Network and Transfer Metrics WG (10th June 2015) Minutes
Agenda/slides presented at https://indico.cern.ch/event/382624/
CHEP paper was submitted, thanks for all contributions. Please add comments at
Very special thanks for major contributions to the WG and farewell to Soichi Hayashi (OSG) and Aaron Brown (Internet2)
- perfSONAR mesh re-organization
- Proximity service
Next meetings: 8 July, 2 Sept, 7 Oct, - all at 4pm CEST
1) perfSONAR status
Detailed report from the WG was presented on Monday at the LHCOPN-LHCONE meeting - LBL Berkeley (US) (https://indico.cern.ch/event/376098/)
In collaboration with ESNet, a bug was found in parsing tracepath results, causing significant reduction in efficiency of getting tracepath results. Plan is to revert back to traceroutes and only run low frequency tracepath tests until the issue is fixed. Another bug currently under investigation, degradation of the latencies seen for certain period during the day (every day repeatedly) likely connected to a restart/refresh of certain processes.
Mesh changes: RRC-KI-T1 sonars added to the OPN mesh
WLCG-wide meshes proposal - see slides.
2) Network Incidents Follow Up
Network performance incidents process - new GGUS SU (WLCG Network Throughput) already available, more information athttps://twiki.cern.ch/twiki/bin/view/LCG/NetworkTransferMetrics#Network_Performance_Incidents
Mailing lists summary:
WG mailing list - ALL
wlcg-perfsonar-support - connected to GGUS SU (WLCG perfSONAR Support), contains Mesh Leaders
wlcg-network-throughput - connected to GGUS SU (WLCG Network Throughput), based on WG list, includes wlcg-perfsonar-support, FTS, FAX, Alice (Costin), ATLAS (Ale), CMS (Tony), LHCb (Joel, Stefan)
ACTION: Please let me know if you’d like to change the contacts for the wlcg-network-throughput
3) Datastore/esmond status - detailed report at the next meeting
4) Pilot projects
Proximity service - see slides
Test deployed esmond2mq at CERN (developed in collaboration with LHCb), core functionality works fine, waiting for the OSG datastore to enter production in order to run it continuously.
Submitted set of patches to enable publishing to the message bus directly from the RSV collector, waiting on OSG to evaluate/test them.
FTS Study - report from Saul - detailed report at the next meeting
Pointing out some interesting features:
Suggestion about improving things re: TCP streams in FTS: