Helm chart for pcm - initial version

.gitignore

@@ -32,4 +32,6 @@ latex/
 .vs/
 .idea/
 build
-src/simdjson
+src/simdjson
+/deployment/pcm/smarter-device-manager/
+/deployment/pcm/nri/

Dockerfile

@@ -2,9 +2,12 @@ FROM fedora:40@sha256:4e007f288dce23966216be81ef62ba05d139b9338f327c1d1c73b7167d
 
 RUN dnf -y install gcc-c++ git findutils make cmake
 COPY . /tmp/pcm
-RUN cd /tmp/pcm && mkdir build && cd build && cmake .. && make
+# TEMPORARY change to be remove before merge, to not conflict with local builds + use cache
+# WARNING this approach requires me to build locally before docker build to get updated
+RUN --mount=type=cache,target=/tmp/pcm/build2 cd /tmp/pcm && cd build2 && cmake -D CMAKE_BUILD_TYPE=Debug .. && make -j pcm pcm-sensor-server
 
 FROM fedora:40@sha256:4e007f288dce23966216be81ef62ba05d139b9338f327c1d1c73b7167dd47312
+RUN yum install -y strace gdb util-linux
 COPY --from=builder /tmp/pcm/build/bin/* /usr/local/bin/
 ENV PCM_NO_PERF=1
 

KUBERNETES.md

@@ -0,0 +1,92 @@
+##### Create kind based development cluster
+
+```sh
+kind create cluster
+kind export kubeconfig
+```
+
+##### 1) Install Prometheus operator required for PodMonitor CRD
+
+E.g. use prometheus operator helm chart from here: https://artifacthub.io/packages/helm/prometheus-community/kube-prometheus-stack
+
+https://prometheus-operator.dev/docs/operator/design/#podmonitor
+
+```sh
+helm repo add prometheus-community https://prometheus-community.github.io/helm-charts
+
+helm repo update
+helm repo list
+
+# check prometheus source if needed
+helm pull prometheus-community/kube-prometheus-stack
+tar -xzvf kube-prometheus-stack-56.6.2.tgz
+
+# show/customize values e.g. pod monitor namespace selector
+helm show values prometheus-community/kube-prometheus-stack
+helm show values prometheus-community/kube-prometheus-stack | vim - +'set ft=yaml'
+helm template prometheus-community/kube-prometheus-stack --set-json prometheus.prometheusSpec.podMonitorNamespaceSelector='{"matchLabels": {"kubernetes.io/metadata.name": "intel-pcm"}}' | vim - +'set ft=yaml'
+
+# Install
+helm install prometheus prometheus-community/kube-prometheus-stack --set prometheus.prometheusSpec.podMonitorSelectorNilUsesHelmValues=false
+
+helm list
+
+kubectl --namespace default get pods -l "release=prometheus"
+```
+
+To remove:
+```sh
+helm uninstall prometheus
+helm repo remove prometheus-community
+```
+
+##### 2) Deploy PCM daemonset
+
+```sh
+kubectl apply -f pcm-kubernetes.yaml
+
+# and verify ...
+kubectl -n intel-pcm get daemonset
+kubectl -n intel-pcm get pods
+podname=`kubectl -n intel-pcm get pods -ojsonpath='{.items[0].metadata.name}'`
+```
+
+##### 3) Verirfy PCM metrics are collected by Prometheus
+
+```sh
+kubectl proxy &
+```
+
+Access PCM metrics directly:
+```sh
+curl -Ls http://127.0.0.1:8001/api/v1/namespaces/intel-pcm/pods/$podname/proxy/metrics
+curl -Ls http://127.0.0.1:8001/api/v1/namespaces/intel-pcm/pods/$podname/proxy/metrics | grep DRAM_Writes
+```
+
+or through Prometheus UI:
+```
+http://127.0.0.1:8001/api/v1/namespaces/default/services/prometheus-kube-prometheus-prometheus:http-web/proxy/graph
+promtool query range --step 1m http://127.0.0.1:8001/api/v1/namespaces/default/services/prometheus-kube-prometheus-prometheus:http-web/proxy 'rate(DRAM_Writes{aggregate="system"}[5m])/1e9'
+promtool query instant http://127.0.0.1:8001/api/v1/namespaces/default/services/prometheus-kube-prometheus-prometheus:http-web/proxy 'avg by(__name__) ({job="pcm"})'
+```
+
+query metrics via promtool
+```sh
+promtool query range --step 1m http://127.0.0.1:8001/api/v1/namespaces/default/services/prometheus-kube-prometheus-prometheus:http-web/proxy 'rate(DRAM_Writes{aggregate="system"}[5m])/1e9'
+promtool query instant http://127.0.0.1:8001/api/v1/namespaces/default/services/prometheus-kube-prometheus-prometheus:http-web/proxy 'avg by(__name__) ({job="pcm"})'
+```
+
+run some workloads:
+```sh
+kubectl run -ti stress --image=alexeiled/stress-ng  --restart=Never --rm -- --stream 8
+```
+
+
+##### Uninstall PCM
+
+```sh
+kubectl delete -f pcm-kubernetes.yaml
+```
+
+
+

deployment/pcm/.helmignore

@@ -0,0 +1,25 @@
+# Patterns to ignore when building packages.
+# This supports shell glob matching, relative path matching, and
+# negation (prefixed with !). Only one pattern per line.
+.DS_Store
+# Common VCS dirs
+.git/
+.gitignore
+.bzr/
+.bzrignore
+.hg/
+.hgignore
+.svn/
+# Common backup files
+*.swp
+*.bak
+*.tmp
+*.orig
+*~
+# Various IDEs
+.project
+.idea/
+*.tmproj
+.vscode/
+smarter-device-manager/
+nri/

deployment/pcm/Chart.yaml

@@ -0,0 +1,9 @@
+apiVersion: v2
+name: pcm
+version: 0.1.0
+appVersion: "202403"
+description: A PCM Helm chart for Kubernetes
+home: https://github.com/intel/pcm
+maintainers:
+  - name: Pawel Palucki
+    email: pawel.palucki@intel.com

deployment/pcm/LICENSE

@@ -0,0 +1,30 @@
+BSD 3-Clause License
+
+Copyright (c) 2009-2023, Intel Corporation
+Copyright (c) 2016-2020, opcm
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+* Redistributions of source code must retain the above copyright notice, this
+  list of conditions and the following disclaimer.
+
+* Redistributions in binary form must reproduce the above copyright notice,
+  this list of conditions and the following disclaimer in the documentation
+  and/or other materials provided with the distribution.
+
+* Neither the name of the copyright holder nor the names of its
+  contributors may be used to endorse or promote products derived from
+  this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.