Difference between revisions of "EJFAT Group Meeting Sep. 7, 2023"

From epsciwiki
Jump to navigation Jump to search
(Created page with "The meeting time is 11:00am Eastern/USA. === Connection Info: === <div class="toccolours mw-collapsible mw-collapsed"> You can connect using [ https://jlab-org.zoomgov.com/j/...")
 
 
(2 intermediate revisions by the same user not shown)
Line 52: Line 52:
 
### Configure hosts to use tunnel, confirm traffic flow is as expected - '''<s>IPV4</s>, IPV6 pending'''
 
### Configure hosts to use tunnel, confirm traffic flow is as expected - '''<s>IPV4</s>, IPV6 pending'''
 
#### '''"There is a mapping that you can use to obtain IPv6 addresses from the IPv4 address. E.g., IPv4 129.57.177.121 ---> IPv6 2620:0:22f0:677::177:121 "'''
 
#### '''"There is a mapping that you can use to obtain IPv6 addresses from the IPv4 address. E.g., IPv4 129.57.177.121 ---> IPv6 2620:0:22f0:677::177:121 "'''
 +
#### In general, for the hi-speed network: IPv4: 129.57.177.0/25  IPv6: 2620:0:22f0:677::<3rd octet of IPv4>:<4th octet of IPv4>/64  And for the low-speed (mgmt) network: IPv4: 129.57.177.128/25 IPv6: 2620:0:22f0:1677::<3rd octet of IPv4>:<4th octet of IPv4>/64
 
### '''Unexpected Prefix''' - have withdrawn the advertisement of that network from the EJFAT tunnel  
 
### '''Unexpected Prefix''' - have withdrawn the advertisement of that network from the EJFAT tunnel  
 +
### '''Jumbo Frame availability thru ESnet network layers to LB'''
 
## JLab Preliminary NERSC Test
 
## JLab Preliminary NERSC Test
 
### <s>Vardan's Metrics/Horizontal Scaling</s> - '''Using for CHEP Paper'''
 
### <s>Vardan's Metrics/Horizontal Scaling</s> - '''Using for CHEP Paper'''
Line 68: Line 70:
 
## '''LDRD Pending'''
 
## '''LDRD Pending'''
 
## '''Targeting May 2024 during Beam downtime in Hall B'''
 
## '''Targeting May 2024 during Beam downtime in Hall B'''
 +
## '''Data Comprehensibility Studies using Hall B/D sample data'''
 
# [https://ieeexplore.ieee.org/document/10046405 RT2022 Paper]: Submission Process Complete
 
# [https://ieeexplore.ieee.org/document/10046405 RT2022 Paper]: Submission Process Complete
 
# [https://jeffersonlab.sharepoint.com/:b:/r/sites/SciComp/Shared%20Documents/EPSCI/EJFAT/EJFAT_ACAT_2022_QL_sub.pdf?csf=1&web=1&e=dR566P ACAT2022 Paper]: - submitted
 
# [https://jeffersonlab.sharepoint.com/:b:/r/sites/SciComp/Shared%20Documents/EPSCI/EJFAT/EJFAT_ACAT_2022_QL_sub.pdf?csf=1&web=1&e=dR566P ACAT2022 Paper]: - submitted
Line 77: Line 80:
 
## Run with real CP using simware sender/rcvrs to compare to simulations
 
## Run with real CP using simware sender/rcvrs to compare to simulations
 
## Compare all results to Queuing Theory predictions
 
## Compare all results to Queuing Theory predictions
−
# '''EJFAT Phase II (new mtgs in September)'''
+
# '''EJFAT Phase II - will use this mtg in September'''
 
# Demo Ready EJFAT Instance
 
# Demo Ready EJFAT Instance
 
# EJFAT Operational Status Board -> Prometheus Reporting
 
# EJFAT Operational Status Board -> Prometheus Reporting

Latest revision as of 15:31, 7 September 2023

The meeting time is 11:00am Eastern/USA.

Connection Info:

You can connect using [ https://jlab-org.zoomgov.com/j/1611828967?pwd=UVVCS0pUVW5FMlphT0lRQXdoQ0o4Zz09&from=addon ZoomGov Video conferencing (ID: 161 012 5238)]. (Click "Expand" to the right for details -->): 

Meeting URL
 https://jlab-org.zoomgov.com/j/1611828967

Meeting ID
161 182 8967

Passcode
570041

Want to dial in from a phone?

Dial one of the following numbers:
US: +1 669 254 5252 or +1 646 828 7666 or +1 551 285 1373 or +1 669 216 1590 or 833 568 8864 (Toll Free)

Enter the meeting ID and passcode followed by #

Connecting from a room system?
Dial: bjn.vc or 199.48.152.152 and enter your meeting ID & passcode


Agenda:

  1. Previous meeting
  2. Announcements:
  3. NERSC Test Development:
    1. Data Source:
      1. JLAB, CLAS12, pre-triggered events - 1 channel
      2. Front End Packetizer pending mods for Tick-sync msg to CP - UDP packet to port on CP Host
    2. Derek Howard (ESnet) to build CP for EJFAT and Perlmutter at NERSC with JLab assisting - complete
      1. Local Installation of ESnet CP - complete
    3. Data Sink:
      1. Perlmutter
      2. ERSAP
    4. Networking for Test
      1. L3VPN Design with ESNet
      2. Vet the cybersecurity controls with the security group.
      3. Implement Local network configuration changes/cybersecurity controls
      4. Configure L3VPN, establish peering
      5. Relocate to HACS-4
      6. Configure hosts to use tunnel, confirm traffic flow is as expected - IPV4, IPV6 pending
        1. "There is a mapping that you can use to obtain IPv6 addresses from the IPv4 address. E.g., IPv4 129.57.177.121 ---> IPv6 2620:0:22f0:677::177:121 "
        2. In general, for the hi-speed network: IPv4: 129.57.177.0/25 IPv6: 2620:0:22f0:677::<3rd octet of IPv4>:<4th octet of IPv4>/64 And for the low-speed (mgmt) network: IPv4: 129.57.177.128/25 IPv6: 2620:0:22f0:1677::<3rd octet of IPv4>:<4th octet of IPv4>/64
      7. Unexpected Prefix - have withdrawn the advertisement of that network from the EJFAT tunnel
      8. Jumbo Frame availability thru ESnet network layers to LB
    5. JLab Preliminary NERSC Test
      1. Vardan's Metrics/Horizontal Scaling - Using for CHEP Paper
      2. Preliminary Testing: New LB f/w and CP: JLab, ESnet
        1. new CP bug - rule update failure
        2. NERSC may be ready for connectivity test soon
    6. Test Plans - JLab, ESnet, NERSC:
  4. Hall B CLAS12 detector streaming test
    1. Switch 7050 is expected to arrive some time around October; we have already transceivers, short cables and patch panel to connect up to 32 VTPs to it using two 10GBit links per VTP
    2. Fiber installation between hallb forward carriage and hallb counting room should be done this summer, will be enough for 24 VTPs using two 10GBit links per VTP
    3. We have only one fiber between hallb counting room and counting house second floor available right now, will order more fibers installation, may take several months
    4. There are several available fibers between counting house second floor and computer center (like 6), we can use a couple of them for our test
    5. Summary: sometime in October, we should have 48 10GBit links from 24 VTPs connected to the switch in hallb counting room, with that switch connected to computer center by 2x100GBit links
    6. Need to develop CONOPS with Streaming group (Abbott)
    7. LDRD Pending
    8. Targeting May 2024 during Beam downtime in Hall B
    9. Data Comprehensibility Studies using Hall B/D sample data
  5. RT2022 Paper: Submission Process Complete
  6. ACAT2022 Paper: - submitted
  7. CHEP 2023 Conference Publication - QL/PID focused - Derek/Mike/Carl - deadline September 8, 2023
    1. Define the problem - all constants, parameters, etc. for both homogeneous cluster, heterogeneous cluster
    2. Run baseline sims for both using no control
    3. Incrementally show value of PID control; first Kp, then Kp+Kd, then Kp+Kd+Ki
    4. Show value of QL control
    5. Run with real CP using simware sender/rcvrs to compare to simulations
    6. Compare all results to Queuing Theory predictions
  8. EJFAT Phase II - will use this mtg in September
  9. Demo Ready EJFAT Instance
  10. EJFAT Operational Status Board -> Prometheus Reporting
  11. Resources:
    1. HPDF
  12. AOT
Retrieved from "https://wiki.jlab.org/epsciwiki/index.php?title=EJFAT_Group_Meeting_Sep._7,_2023&oldid=3823"