar 2008 - 18:29 by Repr

NIS

NIS Developed at SUN as "Yellow Pages" (see name of commands,configuration files) is a client server directory service protocol. Visit a NIS HOWTO Configuration ...

NEW - 13 Mar 2008 - 09:05 by Fehrmann

NUTTunnel

NUTTunnel This script should enable you to tunnel UDP connections from .102 to the UPS in the prototype hall: # cat nut tunnel.sh #!/bin/bash # this is ugly ...

NEW - 12 Mar 2008 - 09:06 by Oliver

DNSScheme

DNS scheme The internal domain is atlas.local (managed by us), external domain might be atlas.uni hannover.de (managed by RRZN) Nodes Nodes have three networking...

NEW - 04 Mar 2008 - 12:46 by Carsten

SecondTestComputeNodes

SecondTest Compute Nodes A script is run for basic testing, here are the current findings: NodeError messages n0001 Permission denied. n0002 Permission denied. n0...

NEW - 02 Mar 2008 - 15:33 by Carsten

ManagementSwitches

ManagementSwitches Test on two kinds of management switches AlliedTelesis AT 750/48 and Linksys SRW248, both have 48 Ports 10/100T and 4 gigabit uplink ports. Al...

NEW - 24 Feb 2008 - 15:29 by Xm

CoolingSystem

Description Observations low load on the system 1. When the cooling system (DC4200 and Rack) are set to 'auto' on most of their switches and the thermal load...

NEW - 14 Feb 2008 - 16:33 by MatthiasLInden

ClusterchangesSeismic

Monday 2008 02 04 30 nodes in rack down at about 16:00 UTC All computers and switches were off by about 16:11 UTC Tuesday 2008 02 05 Computers were started at th...

NEW - 14 Feb 2008 - 08:19 by Carsten

PostgreSQL

PostgreSQL Setup On Debian, the PostgreSQl package automatically creates a user 'postgres'. For a quick start, do the following (assuming you installed version 7...

NEW - 06 Feb 2008 - 13:46 by HenningPerl

ArecaTest4

Areca test 4 Abstract confirm that the controller automatically repair bad sectorts, without need of manual volume check Test steps * turn off the storage ...

NEW - 04 Feb 2008 - 09:43 by Shaltev

ArecaTest3

Areca test 3 Abstract check if the controller does auto rebuild Test steps * there was a running rebuild, so i first powered off init 0 * the drive in r...

NEW - 02 Feb 2008 - 11:04 by Shaltev

ArecaTest2

Areca test 2 * first see areca_test_1 Abstract check if the controller repair the drive while reading bad sectors HDD prepare * use the same setup like in...

NEW - 02 Feb 2008 - 11:04 by Shaltev

ArecaTest1

Areca test 1 Abstract damage the raid area to test the error recovery function Initial setup Raid Subsystem Information Controller Name ARC 1261 Firmware Vers...

NEW - 02 Feb 2008 - 11:03 by Shaltev

Stundenzettel

Stundenzettel Send your worked hours to Stundenzettel@lns01.aei.mpg.de. Subject: "worked" Insert the entrys to the mailbody. Format: ISO Date,Starttime,Endtime,De...

NEW - 31 Jan 2008 - 17:15 by MatthiasLInden

NetworkTestNetperf4

Netperf test with irqbalance userspace * same set up as in round 3, but with irqbalance user space daemon * virtually no change Setting eth1 tso off, ring ...

NEW - 31 Jan 2008 - 16:58 by Carsten

NetworkTest

Category :Network Network Testing To ensure maximum network performance, we ran several tests. First only with a cable running between two nodes then with one or...

NEW - 31 Jan 2008 - 16:57 by Carsten

NetworkTestNetperf3

Round 3 * same test as in round 2 (burst mode for TCP_RR, c C everywhere) * new this time: tso off for nic Setting eth1 tso off Setting tcp congestion c...

NEW - 31 Jan 2008 - 15:57 by Carsten

NetworkTestNetperf2

Netperf results back2back round 3 * netperf 2.4.4 (Debian) * added use burst at compile time * used c C in all tests and " b 4 r 64K" for TCP_RR M...

NEW - 31 Jan 2008 - 13:40 by Carsten

NetworkTestNetperf1

Netperf results back2back round 1 * netperf 2.4.4 (Debian) * no special compile options * no special command line options, only UDP_STREAM, TCP_STREAM, T...

NEW - 31 Jan 2008 - 13:35 by Carsten

NetworkTestSkript

master script This script just uses dsh to call the various tests on the nodes. UDP_STREAM and TCP_STREAM are run first in single and in dual direction mode (with...

NEW - 31 Jan 2008 - 12:30 by MatthiasLInden

ScrubbingTests

Steps performed * Power off data server * Take one drive out of the data server and put it into powered off compute node * power on compute node * cho...

NEW - 28 Jan 2008 - 15:25 by Shaltev

StorageNodes

Performance Tests * RAID performance * Scheduler * SchedulerTests * ScrubbingTests

NEW - 26 Jan 2008 - 15:03 by Carsten

Rack

Category: Rack Rittal rack design The water cooled Rittal racks are composed of two rack units sharing one Liquid Cooling Package LCP . The racks are on the rig...

NEW - 23 Jan 2008 - 17:51 by MatthiasLInden

DistributedFAI

With 1340 nodes it might be wise to split services among many boxes to ensure that not half of the cluster is waiting to a single server to serve data through its...

NEW - 11 Jan 2008 - 15:42 by Carsten

FirstTestComputeNodes

These items need to be fixed * mcelog needs to be installed and evaluated * maybe the former two and smartctl can be integrated into single script (Carsten ...

NEW - 09 Jan 2008 - 08:22 by Carsten

FirstTestLVPF

FirstTest LV PF Power factor results nodes on phase idle load 1 0.82 0.86 4 0.84 0.86 ...

NEW - 08 Jan 2008 - 08:59 by Carsten

FirstTestLVCompute

FirstTest LV compute The following items need to be checked for compute nodes (please add your name to the test you have performed). If you need much more space p...

NEW - 08 Jan 2008 - 08:56 by Carsten

SchedulerTests

single threaded bonnie Running bonnie in single threaded mode with this short script yielded the following results. script #!/bin/bash SCHEDS="anticipatory ...

NEW - 08 Jan 2008 - 08:53 by Carsten

ToDoPyramid

Nodes * Power factor is too low, use different PSU! * Need electronic document with all MAC numbers (eth0,eth1,IPMI) * Why does SM suggest IMPI to have sam...

NEW - 04 Jan 2008 - 14:30 by Carsten

FirstTestLVStorage

FirstTest LV storage The following items need to be checked for compute nodes (please add your name to the test you have performed). If you need much more space p...

NEW - 04 Jan 2008 - 10:16 by Carsten

ToDoStegmann

ToDoStegmann * Very sharp edges in cable trays, need to be grinded^Wground(?) or capped with rubber * Some of the Cat7 cables are damaged one can see the ou...

NEW - 04 Jan 2008 - 08:53 by Carsten

FirstTestStorageNodes

These items need to be fixed * temperature monitoring needs be set (much higher) 55C at least * mcelog needs to be installed and evaluated * maybe the fo...

NEW - 28 Dec 2007 - 11:04 by Carsten

LDRLinux

This document simply follows the instructions given in http://www.lsc group.phys.uwm.edu/LDR/doc/ldr.pdf. Prepare user and place where LDR will reside As root: ...

NEW - 11 Dec 2007 - 13:16 by Carsten

LDRX4500

Enable blastwave package repository pkgadd d http://www.blastwave.org/pkg_get.pkg With this you can install nice tools such as gtar, gcc, wget with pkg get ins...

NEW - 11 Dec 2007 - 08:52 by Carsten

LDRInstall

LDRInstall LDR on X4500 (Solaris, not working right now) LDR on Linux box

NEW - 11 Dec 2007 - 08:52 by Carsten

IPMI

IPMI stays for Intelligent Platform Management Interface http://en.wikipedia.org/wiki/Intelligent_Platform_Management_Interface Issue IMPI has various purposes I...

NEW - 07 Dec 2007 - 14:39 by HenningPerl

Ethtool

Category : Network ethtool is used for querying settings of an ethernet device and changing them. Usage ethtool y ethX ethtool Y ethX ... Lowercase paramet...

NEW - 07 Dec 2007 - 12:50 by MatthiasLInden

Ssh

SSH SSH User settings User settings are usually found in ${HOME}/.ssh/config and can be created by any text editor. Each setting can be specific to all hosts, a...

NEW - 07 Dec 2007 - 11:02 by Carsten

ClusterHall

Compute cluster racks In each compute cluster rack will be stuffed with 42 compute nodes. Each compute nodes needs: * Height units needed: 1 * Ethernet conn...

NEW - 05 Dec 2007 - 11:19 by Carsten

WovenTestAutomatictest

Automatic testing To enable Woven techs to see the results of their tests, the following program will be run (until killed): Master The master process running on...

NEW - 02 Dec 2007 - 16:14 by Carsten

WovenTest

Initial set up Nodes o460 o498 (except o467) and nodes o536/o537 are connected to TRX100 1. Nodes o499 o530 and o538 o545 are connected to TRX100 2. Plan: The EFX...

NEW - 30 Nov 2007 - 15:13 by Carsten

Fai

Category:fai FAI is short for "Fully Automatic Installation". Installation List of important Files * /etc/fai/make fai nfsroot.conf add location of the Image...

NEW - 30 Nov 2007 - 13:33 by Fehrmann

NodeTests

NodeTests Tasks to do: Initial work (HP) Manual work * Blank disk of node, wipe by: dd if=/dev/zero of=/dev/sda; sync * Put MAC address into DHCP table o...

NEW - 29 Nov 2007 - 18:25 by Sebastian

Postfix

Category:Linux What is Postfix? Postfix is a mail transfer agent (MTA), a program for the routing and delivery of mail. Mails to be delivered on the local machin...

NEW - 28 Nov 2007 - 09:48 by Xm

StorageRAIDPerformance

Set up Bonnie was run on a large RAID6 volume: # df H /raid Filesystem Size Used Avail Use% Mounted on /dev/sdb 11T 5.3M 1...

NEW - 23 Nov 2007 - 15:59 by Carsten

Rsh

server Install rsh server using rhosts If you want to have a password less access edit in the home directory the $HOME/.rhosts and add the nodes, from which ac...

NEW - 23 Nov 2007 - 15:10 by Sebastian

TCP

Category:Network Transmission Control Protocol (TCP) vistit wikipedia on TCP . Congestion control Is used to optimize the senders behaviour to the current netwo...

NEW - 21 Nov 2007 - 19:29 by MatthiasLInden

Placement

Boundary Conditions Racks * Cooling: up to 42*220W = 9.24 kW per rack * Electrical Power: up to 9.24 kW per rack * 42 horizontal and a few vertical heig...

NEW - 20 Nov 2007 - 11:23 by Carsten

Faimond

Faimond faimond catches installation messages on port 4711 sent by the clients. The clients use natcat deliver the current status of the installation tasks like...

NEW - 17 Nov 2007 - 15:29 by Fehrmann

LmSensors

Lm sensors lm sensors is a hardware monitoring tool for linux (cf. http://www.lm sensors.org/). Installation apt get install lm sensors modprobe i2c dev i2c...

NEW - 16 Nov 2007 - 12:38 by Sebastian

Softupdate

Softupdate Softupdate runs through the fai installation and performs all the changes which have been made after the installation process. On the client side f...

NEW - 09 Nov 2007 - 11:06 by HenningPerl

Logcheck

Logcheck logcheck and syslog summary Logcheck This program periodically (default: every hour) searches through the logs in /var/log (generated by syslog or sys...

NEW - 31 Oct 2007 - 09:29 by Xm

Automount

Automount atoumount using autofs: 1. enable automount in kernel 2. install autofs 3. edit /etc/auto.master /wtm /etc/auto.wtm 4. edit /etc/auto.wtm keywor...

NEW - 26 Oct 2007 - 09:19 by Shaltev

Upsmon

Upsmon Working ups monitoring with shutdown. * /etc/nut/upsmon.conf MONITOR comet@localhost 1 monuser monuser master MINSUPPLIES 1 SHUTDOWNCMD "echo '/sbin/...

NEW - 22 Oct 2007 - 06:44 by Shaltev

VLAN

Category:Network VLANs are described in IEEE 802.1Q. Description VLANs are a 4 Byte extension to the standart Ethernet frame, the VLAN tag. The Tag is set by the...

NEW - 20 Oct 2007 - 19:31 by MatthiasLInden

NFS

Category: Network NFS stays for Network File System. The available manuals are sufficient. If it does not work after following the instructions, it may help to r...

NEW - 17 Oct 2007 - 07:52 by MatthiasLInden

Netperf

Category : Network Overview NerPerf consists of two programms: * netperf, a command line tool to generate network traffic to a host * netserver, the daemon...

NEW - 05 Oct 2007 - 11:29 by MatthiasLInden

NetworkFoundryLayout

Category:Network Networking Layout for Foundry RX32 Switch The Switch The Foundry Networks switch RX32 (BigIron RX Series Switches #91;6 #93;) has 32 slots, whi...

NEW - 18 Sep 2007 - 15:11 by MatthiasLInden

SVNTips

Tips Tricks with svn Adding all not yet added files to a repository This should work: svn status grep ^? awk '{print $2;}' xargs svn add or without the grep sv...

NEW - 17 Sep 2007 - 11:10 by Carsten

Minicom

minicom s For a guided Configuration. Visit Serial port setup an set Serial Device to /dev/ttyS0. Usefull for ProCurve2900

NEW - 11 Sep 2007 - 13:22 by MatthiasLInden

GlusterFS

GlusterFS Abstract GlusterFS is a clustered file system capable of scaling to several peta bytes. It aggregates various storage bricks over Infiniband RDMA or TC...

NEW - 05 Sep 2007 - 13:54 by Shaltev

Automake

Automake The GNU Automake and Autoconf tool exist to generate the configure and makefiles needed to compile from source. This is mostly the case when the source i...

NEW - 04 Sep 2007 - 18:46 by HenningPerl

Checkinstall

Checkinstall Checkinstall is a tool to easily generate a debian package from a source tree. To use checkinstall, simply substitute the command with "make install"...

NEW - 04 Sep 2007 - 16:55 by HenningPerl

PublicKeyInfrastructurePKI

Public Key Infrastructure (PKI) There is an excellent tutorial available #91;3 #93;.

NEW - 27 Aug 2007 - 16:16 by HenningPerl

CiscoIPX

Cisco IPX Category: Network The first step is to gain the Cisco device an ssh connect, we must connect with the blue(!?) Console Cable with the one side to the PC...

NEW - 19 Aug 2007 - 19:53 by HenningPerl

ProcCpuinfo

Proc/cpuinfo Category:CPU Running cat /proc/cpuinfo reveals some information on the CPU, e.g. 1. cat /proc/cpuinfo processor : 0 vendor_id : Genu...

NEW - 19 Aug 2007 - 19:41 by HenningPerl

BIOS

BIOS SuperMicro Although it is possible at least on AMD based A servers to flash the BIOS using the flashrom tool, it is unfortunately impossible to use /de...

NEW - 07 Aug 2007 - 08:25 by Carsten

ZFS

ZFS ZFS is a file system created by Sun Microsystems for Solaris/OpenSolaris in 2005. ZFS combines concepts of filesystem and volume management. The name ZFS ori...

NEW - 30 Jul 2007 - 16:02 by Sebastian

Benchmarks

Benchmarks General description For the Leistungsbeschreibung of the Morgane cluster in 2006, we compiled a statically linked benchmark program which can be found...

NEW - 23 Jul 2007 - 13:21 by Carsten

AptProxy

Apt proxy Category:Linux The apt proxy is running on n0, reachable via 192.168.0.1 or 130.75.117.77 both at port 9999 To Use it, add to your /etc/apt/sources.list...

NEW - 19 Jul 2007 - 12:47 by MatthiasLInden

Dhcp

Dhcp Category:Howto Read the man page of dhcpd.conf and edit /etc/dhcp3/dhcpd.conf . It can happen that a clie...

NEW - 19 Jul 2007 - 06:39 by Fehrmann

Netcat

Netcat Category:Network Netcat is a tool to generate network traffic. Send nc p sourceport destipaddr port and Recive nc l p listenport sourceipaddr port ...

NEW - 18 Jul 2007 - 20:24 by MatthiasLInden

FlowTools

Flow tools Category:Network flow tools contains some nice tools to measure network performance. Tools flow gen flow gen generates data that can be piped to flow...

NEW - 17 Jul 2007 - 18:14 by MatthiasLInden

SophosAntivirOnSamba

Sophos Antivir on Samba The Goal is to have a fileserver with live virus protection..!! We need: * samba sources (I used samba 3.0.22 13.16 bacause the new one...

NEW - 12 Jul 2007 - 08:37 by SergejSchweizer

FAIInstallation

FAI Installation Category:fai Fai Installation at the Max Planck Institute This command install FAI with all dependences..!!! aptitude install fai quickstart P...

NEW - 05 Jul 2007 - 10:49 by MatthiasLInden

SuseHacks

Suse Hacks SLES/openSuse Every one must be able to install or delete software from the shell. To do this your Suse needs an Repository with the Packages. Take Ca...

NEW - 26 Jun 2007 - 11:51 by SergejSchweizer

InstallScript

Install script Category:Installation The install script, as of friday, may 25th 2007 #!/bin/bash export IMAGE_NAME=system image.tar.bz2 cd /tmp echo get...

NEW - 26 May 2007 - 20:46 by MatthiasLInden

Initrd

Category:Howto What is initrd ToDo A few hints on initrd The Script that is executed after Startup is located /usr/share/initrd tools/lnuxrc Runlevel? Files,...

NEW - 25 May 2007 - 14:03 by MatthiasLInden

Installation

Category: Installation autonomous installation debian creating a package list In order to use a package list of a good installed node type dpkg get selectio...

NEW - 25 May 2007 - 13:05 by MatthiasLInden

Chroot

Using the chroot operation, one can reroot a group or user to a different directory. The Called programm cannot reach firther than the newly defined root. This wa...

NEW - 22 May 2007 - 19:09 by MatthiasLInden

Grsecurity

Grsecurity Category: Kernel Grsecurity provides a kernel patch to enable additional security features. * constrains the write accsess in the kernel space ...

NEW - 09 May 2007 - 18:20 by UnknownUser

WebChanges

NEW - 15 Nov 2006 - 19:43 by TWikiContributor

WebIndex

NEW - 15 Nov 2006 - 19:43 by TWikiContributor

WebSearch

NEW - 15 Nov 2006 - 19:43 by TWikiContributor

WebSearchAdvanced

NEW - 15 Nov 2006 - 19:43 by TWikiContributor

WebTopicList

NEW - 15 Nov 2006 - 19:43 by TWikiContributor

WebAtom

Foswiki's ATLAS web

NEW - 24 Jan 2006 - 06:07 by TWikiContributor

WebLeftBar

" warn="off"}% * * * * * * * *

NEW - 28 Mar 2005 - 09:40 by TWikiContributor

WebNotify

* Main.TWikiGuest example #64;your.company __ .WebChangesAlert, ., .TWikiRegistration

NEW - 28 Mar 2005 - 09:40 by TWikiContributor

WebRss

" else="Foswiki's ATLAS web"}% /ATLAS

NEW - 28 Mar 2005 - 09:40 by TWikiContributor

Number of topics: 424

See also:

RSS feed, recent changes with 50, 100, 200, 500, 1000 topics, all changes

Topic revision: r1 - 15 Nov 2006, TWikiContributor

ATLAS

Copyright © by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding Foswiki? Send feedback