We have a complex real time application running RHEL 7.4 on ESX as a virtual machine. The VM is hosted on a large NAS-storage. Currently we have repeated latency bursts also evidenced in a running ping command to a secondary instance.

Pings nominally take ~0.1-0.9ms between the systems, but suddenly we see outbursts of up to 900ms! Additonally, at the start of the outburst the system clock jumps but then is not progressing during the burst.

ping latency

Who can help us identify the source? One hypothesis is that the linux VM is "hanging" waiting on NAS-response. Another hypothesis is a network issue, the third being an ESX-issue.

  • 1
    I think your biggest problem is here, "a complex real time application running [...] as a virtual machine". – roaima Oct 21 '19 at 13:44
  • You're right: there's actually at least 3 possibles root causes for this issue. AT LEAST ... Proceed with dichotomy, try to identify the real root cause, and then we may help. But people here do not have crystal ball ;-) – binarym Oct 21 '19 at 13:46

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.