Site operations Outline Central services VoBox services Monitoring Storage and networking 4/8/20142ALICE-USA Review - Site Operations.

Slides:



Advertisements
Similar presentations
Status GridKa & ALICE T2 in Germany Kilian Schwarz GSI Darmstadt.
Advertisements

ALICE G RID SERVICES IP V 6 READINESS
1 User Analysis Workgroup Update  All four experiments gave input by mid December  ALICE by document and links  Very independent.
GSIAF "CAF" experience at GSI Kilian Schwarz. GSIAF Present status Present status installation and configuration installation and configuration usage.
MONITORING WITH MONALISA Costin Grigoras. M ONITORING WITH M ON ALISA What is MonALISA ? MonALISA communication architecture Monitoring modules ApMon.
Torrent-based Software Distribution in ALICE.
Outline Network related issues and thinking for FAX Cost among sites, who has problems Analytics of FAX meta data, what are the problems  The main object.
ALICE Operations short summary and directions in 2012 Grid Deployment Board March 21, 2011.
ALICE Operations short summary and directions in 2012 WLCG workshop May 19-20, 2012.
Statistics of CAF usage, Interaction with the GRID Marco MEONI CERN - Offline Week –
1 Status of the ALICE CERN Analysis Facility Marco MEONI – CERN/ALICE Jan Fiete GROSSE-OETRINGHAUS - CERN /ALICE CHEP Prague.
Hands-On Microsoft Windows Server 2008 Chapter 1 Introduction to Windows Server 2008.
ALICE DATA ACCESS MODEL Outline ALICE data access model - PtP Network Workshop 2  ALICE data model  Some figures.
Monitoring Scale-Out with the MySQL Enterprise Monitor Andy Bang Lead Software Engineer MySQL-Sun, Enterprise Tools Team Wednesday, April 16, :15.
G RID SERVICES IP V 6 READINESS
ALICE data access WLCG data WG revival 4 October 2013.
ATLAS Off-Grid sites (Tier-3) monitoring A. Petrosyan on behalf of the ATLAS collaboration GRID’2012, , JINR, Dubna.
US ATLAS Western Tier 2 Status and Plan Wei Yang ATLAS Physics Analysis Retreat SLAC March 5, 2007.
Online Monitoring with MonALISA Dan Protopopescu Glasgow, UK Dan Protopopescu Glasgow, UK.
1 Ramiro Voicu, Iosif Legrand, Harvey Newman, Artur Barczyk, Costin Grigoras, Ciprian Dobre, Alexandru Costan, Azher Mughal, Sandor Rozsa Monitoring and.
Experiment Support CERN IT Department CH-1211 Geneva 23 Switzerland t DBES P. Saiz (IT-ES) AliEn job agents.
Monitoring, Accounting and Automated Decision Support for the ALICE Experiment Based on the MonALISA Framework.
1 Iosif Legrand, Harvey Newman, Ramiro Voicu, Costin Grigoras, Catalin Cirstoiu, Ciprian Dobre An Agent Based, Dynamic Service System to Monitor, Control.
Status of the production and news about Nagios ALICE TF Meeting 22/07/2010.
CERN – Alice Offline – Thu, 03 Feb 2005 – Marco MEONI - 1/18 Monitoring of a distributed computing system: the AliEn Grid Alice Offline weekly meeting.
PROOF Cluster Management in ALICE Jan Fiete Grosse-Oetringhaus, CERN PH/ALICE CAF / PROOF Workshop,
N EWS OF M ON ALISA SITE MONITORING
Update on replica management
Overview of ALICE monitoring Catalin Cirstoiu, Pablo Saiz, Latchezar Betev 23/03/2007 System Analysis Working Group.
Monitoring with MonALISA Costin Grigoras. What is MonALISA ?  Caltech project started in 2002
SLACFederated Storage Workshop Summary For pre-GDB (Data Access) Meeting 5/13/14 Andrew Hanushevsky SLAC National Accelerator Laboratory.
Xrootd Monitoring and Control Harsh Arora CERN. Setting Up Service  Monalisa Service  Monalisa Repository  Test Xrootd Server  ApMon Module.
INFSO-RI Enabling Grids for E-sciencE ARDA Experiment Dashboard Ricardo Rocha (ARDA – CERN) on behalf of the Dashboard Team.
20409A 7: Installing and Configuring System Center 2012 R2 Virtual Machine Manager Module 7 Installing and Configuring System Center 2012 R2 Virtual.
XROOTD AND FEDERATED STORAGE MONITORING CURRENT STATUS AND ISSUES A.Petrosyan, D.Oleynik, J.Andreeva Creating federated data stores for the LHC CC-IN2P3,
EGEE is a project funded by the European Union under contract IST VO box: Experiment requirements and LCG prototype Operations.
JAliEn Java AliEn middleware A. Grigoras, C. Grigoras, M. Pedreira P Saiz, S. Schreiner ALICE Offline Week – June 2013.
AliEn central services Costin Grigoras. Hardware overview  27 machines  Mix of SLC4, SLC5, Ubuntu 8.04, 8.10, 9.04  100 cores  20 KVA UPSs  2 * 1Gbps.
ALICE DATA ACCESS MODEL Outline 05/13/2014 ALICE Data Access Model 2  ALICE data access model  Infrastructure and SE monitoring.
+ AliEn site services and monitoring Miguel Martinez Pedreira.
Global ADC Job Monitoring Laura Sargsyan (YerPhI).
FTS monitoring work WLCG service reliability workshop November 2007 Alexander Uzhinskiy Andrey Nechaevskiy.
October 2006 Iosif Legrand 1 Iosif Legrand California Institute of Technology An Agent Based, Dynamic Service System to Monitor, Control and Optimize Distributed.
03/09/2007http://pcalimonitor.cern.ch/1 Monitoring in ALICE Costin Grigoras 03/09/2007 WLCG Meeting, CHEP.
Gennaro Tortone, Sergio Fantinel – Bologna, LCG-EDT Monitoring Service DataTAG WP4 Monitoring Group DataTAG WP4 meeting Bologna –
Status of AliEn2 Services ALICE offline week Latchezar Betev Geneva, June 01, 2005.
Data transfers and storage Kilian Schwarz GSI. GSI – current storage capacities vobox LCG RB/CE GSI batchfarm: ALICE cluster (67 nodes/480 cores for batch.
Testing Infrastructure Wahid Bhimji Sam Skipsey Intro: what to test Existing testing frameworks A proposal.
INRNE's participation in LCG Elena Puncheva Preslav Konstantinov IT Department.
+ AliEn status report Miguel Martinez Pedreira. + Touching the APIs Bug found, not sending site info from ROOT to central side was causing the sites to.
WMS baseline issues in Atlas Miguel Branco Alessandro De Salvo Outline  The Atlas Production System  WMS baseline issues in Atlas.
MONITORING WITH MONALISA Costin Grigoras. M ON ALISA COMMUNICATION ARCHITECTURE MonALISA software components and the connections between them Data consumers.
1 R. Voicu 1, I. Legrand 1, H. Newman 1 2 C.Grigoras 1 California Institute of Technology 2 CERN CHEP 2010 Taipei, October 21 st, 2010 End to End Storage.
ALICE computing Focus on STEP09 and analysis activities ALICE computing Focus on STEP09 and analysis activities Latchezar Betev Réunion LCG-France, LAPP.
Pledged and delivered resources to ALICE Grid computing in Germany Kilian Schwarz GSI Darmstadt ALICE Offline Week.
MONALISA MONITORING AND CONTROL Costin Grigoras. O UTLINE MonALISA services and clients Usage in ALICE Online SE discovery mechanism Data management 3.
Storage discovery in AliEn
Virtual machines ALICE 2 Experience and use cases Services at CERN Worker nodes at sites – CNAF – GSI Site services (VoBoxes)
Servizi core INFN Grid presso il CNAF: setup attuale
Federating Data in the ALICE Experiment
Diskpool and cloud storage benchmarks used in IT-DSS
ALICE Monitoring
GSIAF & Anar Manafov, Victor Penso, Carsten Preuss, and Kilian Schwarz, GSI Darmstadt, ALICE Offline week, v. 0.8.
Torrent-based software distribution
Storage elements discovery
AliEn central services (structure and operation)
Ákos Frohner EGEE'08 September 2008
Publishing ALICE data & CVMFS infrastructure monitoring
湖南大学-信息科学与工程学院-计算机与科学系
20409A 7: Installing and Configuring System Center 2012 R2 Virtual Machine Manager Module 7 Installing and Configuring System Center 2012 R2 Virtual.
Presentation transcript:

Site operations

Outline Central services VoBox services Monitoring Storage and networking 4/8/20142ALICE-USA Review - Site Operations

Central Services 4/8/20143ALICE-USA Review - Site Operations

Core central services Central MySQL databases + hot backups ◦ Catalogue: 1B files Catalogue ◦ Task Queue: 250K jobs/day (avg) (up to 2x in analysis periods) Task Queue ◦ Scheduled transfers AliEn services ◦ Authen: alice-authen.cern.ch:8080 ◦ PackMan: alice-packman.cern.ch:9991 ◦ Job Broker: alice-jobbroker.cern.ch:8050 ◦ Job Manager: aliendb8.cern.ch:8083 ◦ Job Info Manager: alice-jobinfomanager.cern.ch:8081 ◦ Information Service: alice-is.cern.ch:8099 ◦ API: alice-apiserv1.cern.ch:10000, alice-apiserv2.cern.ch:10000 ◦ LDAP: alice-ldap.cern.ch:8389 ◦ Various optimizers and internal services Transfer agents ◦ Third party copying or store and forward of the data 4/8/20144ALICE-USA Review - Site Operations

Monitoring services MonALISA central repository: alimonitor.cern.ch:80,443central repository ◦ 2 independent PostgreSQL backends MonALISA proxy service: alimlproxy.cern.ch:6001 4/8/2014ALICE-USA Review - Site Operations5

Build servers AliEn and AliROOT build systems for AliEn AliROOT ◦ SLC5, 32b and 64b ◦ SLC6, 32b and 64b ◦ Ubuntu, 64b ◦ Mac OSx Daily analysis tags + 2 revisions weekly ◦ Automatically deployed on CVMFS ◦ Also available for users to install  wget directly from build servers via alienbuild.cern.ch:80,8880,8888,8889  alitorrent.cern.ch:80,8088,8092 4/8/2014ALICE-USA Review - Site Operations6

Various other services Automatic revision testing of QA and refiltering code LEGO train wagon testing machinery AliRoot code checkers Shifter and detector construction databases ALICE public web site Backup service and software repository 4/8/2014ALICE-USA Review - Site Operations7

VoBox services CE ◦ Submitting generic Job Agents to the local BQ when something in the central task queue matches the site resources Cluster Monitor: TCP/8084 ◦ Message proxy between job agents and the central services CMReport ◦ Periodic message buffer flushes to the central services MonALISA: ◦ Collects and aggregates all site-produced monitoring data ◦ Periodic tests of VoBox services health ◦ ApMon listener: UDP/8884 ◦ Xrootd monitoring: UDP/9930 ◦ Bandwidth tests: TCP/1093, ICMP, UDP/ /8/2014ALICE-USA Review - Site Operations8

Job Agent monitoring Instrumented with ApMonApMon Full host monitoring parameters ◦ CPU, load, network traffic, number of processes and sockets in each state, disk and swap IO, CPU type and spec power, OS Self monitoring ◦ Proxy time left, CPU and memory utilization, status, current job ID, number of jobs picked up so far Current job monitoring ◦ CPU, memory and disk utilization, number of open files, job meta information (queue ID, master job ID, owner name) 4/8/2014ALICE-USA Review - Site Operations9

Job monitoring Root is compiled with ApMon support as well, so jobs can use TMonaLisaWriter ◦ Used eg. for grid-wide CPU benchmarking using Root stress benchmark xrdcp command reports transfer details to the VoBox ◦ Source and destination, amount of data, time it took etc 4/8/2014ALICE-USA Review - Site Operations10

Storage monitoring Xrootd and EOS data servers publish two monitoring streams ◦ ApMon daemon reporting the data server host monitoring and external Xrootd params  Node total traffic, load, IO  Version, total and used space ◦ Xrootd internal reporting on file close  xrootd.monitor all flush 60s window 30s dest files info user MONALISA_HOST:9930  Client IP, read and written bytes, speed 4/8/2014ALICE-USA Review - Site Operations11

Site monitoring data aggregation Monitoring data is aggregated in real time by the VoBox ML service Summaries are publishes along side the individual values ◦ Total traffic on the Xrootd servers Total traffic  And split by remote site, LAN/WANremote siteLAN/WAN ◦ Aggregated resource consumption by jobs Aggregated resource consumption  By queue, by user name ◦ Count jobs in each state Count jobs in each state ◦ Various aggregation functions available  min/max/avg/sum  Top jobs in terms of allocated memory 4/8/2014ALICE-USA Review - Site Operations12

Central monitoring repository 4/8/2014ALICE-USA Review - Site Operations13 Long History DB LCG Tools MonALISA AliEn Site ApMon AliEn Job Agent ApMon AliEn Job Agent ApMon AliEn Job Agent MonALISA LCG Site ApMon AliEn CE ApMon AliEn SE ApMon Cluster Monitor ApMon AliEn TQ ApMon AliEn Job Agent ApMon AliEn Job Agent ApMon AliEn Job Agent ApMon AliEn CE ApMon AliEn SE ApMon Cluster Monitor ApMon AliEn IS ApMon AliEn Optimizers ApMon AliEn Brokers ApMon MySQL Servers ApMon CastorGrid Scripts ApMon API Services MonALISARepository Aggregated Data rss vsz cpu time run time job slots free space nr. of files open files Queued JobAgents cpu ksi2k job status disk used processes load net In/out jobs status sockets migrated mbytes active sessions MyProxy status Alerts Actions

What you can see centrally Current status ◦ Of all services, central and site local ◦ Of all jobs and ongoing productions, analysis or user activity ◦ Catalogue browser ◦ Various test results: storage, network Aggregated history data ◦ Job accounting: running time, efficiency, consumed spec power  Per site and per user ◦ Storage status ◦ Network utilization Overview of current issues 4/8/2014ALICE-USA Review - Site Operations14

Network monitoring Periodic one TCP stream throughput test between all VoBoxes in ALICE ◦ Similar to what the jobs would experience Pairs of VoBox machines selected by the repository Very important for debugging network connectivity for new sites or after major changes Also records traceroute/tracepath result along with the test for later comparison And VoBox kernel network parameters See the earlier firewall requirements 4/8/2014ALICE-USA Review - Site Operations15

Topology map (AS level) 4/8/2014ALICE-USA Review - Site Operations16

Storage monitoring Every 2h a full add/get/rm test suite from the repository machine ◦ Storage functional status ◦ Remote access to it If the storage is full only a get operation is performed, but it is still marked as bad for writing For xrootd: individual server testing with a similar test suite Alarms raised on reported size different from LDAP declared size ◦ Sometimes data servers are not seen by the redirector any more – restart usually cures it 4/8/2014ALICE-USA Review - Site Operations17

Storage discovery Closest working replicas are used for both reading and writing ◦ Sorting the SEs by the network distance to the client making the request  Combining network topology data with the geographical location ◦ Leaving as last resort only the SEs that fail the respective functional test ◦ Weighted with their recent reliability and remaining free space Writing is finally slightly randomized for more ‘democratic’ data distribution 4/8/2014ALICE-USA Review - Site Operations18

Distance metric function distance(IP, IP) ◦ Same C-class network ◦ Common domain name ◦ Same AS ◦ Same country (+ function of RTT between the respective AS-es if known) ◦ If distance between the AS-es is known, use it ◦ Same continent ◦ Far, far away distance(IP, Set ): Client's public IP to all known IPs for the storage 4/8/2014ALICE-USA Review - Site Operations19 0 1

Weight factors Free space contributes with ◦ f (ln(free space / 5TB)) Recent history contributes with ◦ 75% * last day success ratio + ◦ 25% * last week success ratio add test result used for write discovery, get test result used for reading Resulting value added to the distance 4/8/2014ALICE-USA Review - Site Operations20

Impact on analysis jobs Local SE problems makes the jobs read remotely In this particular case the SE tests are all fine ◦ Under investigation why the jobs cannot access local data Remote access can severely impact the jobs efficiency 4/8/2014ALICE-USA Review - Site Operations21

Remote access efficiency Problems can come from both network and the storage IO performance seen by jobs doesn’t always match the VoBox- to-VoBox throughput measurements Congested firewall / network segment, different OS settings, saturated storage IO Reflected in the overall efficiency 4/8/2014ALICE-USA Review - Site Operations22 Storage WNs CERNLEGNAROTORINOCNAFFZK CERN2.668 MB/s0.27 MB/s FZK0.486 MB/s0.161 MB/s0.213 MB/s2.963 MB/s LEGNARO1.611 MB/s2.628 MB/s0.673 MB/s0.749 MB/s TORINO1.848 MB/s1.609 MB/s0.684 MB/s0.891 MB/s CNAF2.193 MB/s0.623 MB/s2.126 MB/s

Focus on US 4/8/2014ALICE-USA Review - Site Operations23

LBL::SE traffic during that time 4/8/2014ALICE-USA Review - Site Operations24

LBL::SE server load 4/8/2014ALICE-USA Review - Site Operations25

LBL::SE socket count 4/8/2014ALICE-USA Review - Site Operations26

LBL::SE top client sites 4/8/2014ALICE-USA Review - Site Operations27

LBL WNs data access 4/8/2014ALICE-USA Review - Site Operations28

LLNL WNs data access 4/8/2014ALICE-USA Review - Site Operations29

Remote data access is significant Remember to tune all machines in your clusters for large average RTT (WNs, data servers, and use same values on the VoBox for reference) Kernel parameters as seen here: on_syssettings.html on_syssettings.html Or even better the ESNet recommended values: 4/8/2014ALICE-USA Review - Site Operations30

Network 1 TCP stream throughput 4/8/2014ALICE-USA Review - Site Operations31