Merge pull request #3 from PanKaker/main

Update to 1.2.0.

.gitignore

@@ -0,0 +1 @@
+.idea

.markdownlint.yml

@@ -0,0 +1,6 @@
+{
+    "MD013": false,
+    "MD033": {
+      "allowed_elements": ["br"]
+    }
+}

README.md

@@ -19,25 +19,37 @@ Pre-configuration is needed for a container to read metrics from specific plugin
 
 ### [Intel PowerStat plugin](https://github.com/influxdata/telegraf/tree/master/plugins/inputs/intel_powerstat)
 
-Plugin is based on Linux Kernel modules that expose specific metrics over `sysfs` or `devfs` interfaces.
-The following dependencies are expected by plugin:
-
-- _intel-rapl_ module which exposes Intel Runtime Power Limiting metrics over `sysfs` (`/sys/devices/virtual/powercap/intel-rapl`),
-- _msr_ kernel module that provides access to processor model specific registers over `devfs` (`/dev/cpu/cpu%d/msr`),
-- _cpufreq_ kernel module - which exposes per-CPU Frequency over `sysfs` (`/sys/devices/system/cpu/cpu%d/cpufreq/scaling_cur_freq`).
-
-Minimum kernel version required is 3.13 to satisfy all requirements.
-
-Please make sure that kernel modules are loaded and running (cpufreq is integrated in kernel). Modules might have to be manually enabled by using `modprobe`.
-Depending on the kernel version, run commands:
+Plugin is based on Linux Kernel modules that expose specific metrics over
+`sysfs` or `devfs` interfaces. The following dependencies are expected by
+plugin:
+
+- _intel-rapl_ module which exposes Intel Runtime Power Limiting metrics over
+  `sysfs` (`/sys/devices/virtual/powercap/intel-rapl`),
+- _msr_ kernel module that provides access to processor model specific
+  registers over `devfs` (`/dev/cpu/cpu%d/msr`),
+- _cpufreq_ kernel module - which exposes per-CPU Frequency over `sysfs`
+  (`/sys/devices/system/cpu/cpu%d/cpufreq/scaling_cur_freq`).
+- _intel-uncore-frequency_ module exposes Intel uncore frequency metrics
+  over `sysfs` (`/sys/devices/system/cpu/intel_uncore_frequency`),
+
+Minimum kernel version required is 3.13 to satisfy most of requirements,
+for `uncore_frequency` metrics `intel-uncore-frequency` module is required
+(available since kernel 5.6).
+
+Please make sure that kernel modules are loaded and running (cpufreq is
+integrated in kernel). Modules might have to be manually enabled by using
+`modprobe`. Depending on the kernel version, run commands:
 
 ```sh
 # kernel 5.x.x:
 sudo modprobe rapl
-subo modprobe msr
+sudo modprobe msr
 sudo modprobe intel_rapl_common
 sudo modprobe intel_rapl_msr
 
+# also for kernel >= 5.6.0
+sudo modprobe intel-uncore-frequency
+
 # kernel 4.x.x:
 sudo modprobe msr
 sudo modprobe intel_rapl
@@ -53,12 +65,16 @@ The Redfish plugin needs hardware servers for which
 - The DPDK plugin needs external application built with
 [Data Plane Development Kit](https://www.dpdk.org/).
 - `./telegraf-intel-docker.sh` has default location of DPDK socket -`/var/run/dpdk/rte`, if DPDK socket is located
-somewhere else, user must specify this in running stage providing `--dpdk_socket_path` flag.
+somewhere else, user must specify this in running stage providing `--dpdk_socket_path` flag. Providing path to a
+directory that contains the hosts' own Docker socket file is not recommended.
 
 ### [Intel PMU](https://github.com/influxdata/telegraf/tree/master/plugins/inputs/intel_pmu)
 
 The plugin requires JSON files with event definitions to work properly. Those can be specified in `./telegraf-intel-docker.sh`
-by providing `--pmu_events` parameter. More information about event definitions and where to get them should be found in plugin's
+by providing `--pmu_events` parameter. Providing path to a directory that contains the hosts' own Docker socket file
+is not recommended.
+
+More information about event definitions and where to get them should be found in plugin's
 [README](https://github.com/influxdata/telegraf/blob/master/plugins/inputs/intel_pmu/README.md).
 
 ### [RAS](https://github.com/influxdata/telegraf/tree/master/plugins/inputs/ras)
@@ -201,14 +217,15 @@ The following plugins should work on a majority of the host's configurations.
 4. [Disk IO](https://github.com/influxdata/telegraf/tree/master/plugins/inputs/diskio)
 5. [DNS Query](https://github.com/influxdata/telegraf/tree/master/plugins/inputs/dns_query)
 6. [ETH Tool](https://github.com/influxdata/telegraf/tree/master/plugins/inputs/ethtool)
-7. [IP Tables](https://github.com/influxdata/telegraf/tree/master/plugins/inputs/iptables)
-8. [Kernel VMStat](https://github.com/influxdata/telegraf/tree/master/plugins/inputs/kernel_vmstat)
-9. [Mem](https://github.com/influxdata/telegraf/tree/master/plugins/inputs/mem)
-10. [Net](https://github.com/influxdata/telegraf/tree/master/plugins/inputs/net)
-11. [Ping](https://github.com/influxdata/telegraf/tree/master/plugins/inputs/ping)
-12. [Smart](https://github.com/influxdata/telegraf/tree/master/plugins/inputs/smart)
-13. [System](https://github.com/influxdata/telegraf/tree/master/plugins/inputs/system)
-14. [Temp](https://github.com/influxdata/telegraf/tree/master/plugins/inputs/temp)
+7. [Hugepages](https://github.com/influxdata/telegraf/tree/master/plugins/inputs/hugepages)
+8. [IP Tables](https://github.com/influxdata/telegraf/tree/master/plugins/inputs/iptables)
+9. [Kernel VMStat](https://github.com/influxdata/telegraf/tree/master/plugins/inputs/kernel_vmstat)
+10. [Mem](https://github.com/influxdata/telegraf/tree/master/plugins/inputs/mem)
+11. [Net](https://github.com/influxdata/telegraf/tree/master/plugins/inputs/net)
+12. [Ping](https://github.com/influxdata/telegraf/tree/master/plugins/inputs/ping)
+13. [Smart](https://github.com/influxdata/telegraf/tree/master/plugins/inputs/smart)
+14. [System](https://github.com/influxdata/telegraf/tree/master/plugins/inputs/system)
+15. [Temp](https://github.com/influxdata/telegraf/tree/master/plugins/inputs/temp)
 
 #### Disabled by default
 
@@ -230,3 +247,13 @@ List of supported Telegraf output plugins enabled by default.
 
 1. [File](https://github.com/influxdata/telegraf/tree/master/plugins/outputs/file)
 2. [Prometheus client](https://github.com/influxdata/telegraf/tree/master/plugins/outputs/prometheus_client)
+
+### Changelog
+
+#### 1.2.0
+
+- Update telegraf version: 1.21.3 -> 1.24.3
+- Update version of pqos (intel_cmt_cat): 4.2.0 -> 4.4.1
+- Add Hugepages plugin (enabled by default)
+- Add new features: uncore_freq and max_turbo_freq for Powerstat plugin
+- Update the final alpine image: 3.15 -> 3.16

images/telegraf/Dockerfile

@@ -22,15 +22,15 @@
 # 
 
 ARG TELEGRAF_TAG
+ARG FINAL_BASE_IMAGE
 FROM telegraf:$TELEGRAF_TAG AS builder
 
 RUN apk update && \
     apk add --update --no-cache \
-    zlib=~1.2.12 \
     build-base=~0.5 \
     bash=~5.1 \
     sudo=~1.9 \
-    git=~2.34 \
+    git=~2.36 \
     alpine-sdk=~1.0 \
     libffi-dev=~3.4 \
     openssl-dev=~1.1 && \
@@ -43,27 +43,25 @@ COPY ./images/telegraf/script/install_intel_cmt_cat.sh ./
 RUN ./install_intel_cmt_cat.sh
 
 # Build final image where telegraf is running.
-FROM alpine:3.15.0
+FROM $FINAL_BASE_IMAGE
 
 RUN export PATH="/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin" && \
     apk update && \
     apk add --update --no-cache \
-    zlib=~1.2.12 \
-    util-linux=~2.37 \
+    util-linux=~2.38 \
     bash=~5.1 \
     sudo=~1.9 \
-    smartmontools=~7.2 \
-    nvme-cli=~1.16 \
+    smartmontools=~7.3 \
+    nvme-cli=~2.0 \
     rasdaemon=~0.6 \
     iptables=~1.8 \
     ipmitool=~1.8 \
     su-exec=~0.2 \
-    iputils=~20210722 && \
+    iputils=~20211215 && \
     rm -rf /var/lib/apt/lists/*
 
 WORKDIR "/telegraf_docker/"
 
-COPY ./images/telegraf/script/sudo_configuration.sh .
 COPY ./DEPENDENCIES_SOURCE_CODE_INFO.md .
 
 # Copy dependecies from previous step called builder, where intel-cmt-cat is installed.
@@ -73,8 +71,6 @@ COPY --from=builder /usr/share/snmp/mibs/ /usr/share/snmp/mibs/
 COPY --from=builder /usr/bin/telegraf /usr/bin/telegraf
 COPY --from=builder entrypoint.sh .
 
-# Set sudo config for specific plugins, and just in case update alternatives, because sometimes docker can mess it up.
-RUN ./sudo_configuration.sh
 
 # Override entrypoint
 ENTRYPOINT ["sh", "-c", "rasdaemon -r && sleep 10s && ./entrypoint.sh telegraf"]

images/telegraf/script/install_intel_cmt_cat.sh

@@ -1,6 +1,6 @@
 #!/bin/bash
 
-git clone -b v4.2.0 https://github.com/intel/intel-cmt-cat.git && cd intel-cmt-cat || exit
+git clone -b v4.4.1 https://github.com/intel/intel-cmt-cat.git && cd intel-cmt-cat || exit
 
 make
 sudo NOLDCONFIG=y make install

telegraf-intel-docker.sh

@@ -8,12 +8,12 @@ DOCKER_CONTAINER_NAME=$3
 DOCKER_DPDK_SOCKET_PATH="/var/run/dpdk/rte"
 DOCKER_PMU_EVENTS_PATH="/var/cache/pmu"
 
-readonly TELEGRAF_VERSION='1.21.3-alpine'
+readonly TELEGRAF_VERSION='1.24.3-alpine'
 
 readonly DOCKER_IMAGE_NAME=$2
-readonly DOCKER_IMAGE_TAG='1.1'
-readonly DOCKER_TELEGRAF_BUILD_IMAGE='telegraf:1.21.3-alpine'
-readonly DOCKER_TELEGRAF_FINAL_BASE_IMAGE='alpine:3.15.0'
+readonly DOCKER_IMAGE_TAG='1.2.0'
+readonly DOCKER_TELEGRAF_BUILD_IMAGE="telegraf:${TELEGRAF_VERSION}"
+readonly DOCKER_TELEGRAF_FINAL_BASE_IMAGE='alpine:3.16'
 
 readonly CONTAINER_MEMORY_LIMIT=200m
 readonly CONTAINER_CPU_SHARES=512
@@ -32,8 +32,9 @@ fi
 # Build docker image.
 function build_docker() {
   echo -e "${GREEN}Building Telegraf Docker image...${NO_COLOR}"
+  echo -e "Using telegraf version: ${TELEGRAF_VERSION}. Final base image: ${DOCKER_TELEGRAF_FINAL_BASE_IMAGE}"
   echo "If this is your first time building image this might take a minute..."
-  docker build --build-arg TELEGRAF_TAG=$TELEGRAF_VERSION -f images/telegraf/Dockerfile . -t "$DOCKER_IMAGE_NAME":$DOCKER_IMAGE_TAG
+  docker build --build-arg TELEGRAF_TAG=$TELEGRAF_VERSION --build-arg FINAL_BASE_IMAGE=$DOCKER_TELEGRAF_FINAL_BASE_IMAGE -f images/telegraf/Dockerfile . -t "$DOCKER_IMAGE_NAME":$DOCKER_IMAGE_TAG
 }
 
 # Build and run docker container.

telegraf/telegraf.conf

@@ -302,15 +302,31 @@
   # normalize_keys = ["snakecase", "trim", "lower", "underscore"]
 
 
-# # Intel PowerStat plugin enables monitoring of platform metrics (power, TDP) and Core metrics like temperature, power and utilization.
+# # Intel PowerStat plugin enables monitoring of platform metrics (power, TDP)
+# # and per-CPU metrics like temperature, power and utilization.
 # [[inputs.intel_powerstat]]
-#   ## All global metrics are always collected by Intel PowerStat plugin.
-#   ## User can choose which per-CPU metrics are monitored by the plugin in cpu_metrics array.
-#   ## Empty array means no per-CPU specific metrics will be collected by the plugin - in this case only platform level
-#   ## telemetry will be exposed by Intel PowerStat plugin.
+#   ## The user can choose which package metrics are monitored by the plugin with
+#   ## the package_metrics setting:
+#   ## - The default, will collect "current_power_consumption",
+#   ##   "current_dram_power_consumption" and "thermal_design_power"
+#   ## - Leaving this setting empty means no package metrics will be collected
+#   ## - Finally, a user can specify individual metrics to capture from the
+#   ##   supported options list
 #   ## Supported options:
-#   ## "cpu_frequency", "cpu_busy_frequency", "cpu_temperature", "cpu_c1_state_residency", "cpu_c6_state_residency", "cpu_busy_cycles"
-#   cpu_metrics = ["cpu_frequency", "cpu_busy_frequency", "cpu_temperature", "cpu_c1_state_residency", "cpu_c6_state_residency", "cpu_busy_cycles"]
+#   ##   "current_power_consumption", "current_dram_power_consumption",
+#   ##   "thermal_design_power", "max_turbo_frequency", "uncore_frequency"
+#   package_metrics = ["current_power_consumption", "current_dram_power_consumption", "thermal_design_power", "max_turbo_frequency", "uncore_frequency"]
+# 
+#   ## The user can choose which per-CPU metrics are monitored by the plugin in
+#   ## cpu_metrics array.
+#   ## Empty or missing array means no per-CPU specific metrics will be collected
+#   ## by the plugin.
+#   ## Supported options:
+#   ##   "cpu_frequency", "cpu_c0_state_residency", "cpu_c1_state_residency",
+#   ##   "cpu_c6_state_residency", "cpu_busy_cycles", "cpu_temperature",
+#   ##   "cpu_busy_frequency"
+#   ## ATTENTION: cpu_busy_cycles is DEPRECATED - use cpu_c0_state_residency
+#   cpu_metrics = ["cpu_frequency", "cpu_c0_state_residency", "cpu_c1_state_residency", "cpu_c6_state_residency", "cpu_temperature", "cpu_busy_frequency"] 
 
 
 # # Read metrics from the bare metal servers via IPMI
@@ -377,6 +393,15 @@
   ## Read the plugin documentation for more information.
   chains = [ "INPUT" ]
 
+# Gathers huge pages measurements.
+[[inputs.hugepages]]
+  ## Supported huge page types:
+  ##   - "root"     - based on root huge page control directory:
+  ##                  /sys/kernel/mm/hugepages
+  ##   - "per_node" - based on per NUMA node directories:
+  ##                  /sys/devices/system/node/node[0-9]*/hugepages
+  ##   - "meminfo"  - based on /proc/meminfo file
+  # types = ["root", "per_node"]
 
 # Get kernel statistics from /proc/vmstat
 [[inputs.kernel_vmstat]]