[hackathon] kubectl trace based testing (#2549)

* add script and basic docs * Adding k3d setup docs * finish script * Adding containerd tracing to our Kube Tracing example * add kubelet script * add example * Updating docs * Update files * Fix rebase error * Removing file --------- Co-authored-by: Daniel Dias <danielbpdias@gmail.com>
kubeshop · May 18, 2023 · efb642f · efb642f
1 parent 64c34a3
commit efb642f
Show file tree

Hide file tree

Showing 10 changed files with 609 additions and 0 deletions.
diff --git a/examples/tracetesting-kubernetes/kubetracing/config.toml.tmpl b/examples/tracetesting-kubernetes/kubetracing/config.toml.tmpl
@@ -0,0 +1,127 @@
+# File generated by {{ .Program }}. DO NOT EDIT. Use config.toml.tmpl instead.
+version = 2
+
+[plugins."io.containerd.internal.v1.opt"]
+  path = "{{ .NodeConfig.Containerd.Opt }}"
+[plugins."io.containerd.grpc.v1.cri"]
+  stream_server_address = "127.0.0.1"
+  stream_server_port = "10010"
+  enable_selinux = {{ .NodeConfig.SELinux }}
+  enable_unprivileged_ports = {{ .EnableUnprivileged }}
+  enable_unprivileged_icmp = {{ .EnableUnprivileged }}
+
+{{- if .DisableCgroup}}
+  disable_cgroup = true
+{{end}}
+{{- if .IsRunningInUserNS }}
+  disable_apparmor = true
+  restrict_oom_score_adj = true
+{{end}}
+
+{{- if .NodeConfig.AgentConfig.PauseImage }}
+  sandbox_image = "{{ .NodeConfig.AgentConfig.PauseImage }}"
+{{end}}
+
+{{- if .NodeConfig.AgentConfig.Snapshotter }}
+[plugins."io.containerd.grpc.v1.cri".containerd]
+  snapshotter = "{{ .NodeConfig.AgentConfig.Snapshotter }}"
+  disable_snapshot_annotations = {{ if eq .NodeConfig.AgentConfig.Snapshotter "stargz" }}false{{else}}true{{end}}
+{{ if eq .NodeConfig.AgentConfig.Snapshotter "stargz" }}
+{{ if .NodeConfig.AgentConfig.ImageServiceSocket }}
+[plugins."io.containerd.snapshotter.v1.stargz"]
+cri_keychain_image_service_path = "{{ .NodeConfig.AgentConfig.ImageServiceSocket }}"
+[plugins."io.containerd.snapshotter.v1.stargz".cri_keychain]
+enable_keychain = true
+{{end}}
+{{ if .PrivateRegistryConfig }}
+{{ if .PrivateRegistryConfig.Mirrors }}
+[plugins."io.containerd.snapshotter.v1.stargz".registry.mirrors]{{end}}
+{{range $k, $v := .PrivateRegistryConfig.Mirrors }}
+[plugins."io.containerd.snapshotter.v1.stargz".registry.mirrors."{{$k}}"]
+  endpoint = [{{range $i, $j := $v.Endpoints}}{{if $i}}, {{end}}{{printf "%q" .}}{{end}}]
+{{if $v.Rewrites}}
+  [plugins."io.containerd.snapshotter.v1.stargz".registry.mirrors."{{$k}}".rewrite]
+{{range $pattern, $replace := $v.Rewrites}}
+    "{{$pattern}}" = "{{$replace}}"
+{{end}}
+{{end}}
+{{end}}
+{{range $k, $v := .PrivateRegistryConfig.Configs }}
+{{ if $v.Auth }}
+[plugins."io.containerd.snapshotter.v1.stargz".registry.configs."{{$k}}".auth]
+  {{ if $v.Auth.Username }}username = {{ printf "%q" $v.Auth.Username }}{{end}}
+  {{ if $v.Auth.Password }}password = {{ printf "%q" $v.Auth.Password }}{{end}}
+  {{ if $v.Auth.Auth }}auth = {{ printf "%q" $v.Auth.Auth }}{{end}}
+  {{ if $v.Auth.IdentityToken }}identitytoken = {{ printf "%q" $v.Auth.IdentityToken }}{{end}}
+{{end}}
+{{ if $v.TLS }}
+[plugins."io.containerd.snapshotter.v1.stargz".registry.configs."{{$k}}".tls]
+  {{ if $v.TLS.CAFile }}ca_file = "{{ $v.TLS.CAFile }}"{{end}}
+  {{ if $v.TLS.CertFile }}cert_file = "{{ $v.TLS.CertFile }}"{{end}}
+  {{ if $v.TLS.KeyFile }}key_file = "{{ $v.TLS.KeyFile }}"{{end}}
+  {{ if $v.TLS.InsecureSkipVerify }}insecure_skip_verify = true{{end}}
+{{end}}
+{{end}}
+{{end}}
+{{end}}
+{{end}}
+
+{{- if not .NodeConfig.NoFlannel }}
+[plugins."io.containerd.grpc.v1.cri".cni]
+  bin_dir = "{{ .NodeConfig.AgentConfig.CNIBinDir }}"
+  conf_dir = "{{ .NodeConfig.AgentConfig.CNIConfDir }}"
+{{end}}
+
+[plugins."io.containerd.grpc.v1.cri".containerd.runtimes.runc]
+  runtime_type = "io.containerd.runc.v2"
+
+[plugins."io.containerd.grpc.v1.cri".containerd.runtimes.runc.options]
+  SystemdCgroup = {{ .SystemdCgroup }}
+
+{{ if .PrivateRegistryConfig }}
+{{ if .PrivateRegistryConfig.Mirrors }}
+[plugins."io.containerd.grpc.v1.cri".registry.mirrors]{{end}}
+{{range $k, $v := .PrivateRegistryConfig.Mirrors }}
+[plugins."io.containerd.grpc.v1.cri".registry.mirrors."{{$k}}"]
+  endpoint = [{{range $i, $j := $v.Endpoints}}{{if $i}}, {{end}}{{printf "%q" .}}{{end}}]
+{{if $v.Rewrites}}
+  [plugins."io.containerd.grpc.v1.cri".registry.mirrors."{{$k}}".rewrite]
+{{range $pattern, $replace := $v.Rewrites}}
+    "{{$pattern}}" = "{{$replace}}"
+{{end}}
+{{end}}
+{{end}}
+
+{{range $k, $v := .PrivateRegistryConfig.Configs }}
+{{ if $v.Auth }}
+[plugins."io.containerd.grpc.v1.cri".registry.configs."{{$k}}".auth]
+  {{ if $v.Auth.Username }}username = {{ printf "%q" $v.Auth.Username }}{{end}}
+  {{ if $v.Auth.Password }}password = {{ printf "%q" $v.Auth.Password }}{{end}}
+  {{ if $v.Auth.Auth }}auth = {{ printf "%q" $v.Auth.Auth }}{{end}}
+  {{ if $v.Auth.IdentityToken }}identitytoken = {{ printf "%q" $v.Auth.IdentityToken }}{{end}}
+{{end}}
+{{ if $v.TLS }}
+[plugins."io.containerd.grpc.v1.cri".registry.configs."{{$k}}".tls]
+  {{ if $v.TLS.CAFile }}ca_file = "{{ $v.TLS.CAFile }}"{{end}}
+  {{ if $v.TLS.CertFile }}cert_file = "{{ $v.TLS.CertFile }}"{{end}}
+  {{ if $v.TLS.KeyFile }}key_file = "{{ $v.TLS.KeyFile }}"{{end}}
+  {{ if $v.TLS.InsecureSkipVerify }}insecure_skip_verify = true{{end}}
+{{end}}
+{{end}}
+{{end}}
+
+{{range $k, $v := .ExtraRuntimes}}
+[plugins."io.containerd.grpc.v1.cri".containerd.runtimes."{{$k}}"]
+  runtime_type = "{{$v.RuntimeType}}"
+[plugins."io.containerd.grpc.v1.cri".containerd.runtimes."{{$k}}".options]
+  BinaryName = "{{$v.BinaryName}}"
+{{end}}
+
+[plugins."io.containerd.tracing.processor.v1.otlp"]
+  endpoint = "host.k3d.internal:4317"
+  protocol = "grpc"
+  insecure = true
+
+[plugins."io.containerd.internal.v1.tracing"]
+  sampling_ratio = 1.0
+  service_name = "containerd"
diff --git a/examples/tracetesting-kubernetes/kubetracing/config/apiserver-tracing.yaml b/examples/tracetesting-kubernetes/kubetracing/config/apiserver-tracing.yaml
@@ -0,0 +1,4 @@
+apiVersion: apiserver.config.k8s.io/v1beta1
+kind: TracingConfiguration
+endpoint: host.k3d.internal:4317
+samplingRatePerMillion: 1000000 # 100%
diff --git a/examples/tracetesting-kubernetes/kubetracing/config/kubelet-tracing.yaml b/examples/tracetesting-kubernetes/kubetracing/config/kubelet-tracing.yaml
@@ -0,0 +1,7 @@
+apiVersion: kubelet.config.k8s.io/v1beta1
+kind: KubeletConfiguration
+featureGates:
+  KubeletTracing: true
+tracing:
+  endpoint: host.k3d.internal:4317
+  samplingRatePerMillion: 1000000
diff --git a/examples/tracetesting-kubernetes/kubetracing/docker-compose.yaml b/examples/tracetesting-kubernetes/kubetracing/docker-compose.yaml
@@ -0,0 +1,27 @@
+services:
+  jaeger:
+    healthcheck:
+      test:
+        - CMD
+        - wget
+        - --spider
+        - localhost:16686
+      timeout: 3s
+      interval: 1s
+      retries: 60
+    image: jaegertracing/all-in-one:latest
+    restart: unless-stopped
+    ports:
+      - 16686:16686
+  otel-collector:
+    command:
+      - --config
+      - /otel-local-config.yaml
+    depends_on:
+      jaeger:
+        condition: service_started
+    image: otel/opentelemetry-collector:0.54.0
+    ports:
+      - 4317:4317
+    volumes:
+      - ./otel-collector.yaml:/otel-local-config.yaml
diff --git a/examples/tracetesting-kubernetes/kubetracing/otel-collector.yaml b/examples/tracetesting-kubernetes/kubetracing/otel-collector.yaml
@@ -0,0 +1,25 @@
+receivers:
+  otlp:
+    protocols:
+      grpc:
+      http:
+processors:
+  # Data sources: traces
+  probabilistic_sampler:
+    hash_seed: 22
+    sampling_percentage: 100
+  batch:
+    timeout: 100ms
+exporters:
+  logging:
+    logLevel: debug
+  jaeger:
+    endpoint: jaeger:14250
+    tls:
+      insecure: true
+service:
+  pipelines:
+    traces:
+      receivers: [otlp]
+      processors: [probabilistic_sampler, batch]
+      exporters: [jaeger,logging]
diff --git a/examples/tracetesting-kubernetes/setup-k3s.md b/examples/tracetesting-kubernetes/setup-k3s.md
@@ -0,0 +1,182 @@
+# Test Kubectl commands
+
+This example shows how one can use Tracetest to do trace based testing for kubectl commands. This works by leveraging the `Audit-Id` header sent back from the kubernetes api server for every request.
+
+the `kubectl` command allows to enable a very verbose output, where it includes the response headers. This example script parses that info and maps it to the corresponding Trace ID.
+
+## Requirements
+
+This setup is a bit limited at the moment. It only works with Jaeger backend, becasue it provides a search API that allows us to search spans that include the correct `Audit-Id` tag.
+
+For everything to work, we need the following environment configured:
+
+1. A Kubernetes cluster with `APIServerTracing` enabled and configured
+2. A OtelCollector that can be accessed by the k8s api server to send its tracing data
+3. A Jager backend to store the traces
+
+
+## Setup
+
+k3s can be used to easily setup a cluster with the correct configuration. It's easy enough to be configured in any dev environment, even a CICD.
+
+The otelcollector cannot be deployed in the target cluster because it complicates the networking setup needed to have the k8s apiserver communicating with the collector.
+An easy solution for this is to have docker compose starting the otelcol/jaeger services, so their ports can be exposed directly to the host network.
+
+### 1. Setup OtelCollector/Jaeger
+
+create a `docker-compose.yaml` file that includes both services:
+
+```yaml
+# docker-compose.yaml
+services:
+  jaeger:
+      healthcheck:
+          test:
+              - CMD
+              - wget
+              - --spider
+              - localhost:16686
+          timeout: 3s
+          interval: 1s
+          retries: 60
+      image: jaegertracing/all-in-one:latest
+      restart: unless-stopped
+      ports:
+        - 16686:16686
+  otel-collector:
+      command:
+          - --config
+          - /otel-local-config.yaml
+      depends_on:
+          jaeger:
+              condition: service_started
+      image: otel/opentelemetry-collector:0.54.0
+      ports:
+        - 4317:4317
+      volumes:
+          - ./otel-collector.yaml:/otel-local-config.yaml
+```
+
+We need to create a config file in the same directory for the otel-collector so it can communicate with Jaeger:
+
+```yaml
+# otel-collector.yaml
+receivers:
+  otlp:
+    protocols:
+      grpc:
+      http:
+
+processors:
+  # Data sources: traces
+  probabilistic_sampler:
+    hash_seed: 22
+    sampling_percentage: 100
+
+  batch:
+    timeout: 100ms
+
+exporters:
+  # logging is optional, but useful for making sure the collector is receiving traces
+  logging:
+    logLevel: debug
+  jaeger:
+    # this url is valid within the `docker-compose` environmet this collector is running
+    endpoint: jaeger:14250 
+    tls:
+      insecure: true
+
+service:
+  pipelines:
+    traces:
+      receivers: [otlp]
+      processors: [probabilistic_sampler, batch]
+      exporters: [jaeger,logging] # logging is optional,
+```
+
+With both files created on the same director, we can start them:
+
+```
+sudo docker compose up -d
+```
+
+### 2. Start a k3s cluster
+
+We need to start a k3s cluster, but we need some special configurations:
+
+1. the k8s version needs to be 1.27+ for traces to work
+2. we need to enable the tracing feature flag
+3. we need to pass the otel-collector address to the apiserver
+
+
+First, we'll create the tracing config files, because it's required for the apiserver to start.
+
+> Make sure that the directory exists by running: `sudo mkdir -p /etc/kube-tracing/`
+
+```yaml
+# /etc/kube-tracing/apiserver-tracing.yaml
+apiVersion: apiserver.config.k8s.io/v1beta1
+kind: TracingConfiguration
+# default value
+endpoint: localhost:4317
+samplingRatePerMillion: 1000000 # 100%
+EOF
+```
+
+```yaml
+# /etc/kube-tracing/kubelet-tracing.yaml
+apiVersion: kubelet.config.k8s.io/v1beta1
+kind: KubeletConfiguration
+featureGates:
+  KubeletTracing: true
+tracing:
+  endpoint: host.k3d.internal:4317
+  samplingRatePerMillion: 1000000
+```
+
+
+This settings are documented [here](https://kubernetes.io/docs/concepts/cluster-administration/system-traces/). The only difference is that we are setting the `samplingRatePerMillion` value to 1.000.000 (meaning, 100%) so that all traces are send to the collector.
+This effectively disables sampling. Use this setting with care, and you probablly shouldn't do this in a prod environment.
+
+Now we can install the k3s cluster:
+
+```sh
+curl -sfL https://get.k3s.io | \
+  INSTALL_K3S_VERSION="v1.27.1+k3s1" \
+  INSTALL_K3S_EXEC="--kube-apiserver-arg=feature-gates=APIServerTracing=true --kube-apiserver-arg=tracing-config-file=/etc/kube-tracing/apiserver-tracing.yaml --kubelet-arg=config=/etc/kube-tracing/kubelet-tracing.yaml" \
+   sh -s - server --cluster-init
+```
+
+We use the `INSTALL_K3S_VERSION` env var to set the correct version, and the `INSTALL_K3S_EXEC` to pass flags and settings to the k8s apiserver.
+
+## Running tests
+
+That's it! We have a k8s apiserver ready to do trace based testing. With our [sample script](./test-kubectl.bash) it's very easy.
+
+You only need to set the correct jaeger UI url and the command you want to run. For example:
+
+```sh
+JAEGER_UI_URL="http://127.0.0.1:16686" ./test-kubectl.bash ./test.yaml "kubectl get pods -A"
+```
+
+The `test.yaml` file can be named as you want, but it needs to look like this:
+
+```yaml
+type: Test
+spec:
+  id: ze90fyU4R # can be anything
+  name: kubectl # can be anything
+  trigger:
+    type: traceid # MUST BE traceide
+    traceid:
+      id: ${env:asd} # MUST BE in line 8
+  # the rest of the file can be modified as needed
+  specs:
+  - name: List span exists
+    selector: span[tracetest.span.type="general" name="List"]
+    assertions:
+    - attr:tracetest.selected_spans.count = 1
+```
+
+You also need to have the `tracetest` cli configured to talk with the correct tracetest server.
+The tracetest server also needs to be configured to use the same Jaeger instance as the k8s for its datastore