chore: add scaletest convenience script (#7819)

- Adds a convenience script `scaletest.sh` to automate process of running scale tests
- Enables pprof endpoint by default, and captures pprof traces before tearing down infra.
- Improves idempotency of coder_init.sh
- Removes the promtest.Float64 invocations in workspacetraffic runner, these metrics will be in prometheus.
- Increases default workspace traffic output to 40KB/s/workspace.

.gitignore

@@ -58,5 +58,5 @@ site/stats/
 # Loadtesting
 ./scaletest/terraform/.terraform
 ./scaletest/terraform/.terraform.lock.hcl
-terraform.tfstate.*
+scaletest/terraform/secrets.tfvars
-**/*.tfvars
+.terraform.tfstate.*

.prettierignore

@@ -61,8 +61,8 @@ site/stats/
 # Loadtesting
 ./scaletest/terraform/.terraform
 ./scaletest/terraform/.terraform.lock.hcl
-terraform.tfstate.*
+scaletest/terraform/secrets.tfvars
-**/*.tfvars
+.terraform.tfstate.*
 # .prettierignore.include:
 # Helm templates contain variables that are invalid YAML and can't be formatted
 # by Prettier.

scaletest/README.md

@@ -0,0 +1,83 @@
+# Scale Testing
+
+This folder contains CLI commands, Terraform code, and scripts to aid in performing load tests of Coder.
+At a high level, it performs the following steps:
+
+- Using the Terraform code in `./terraform`, stands up a preconfigured Google Cloud environment
+  consisting of a VPC, GKE Cluster, and CloudSQL instance.
+  > **Note: You must have an existing Google Cloud project available.**
+- Creates a dedicated namespace for Coder and installs Coder using the Helm chart in this namespace.
+- Configures the Coder deployment with random credentials and a predefined Kubernetes template.
+  > **Note:** These credentials are stored in `${PROJECT_ROOT}/scaletest/.coderv2/coder.env`.
+- Creates a number of workspaces and waits for them to all start successfully. These workspaces
+  are ephemeral and do not contain any persistent resources.
+- Waits for 10 minutes to allow things to settle and establish a baseline.
+- Generates web terminal traffic to all workspaces for 30 minutes.
+- Directly after traffic generation, captures goroutine and heap snapshots of the Coder deployment.
+- Tears down all resources (unless `--skip-cleanup` is specified).
+
+## Usage
+
+The main entrypoint is the `scaletest.sh` script.
+
+```console
+$ scaletest.sh --help
+Usage: scaletest.sh --name <name> --project <project> --num-workspaces <num-workspaces> --scenario <scenario> [--dry-run] [--skip-cleanup]
+```
+
+### Required arguments:
+
+- `--name`: Name for the loadtest. This is added as a prefix to resources created by Terraform (e.g. `joe-big-loadtest`).
+- `--project`: Google Cloud project in which to create the resources (example: `my-loadtest-project`).
+- `--num-workspaces`: Number of workspaces to create (example: `10`).
+- `--scenario`: Deployment scenario to use (example: `small`). See `terraform/scenario-*.tfvars`.
+
+> **Note:** In order to capture Prometheus metrics, you must define the environment variables
+> `SCALETEST_PROMETHEUS_REMOTE_WRITE_USER` and `SCALETEST_PROMETHEUS_REMOTE_WRITE_PASSWORD`.
+
+### Optional arguments:
+
+- `--dry-run`: Do not perform any action and instead print what would be executed.
+- `--skip-cleanup`: Do not perform any cleanup. You will be responsible for deleting any resources this creates.
+
+### Environment Variables
+
+All of the above arguments may be specified as environment variables. Consult the script for details.
+
+### Prometheus Metrics
+
+To capture Prometheus metrics from the loadtest, two environment
+
+## Scenarios
+
+A scenario defines a number of variables that override the default Terraform variables.
+A number of existing scenarios are provided in `scaletest/terraform/scenario-*.tfvars`.
+
+For example, `scenario-small.tfvars` includes the following variable definitions:
+
+```
+nodepool_machine_type_coder      = "t2d-standard-2"
+nodepool_machine_type_workspaces = "t2d-standard-2"
+coder_cpu                        = "1000m" # Leaving 1 CPU for system workloads
+coder_mem                        = "4Gi"   # Leaving 4GB for system workloads
+```
+
+To create your own scenario, simply add a new file `terraform/scenario-$SCENARIO_NAME.tfvars`.
+In this file, override variables as required, consulting `vars.tf` as needed.
+You can then use this scenario by specifying `--scenario $SCENARIO_NAME`.
+For example, if your scenario file were named `scenario-big-whopper2x.tfvars`, you would specify
+`--scenario=big-whopper2x`.
+
+## Utility scripts
+
+A number of utility scripts are provided in `lib`, and are used by `scaletest.sh`:
+
+- `coder_shim.sh`: a convenience script to run the `coder` binary with a predefined config root.
+  This is intended to allow running Coder CLI commands against the loadtest cluster without
+  modifying a user's existing Coder CLI configuration.
+- `coder_init.sh`: Performs first-time user setup of an existing Coder instance, generating
+  a random password for the admin user. The admin user is named `admin@coder.com` by default.
+  Credentials are written to `scaletest/.coderv2/coder.env`.
+- `coder_workspacetraffic.sh`: Runs traffic generation against the loadtest cluster and creates
+  a monitoring manifest for the traffic generation pod. This pod will restart automatically
+  after the traffic generation has completed.

scaletest/lib/coder_init.sh

@@ -11,17 +11,27 @@ fi
 [[ -n ${VERBOSE:-} ]] && set -x
 
 CODER_URL=$1
-CONFIG_DIR="${PWD}/.coderv2"
+DRY_RUN="${DRY_RUN:-0}"
+PROJECT_ROOT="$(git rev-parse --show-toplevel)"
+# shellcheck source=scripts/lib.sh
+source "${PROJECT_ROOT}/scripts/lib.sh"
+CONFIG_DIR="${PROJECT_ROOT}/scaletest/.coderv2"
 ARCH="$(arch)"
 if [[ "$ARCH" == "x86_64" ]]; then
 	ARCH="amd64"
 fi
 PLATFORM="$(uname | tr '[:upper:]' '[:lower:]')"
 
-mkdir -p "${CONFIG_DIR}"
+if [[ -f "${CONFIG_DIR}/coder.env" ]]; then
+	echo "Found existing coder.env in ${CONFIG_DIR}!"
+	echo "Nothing to do, exiting."
+	exit 0
+fi
+
+maybedryrun "$DRY_RUN" mkdir -p "${CONFIG_DIR}"
 echo "Fetching Coder CLI for first-time setup!"
-curl -fsSLk "${CODER_URL}/bin/coder-${PLATFORM}-${ARCH}" -o "${CONFIG_DIR}/coder"
+maybedryrun "$DRY_RUN" curl -fsSLk "${CODER_URL}/bin/coder-${PLATFORM}-${ARCH}" -o "${CONFIG_DIR}/coder"
-chmod +x "${CONFIG_DIR}/coder"
+maybedryrun "$DRY_RUN" chmod +x "${CONFIG_DIR}/coder"
 
 set +o pipefail
 RANDOM_ADMIN_PASSWORD=$(tr </dev/urandom -dc _A-Z-a-z-0-9 | head -c16)
@@ -31,7 +41,7 @@ CODER_FIRST_USER_USERNAME="coder"
 CODER_FIRST_USER_PASSWORD="${RANDOM_ADMIN_PASSWORD}"
 CODER_FIRST_USER_TRIAL="false"
 echo "Running login command!"
-"${CONFIG_DIR}/coder" login "${CODER_URL}" \
+DRY_RUN="$DRY_RUN" "${PROJECT_ROOT}/scaletest/lib/coder_shim.sh" login "${CODER_URL}" \
 	--global-config="${CONFIG_DIR}" \
 	--first-user-username="${CODER_FIRST_USER_USERNAME}" \
 	--first-user-email="${CODER_FIRST_USER_EMAIL}" \
@@ -39,7 +49,7 @@ echo "Running login command!"
 	--first-user-trial=false
 
 echo "Writing credentials to ${CONFIG_DIR}/coder.env"
-cat <<EOF >"${CONFIG_DIR}/coder.env"
+maybedryrun "$DRY_RUN" cat <<EOF >"${CONFIG_DIR}/coder.env"
 CODER_FIRST_USER_EMAIL=admin@coder.com
 CODER_FIRST_USER_USERNAME=coder
 CODER_FIRST_USER_PASSWORD="${RANDOM_ADMIN_PASSWORD}"
@@ -47,5 +57,7 @@ CODER_FIRST_USER_TRIAL="${CODER_FIRST_USER_TRIAL}"
 EOF
 
 echo "Importing kubernetes template"
-"${CONFIG_DIR}/coder" templates create --global-config="${CONFIG_DIR}" \
+DRY_RUN="$DRY_RUN" "$PROJECT_ROOT/scaletest/lib/coder_shim.sh" templates create \
-	--directory "${CONFIG_DIR}/templates/kubernetes" --yes kubernetes
+	--global-config="${CONFIG_DIR}" \
+	--directory "${CONFIG_DIR}/templates/kubernetes" \
+	--yes kubernetes

scaletest/lib/coder_shim.sh

@@ -0,0 +1,11 @@
+#!/usr/bin/env bash
+
+# This is a shim for easily executing Coder commands against a loadtest cluster
+# without having to overwrite your own session/URL
+PROJECT_ROOT="$(git rev-parse --show-toplevel)"
+# shellcheck source=scripts/lib.sh
+source "${PROJECT_ROOT}/scripts/lib.sh"
+CONFIG_DIR="${PROJECT_ROOT}/scaletest/.coderv2"
+CODER_BIN="${CONFIG_DIR}/coder"
+DRY_RUN="${DRY_RUN:-0}"
+maybedryrun "$DRY_RUN" exec "${CODER_BIN}" --global-config "${CONFIG_DIR}" "$@"

scaletest/lib/coder_workspacetraffic.sh

@@ -11,9 +11,13 @@ fi
 [[ -n ${VERBOSE:-} ]] && set -x
 
 LOADTEST_NAME="$1"
-CODER_TOKEN=$(./coder_shim.sh tokens create)
+PROJECT_ROOT="$(git rev-parse --show-toplevel)"
+CODER_TOKEN=$("${PROJECT_ROOT}/scaletest/lib/coder_shim.sh" tokens create)
 CODER_URL="http://coder.coder-${LOADTEST_NAME}.svc.cluster.local"
-export KUBECONFIG="${PWD}/.coderv2/${LOADTEST_NAME}-cluster.kubeconfig"
+export KUBECONFIG="${PROJECT_ROOT}/scaletest/.coderv2/${LOADTEST_NAME}-cluster.kubeconfig"
+
+# Clean up any pre-existing pods
+kubectl -n "coder-${LOADTEST_NAME}" delete pod coder-scaletest-workspace-traffic --force || true
 
 cat <<EOF | kubectl apply -f -
 apiVersion: v1
@@ -37,7 +41,7 @@ spec:
   - command:
     - sh
     - -c
-    - "curl -fsSL $CODER_URL/bin/coder-linux-amd64 -o /tmp/coder && chmod +x /tmp/coder && /tmp/coder --url=$CODER_URL --token=$CODER_TOKEN scaletest workspace-traffic"
+    - "curl -fsSL $CODER_URL/bin/coder-linux-amd64 -o /tmp/coder && chmod +x /tmp/coder && /tmp/coder --verbose --url=$CODER_URL --token=$CODER_TOKEN scaletest workspace-traffic --concurrency=0 --bytes-per-tick=4096 --tick-interval=100ms"
     env:
     - name: CODER_URL
       value: $CODER_URL

scaletest/scaletest.sh

@@ -0,0 +1,190 @@
+#!/usr/bin/env bash
+
+[[ -n ${VERBOSE:-} ]] && set -x
+set -euo pipefail
+
+PROJECT_ROOT="$(git rev-parse --show-toplevel)"
+# shellcheck source=scripts/lib.sh
+source "${PROJECT_ROOT}/scripts/lib.sh"
+
+DRY_RUN="${DRY_RUN:-0}"
+SCALETEST_NAME="${SCALETEST_NAME:-}"
+SCALETEST_NUM_WORKSPACES="${SCALETEST_NUM_WORKSPACES:-}"
+SCALETEST_SCENARIO="${SCALETEST_SCENARIO:-}"
+SCALETEST_PROJECT="${SCALETEST_PROJECT:-}"
+SCALETEST_PROMETHEUS_REMOTE_WRITE_USER="${SCALETEST_PROMETHEUS_REMOTE_WRITE_USER:-}"
+SCALETEST_PROMETHEUS_REMOTE_WRITE_PASSWORD="${SCALETEST_PROMETHEUS_REMOTE_WRITE_PASSWORD:-}"
+SCALETEST_SKIP_CLEANUP="${SCALETEST_SKIP_CLEANUP:-0}"
+
+script_name=$(basename "$0")
+args="$(getopt -o "" -l dry-run,help,name:,num-workspaces:,project:,scenario:,skip-cleanup -- "$@")"
+eval set -- "$args"
+while true; do
+	case "$1" in
+	--dry-run)
+		DRY_RUN=1
+		shift
+		;;
+	--help)
+		echo "Usage: $script_name --name <name> --project <project> --num-workspaces <num-workspaces> --scenario <scenario> [--dry-run] [--skip-cleanup]"
+		exit 1
+		;;
+	--name)
+		SCALETEST_NAME="$2"
+		shift 2
+		;;
+	--num-workspaces)
+		SCALETEST_NUM_WORKSPACES="$2"
+		shift 2
+		;;
+	--project)
+		SCALETEST_PROJECT="$2"
+		shift 2
+		;;
+	--scenario)
+		SCALETEST_SCENARIO="$2"
+		shift 2
+		;;
+	--skip-cleanup)
+		SCALETEST_SKIP_CLEANUP=1
+		shift
+		;;
+	--)
+		shift
+		break
+		;;
+	*)
+		error "Unrecognized option: $1"
+		;;
+	esac
+done
+
+dependencies gcloud kubectl terraform
+
+if [[ -z "${SCALETEST_NAME}" ]]; then
+	echo "Must specify --name"
+	exit 1
+fi
+
+if [[ -z "${SCALETEST_PROJECT}" ]]; then
+	echo "Must specify --project"
+	exit 1
+fi
+
+if [[ -z "${SCALETEST_NUM_WORKSPACES}" ]]; then
+	echo "Must specify --num-workspaces"
+	exit 1
+fi
+
+if [[ -z "${SCALETEST_SCENARIO}" ]]; then
+	echo "Must specify --scenario"
+	exit 1
+fi
+
+if [[ -z "${SCALETEST_PROMETHEUS_REMOTE_WRITE_USER}" ]] || [[ -z "${SCALETEST_PROMETHEUS_REMOTE_WRITE_PASSWORD}" ]]; then
+	echo "SCALETEST_PROMETHEUS_REMOTE_WRITE_USER or SCALETEST_PROMETHEUS_REMOTE_WRITE_PASSWORD not specified."
+	echo "No prometheus metrics will be collected!"
+	read -pr "Continue (y/N)? " choice
+	case "$choice" in
+	y | Y | yes | YES) ;;
+	*) exit 1 ;;
+	esac
+fi
+
+SCALETEST_SCENARIO_VARS="${PROJECT_ROOT}/scaletest/terraform/scenario-${SCALETEST_SCENARIO}.tfvars"
+if [[ ! -f "${SCALETEST_SCENARIO_VARS}" ]]; then
+	echo "Scenario ${SCALETEST_SCENARIO_VARS} not found."
+	echo "Please create it or choose another scenario:"
+	find "${PROJECT_ROOT}/scaletest/terraform" -type f -name 'scenario-*.tfvars'
+	exit 1
+fi
+
+if [[ "${SCALETEST_SKIP_CLEANUP}" == 1 ]]; then
+	log "WARNING: you told me to not clean up after myself, so this is now your job!"
+fi
+
+CONFIG_DIR="${PROJECT_ROOT}/scaletest/.coderv2"
+if [[ -d "${CONFIG_DIR}" ]] && files=$(ls -qAH -- "${CONFIG_DIR}") && [[ -z "$files" ]]; then
+	echo "Cleaning previous configuration"
+	maybedryrun "$DRY_RUN" rm -fv "${CONFIG_DIR}/*"
+fi
+maybedryrun "$DRY_RUN" mkdir -p "${CONFIG_DIR}"
+
+SCALETEST_SCENARIO_VARS="${PROJECT_ROOT}/scaletest/terraform/scenario-${SCALETEST_SCENARIO}.tfvars"
+SCALETEST_SECRETS="${PROJECT_ROOT}/scaletest/terraform/secrets.tfvars"
+SCALETEST_SECRETS_TEMPLATE="${PROJECT_ROOT}/scaletest/terraform/secrets.tfvars.tpl"
+
+log "Writing scaletest secrets to file."
+SCALETEST_NAME="${SCALETEST_NAME}" \
+	SCALETEST_PROJECT="${SCALETEST_PROJECT}" \
+	SCALETEST_PROMETHEUS_REMOTE_WRITE_USER="${SCALETEST_PROMETHEUS_REMOTE_WRITE_USER}" \
+	SCALETEST_PROMETHEUS_REMOTE_WRITE_PASSWORD="${SCALETEST_PROMETHEUS_REMOTE_WRITE_PASSWORD}" \
+	envsubst <"${SCALETEST_SECRETS_TEMPLATE}" >"${SCALETEST_SECRETS}"
+
+pushd "${PROJECT_ROOT}/scaletest/terraform"
+
+echo "Initializing terraform."
+maybedryrun "$DRY_RUN" terraform init
+
+echo "Setting up infrastructure."
+maybedryrun "$DRY_RUN" terraform apply --var-file="${SCALETEST_SCENARIO_VARS}" --var-file="${SCALETEST_SECRETS}" --auto-approve
+
+if [[ "${DRY_RUN}" != 1 ]]; then
+	SCALETEST_CODER_URL=$(<"${CONFIG_DIR}/url")
+else
+	SCALETEST_CODER_URL="http://coder.dryrun.local:3000"
+fi
+KUBECONFIG="${PROJECT_ROOT}/scaletest/.coderv2/${SCALETEST_NAME}-cluster.kubeconfig"
+echo "Waiting for Coder deployment at ${SCALETEST_CODER_URL} to become ready"
+maybedryrun "$DRY_RUN" kubectl --kubeconfig="${KUBECONFIG}" -n "coder-${SCALETEST_NAME}" rollout status deployment/coder
+
+echo "Initializing Coder deployment."
+DRY_RUN="$DRY_RUN" "${PROJECT_ROOT}/scaletest/lib/coder_init.sh" "${SCALETEST_CODER_URL}"
+
+echo "Creating ${SCALETEST_NUM_WORKSPACES} workspaces."
+DRY_RUN="$DRY_RUN" "${PROJECT_ROOT}/scaletest/lib/coder_shim.sh" scaletest create-workspaces \
+	--count "${SCALETEST_NUM_WORKSPACES}" \
+	--template=kubernetes \
+	--concurrency 10 \
+	--no-cleanup
+
+echo "Sleeping 10 minutes to establish a baseline measurement."
+maybedryrun "$DRY_RUN" sleep 600
+
+echo "Sending traffic to workspaces"
+maybedryrun "$DRY_RUN" "${PROJECT_ROOT}/scaletest/lib/coder_workspacetraffic.sh" "${SCALETEST_NAME}"
+maybedryrun "$DRY_RUN" kubectl --kubeconfig="${KUBECONFIG}" -n "coder-${SCALETEST_NAME}" wait pods coder-scaletest-workspace-traffic --for condition=Ready
+maybedryrun "$DRY_RUN" kubectl --kubeconfig="${KUBECONFIG}" -n "coder-${SCALETEST_NAME}" logs -f pod/coder-scaletest-workspace-traffic
+
+echo "Starting pprof"
+maybedryrun "$DRY_RUN" kubectl -n "coder-${SCALETEST_NAME}" port-forward deployment/coder 6061:6060 &
+pfpid=$!
+maybedryrun "$DRY_RUN" trap "kill $pfpid" EXIT
+
+echo "Waiting for pprof endpoint to become available"
+pprof_attempt_counter=0
+while ! maybedryrun "$DRY_RUN" timeout 1 bash -c "echo > /dev/tcp/localhost/6061"; do
+	if [[ $pprof_attempt_counter -eq 10 ]]; then
+		echo
+		echo "pprof failed to become ready in time!"
+		exit 1
+	fi
+	maybedryrun "$DRY_RUN" sleep 3
+done
+
+echo "Taking pprof snapshots"
+maybedryrun "$DRY_RUN" curl --silent --fail --output "${SCALETEST_NAME}-heap.pprof.gz" http://localhost:6061/debug/pprof/heap
+maybedryrun "$DRY_RUN" curl --silent --fail --output "${SCALETEST_NAME}-goroutine.pprof.gz" http://localhost:6061/debug/pprof/goroutine
+# No longer need to port-forward
+maybedryrun "$DRY_RUN" kill "$pfpid"
+maybedryrun "$DRY_RUN" trap - EXIT
+
+if [[ "${SCALETEST_SKIP_CLEANUP}" == 1 ]]; then
+	echo "Leaving resources up for you to inspect."
+	echo "Please don't forget to clean up afterwards:"
+	echo "cd terraform && terraform destroy --var-file=${SCALETEST_SCENARIO_VARS} --var-file=${SCALETEST_SECRETS} --auto-approve"
+	exit 0
+fi
+
+echo "Cleaning up"
+maybedryrun "$DRY_RUN" terraform destroy --var-file="${SCALETEST_SCENARIO_VARS}" --var-file="${SCALETEST_SECRETS}" --auto-approve

scaletest/terraform/README.md

@@ -1,43 +0,0 @@
-# Load Test Terraform
-
-This folder contains Terraform code and scripts to aid in performing load tests of Coder.
-It does the following:
-
-- Creates a GCP VPC.
-- Creates a CloudSQL instance with a global peering rule so it's accessible inside the VPC.
-- Creates a GKE cluster inside the VPC with separate nodegroups for Coder and workspaces.
-- Installs Coder in a new namespace, using the CloudSQL instance.
-
-## Usage
-
-> You must have an existing Google Cloud project available.
-
-1. Create a file named `override.tfvars` with the following content, modifying as appropriate:
-
-```terraform
-name = "some_unique_identifier"
-project_id = "some_google_project_id"
-```
-
-1. Inspect `vars.tf` and override any other variables you deem necessary.
-
-1. Run `terraform init`.
-
-1. Run `terraform plan -var-file=override.tfvars` and inspect the output.
-   If you are not satisfied, modify `override.tfvars` until you are.
-
-1. Run `terraform apply -var-file=override.tfvars`. This will spin up a pre-configured environment
-   and emit the Coder URL as an output.
-
-1. Run `coder_init.sh <coder_url>` to setup an initial user and a pre-configured Kubernetes
-   template. It will also download the Coder CLI from the Coder instance locally.
-
-1. Do whatever you need to do with the Coder instance:
-
-   > Note: To run Coder commands against the instance, you can use `coder_shim.sh <command>`.
-   > You don't need to run `coder login` yourself.
-
-   - To create workspaces, run `./coder_shim.sh scaletest create-workspaces --template="kubernetes" --count=N`
-   - To generate workspace traffic, run `./coder_trafficgen.sh <name of loadtest from your Terraform vars>`. This will keep running until you delete the pod `coder-scaletest-workspace-traffic`.
-
-1. When you are finished, you can run `terraform destroy -var-file=override.tfvars`.

scaletest/terraform/coder.tf

@@ -96,8 +96,12 @@ coder:
         secretKeyRef:
           name: "${kubernetes_secret.coder-db.metadata.0.name}"
           key: url
+    - name: "CODER_PPROF_ENABLE"
+      value: "true"
     - name: "CODER_PROMETHEUS_ENABLE"
       value: "true"
+    - name: "CODER_PROMETHEUS_COLLECT_AGENT_STATS"
+      value: "true"
     - name: "CODER_VERBOSE"
       value: "true"
   image:
@@ -129,7 +133,7 @@ EOF
 }
 
 resource "local_file" "kubernetes_template" {
-  filename = "${path.module}/.coderv2/templates/kubernetes/main.tf"
+  filename = "${path.module}/../.coderv2/templates/kubernetes/main.tf"
   content  = <<EOF
     terraform {
       required_providers {
@@ -216,6 +220,11 @@ resource "local_file" "kubernetes_template" {
   EOF
 }
 
+resource "local_file" "output_vars" {
+  filename = "${path.module}/../.coderv2/url"
+  content  = local.coder_url
+}
+
 output "coder_url" {
   description = "URL of the Coder deployment"
   value       = local.coder_url

scaletest/terraform/coder_shim.sh

@@ -1,8 +0,0 @@
-#!/usr/bin/env bash
-
-# This is a shim for easily executing Coder commands against a loadtest cluster
-# without having to overwrite your own session/URL
-SCRIPT_DIR=$(dirname "${BASH_SOURCE[0]}")
-CONFIG_DIR="${SCRIPT_DIR}/.coderv2"
-CODER_BIN="${CONFIG_DIR}/coder"
-exec "${CODER_BIN}" --global-config "${CONFIG_DIR}" "$@"

scaletest/terraform/prometheus.tf

@@ -102,7 +102,7 @@ prometheus:
 # after creating a cluster, and we want this to be brought up
 # with a single command.
 resource "local_file" "coder-monitoring-manifest" {
-  filename   = "${path.module}/.coderv2/coder-monitoring.yaml"
+  filename   = "${path.module}/../.coderv2/coder-monitoring.yaml"
   depends_on = [helm_release.prometheus-chart]
   content    = <<EOF
 apiVersion: monitoring.coreos.com/v1
@@ -122,7 +122,7 @@ spec:
 
 resource "null_resource" "coder-monitoring-manifest_apply" {
   provisioner "local-exec" {
-    working_dir = "${abspath(path.module)}/.coderv2"
+    working_dir = "${abspath(path.module)}/../.coderv2"
     command     = <<EOF
 KUBECONFIG=${var.name}-cluster.kubeconfig gcloud container clusters get-credentials ${google_container_cluster.primary.name} --project=${var.project_id} --zone=${var.zone} && \
 KUBECONFIG=${var.name}-cluster.kubeconfig kubectl apply -f ${abspath(local_file.coder-monitoring-manifest.filename)}

scaletest/terraform/scenario-large.tfvars

@@ -0,0 +1,4 @@
+nodepool_machine_type_coder      = "t2d-standard-8"
+nodepool_machine_type_workspaces = "t2d-standard-8"
+coder_cpu                        = "7"    # Leaving 1 CPU for system workloads
+coder_mem                        = "28Gi" # Leaving 4GB for system workloads

scaletest/terraform/scenario-medium.tfvars

@@ -0,0 +1,4 @@
+nodepool_machine_type_coder      = "t2d-standard-4"
+nodepool_machine_type_workspaces = "t2d-standard-4"
+coder_cpu                        = "3000m" # Leaving 1 CPU for system workloads
+coder_mem                        = "12Gi"  # Leaving 4 GB for system workloads

scaletest/terraform/scenario-small.tfvars

@@ -0,0 +1,4 @@
+nodepool_machine_type_coder      = "t2d-standard-2"
+nodepool_machine_type_workspaces = "t2d-standard-2"
+coder_cpu                        = "1000m" # Leaving 1 CPU for system workloads
+coder_mem                        = "4Gi"   # Leaving 4GB for system workloads

scaletest/terraform/secrets.tfvars.tpl

@@ -0,0 +1,4 @@
+name = "${SCALETEST_NAME}"
+project_id = "${SCALETEST_PROJECT}"
+prometheus_remote_write_user = "${SCALETEST_PROMETHEUS_REMOTE_WRITE_USER}"
+prometheus_remote_write_password = "${SCALETEST_PROMETHEUS_REMOTE_WRITE_PASSWORD}"

scaletest/workspacetraffic/run.go

@@ -19,8 +19,6 @@ import (
 	"github.com/coder/coder/cryptorand"
 	"github.com/coder/coder/scaletest/harness"
 	"github.com/coder/coder/scaletest/loadtestutil"
-
-	promtest "github.com/prometheus/client_golang/prometheus/testutil"
 )
 
 type Runner struct {
@@ -144,15 +142,6 @@ func (r *Runner) Run(ctx context.Context, _ string, logs io.Writer) error {
 		return xerrors.Errorf("read from pty: %w", rErr)
 	}
 
-	duration := time.Since(start)
-	logger.Info(ctx, "Test Results",
-		slog.F("duration", duration),
-		slog.F("bytes_read_total", promtest.ToFloat64(r.metrics.BytesReadTotal)),
-		slog.F("bytes_written_total", promtest.ToFloat64(r.metrics.BytesWrittenTotal)),
-		slog.F("read_errors_total", promtest.ToFloat64(r.metrics.ReadErrorsTotal)),
-		slog.F("write_errors_total", promtest.ToFloat64(r.metrics.WriteErrorsTotal)),
-	)
-
 	return nil
 }
 

site/.eslintignore

@@ -61,8 +61,8 @@ stats/
 # Loadtesting
 .././scaletest/terraform/.terraform
 .././scaletest/terraform/.terraform.lock.hcl
-terraform.tfstate.*
+../scaletest/terraform/secrets.tfvars
-**/*.tfvars
+.terraform.tfstate.*
 # .prettierignore.include:
 # Helm templates contain variables that are invalid YAML and can't be formatted
 # by Prettier.

site/.prettierignore

@@ -61,8 +61,8 @@ stats/
 # Loadtesting
 .././scaletest/terraform/.terraform
 .././scaletest/terraform/.terraform.lock.hcl
-terraform.tfstate.*
+../scaletest/terraform/secrets.tfvars
-**/*.tfvars
+.terraform.tfstate.*
 # .prettierignore.include:
 # Helm templates contain variables that are invalid YAML and can't be formatted
 # by Prettier.