From 36de30c623802d05759e373fae2c0a3ed6b53344 Mon Sep 17 00:00:00 2001 From: YuviPanda Date: Thu, 16 Jun 2022 17:06:54 -0700 Subject: [PATCH] Switch meom-ige core node to n1-highmem-2 g1-small is too small apparently - CPU usage was too high, and the nodes kept going into NotReady. Ref https://github.com/2i2c-org/infrastructure/issues/1423 --- docs/topic/cluster-design.md | 2 +- terraform/gcp/projects/meom-ige.tfvars | 11 +---------- terraform/gcp/variables.tf | 4 ++-- 3 files changed, 4 insertions(+), 13 deletions(-) diff --git a/docs/topic/cluster-design.md b/docs/topic/cluster-design.md index d9e9a5a835..5c16f3d779 100644 --- a/docs/topic/cluster-design.md +++ b/docs/topic/cluster-design.md @@ -35,7 +35,7 @@ or enabling [Network Policy](https://cloud.google.com/kubernetes-engine/docs/how requires more resources as well. With poorly structured experimentation, the current recommendation is to run -3 `g1-small` instances for a cluster without config connector or network policy, +3 `n1-highmem-2` instances for a cluster without config connector or network policy, or a single `n1-highmem-4` instance for a cluster with either of those options turned on. This needs to be better investigated. diff --git a/terraform/gcp/projects/meom-ige.tfvars b/terraform/gcp/projects/meom-ige.tfvars index 3554275f47..e3ee34c72c 100644 --- a/terraform/gcp/projects/meom-ige.tfvars +++ b/terraform/gcp/projects/meom-ige.tfvars @@ -1,16 +1,7 @@ prefix = "meom-ige" project_id = "meom-ige-cnrs" -# Minimum number of nodes required to fit kube-system is either -# 2 n1-highcpu-2 nodes, or 3 g1-small nodes. If you don't enable -# networkpolicy, you can get away with 1 n1-custom-4-3840 node - -# but with that enable, calico-typha wants 2 replicas that -# must run on two nodes since they both want the same hostport. -# 3 g1-small is 13$ a month, wile a single n2-highcpu-2 is -# already 36$ a month. We want very low base price, and -# our core nodes will barely see any CPU usage, so g1-small is -# the way to go -core_node_machine_type = "g1-small" +core_node_machine_type = "n1-highmem-2" # Single-tenant cluster, network policy not needed enable_network_policy = false diff --git a/terraform/gcp/variables.tf b/terraform/gcp/variables.tf index ad8613763c..5adcfbff72 100644 --- a/terraform/gcp/variables.tf +++ b/terraform/gcp/variables.tf @@ -118,7 +118,7 @@ variable "zone" { variable "core_node_machine_type" { type = string - default = "g1-small" + default = "n1-highmem-2" description = <<-EOT Machine type to use for core nodes. @@ -126,7 +126,7 @@ variable "core_node_machine_type" { for a cluster. We should try to run with as few of them as possible. - For single-tenant clusters, a single g1-small node seems + For single-tenant clusters, a single n1-highmem-2 node seems enough - if network policy and config connector are not on. For others, please experiment to see what fits. EOT