End-to-End performance tuning Brian Davies Gridpp28 Manchester 2012.

Slides:



Advertisements
Similar presentations
ESLEA and HEPs Work on UKLight Network. ESLEA Exploitation of Switched Lightpaths in E- sciences Applications Exploitation of Switched Lightpaths in E-
Advertisements

Clustering Architectures in GIS/SI
Current Testbed : 100 GE 2 sites (NERSC, ANL) with 3 nodes each. Each node with 4 x 10 GE NICs Measure various overheads from protocols and file sizes.
Dr. Kalpakis CMSC 621, Advanced Operating Systems. Fall 2003 URL: Distributed System Architectures.
CS162 Section Lecture 9. KeyValue Server Project 3 KVClient (Library) Client Side Program KVClient (Library) Client Side Program KVClient (Library) Client.
1 © Copyright 2010 EMC Corporation. All rights reserved. EMC RecoverPoint/Cluster Enabler for Microsoft Failover Cluster.
Network Operating Systems Users are aware of multiplicity of machines. Access to resources of various machines is done explicitly by: –Logging into the.
IP –Based SAN extensions and Performance Thao Pham CS 622 Fall 07.
CSE 190: Internet E-Commerce Lecture 16: Performance.
GridPP meeting Feb 03 R. Hughes-Jones Manchester WP7 Networking Richard Hughes-Jones.
1 Web Proxies Dr. Rocky K. C. Chang 6 November 2005.
EEC-681/781 Distributed Computing Systems Lecture 3 Wenbing Zhao Department of Electrical and Computer Engineering Cleveland State University
Lesson 20 – OTHER WINDOWS 2000 SERVER SERVICES. DHCP server DNS RAS and RRAS Internet Information Server Cluster services Windows terminal services OVERVIEW.
EECE 411: Design of Distributed Software Applications What is a Distributed System? You know when you have one … … when the failure of a computer you’ve.
Performance Comparison of Congested HTTP/2 Links Brian Card, CS /7/
Lecture 8 Epidemic communication, Server implementation.
1© Copyright 2011 EMC Corporation. All rights reserved. EMC RECOVERPOINT/ CLUSTER ENABLER FOR MICROSOFT FAILOVER CLUSTER.
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 DATA ACCESS MODEL Outline ALICE data access model - PtP Network Workshop 2  ALICE data model  Some figures.
Chapter 2 Architectural Models. Keywords Middleware Interface vs. implementation Client-server models OOP.
Protocols for Wide-Area Data-intensive Applications: Design and Performance Issues Yufei Ren, Tan Li, Dantong Yu, Shudong Jin, Thomas Robertazzi, Brian.
FZU participation in the Tier0 test CERN August 3, 2006.
ALICE data access WLCG data WG revival 4 October 2013.
70-291: MCSE Guide to Managing a Microsoft Windows Server 2003 Network Chapter 6: Name Resolution.
70-291: MCSE Guide to Managing a Microsoft Windows Server 2003 Network, Enhanced Chapter 6: Name Resolution.
Digital Multimedia, 2nd edition Nigel Chapman & Jenny Chapman Chapter 17 This presentation © 2004, MacAvon Media Productions Multimedia and Networks.
Assignment 5/9 – 2005 INF 5070 – Media Servers and Distribution Systems:
Current Testbed : 100 GE 2 sites (NERSC, ANL) with 3 nodes each. Each node with 4 x 10 GE NICs Measure various overheads from protocols and file sizes.
1 The Internet and Networked Multimedia. 2 Layering  Internet protocols are designed to work in layers, with each layer building on the facilities provided.
The Transmission Control Protocol (TCP) Application Services (Telnet, FTP, , WWW) Reliable Stream Transport (TCP) Connectionless Packet Delivery.
Data transfer over the wide area network with a large round trip time H. Matsunaga, T. Isobe, T. Mashimo, H. Sakamoto, I. Ueda International Center for.
PARALLEL APPLICATIONS EE 524/CS 561 Kishore Dhaveji 01/09/2000.
The Alternative Larry Moore. 5 Nodes and Variant Input File Sizes Hadoop Alternative.
Testing the UK Tier 2 Data Storage and Transfer Infrastructure C. Brew (RAL) Y. Coppens (Birmingham), G. Cowen (Edinburgh) & J. Ferguson (Glasgow) 9-13.
Optimisation of Grid Enabled Storage at Small Sites Jamie K. Ferguson University of Glasgow – Jamie K. Ferguson – University.
Multimedia and Networks. Protocols (rules) Rules governing the exchange of data over networks Conceptually organized into stacked layers – Application-oriented.
Problem-solving on large-scale clusters: theory and applications Lecture 4: GFS & Course Wrap-up.
Grid Technology CERN IT Department CH-1211 Geneva 23 Switzerland t DBCF GT DPM / LFC and FTS news Ricardo Rocha ( on behalf of the IT/GT/DMS.
EGEE-II INFSO-RI Enabling Grids for E-sciencE EGEE Site Architecture Resource Center Deployment Considerations MIMOS EGEE Tutorial.
Digital Multimedia, 2nd edition Nigel Chapman & Jenny Chapman Chapter 17 This presentation © 2004, MacAvon Media Productions Multimedia and Networks.
Computer Communication: An example What happens when I click on
Data Transfer Service Challenge Infrastructure Ian Bird GDB 12 th January 2005.
ALICE DATA ACCESS MODEL Outline 05/13/2014 ALICE Data Access Model 2  ALICE data access model  Infrastructure and SE monitoring.
Andrea Manzi CERN On behalf of the DPM team HEPiX Fall 2014 Workshop DPM performance tuning hints for HTTP/WebDAV and Xrootd 1 16/10/2014.
Distributed DBMS, Query Processing and Optimization
File Transfer And Access (FTP, TFTP, NFS). Remote File Access, Transfer and Storage Networks For different goals variety of approaches to remote file.
Grid Technology CERN IT Department CH-1211 Geneva 23 Switzerland t DBCF GT Overview of DMLite Ricardo Rocha ( on behalf of the LCGDM team.
9/29/04 GGF Random Thoughts on Application Performance and Network Characteristics Distributed Systems Department Lawrence Berkeley National Laboratory.
Service Challenge Meeting “Review of Service Challenge 1” James Casey, IT-GD, CERN RAL, 26 January 2005.
Virtual Machine Movement and Hyper-V Replica
Em Spatiotemporal Database Laboratory Pusan National University File Processing : Database Management System Architecture 2004, Spring Pusan National University.
Run-time Adaptation of Grid Data Placement Jobs George Kola, Tevfik Kosar and Miron Livny Condor Project, University of Wisconsin.
INFSO-RI Enabling Grids for E-sciencE File Transfer Software and Service SC3 Gavin McCance – JRA1 Data Management Cluster Service.
Client-server communication Prof. Wenwen Li School of Geographical Sciences and Urban Planning 5644 Coor Hall
All the things you need to know before setting up AlwaysOn Michael Steineke SQL & BI Solution Lead Enterprise Architect Concurrency, Inc.
Operating Systems Distributed-System Structures. Topics –Network-Operating Systems –Distributed-Operating Systems –Remote Services –Robustness –Design.
CERN IT Department CH-1211 Genève 23 Switzerland t Towards end-to-end debugging for data transfers Gavin McCance Javier Conejero Banon Sophie.
Design and Implementation of a High-Performance distributed web crawler Vladislav Shkapenyuk and Torsten Suel Proc. 18 th Data Engineering Conf., pp ,
Understand Names Resolution
James Casey, IT-GD, CERN CERN, 5th September 2005
BNL FTS services Hironori Ito.
Storage elements discovery
Ákos Frohner EGEE'08 September 2008
Working at a Small-to-Medium Business or ISP – Chapter 7
Working at a Small-to-Medium Business or ISP – Chapter 7
Working at a Small-to-Medium Business or ISP – Chapter 7
Australia Site Report Sean Crosby DPM Workshop – 13 December 2013.
lundi 25 février 2019 FTS configuration
FTS Issue in Beijing Erming PEI 2010/06/18.
Presentation transcript:

End-to-End performance tuning Brian Davies Gridpp28 Manchester 2012

18/04/2012 End-End performance tuning 2 Areas of Improvements FTS –# Streams –# Files –Tx Timeout –Preparing File Ratio –Copy Mechanism G-U-C vs srmcp Asynchronous Ptp Access Method –Synchronous vs Asynchronous calls –Scheduled vs unscheduled connections. –Srm-less –Federated xrootd Costs as well as benefits TCP/ Window Tuning Jumbo Frames –Some changes only see benefit in end site also make changes. WN-WAN tuning –Tcp Window size –‘Nat’ing –Xrootd configuration/optimisation.

18/04/2012 End-End performance tuning 3 Other areas of optimisation?? Homogenous network –Mixing WN and Disk Servers can easily reduce network bandwidth VM components –Splitting services Databases –Type –Separate node –Internal operation Cleansing –EG DPM requests DB DNS Aliasing of multiple machines Knowledge transfer

18/04/2012 End-End performance tuning 4 Who does optimisation and when is the benefit seen. Some optimisations can be unilateral. FTS tuning, database improvements etc. –Others have to be co-ordinated Jumbo Frames Some optimisation benefits seen straight away. –Others require end host to make changes before benefit is seen. An “improvement” at one site may degrade another site. –TCP tuning at QMUL/RHUL

18/04/2012 End-End performance tuning 5 Differences between T1 and T2s? (Some) Current T1 issues will/are problems that a “large” T2 will face in X* years time. Problems a T2 are facing now may have been solved by (a) T1 Y* years ago. A site should/does not need try to re-solve a problem(s) that another site(s)/tier has solved in the past. *(Where X and Y are to be determined).

18/04/2012 End-End performance tuning 6 Manchester Network improvements Transfers from Manc’ to T1s

18/04/2012 End-End performance tuning 7 Manchester network improvements Reverse direction

18/04/2012 End-End performance tuning 8 Manchester Network improvements Transfers from Manc’ to UK T2s

18/04/2012 End-End performance tuning 9 Manchester Network improvements Transfers from Manc’ to Non UK T2s

18/04/2012 End-End performance tuning 10 Manchester Network improvements

18/04/2012 End-End performance tuning 11 Effect of streams on RALPPD-T1s Failing transfers required number of threads per transfer to have to be reduced to 1 per file transfer.` –Deemed more important to receive data from CERN than getting good rate for other sites Mitigated overall throughput by increasing number of concurrent transfers. –Individual file transfer speed reduced and latency increased. Once underlining issue re-solved returned to previous settings.

18/04/2012 End-End performance tuning 12 Effect of streams on T1s- RALPPD #Streams reduced/Increased Effects transfers TO the site. Effects Some T1s more than others

18/04/2012 End-End performance tuning 13 Effect of streams on RALPPD- T1s No (known) changes in streams in reverse direction

18/04/2012 End-End performance tuning 14 Other areas of optimisation?? “In the wiki” –But where? Which wiki? ????