DAQ interface + implications for the electronics Niko Neufeld LHCb Electronics Upgrade June 10 th, 2010.

Slides:



Advertisements
Similar presentations
CCNA3: Switching Basics and Intermediate Routing v3.0 CISCO NETWORKING ACADEMY PROGRAM Switching Concepts Introduction to Ethernet/802.3 LANs Introduction.
Advertisements

LHCb Upgrade Overview ALICE, ATLAS, CMS & LHCb joint workshop on DAQ Château de Bossey 13 March 2013 Beat Jost / Cern.
The LHCb Event-Builder Markus Frank, Jean-Christophe Garnier, Clara Gaspar, Richard Jacobson, Beat Jost, Guoming Liu, Niko Neufeld, CERN/PH 17 th Real-Time.
TDC 461 Basic Communications Systems Local Area Networks 29 May, 2001.
LHCb readout infrastructure NA62 TDAQ WG Meeting April 1 st, 2009 Niko Neufeld, PH/LBC.
Chapter 4 Queuing, Datagrams, and Addressing
The LHCb Online System Design, Implementation, Performance, Plans Presentation at the 2 nd TIPP Conference Chicago, 9 June 2011 Beat Jost Cern.
5 Feb 2002Alternative Ideas for the CALICE Backend System 1 Alternative Ideas for the CALICE Back-End System Matthew Warren and Gordon Crone University.
The Network Layer. Network Projects Must utilize sockets programming –Client and Server –Any platform Please submit one page proposal Can work individually.
K. Honscheid RT-2003 The BTeV Data Acquisition System RT-2003 May 22, 2002 Klaus Honscheid, OSU  The BTeV Challenge  The Project  Readout and Controls.
Straw electronics Straw Readout Board (SRB). Full SRB - IO Handling 16 covers – Input 16*2 links 400(320eff) Mbits/s Control – TTC – LEMO – VME Output.
Architecture and Dataflow Overview LHCb Data-Flow Review September 2001 Beat Jost Cern / EP.
A TCP/IP transport layer for the DAQ of the CMS Experiment Miklos Kozlovszky for the CMS TriDAS collaboration CERN European Organization for Nuclear Research.
Status and plans for online installation LHCb Installation Review April, 12 th 2005 Niko Neufeld for the LHCb Online team.
CERN Real Time conference, Montreal May 18 – 23, 2003 Richard Jacobsson 1 Driving the LHCb Front-End Readout TFC Team: Arek Chlopik, IPJ, Poland Zbigniew.
VLVNT Amsterdam 2003 – J. Panman1 DAQ: comparison with an LHC experiment J. Panman CERN VLVNT workshop 7 Oct 2003 Use as example CMS (slides taken from.
Network Architecture for the LHCb DAQ Upgrade Guoming Liu CERN, Switzerland Upgrade DAQ Miniworkshop May 27, 2013.
Management of the LHCb DAQ Network Guoming Liu * †, Niko Neufeld * * CERN, Switzerland † University of Ferrara, Italy.
1 Network Performance Optimisation and Load Balancing Wulf Thannhaeuser.
Features of the new Alibava firmware: 1. Universal for laboratory use (readout of stand-alone detector via USB interface) and for the telescope readout.
LHCb Upgrade Architecture Review BE DAQ Interface Rainer Schwemmer.
LHCb front-end electronics and its interface to the DAQ.
LHCb DAQ system LHCb SFC review Nov. 26 th 2004 Niko Neufeld, CERN.
Guido Haefeli CHIPP Workshop on Detector R&D Geneva, June 2008 R&D at LPHE/EPFL: SiPM and DAQ electronics.
Modeling PANDA TDAQ system Jacek Otwinowski Krzysztof Korcyl Radoslaw Trebacz Jagiellonian University - Krakow.
LNL 1 SADIRC2000 Resoconto 2000 e Richieste LNL per il 2001 L. Berti 30% M. Biasotto 100% M. Gulmini 50% G. Maron 50% N. Toniolo 30% Le percentuali sono.
Niko Neufeld, CERN/PH. Online data filtering and processing (quasi-) realtime data reduction for high-rate detectors High bandwidth networking for data.
Management of the LHCb Online Network Based on SCADA System Guoming Liu * †, Niko Neufeld † * University of Ferrara, Italy † CERN, Geneva, Switzerland.
The CMS Event Builder Demonstrator based on MyrinetFrans Meijers. CHEP 2000, Padova Italy, Feb The CMS Event Builder Demonstrator based on Myrinet.
A Super-TFC for a Super-LHCb (II) 1. S-TFC on xTCA – Mapping TFC on Marseille hardware 2. ECS+TFC relay in FE Interface 3. Protocol and commands for FE/BE.
Future experiment specific needs for LHCb OpenFabrics/Infiniband Workshop at CERN Monday June 26 Sai Suman Cherukuwada Sai Suman Cherukuwada and Niko Neufeld.
Common meeting of CERN DAQ teams CERN May 3 rd 2006 Niko Neufeld PH/LBC for the LHCb Online team.
Niko Neufeld HL-LHC Trigger, Online and Offline Computing Working Group Topical Workshop Sep 5 th 2014.
SRB data transmission Vito Palladino CERN 2 June 2014.
LKr readout and trigger R. Fantechi 3/2/2010. The CARE structure.
Niko Neufeld, CERN. Trigger-free read-out – every bunch-crossing! 40 MHz of events to be acquired, built and processed in software 40 Tbit/s aggregated.
Management of the LHCb DAQ Network Guoming Liu *†, Niko Neufeld * * CERN, Switzerland † University of Ferrara, Italy.
Niko Neufeld LHCC Detector Upgrade Review, June 3 rd 2014.
1 Event Building L1&HLT Implementation Review Niko Neufeld, CERN-EP Tuesday, April 29 th.
SL-PGA firmware overview M. Sozzi Pisa - January 30/31, 2014.
DAQ & ConfDB Configuration DB workshop CERN September 21 st, 2005 Artur Barczyk & Niko Neufeld.
Artur BarczykRT2003, High Rate Event Building with Gigabit Ethernet Introduction Transport protocols Methods to enhance link utilisation Test.
Introduction to DAQ Architecture Niko Neufeld CERN / IPHE Lausanne.
Grzegorz Korcyl - Jagiellonian University, Kraków Grzegorz Korcyl – PANDA TDAQ Workshop, Giessen April 2010.
The Evaluation Tool for the LHCb Event Builder Network Upgrade Guoming Liu, Niko Neufeld CERN, Switzerland 18 th Real-Time Conference June 13, 2012.
Grzegorz Kasprowicz1 Level 1 trigger sorter implemented in hardware.
Eric Hazen1 Ethernet Readout With: E. Kearns, J. Raaf, S.X. Wu, others... Eric Hazen Boston University.
Graciela Perera Department of Computer Science and Information Systems Slide 1 of 18 INTRODUCTION NETWORKING CONCEPTS AND ADMINISTRATION CSIS 3723 Graciela.
HTCC coffee march /03/2017 Sébastien VALAT – CERN.
Giovanna Lehmann Miotto CERN EP/DT-DI On behalf of the DAQ team
Modeling event building architecture for the triggerless data acquisition system for PANDA experiment at the HESR facility at FAIR/GSI Krzysztof Korcyl.
DAQ Requirements M. Villa 21/02/2011.
LHCb and InfiniBand on FPGA
High Rate Event Building with Gigabit Ethernet
Chapter 4 Network Layer All material copyright
Electronics Trigger and DAQ CERN meeting summary.
Enrico Gamberini, Giovanna Lehmann Miotto, Roland Sipos
TELL1 A common data acquisition board for LHCb
RT2003, Montreal Niko Neufeld, CERN-EP & Univ. de Lausanne
CMS DAQ Event Builder Based on Gigabit Ethernet
The LHCb Event Building Strategy
VELO readout On detector electronics Off detector electronics to DAQ
Example of DAQ Trigger issues for the SoLID experiment
Event Building With Smart NICs
LHCb Electronics Brainstorm
LHCb Trigger, Online and related Electronics
Chapter 4 Network Layer Computer Networking: A Top Down Approach 5th edition. Jim Kurose, Keith Ross Addison-Wesley, April Network Layer.
Network Processors for a 1 MHz Trigger-DAQ System
LHCb Online Meeting November 15th, 2000
TELL1 A common data acquisition board for LHCb
Presentation transcript:

DAQ interface + implications for the electronics Niko Neufeld LHCb Electronics Upgrade June 10 th, 2010

The LHCb 1 MHz DAQ DAQ & electronics upgrade - Niko Neufeld 2 Detector TFC System L0 trigger LHC clock MEP Request Front-End Readout Board VELO STOT RICH ECalHCalMuon L0 Trigger Event data Timing and Fast Control Signals Control and Monitoring data Readout Board FE Electronics CASTOR x 50 x 313

A few numbers you know… # links (UTP Cat 6)~ 3000 Event-size (total – zero-suppressed)35 kB Read-out rate1 MHz # read-out boards313 output bandwidth / read-out boardup to 4 Gigabit/s (4 Ethernet links) # farm-nodes550 (will grow to 1500) input bandwidth / farm-node1 Gigabit (1 dedicated Ethernet link) # core-routers1 (1260 ports) # edge routers50 (48 ports) Event-rate to storage2000 Hz (nominal) DAQ & electronics upgrade - Niko Neufeld 3

The “data-source” TEL(UK)L1 DAQ & electronics upgrade - Niko Neufeld 4 12 * 1.6 Gbit/s 9.6 Gbit/s Preprocessing Feature Extraction Zero-suppression Event fragment merging FDAQ framing Frame transmission 4 x 1000 BaseT To DAQ 4 x 1 Gbit/s

MEP Event fragments from up to 16 triggers packed into one Multi-Eventfragment Packet (MEP) A MEP must fit into one IPv4 packet ( 64 kB max !) IPv4 packets will be fragmented into Ethernet frames of MTU size MEP header is 12 bytes only (Event-number + length) IP address information is used in event-building Unreliable / no duplication / no re-transmission DAQ & electronics upgrade - Niko Neufeld 5 Header Event 2 Event 1 Event n MEP Ether header IP header Payload Ether header IP header Payload Ether header IP header Payload

Dataflow in LHCb 6 6 Switch Buffer Data Acquisition Switch 2 Readout Supervisor tells readout boards where events must be sent (round-robin) 3 Readout boards do not buffer, so switch must 1 Event Builders inform Readout supervisor about availability “Send next event to EB1” “Send next event to EB2” Event Builder 2 Event Builder 1 Readout Supervisor EB2 available for events EB1 available for events DAQ & electronics upgrade - Niko Neufeld

So we can do 1 MHz Or can we ?

Can we do 40 MHz? How

40 = 10 x 4 We get a factor 10 from the link- speed: 1 Gigabit  10 Gigabit throughout the DAQ We get a factor 4 by deploying several slices of the DAQ network and farm ( a concept taken from the CMS DAQ) DAQ & electronics upgrade - Niko Neufeld 9

Buffer Usage DAQ & electronics upgrade - Niko Neufeld 10 Buffer usage in Force10 E1200i with a test using kHz event-rate 256 MB shared between 48 ports 17 ports used as “output” Non- uniformity under investigation Buffering in switches remains the main challenge

Inside the network bubble Currently only 1 device identified which can handle the current LHCb traffic There are probably a few more These devices are very expensive and it is not clear if they will scale up by a factor 10 within 5 years  –try to build network from smaller & cheaper units –need to ease buffering requirements DAQ & electronics upgrade - Niko Neufeld 11 Main Router Need buffering in TELL boards

Buffering Need buffering for at least 4 s –corresponds to 4 20 Gbit/s per 10 Gbit/s link Any kind of “traffic-shaping” (random backoff, pulling the data requires buffering in the sources MEPs must be accessible randomly in this buffer (not like in a FIFO) DAQ & electronics upgrade - Niko Neufeld 12

Reimplementing MEP MEP was successful but quite some work was needed to work with a “non- standard” protocol. Special tools, hardwired settings, special requirements on hard- and software MEP2 will be more standard and implemented in UDP  –IPv4 RFC 791 must be implemented, as well as ARP (RFC 826) and ICMP a.k.a. ping (RFC 1122) finally UDP (RFC 768) –MEP size and maximum packing factor will be increased: 2 MB or even infinite if required DAQ & electronics upgrade - Niko Neufeld 13

Miscelleaneous ECS –It must be possible take a snapshot of a number of MEPs by latching them into a memory which can be accessed from the ECS –ECS must be accessible via a Gigabit Ethernet link which is strictly independent from the data links –It must be possible to reset the ECS interface out-of- band –It must be possible to do a consistent latch of all counters pertaining to the data-flow in a coherent way so that they can be read by the ECS –Write-only registers are not permitted. Debugging –A data-generator must be provided which works at wire-speed for all output links and is completely independent of the input (front-end). DAQ & electronics upgrade - Niko Neufeld 14