Difference between revisions of "EJFAT Group Meeting May. 12, 2022"

From epsciwiki
Jump to navigation Jump to search
Line 42: Line 42:
 
** Using script based LB Control Plane
 
** Using script based LB Control Plane
 
** ERSAP feed end bottleneck needs investigation; Timmer's blaster may provide relief
 
** ERSAP feed end bottleneck needs investigation; Timmer's blaster may provide relief
** EJFAT subnet VLAN 937 172.19.22.0/24
+
** Spare EJFAT equip loaners:
** EJFAT equip inventory:
 
*** Loaners:
 
**** (2) switches: ejfat-sw, daq-cc-f109-sw-1
 
 
**** (3) DAQ dev machines ''indra-s[1-3]'' 129.57.29/109.23[0-2]
 
**** (3) DAQ dev machines ''indra-s[1-3]'' 129.57.29/109.23[0-2]
**** (4) DAQ Farm machines ''dafarm6[1-4]'' currently on 129.57.29.17[1-4]
+
**** (4) DAQ Farm machines ''dafarm6[1-4]'' currently on 129.57.29.17[1-4] - 32 Xeon 2.0Ghz cores
 
**** (17) Hall-D machines - ''gluon120-36'' 129.57.172.1[20-36]
 
**** (17) Hall-D machines - ''gluon120-36'' 129.57.172.1[20-36]
**** 10Gbs NICs
+
**** (4) 10Gbs NICs
 
*** On Order:
 
*** On Order:
**** Compute Equip.- ETA 1 June - '''sans 100Gbs NICs''' (ETA 1 July)
+
**** (6) 100Gbs NICs - ETA 1 July
 
**** Networking Equip. - ETA <s>1 July</s> 5 October
 
**** Networking Equip. - ETA <s>1 July</s> 5 October
 
** LAN Speed Tests (iperf3 to indra-s2)
 
** LAN Speed Tests (iperf3 to indra-s2)
Line 71: Line 68:
 
**** May be able to use new VTP f/w with  Hall-B VTP's - (Ben Raydo)
 
**** May be able to use new VTP f/w with  Hall-B VTP's - (Ben Raydo)
 
**** CODA 3.10 + ERSAP for new VTP f/w
 
**** CODA 3.10 + ERSAP for new VTP f/w
**** CODA 2.0 for old VTP f/w
+
**** CODA 2.0 (non-streaming) for old VTP f/w
 
**** [https://jeffersonlab-my.sharepoint.com/:p:/r/personal/goodrich_jlab_org/Documents/EJFAT/hall-b_test.pptx?d=w31891fd52c1a420ea2b29efcdf5f9ed2&csf=1&web=1&e=JGyxHO Diagram]
 
**** [https://jeffersonlab-my.sharepoint.com/:p:/r/personal/goodrich_jlab_org/Documents/EJFAT/hall-b_test.pptx?d=w31891fd52c1a420ea2b29efcdf5f9ed2&csf=1&web=1&e=JGyxHO Diagram]
** Downstream:
+
** Downstream (June/July):
 
*** [https://www.epj-conferences.org/articles/epjconf/abs/2021/05/epjconf_chep2021_04005/epjconf_chep2021_04005.html HOSS] - June 1
 
*** [https://www.epj-conferences.org/articles/epjconf/abs/2021/05/epjconf_chep2021_04005/epjconf_chep2021_04005.html HOSS] - June 1
 
**** parallelize writing of raw data files
 
**** parallelize writing of raw data files
Line 86: Line 83:
 
**** [https://docs.google.com/presentation/d/1m3rFm-1GymYv8zGimlAjL1NmWtXVfyIQdGzhx_j_BKE/edit?usp=sharing  Hall-D EJFAT use case]
 
**** [https://docs.google.com/presentation/d/1m3rFm-1GymYv8zGimlAjL1NmWtXVfyIQdGzhx_j_BKE/edit?usp=sharing  Hall-D EJFAT use case]
 
**** [https://jeffersonlab-my.sharepoint.com/personal/bmorris_jlab_org/Documents/Microsoft%20Teams%20Chat%20Files/JLab%20Network%20-%20HallD-to-EJFAT.png  Hall-D EJFAT Network Diagram]
 
**** [https://jeffersonlab-my.sharepoint.com/personal/bmorris_jlab_org/Documents/Microsoft%20Teams%20Chat%20Files/JLab%20Network%20-%20HallD-to-EJFAT.png  Hall-D EJFAT Network Diagram]
 +
**** Configuration:
 +
***** ''ejfat-sw'' 100Gbs switcg
 +
***** (6) New Computers w/ X CPUs + U280 fpga
 +
***** (?) Retired Farm Nodes
 +
***** EJFAT subnet VLAN 937 172.19.22.0/24
 
*** [http://www.dpdk.org DPDK]
 
*** [http://www.dpdk.org DPDK]
 
*** IPV6 testing
 
*** IPV6 testing

Revision as of 18:21, 12 May 2022

The meeting time is 11:00am.

Connection Info:

You can connect using ZoomGov Video conferencing (ID: 161 012 5238). (Click "Expand" to the right for details -->):

Meeting URL
 https://jlab-org.zoomgov.com/j/1610125238?pwd=QnEvcjV6VFFndWZsQW15SmJKU0RJZz09&from=addon

Meeting ID
161 012 5238

Passcode
503371

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:

  • Previous meeting
  • Situation:
    • Rec'd new f/w build 28 April
      • Specs
      • Restores Jumbo Frames
      • arp, ping - working
      • Port entropy field - Passed Test for data_id stream horizontal reassembly with 10 streams
    • Using script based LB Control Plane
    • ERSAP feed end bottleneck needs investigation; Timmer's blaster may provide relief
    • Spare EJFAT equip loaners:
        • (3) DAQ dev machines indra-s[1-3] 129.57.29/109.23[0-2]
        • (4) DAQ Farm machines dafarm6[1-4] currently on 129.57.29.17[1-4] - 32 Xeon 2.0Ghz cores
        • (17) Hall-D machines - gluon120-36 129.57.172.1[20-36]
        • (4) 10Gbs NICs
      • On Order:
        • (6) 100Gbs NICs - ETA 1 July
        • Networking Equip. - ETA 1 July 5 October
    • LAN Speed Tests (iperf3 to indra-s2)
      • indra-s3 - 30 Gbs
      • indra-s1 - 20 Gbs
      • alkaid - 17 Gbs
      • indra-s2 - 10 Gbs
      • Look at iperf2 for network testing
      • Look at ROCE / NIC
      • Hall B VTPs on .167. subnet
  • Pending:
    • Support C libraries for LB Host Control Plane - in unit test code review
    • ESnet smartnic open-source GitHub repo (May)
    • ESnet private, forkable Jlab P4 and simulations GitHub repo (May)
  • To Do:
    • Near Term (May):
      • Hall-B FT calorimeter and hodoscope streaming readout test - Pending OK from Sergey B.
        • May be able to use Abbott's indra-s1 setup
        • May be able to use new VTP f/w with Hall-B VTP's - (Ben Raydo)
        • CODA 3.10 + ERSAP for new VTP f/w
        • CODA 2.0 (non-streaming) for old VTP f/w
        • Diagram
    • Downstream (June/July):
      • HOSS - June 1
        • parallelize writing of raw data files
        • distribute raw data across multiple compute nodes for calibration skims
        • 1 Gbs at hi-luminosity
        • Control Plane
          • Will interact with SLURM
          • Python based (?)
          • Control Plane daemon for compute host (?)
          • Demonstrate CP based flexibility/elasticity
        • Hall-D comms with DAQ 109 subnet require network customization; DAQ 29 subnet available
        • Hall-D EJFAT use case
        • Hall-D EJFAT Network Diagram
        • Configuration:
          • ejfat-sw 100Gbs switcg
          • (6) New Computers w/ X CPUs + U280 fpga
          • (?) Retired Farm Nodes
          • EJFAT subnet VLAN 937 172.19.22.0/24
      • DPDK
      • IPV6 testing
      • RT2022 - August 01-05 Conference
  • AOT