This looks something to do with google load balancer or the kube-proxy. I setup
a google Http load balancer pointing to the NodePort and see the same issue. If
I open up the service as LoadBalancer and access it directly I don’t see any
issues.
On 5/21/18, 10:07 PM, "kubernetes-users@googleg
Just wanna note we're seeing this on our end too. Narrowed it down to being the
GCE Ingress by testing our deployment behind the older style LoadBalancer
service, where we are seeing sub-200ms responses. Also confirmed Cloudflare
wasn't the issue by preventing the host from being resolved via SS
The issue appears to be back. For the past few nights I've been seeing
sporadic 4-5 second response times on calls. Again, it's calls like OPTIONS
that really stand out.
On Thursday, May 17, 2018 at 11:37:28 AM UTC-7, Dave Jensen wrote:
> Thank you, I think this solved the issue. We set the Idl
Thank you, I think this solved the issue. We set the IdleTimeout (in
Golang) to 620s and, in our staging environment, I have not seen a request
take longer than 200ms.
On Wednesday, May 16, 2018 at 2:41:32 PM UTC-7, Nicks wrote:
>
> I created an HTTP LB setup on GCP using a golang HTTP server wi
I created an HTTP LB setup on GCP using a golang HTTP server without
kubernetes and was able to see rare long-tail latencies in >1 second. After
I set `IdleTimeout` to larger than ten minutes, I stopped seeing those slow
responses. The echoheaders image uses nginx and doesn't set
`keepalive_ti
On Monday, May 14, 2018 at 5:10:55 PM UTC-4, francois...@polynom.io wrote:
> Le jeudi 19 avril 2018 02:14:28 UTC+2, Dave Jensen a écrit :
> > We have what I believe to be a very straightforward ingress setup on GKE.
> > However, we started noticing random slowdowns almost immediately. On
> > furt
Le jeudi 19 avril 2018 02:14:28 UTC+2, Dave Jensen a écrit :
> We have what I believe to be a very straightforward ingress setup on GKE.
> However, we started noticing random slowdowns almost immediately. On further
> investigation it looked like the time to first byte (TTFB) was very slow (1 -
Hi Dave,
What version of GKE (master) are you currently using?
Is there a URL that can be tested/probed? (i.e. repro case)?
As a start, it would be useful to post an anonymized `tcpdump` of the HTTP
session that exhibits the delay, the output of curl with timing (something
like:
https://stack
Hi Dave, we are experiencing identical conditions with a very similar setup.
Please let us know if you learn anything and we will do the same.
--
You received this message because you are subscribed to the Google Groups
"Kubernetes user discussion and Q&A" group.
To unsubscribe from this group
> Have you tried using the service nodeport? You can do that and send
traffic to one node, this will be round robin to all pods anyways. To see
if it happens too.
I just tried a portforward to the service (instead of a single pod) and
it's blazing fast.
Either the GCP LB is bad or the ingress
Hello fa...,
We followed the tutorial [3] and it technically works but it does not
perform to expectations.
Dave
On Sunday, April 22, 2018 at 11:15:59 AM UTC-7, fa...@google.com wrote:
>
>
> Hello Dave,
>
> Since your question is technical, you may get help from community experts
> and enthus
The @GCPcloud twitter account said that I would receive a follow-up from
support early last week. There has been no response from them. I've decided
to file an issue on the github repo for the project.
On Monday, April 23, 2018 at 9:57:26 AM UTC-7, Ahmet Alp Balkan wrote:
>
> I suspect this issu
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 Go
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 [k
Is there a community of Kubernetes/GCP users that is more active than this
Google Group?
On Wednesday, April 18, 2018 at 5:14:28 PM UTC-7, Dave Jensen wrote:
>
> We have what I believe to be a very straightforward ingress setup on GKE.
> However, we started noticing random slowdowns almost immed
15 matches
Mail list logo
