I suspect this issue is rooted in the GCP infrastructure and does not have much to do with the open source part of the system. There's a good #gke community on kubernetes slack channel, however I don't think anyone will be able to help with this particular issue.
I recommend reaching out to the Google Cloud Platform Support. They should be able to help by routing your issue through the right channels. I also recommend you to come up with a good way to reproduce and measure the TTFB and provide some endpoints that Google folks can reproduce on their end. To measure tail latency etc. You can use tools like Apache AB or https://github.com/rakyll/hey to do send some load and see the tail latencies. On Sun, Apr 22, 2018 at 11:16 AM fadya via Kubernetes user discussion and Q&A <kubernetes-users@googlegroups.com> wrote: > > Hello Dave, > > Since your question is technical, you may get help from community experts > and enthusiasts at serverfault.com. Make sure you include proper tags > when you ask your question. For example, if using Google Cloud Kubernetes > Engine [1] you may tag it as [google-kubernetes-engine], and [kubernetes]; > but if using a Kubernetes cluster on Compute Engine, you may tag it as > [kubernetes], and [google-compute-engine]. > > On the other hand, while I was checking the Ingress prerequisites [2], I > understood that “Google Kubernetes Engine deploys an ingress controller on > the master” for you, and like this tutorial [3] it creates the load > balancer. According to the prerequisites, and this github page [4], it is > still in beta, and you may check the limitations and expectations [5] with > latency on the same page. > That said, and if you suspect a defect with the Ingress Controller/ Google > Cloud Load Balancer you may open a report through issue tracker [6]. But > after verifying the correct settings with the community, and reviewing the > above as not an expected behavior. I hope that helps. > > [1] https://console.cloud.google.com/kubernetes > [2] > https://kubernetes.io/docs/concepts/services-networking/ingress/#prerequisites > [3] > https://cloud.google.com/kubernetes-engine/docs/tutorials/http-balancer > [4] > https://github.com/kubernetes/ingress-gce/blob/master/BETA_LIMITATIONS.md#glbc-beta-limitations > [5] > https://github.com/kubernetes/ingress-gce/blob/master/BETA_LIMITATIONS.md#latency > [6] https://cloud.google.com/support/docs/issue-trackers > > -- > You received this message because you are subscribed to the Google Groups > "Kubernetes user discussion and Q&A" group. > To unsubscribe from this group and stop receiving emails from it, send an > email to kubernetes-users+unsubscr...@googlegroups.com. > To post to this group, send email to kubernetes-users@googlegroups.com. > Visit this group at https://groups.google.com/group/kubernetes-users. > For more options, visit https://groups.google.com/d/optout. > -- You received this message because you are subscribed to the Google Groups "Kubernetes user discussion and Q&A" group. To unsubscribe from this group and stop receiving emails from it, send an email to kubernetes-users+unsubscr...@googlegroups.com. To post to this group, send email to kubernetes-users@googlegroups.com. Visit this group at https://groups.google.com/group/kubernetes-users. For more options, visit https://groups.google.com/d/optout.
