Uploaded image for project: 'Network Observability'
  1. Network Observability
  2. NETOBSERV-1889

Regression in FLP and ebpf-agent resource utilization in 1.7.0 builds

XMLWordPrintable

    • Icon: Bug Bug
    • Resolution: Done
    • Icon: Major Major
    • netobserv-1.7
    • netobserv-1.7-candidate
    • eBPF
    • None
    • False
    • None
    • False
    • NetObserv - Sprint 259, NetObserv - Sprint 260
    • Important

      Description of problem:

      CD and IP workloads monthly runs shows regression for Sept run on 1.7.0 builds compared to their Aug run build.
      CD Comparison:

      rssFLPTotals	rssFLPTotals	avg(value)	Fail	26.28%	1554664653	1963277844																			
rssEBPFTotals	rssEBPFTotals	avg(value)	Fail	24.62%	7776460800	9691220705

       
      IP Comparison:

      rssFLPTotals	rssFLPTotals	avg(value)	Fail	18.25%	785475472.3	928792576																			
rssEBPFTotals	rssEBPFTotals	avg(value)	Fail	10.75%	4899831808	5426441272

      Slack discussion: https://redhat-internal.slack.com/archives/C03SHCD5C9M/p1725374622896389

       

      hey-ho tests: https://docs.google.com/spreadsheets/d/1qakBaK1dk_rERO30k1cSR4W-Nn0SXW4A3lqQ1sZC4rE/edit?gid=430054068#gid=430054068

       

      NDH comparison 09/30:

      cpuEBPFTotals	cpuEBPFTotals	avg(value)	Fail	11.71%	0.8600900597	0.9608221604																			
rssFLPTotals	rssFLPTotals	avg(value)	Fail	28.28%	437881304.6	561735522.5

              jtakvori Joel Takvorian
              rhn-support-memodi Mehul Modi
              Mehul Modi Mehul Modi
              Votes:
              0 Vote for this issue
              Watchers:
              4 Start watching this issue

                Created:
                Updated:
                Resolved: