Difference between revisions of "EJFAT EPSCI Meeting Mar. 30, 2022"

From epsciwiki
Jump to navigation Jump to search
Line 49: Line 49:
 
* To Do:
 
* To Do:
 
** Near Term:
 
** Near Term:
*** <s>[[Test Plans | Test Plan]]</s>
 
 
*** RT2022 - April 01 submission
 
*** RT2022 - April 01 submission
 
*** Performance Measures / ERSAP
 
*** Performance Measures / ERSAP
*** <s>Control Plane ARP poisoning</s>
 
***<s> '''alkaid''' -> jumbo frames</s>
 
***<s> Linux IP stack buffer size</s>
 
 
*** data_id <-> reassembly port mapping
 
*** data_id <-> reassembly port mapping
 
*** Hall-B has an old version of the firmware, so VTP will send TCP (no UDP). Could intercept and resend UDP VTP streams (12 streams, if we get 3 crates) to how LB can handle 12 ID's and do effectively an aggregation.
 
*** Hall-B has an old version of the firmware, so VTP will send TCP (no UDP). Could intercept and resend UDP VTP streams (12 streams, if we get 3 crates) to how LB can handle 12 ID's and do effectively an aggregation.
 
** Downstream:
 
** Downstream:
 
*** P4 enhancements for  
 
*** P4 enhancements for  
****<s> data_id <-> reassembly port mapping</s>
 
 
**** P4 ipv4 ping, arp
 
**** P4 ipv4 ping, arp
 
*** C-based control plane
 
*** C-based control plane
Line 67: Line 62:
 
*** EJFAT Subnet
 
*** EJFAT Subnet
 
*** Hall-D EJFAT + SLURM use case
 
*** Hall-D EJFAT + SLURM use case
* Issues:
 
**<s> O/S / Dev Tools on indra-s1,3, '''alkaid''', etc.</s>
 
**<s> Abbott spare 8 nodes - OBE?</s>
 
**<s> Hall-D spare 10Gbs NICs - OBE?</s>
 
**<s> CentOS 7 install on interim boxes - OBE?</s>
 
**<s> [https://jeffersonlab-my.sharepoint.com/:b:/r/personal/goodrich_jlab_org/Documents/EJFAT/EJFAT%20Network%20Setup.pdf?csf=1&web=1&e=hkUo8k Diagram] - OBE?</s>
 
 
* AOT
 
* AOT
 
<hr>
 
<hr>

Revision as of 16:58, 30 March 2022

The meeting time is 2:00pm.

Connection Info:

You can connect using ZoomGov Video conferencing (ID: 161 203 8101). (Click "Expand" to the right for details -->):

Meeting URL
https://jlab-org.zoomgov.com/j/1612038101?pwd=Yk96QUcyT1NDVTRRUGNtOFVSSTdaUT09&from=addon

Meeting ID
161 203 8101

Passcode
378382

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:
    • Testing with End-to-end EJFAT ERSAP solution on FPGA LB
    • Jumbo Frames - indra-s2,s3, alkaid, fpga
    • Linux IP stack buffer size increased
    • Using script based LB Control Plane
    • Control Plane Gratuitous Arp cache updating (Scapy)
    • Awaiting Compute Equip.- ETA 1 June
    • Awaiting Networking Equip. - ETA 1 July
    • Benchmarks for RT2022 (April 1)
  • Pending:
    • Support C libraries for LB Host Control Plane
    • ESnet smartnic open-source GitHub repo (April)
    • ESnet private, forkable Jlab P4 and simulations GitHub repo (April)
  • To Do:
    • Near Term:
      • RT2022 - April 01 submission
      • Performance Measures / ERSAP
      • data_id <-> reassembly port mapping
      • Hall-B has an old version of the firmware, so VTP will send TCP (no UDP). Could intercept and resend UDP VTP streams (12 streams, if we get 3 crates) to how LB can handle 12 ID's and do effectively an aggregation.
    • Downstream:
      • P4 enhancements for
        • P4 ipv4 ping, arp
      • C-based control plane
        • Feedback from Compute hosts design
        • Control Plane daemon for compute host
      • IPV6 testing
      • EJFAT Subnet
      • Hall-D EJFAT + SLURM use case
  • AOT