Difference between revisions of "EJFAT Group Meeting Nov. 10, 2022"

Latest revision as of 17:04, 10 November 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/16184166709

Meeting ID
161 8416 6709

Passcode
(none)

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
Status:
- Using ESnet FPGA f/w build 28 April
  - Specs
  - Jumbo Frames
  - arp, ping, ICMP filtering
  - Port entropy
- Script based LB Control Plane
- EJFAT VLAN Open for Business:
  - Hosts running Ubuntu 20.04
  - 1 Gbs i/f are: ejfat-1, ejfat-2, ejfat-3, ejfat-3, ejfat-5, ejfat-6, ejfat-fs
  - 100 Gbs i/f are: ejfat-1-daq, ejfat-2-daq, ejfat-3-daq, ejfat-3-daq, ejfat-5-daq, ejfat-6-daq, ejfat-fs-daq
  - LBs: 172.19.22.241-247, indra-s2
    - 172.19.22.241 - Currently reserved for Carl
    - 172.19.22.242 - Currently reserved for Stacey
    - 172.19.22.247 - Currently reserved for Mike
  - indra-s2 upgraded to Ubuntu 20.04 LB sucessfully installed, now on EJFAT VLAN / DAQ lo-speed networks via Indra-Lab switch
  - /daq-fs/gyurjyan self-contained ERSAP event processing package
- Spare EJFAT equip loaners:
  - (4) DAQ dev machines indra-s[1-3] 129.57.29/109.23[0-2]
    - alkaid: 24 Xeon Gold 3.4 GHz cores, 100Gbs
    - indra-s1: 24 Xeon Gold 3.0 GHz cores, 100Gbs
    - indra-s2: 32 Xeon Gold 3.2 GHz cores, 100Gbs
    - indra-s3: 32 Xeon Gold 2.3 GHz cores, 100Gbs, 750GB ram disk
  - (4) DAQ Farm machines dafarm6[1-4] currently on 129.57.29.17[1-4] - each 32 Xeon 2.0Ghz cores - 1 Gbs NIC + (4) 10Gbs Spare NICs
  - (4) Unbuilt DAQ Farm machines - each 32 Xeon 2.0Ghz cores - 1 Gbs NIC + (4) 10Gbs Spare NICs
- PR408870 PR408938 (2) 100Gbs Arista switches, ~~transceivers, cables~~, etc - ETA ~~1 July~~ ~~5 October~~ Ships 11 November
- FPGA LB Throughput - max sustained 90Gbs with s/w data generation
- RT 2022 Paper - submitted August 22 - up to 8 mos. review process
Current Activities
- Test plan for all pieces required for integration test
  - Plan A: CLAS12 files -> Carl C++ Packetizer -> LB -> Carls's C++ Reassembler -> ERSAP
  - Plan B: CLAS12 files -> ERSAP C++ Packetizer -> LB -> Mike's C++ Reassembler -> (tcp) -> ERSAP
  - Plan C: Simulated Packets -> LB -> Mike's C++ Reassembler -> Simulated Host Loading/Feedback
- Control Plane
  - Compute Farm Feed Back Monitor
  - Have working RL (Q-Learning) Schedule Density Adjuster (to be integrated)
  - Need to define Optimality Criterion for Schedule Density
  - DP Supervisor
  - Demonstrate CP based flexibility/elasticity
- Abstract Submission for CHEP 2023 (Nov 17)
- Paper for ACAT 2022 Conf Proc. (TBD)
- Engage Data Science Dept for CP AI component
ESnet Update:
- IPV6 neighbor discovery
- LB F/W Installation Manual - with PCI buffer allocation assurance steps
- In ESnet Legal Review
  - Support C libraries for LB Host Control Plane
  - ESnet smartnic open-source GitHub repo - in legal review
  - ESnet private, forkable Jlab P4 and simulations GitHub repo - in legal review
  - FPGA LB data generation capability
Next Steps:
- FireHose Benchmark
- Network Performance:
  - cpusets
  - Pktgen-DPDK
  - Receive Side Scaling
  - Packet Loss Studies / LB Round Robin Studies - migrated to Compute Center / EJFAT / EJFAT VLAN
  - DAQ/VTP Data Generation Test Harness - 40 Gbs initially - after FEG ???
  - Host NICs
  - Host S/W Reassembly - better algorithms, buffering, asynchronicity, etc.
  - EJFAT UDP Transmission Performance
  - Need better parameters for event reassembly/reconstruction
  - DPDK will own NIC bypassing kernel, etc. - ESnet reports can stream 100 Gbps using DPDK; Pktgen-DPDK
  - Look at ROCE / NIC
- SPDK for hyper storage performance
- ESnet UDP tuning
- SLURM env for EJFAT VLAN (Hess)
- Vivado Licesnses for new machines - AI/ML ? D. Lawrence POC
- Open Nic Shell
Back Burner / Downstream:
- Hall-B FT calorimeter and hodoscope streaming readout test
  - May be able to use Abbott's indra-s1 setup
  - May be able to use new VTP f/w with Hall-B VTP's
  - CODA 3.10 + ERSAP for new VTP f/w
  - CODA 2.0 (non-streaming) for old VTP f/w
  - Diagram
  - Hall-B to start taking data June 8
  - Hall B VTPs on .167. subnet
- HOSS
  - parallelize writing of raw data files
  - distribute raw data across multiple compute nodes for calibration skims
  - 1 Gbs at hi-luminosity
  - Hall-D comms with DAQ 109 subnet require network customization; (EJFAT subnet)
  - Hall-D EJFAT use case
  - Hall-D EJFAT Network Diagram
- IPV6 testing
AOT

@@ Line 61: / Line 61: @@
 ** [https://misportal.jlab.org/reqs/pr/viewPr.do?prNum=408870 PR408870] [https://misportal.jlab.org/reqs/pr/viewPr.do?prNum=408938 PR408938] (2) 100Gbs Arista switches, <s>transceivers, cables</s>, etc - ETA <s>1 July</s> <s>5 October</s> Ships '''11 November'''
 ** FPGA LB Throughput - max sustained 90Gbs with s/w data generation
+** RT 2022 Paper - submitted August 22 - up to 8 mos. review process
 * '''Current Activities'''
-** ERSAP feed end bottleneck needs investigation; Timmer/Gyurjyan investigating
+** Test plan for all pieces required for integration test
-** EJFAT VLAN Infrastructure
+*** Plan A: CLAS12 files -> Carl C++ Packetizer -> LB -> Carls's C++ Reassembler -> ERSAP
-*** Test plan for all pieces required for integration test
+*** Plan B: CLAS12 files -> ERSAP C++ Packetizer  -> LB -> Mike's C++ Reassembler -> (tcp) -> ERSAP
-**** Plan A: CLAS12 files -> Carl C++ Packetizer -> LB -> Carls's C++ Reassembler -> ERSAP
+*** Plan C: Simulated Packets -> LB -> Mike's C++ Reassembler -> Simulated Host Loading/Feedback
-**** Plan B: CLAS12 files -> ERSAP C++ Packetizer  -> LB -> Mike's C++ Reassembler -> (tcp) -> ERSAP
+** Control Plane
-**** Plan C: Simulated Packets -> LB -> Mike's C++ Reassembler -> Simulated Host Loading/Feedback
+*** Compute Farm Feed Back Monitor
-*** Control Plane
+*** Have working RL (Q-Learning) Schedule Density Adjuster (to be integrated)
-**** Compute Farm Feed Back Monitor
+*** Need to define Optimality Criterion for Schedule Density
-**** AI/ML Schedule Density Adjuster - have working RL (Q-Learning) component
+*** DP Supervisor
-**** DP Supervisor
 *** Demonstrate CP based flexibility/elasticity
-*** Paper for ACAT 2022 Conf Proc. (TBD)
+** Abstract Submission for CHEP 2023 (Nov 17)
+** Paper for ACAT 2022 Conf Proc. (TBD)
+** Engage Data Science Dept for CP AI component
 * ESnet Update:
 ** IPV6 neighbor discovery
@@ Line 103: / Line 105: @@
 ** [https://spdk.io/ SPDK] for hyper storage performance
 ** [https://fasterdata.es.net/host-tuning/linux/udp-tuning/ ESnet UDP tuning]
-*** SLURM env for EJFAT VLAN (Hess)
+** SLURM env for EJFAT VLAN (Hess)
 ** Vivado Licesnses for new machines - AI/ML ? D. Lawrence POC
 ** [https://github.com/Xilinx/open-nic-shell Open Nic Shell]
-** '''RT 2022 Paper - submitted August 22 - up to 8 mos. review process'''
 * Back Burner / Downstream:
 ** Hall-B FT calorimeter and hodoscope streaming readout test

Difference between revisions of "EJFAT Group Meeting Nov. 10, 2022"

Latest revision as of 17:04, 10 November 2022

Connection Info:

Agenda:

Navigation menu

Search