Network Engineering for High Speed Data Sharing
The document discusses modernizing network architecture to improve data sharing performance for science. It proposes separating portal logic from data handling by placing data on dedicated high-performance infrastructure in science DMZs. This allows data to be efficiently transferred between facilities while portals focus on search and access. The Petascale DTN project achieved over 50Gbps transfers between HPC sites using this model. Long-term, interconnected science DMZs could create a global high-performance network enabling efficient data movement for discovery.
Gen AI in Business - Global Trends Report 2024.pdf
Network Engineering for High Speed Data Sharing
1. Network Engineering for High Speed
Data Sharing
Eli Dart, Science Engagement
Energy Sciences Network (ESnet)
Lawrence Berkeley National Laboratory
AGU 2018
Washington, DC
December 12, 2018
4. Data Placement: A Common Problem
• Scientists often need to move data from where it is to where it needs to be
– Observation to analysis
– Assemble data set from multiple sources
– Transfer data to/from supercomputer center
• Data movement tools run on systems which use networks – lots involved:
– Servers, storage
– Networks, security policy
• Lots of ways to assemble these things architecture
• Traditional architectures are not performant in today’s context
– Large data objects
– Data sets with tens of thousands (or more) files
12/20/20184
5. Science Data Portals
• Large repositories of scientific data
– Climate data
– Sky surveys (astronomy, cosmology)
– Many others
– Data search, browsing, access
• Many scientific data portals were designed 15+ years ago
– Single-web-server design
– Data browse/search, data access, user awareness all in a single system
– All the data goes through the portal server
• In many cases by design
• E.g. embargo before publication (enforce access control)
– Better than old command-line FTP, but outdated by today’s standards
12/20/20185
6. Legacy Portal Design
10GE
Border Router
WAN
Firewall
Enterprise
perfSONAR
perfSONAR
Filesystem
(data store)
10GE
Portal
Server
Browsing path
Query path
Data path
Portal server applications:
web server
search
database
authentication
data service
12/20/20186
• Very difficult to improve performance
without architectural change
– Software components all tangled
together
– Complexity makes security hard
– Many components aren’t scalable
• What does architectural change mean?
7. Architectural Examination of Data Portals
• Common data portal functions (most portals have these)
– Search/query/discovery
– Data download method for data access
– GUI for browsing by humans
– API for machine access – ideally incorporates search/query + download
• Performance pain is primarily in the data handling piece
– Rapid increase in data scale eclipsed legacy software stack capabilities
– Portal servers often stuck in enterprise network
• Can we “disassemble” the portal and put the pieces back together better?
12/20/20187
8. Legacy Portal Design
10GE
Border Router
WAN
Firewall
Enterprise
perfSONAR
perfSONAR
Filesystem
(data store)
10GE
Portal
Server
Browsing path
Query path
Data path
Portal server applications:
web server
search
database
authentication
data service
12/20/20188
9. Next-Generation Portal Leverages Science DMZ
10GE10GE
10GE
10GE
Border Router
WAN
Science DMZ
Switch/Router
Firewall
Enterprise
perfSONAR
perfSONAR
10GE
10GE
10GE
10GE
DTN
DTN
API DTNs
(data access governed
by portal)
DTN
DTN
perfSONAR
Filesystem
(data store)
10GE
Portal
Server
Browsing path
Query path
Portal server applications:
web server
search
database
authentication
Data Path
Data Transfer Path
Portal Query/Browse Path
12/20/20189
https://peerj.com/articles/cs-144/
10. NCAR RDA Data Portal
• Let’s say I have a nice compute allocation at NERSC – a national
supercomputer center
• Let’s say I need some data from NCAR for my project
• https://rda.ucar.edu/
• Data sets (there are many more, but these are two examples):
• https://rda.ucar.edu/datasets/ds199.1/
• https://rda.ucar.edu/datasets/ds313.0/
• Download to NERSC (could also do ALCF or NCSA or OLCF)
12/20/201810
19. Put The Data On Dedicated Infrastructure
• We have separated the data handling from the portal logic
• Portal is still its normal self, but enhanced
– Portal GUI, database, search, etc. all function as they did before
– Query returns pointers to data objects in the Science DMZ
– Portal is now freed from the data servers (run it in the Cloud if you want!)
• Data handling is separate, and scalable
– High-performance data cluster in the Science DMZ
– Scale as much as you need to without modifying the portal software
• Shift data management to computing centers
– Computing centers are set up for large-scale data
– Let them handle the large-scale data, and let the portal do the orchestration
of data placement
• https://peerj.com/articles/cs-144/ - Modern Research Data Portal paper
12/20/201819
20. Data And HPC: The Petascale DTN Project
• Built on top of the Science DMZ
• Effort to improve data transfer performance between the DOE ASCR HPC
facilities at ANL, LBNL, and ORNL, and also NCSA.
– Multiple current and future science projects need to transfer data between HPC
facilities
– Performance was slow, configurations inconsistent
– Performance goal of 15 gigabits per second (equivalent to 1PB/week)
– Realize performance goal for routine Globus transfers without special tuning
• Reference data set is 4.4TB of cosmology simulation data
• Use performant, easy-to-use tools with production options on
– Globus Transfer service (previously Globus Online)
– Use GUI just like a user would, with default options
• E.g. integrity checksums enabled, as they should be
• No arcane magic!
12/20/201820
24. Modernized Cyberinfrastructure
• This is an example of the capabilities of modern cyberinfrastructure
– High speed networks
– Science DMZ design pattern
– Modern Research Data Portal design pattern
– HPC facilities
– High performance data platforms
• Together these enable dramatically-improved data placement performance
• Large-scale data analysis is now possible
– Data from portals analyzed at supercomputer centers
– Data shared between supercomputer centers
12/20/201824
25. Larger Strategic Picture
• Across the scientific community, larger structures are being built
– HPC facilities combined with experiments
– DTNs between campuses
– These create the platform for future scientific discoveries.
• Building DMZs, DTNs, and similar things for scientists puts the power of
modern cyberinfrastructure in the hands of the people who will make the
discoveries that change our world for the better.
• By doing this work, we help bring about the future that we all want - better
medicine, better technology, more energy, a cleaner environment, etc.
12/20/201825
26. Long-Term Vision
ESnet
(Big Science facilities,
DOE labs)
Internet2 + Regionals
(US Universities and
affiliated institutions)
International Networks
(Universities and labs in Europe,
Asia, Americas, Australia, etc.)
High-performance feature-rich
science network ecosystem
Commercial Clouds
(Amazon, Google,
Microsoft, etc.)
Agency Networks
(NASA, NOAA, etc.)
Campus HPC
+
Data
12/20/201826
27. It’s All A Bunch Of Science DMZs
High-performance feature-rich
science network ecosystem
DTN
DTN
DTN
DTN
DMZDMZ
DMZDMZ
DTN
DATA
DTN
DMZDMZ
DTN
DTN
DMZDMZ
DATA
DTN DTN
DMZDMZ
Parallel
Filesystem
DTN DTN
DTN
DTNDMZDMZ
DATA
DTN
DTN
DMZDMZ
Experiment
Data Archive
DTN
DTN
DTN
DTN
DTN DMZDMZ
DTN DTN
DMZDMZ
DATA
12/20/201827
28. It’s All A Bunch Of Science DMZs
High-performance feature-rich
science network ecosystem
DTN
DTN
DTN
DTN
DMZDMZ
DMZDMZ
DTN
DATA
DTN
DMZDMZ
DTN
DTN
DMZDMZ
DATA
DTN DTN
DMZDMZ
Parallel
Filesystem
DTN DTN
DTN
DTNDMZDMZ
DATA
DTN
DTN
DMZDMZ
Experiment
Data Archive
DTN
DTN
DTN
DTN
DTN DMZDMZ
DTN DTN
DMZDMZ
DATA
HPC Facilities
Single Lab
Experiments
Data
Portal
LHC
Experiments
University
Computing
12/20/201828
29. Thanks!
Eli Dart - dart@es.net
Energy Sciences Network (ESnet)
Lawrence Berkeley National Laboratory
engage@es.net
http://my.es.net/
http://www.es.net/
http://fasterdata.es.net/
31. ESnet - the basic facts:
High-speed international networking facility,
optimized for data-intensive science:
• connecting 50 labs, plants and facilities with >150 networks,
universities, research partners globally
• supporting every science office, and serving as an integral
extension of many instruments
• 400Gbps transatlantic extension in production since Dec 2014
• >1.3 Tbps of external connectivity, including high speed access
to commercial partners such as Amazon
• growing number university connections to better serve LHC
science (and eventually: Belle II)
• older than commercial Internet, growing ~twice as fast
Areas of strategic focus: software, science engagement.
• Engagement effort now 12% of staff
• Software capability critical to next-generation network
31
61. Say NO to SCP (2016)
• Using the right data transfer tool is very important
• Sample Results: Berkeley, CA to Argonne, IL (near Chicago ) RTT = 53 ms,
network capacity = 10Gbps.
• Notes
– scp is 24x slower than GridFTP on this path!!
– to get more than 1 Gbps (125 MB/s) disk to disk requires RAID array.
– (Assumes host TCP buffers are set correctly for the RTT)
Tool Throughput
scp 330 Mbps
wget, GridFTP, FDT, 1 stream 6 Gbps
GridFTP and FDT, 4 streams 8 Gbps (disk limited)
61 – ESnet Science Engagement (engage@es.net) -
12/20/2018
68. Context: Science DMZ Adoption
• DOE National Laboratories
– Supercomputer centers, LHC sites, experimental facilities
– Both large and small sites
• NSF CC* programs have funded many Science DMZs
– Large investments across the US university complex: over $100M
– Significant strategic importance
• Outside the USA
– Australia
– Brazil
– UK
– More…
12/20/201868
69. Strategic Impacts
• What does this mean?
– We are in the midst of a significant cyberinfrastructure upgrade
– Enterprise networks need not be unduly perturbed
• Significantly enhanced capabilities compared to 5 years ago
– Terabyte-scale data movement is much easier
– Petabyte-scale data movement possible outside the LHC experiments
• ~3.1Gbps = 1PB/month
• ~14Gbps = 1PB/week
– Widely-deployed tools are much better (e.g. Globus)
• Metcalfe’s Law of Network Utility
– Value of Science DMZ proportional to the number of DMZs
• n2 or n(logn) doesn’t matter – the effect is real
– Cyberinfrastructure value increases as we all upgrade
12/20/201869
70. Next Steps – Building On The Science DMZ
• Enhanced cyberinfrastructure substrate now exists
– Wide area networks (ESnet, GEANT, NRENs, Internet2, Regionals)
– Science DMZs connected to those networks
– DTNs in the Science DMZs
• What does the scientist see?
– Scientist sees a science application
• Data transfer
• Data portal
• Data analysis
– Science applications are the user interface to networks and DMZs
• Large-scale data-intensive science requires that we build science
applications on top of the substrate components
12/20/201870