[otel container]: Create otel container for HFT (#23666)

Makefile.work

@@ -538,6 +538,7 @@ SONIC_BUILD_INSTRUCTION :=  $(MAKE) \
                            SONIC_INCLUDE_SYSTEM_GNMI=$(INCLUDE_SYSTEM_GNMI) \
                            SONIC_INCLUDE_SYSTEM_BMP=$(INCLUDE_SYSTEM_BMP) \
                            SONIC_INCLUDE_SYSTEM_EVENTD=$(INCLUDE_SYSTEM_EVENTD) \
+                           SONIC_INCLUDE_SYSTEM_OTEL=$(INCLUDE_SYSTEM_OTEL) \
                            INCLUDE_DHCP_RELAY=$(INCLUDE_DHCP_RELAY) \
                            INCLUDE_DHCP_SERVER=$(INCLUDE_DHCP_SERVER) \
                            INCLUDE_MACSEC=$(INCLUDE_MACSEC) \

dockers/docker-sonic-otel/Dockerfile.j2

@@ -0,0 +1,63 @@
+{% from "dockers/dockerfile-macros.j2" import install_debian_packages, install_python_wheels, copy_files %}
+ARG BASE=docker-config-engine-bookworm-{{DOCKER_USERNAME}}:{{DOCKER_USERTAG}}
+
+FROM $BASE AS base
+
+ARG docker_container_name
+ARG image_version
+
+## Make apt-get non-interactive
+ENV DEBIAN_FRONTEND=noninteractive
+
+# Pass the image_version to container
+ENV IMAGE_VERSION=$image_version
+
+RUN apt-get update
+
+{% if docker_sonic_otel_debs.strip() -%}
+# Copy locally-built Debian package dependencies
+{{ copy_files("debs/", docker_sonic_otel_debs.split(' '), "/debs/") }}
+
+# Install locally-built Debian packages and implicitly install their dependencies
+{{ install_debian_packages(docker_sonic_otel_debs.split(' ')) }}
+{%- endif %}
+
+# Install dependencies
+RUN apt-get install -y \
+    ca-certificates \
+    curl \
+    wget
+
+# Install OpenTelemetry Collector from official .deb package
+ARG OTEL_VERSION=0.114.0
+
+# Download and install official .deb package with architecture-specific logic
+{% if CONFIGURED_ARCH == "armhf" %}
+RUN wget -v -O /tmp/otelcol-contrib.deb \
+        "https://github.com/open-telemetry/opentelemetry-collector-releases/releases/download/v${OTEL_VERSION}/otelcol-contrib_${OTEL_VERSION}_linux_armv7.deb" && \
+    dpkg --info /tmp/otelcol-contrib.deb && \
+    (dpkg -i /tmp/otelcol-contrib.deb || apt-get install -f -y) && \
+    ln -sf /usr/bin/otelcol-contrib /usr/local/bin/otelcol-contrib && \
+    rm /tmp/otelcol-contrib.deb
+{% elif CONFIGURED_ARCH == "arm64" %}
+RUN wget -v -O /tmp/otelcol-contrib.deb \
+        "https://github.com/open-telemetry/opentelemetry-collector-releases/releases/download/v${OTEL_VERSION}/otelcol-contrib_${OTEL_VERSION}_linux_arm64.deb" && \
+    dpkg --info /tmp/otelcol-contrib.deb && \
+    (dpkg -i /tmp/otelcol-contrib.deb || apt-get install -f -y) && \
+    ln -sf /usr/bin/otelcol-contrib /usr/local/bin/otelcol-contrib && \
+    rm /tmp/otelcol-contrib.deb
+{% else %}
+RUN wget -v -O /tmp/otelcol-contrib.deb \
+        "https://github.com/open-telemetry/opentelemetry-collector-releases/releases/download/v${OTEL_VERSION}/otelcol-contrib_${OTEL_VERSION}_linux_amd64.deb" && \
+    dpkg --info /tmp/otelcol-contrib.deb && \
+    (dpkg -i /tmp/otelcol-contrib.deb || apt-get install -f -y) && \
+    ln -sf /usr/bin/otelcol-contrib /usr/local/bin/otelcol-contrib && \
+    rm /tmp/otelcol-contrib.deb
+{% endif %}
+
+COPY ["start.sh", "otel.sh", "/usr/bin/"]
+RUN chmod +x /usr/bin/start.sh /usr/bin/otel.sh
+COPY ["supervisord.conf", "/etc/supervisor/conf.d/"]
+COPY ["critical_processes", "/etc/supervisor"]
+
+ENTRYPOINT ["/usr/local/bin/supervisord"]

dockers/docker-sonic-otel/base_image_files/monit_otel

@@ -0,0 +1,5 @@
+###############################################################################
+## Monit configuration for otel container
+###############################################################################
+check program container_memory_otel with path "/usr/bin/memory_checker otel 419430400"
+    if status == 3 for 10 times within 20 cycles then exec "/usr/bin/restart_service otel" repeat every 2 cycles

dockers/docker-sonic-otel/critical_processes

@@ -0,0 +1,2 @@
+program:otel
+

dockers/docker-sonic-otel/otel.sh

@@ -0,0 +1,38 @@
+#!/usr/bin/env bash
+
+EXIT_OTEL_CONFIG_FILE_NOT_FOUND=1
+OTEL_CONFIG_FILE=/etc/sonic/otel_config.yml
+
+echo "Starting otel.sh script"
+echo "Checking for config file: $OTEL_CONFIG_FILE"
+
+if [ ! -f "$OTEL_CONFIG_FILE" ]; then
+    echo "ERROR: OTEL config file not found at $OTEL_CONFIG_FILE"
+    exit $EXIT_OTEL_CONFIG_FILE_NOT_FOUND
+fi
+
+echo "Config file found at: $OTEL_CONFIG_FILE"
+
+# Validate the YAML configuration
+echo "Validating YAML configuration..."
+python3 -c "import yaml; yaml.safe_load(open(\"$OTEL_CONFIG_FILE\"))" 2>&1
+if [ $? -ne 0 ]; then
+    echo "ERROR: YAML configuration is invalid"
+    exit 1
+fi
+
+OTEL_ARGS="--config=$OTEL_CONFIG_FILE"
+
+echo "Checking otelcol-contrib binary"
+ls -la /usr/local/bin/otelcol-contrib
+
+if [ ! -x "/usr/local/bin/otelcol-contrib" ]; then
+    echo "ERROR: otelcol-contrib binary not found or not executable"
+    exit 1
+fi
+
+echo "otel collector args: $OTEL_ARGS"
+echo "Starting OTEL Collector with config file: $OTEL_CONFIG_FILE"
+
+exec /usr/local/bin/otelcol-contrib ${OTEL_ARGS}
+

dockers/docker-sonic-otel/start.sh

@@ -0,0 +1,14 @@
+#!/usr/bin/env bash
+
+if [ "${RUNTIME_OWNER}" == "" ]; then
+    RUNTIME_OWNER="kube"
+fi
+
+CTR_SCRIPT="/usr/share/sonic/scripts/container_startup.py"
+if test -f ${CTR_SCRIPT}
+then
+    ${CTR_SCRIPT} -f otel -o ${RUNTIME_OWNER} -v ${IMAGE_VERSION}
+fi
+
+mkdir -p /var/sonic
+echo "# Config files managed by sonic-config-engine" > /var/sonic/config_status

dockers/docker-sonic-otel/supervisord.conf

@@ -0,0 +1,58 @@
+[supervisord]
+logfile_maxbytes=1MB
+logfile_backups=2
+nodaemon=true
+
+[eventlistener:dependent-startup]
+command=python3 -m supervisord_dependent_startup
+autostart=true
+autorestart=unexpected
+startretries=0
+exitcodes=0,3
+events=PROCESS_STATE
+buffer_size=1024
+
+[eventlistener:supervisor-proc-exit-listener]
+command=/usr/local/bin/supervisor-proc-exit-listener --container-name otel
+events=PROCESS_STATE_EXITED,PROCESS_STATE_RUNNING
+autostart=true
+autorestart=unexpected
+buffer_size=1024
+
+[program:rsyslogd]
+command=/usr/sbin/rsyslogd -n -iNONE
+priority=1
+autostart=false
+autorestart=true
+stdout_logfile=NONE
+stdout_syslog=true
+stderr_logfile=NONE
+stderr_syslog=true
+dependent_startup=true
+
+[program:start]
+command=/usr/bin/start.sh
+priority=2
+autostart=false
+autorestart=false
+startsecs=0
+stdout_logfile=NONE
+stdout_syslog=true
+stderr_logfile=NONE
+stderr_syslog=true
+dependent_startup=true
+dependent_startup_wait_for=rsyslogd:running
+
+[program:otel]
+command=/usr/bin/otel.sh
+priority=3
+autostart=false
+autorestart=true
+startsecs=0
+stdout_logfile=NONE
+stdout_syslog=true
+stderr_logfile=NONE
+stderr_syslog=true
+dependent_startup=true
+dependent_startup_wait_for=start:exited
+

files/build_templates/otel.service.j2

@@ -0,0 +1,15 @@
+[Unit]
+Description=Otel container
+Requires=database.service
+Before=swss.service
+BindsTo=sonic.target
+After=sonic.target
+StartLimitIntervalSec=1200
+StartLimitBurst=3
+
+[Service]
+User={{ sonicadmin_user }}
+ExecStartPre=/usr/local/bin/{{docker_container_name}}.sh start
+ExecStart=/usr/local/bin/{{docker_container_name}}.sh wait
+ExecStop=/usr/local/bin/{{docker_container_name}}.sh stop
+RestartSec=30

files/build_templates/sonic_debian_extension.j2

@@ -651,6 +651,13 @@ sudo LANG=C chroot $FILESYSTEM_ROOT systemctl disable dash-engine
 
 {%- endif %}
 
+{%- if include_system_otel == "y" %}
+
+# Copy OTEL configuration files
+sudo cp $IMAGE_CONFIGS/otel/otel_config.yml $FILESYSTEM_ROOT/etc/sonic/
+
+{%- endif %}
+
 # Copy platform topology configuration scripts
 sudo cp $IMAGE_CONFIGS/config-topology/config-topology.service $FILESYSTEM_ROOT_USR_LIB_SYSTEMD_SYSTEM
 echo "config-topology.service" | sudo tee -a $GENERATED_SERVICE_FILE
@@ -1032,6 +1039,7 @@ sudo LANG=C cp $SCRIPTS_DIR/database.sh $FILESYSTEM_ROOT/usr/local/bin/database.
 sudo LANG=C cp $SCRIPTS_DIR/snmp.sh $FILESYSTEM_ROOT/usr/local/bin/snmp.sh
 sudo LANG=C cp $SCRIPTS_DIR/telemetry.sh $FILESYSTEM_ROOT/usr/local/bin/telemetry.sh
 sudo LANG=C cp $SCRIPTS_DIR/gnmi.sh $FILESYSTEM_ROOT/usr/local/bin/gnmi.sh
+sudo LANG=C cp $SCRIPTS_DIR/otel.sh $FILESYSTEM_ROOT/usr/local/bin/otel.sh
 sudo LANG=C cp $SCRIPTS_DIR/bmp.sh $FILESYSTEM_ROOT/usr/local/bin/bmp.sh
 sudo LANG=C cp $SCRIPTS_DIR/mgmt-framework.sh $FILESYSTEM_ROOT/usr/local/bin/mgmt-framework.sh
 sudo LANG=C cp $SCRIPTS_DIR/asic_status.sh $FILESYSTEM_ROOT/usr/local/bin/asic_status.sh

files/image_config/logrotate/rsyslog.j2

@@ -31,6 +31,7 @@
 /var/log/teamd.log
 /var/log/telemetry.log
 /var/log/gnmi.log
+/var/log/otel.log
 /var/log/frr/bgpd.log
 /var/log/frr/zebra.log
 /var/log/swss/sairedis*.rec

files/image_config/otel/otel_config.yml

@@ -0,0 +1,38 @@
+receivers:
+  otlp:
+    protocols:
+      grpc:
+        endpoint: "127.0.0.1:4317"
+      http:
+        endpoint: "127.0.0.1:4318"
+
+processors:
+  batch:
+    timeout: 1s
+    send_batch_size: 1000
+
+exporters:
+  debug:
+    verbosity: detailed
+
+service:
+  telemetry:
+    logs:
+      level: "info"
+
+  pipelines:
+    metrics:
+      receivers: [otlp]
+      processors: [batch]
+      exporters: [debug]
+
+    logs:
+      receivers: [otlp]
+      processors: [batch]
+      exporters: [debug]
+
+    traces:
+      receivers: [otlp]
+      processors: [batch]
+      exporters: [debug]
+

files/image_config/rsyslog/rsyslog.d/00-sonic.conf.j2

@@ -46,3 +46,18 @@ if $msg startswith  " telemetry" or ($msg startswith  " dialout" )then {
     /var/log/telemetry.log
     stop
 }
+
+## otel rules
+if $msg startswith " otel" then {
+    /var/log/otel.log
+    stop
+}
+
+## stpd rules
+if $programname contains "stp" then {
+    if not ($msg contains "STP_SYSLOG") then {
+        /var/log/stpd.log
+            stop
+    }
+}
+

files/scripts/otel.sh

@@ -0,0 +1 @@
+service_mgmt.sh

rules/config

@@ -133,6 +133,9 @@ INCLUDE_SYSTEM_EVENTD = y
 # INCLUDE_SYSTEM_TELEMETRY - build docker-sonic-telemetry for system telemetry support
 INCLUDE_SYSTEM_TELEMETRY = n
 
+# INCLUDE_SYSTEM_OTEL - build docker-sonic-otel for High Frequency Telemetry (HFT) support
+INCLUDE_SYSTEM_OTEL = y
+
 # INCLUDE_ICCPD - build docker-iccpd for mclag support
 INCLUDE_ICCPD = n
 

rules/docker-otel.dep

@@ -0,0 +1,11 @@
+DPATH       := $($(DOCKER_OTEL)_PATH)
+DEP_FILES   := $(SONIC_COMMON_FILES_LIST) rules/docker-otel.mk rules/docker-otel.dep
+DEP_FILES   += $(SONIC_COMMON_BASE_FILES_LIST)
+DEP_FILES   += $(shell git ls-files $(DPATH))
+
+$(DOCKER_OTEL)_CACHE_MODE  := GIT_CONTENT_SHA
+$(DOCKER_OTEL)_DEP_FLAGS   := $(SONIC_COMMON_FLAGS_LIST)
+$(DOCKER_OTEL)_DEP_FILES   := $(DEP_FILES)
+
+$(eval $(call add_dbg_docker,$(DOCKER_OTEL),$(DOCKER_OTEL_DBG)))
+

rules/docker-otel.mk

@@ -0,0 +1,40 @@
+# docker image for otel collector
+
+DOCKER_OTEL_STEM = docker-sonic-otel
+DOCKER_OTEL = $(DOCKER_OTEL_STEM).gz
+DOCKER_OTEL_DBG = $(DOCKER_OTEL_STEM)-$(DBG_IMAGE_MARK).gz
+
+$(DOCKER_OTEL)_PATH = $(DOCKERS_PATH)/$(DOCKER_OTEL_STEM)
+
+$(DOCKER_OTEL)_DBG_DEPENDS = $($(DOCKER_CONFIG_ENGINE_BOOKWORM)_DBG_DEPENDS)
+$(DOCKER_OTEL)_LOAD_DOCKERS += $(DOCKER_CONFIG_ENGINE_BOOKWORM)
+$(DOCKER_OTEL)_VERSION = 1.0.0
+$(DOCKER_OTEL)_PACKAGE_NAME = otel
+$(DOCKER_OTEL)_DBG_IMAGE_PACKAGES = $($(DOCKER_CONFIG_ENGINE_BOOKWORM)_DBG_IMAGE_PACKAGES)
+
+SONIC_DOCKER_IMAGES += $(DOCKER_OTEL)
+SONIC_BOOKWORM_DOCKERS += $(DOCKER_OTEL)
+ifeq ($(INCLUDE_SYSTEM_OTEL), y)
+SONIC_INSTALL_DOCKER_IMAGES += $(DOCKER_OTEL)
+endif
+
+SONIC_DOCKER_DBG_IMAGES += $(DOCKER_OTEL_DBG)
+SONIC_BOOKWORM_DBG_DOCKERS += $(DOCKER_OTEL_DBG)
+ifeq ($(INCLUDE_SYSTEM_OTEL), y)
+SONIC_INSTALL_DOCKER_DBG_IMAGES += $(DOCKER_OTEL_DBG)
+endif
+
+$(DOCKER_OTEL)_CONTAINER_NAME = otel
+$(DOCKER_OTEL)_RUN_OPT += -t
+$(DOCKER_OTEL)_RUN_OPT += -v /etc/sonic:/etc/sonic:ro
+$(DOCKER_OTEL)_RUN_OPT += -v /etc/localtime:/etc/localtime:ro
+$(DOCKER_OTEL)_RUN_OPT += -v /:/mnt/host:ro
+$(DOCKER_OTEL)_RUN_OPT += -v /tmp:/mnt/host/tmp:rw
+$(DOCKER_OTEL)_RUN_OPT += -v /var/tmp:/mnt/host/var/tmp:rw
+$(DOCKER_OTEL)_RUN_OPT += --pid=host
+$(DOCKER_OTEL)_RUN_OPT += --privileged
+$(DOCKER_OTEL)_RUN_OPT += --userns=host
+
+$(DOCKER_OTEL)_BASE_IMAGE_FILES += monit_otel:/etc/monit/conf.d
+
+

slave.mk

@@ -170,6 +170,10 @@ ifeq ($(SONIC_INCLUDE_SYSTEM_GNMI),y)
 INCLUDE_SYSTEM_GNMI = y
 endif
 
+ifeq ($(SONIC_INCLUDE_SYSTEM_OTEL),y)
+INCLUDE_SYSTEM_OTEL = y
+endif
+
 ifeq ($(SONIC_INCLUDE_SYSTEM_BMP),y)
 INCLUDE_SYSTEM_BMP = y
 endif
@@ -444,6 +448,7 @@ $(info "INCLUDE_ICCPD"                   : "$(INCLUDE_ICCPD)")
 $(info "INCLUDE_SYSTEM_TELEMETRY"        : "$(INCLUDE_SYSTEM_TELEMETRY)")
 $(info "INCLUDE_SYSTEM_GNMI"             : "$(INCLUDE_SYSTEM_GNMI)")
 $(info "INCLUDE_SYSTEM_BMP"              : "$(INCLUDE_SYSTEM_BMP)")
+$(info "INCLUDE_SYSTEM_OTEL"             : "$(INCLUDE_SYSTEM_OTEL)")
 $(info "INCLUDE_SYSTEM_EVENTD"           : "$(INCLUDE_SYSTEM_EVENTD)")
 $(info "ENABLE_HOST_SERVICE_ON_START"    : "$(ENABLE_HOST_SERVICE_ON_START)")
 $(info "INCLUDE_RESTAPI"                 : "$(INCLUDE_RESTAPI)")
@@ -1437,6 +1442,7 @@ $(addprefix $(TARGET_PATH)/, $(SONIC_INSTALLERS)) : $(TARGET_PATH)/% : \
 	export sonic_su_mode="$(SECURE_UPGRADE_MODE)"
 	export sonic_su_prod_signing_tool="/sonic/scripts/$(shell basename -- $(SECURE_UPGRADE_PROD_SIGNING_TOOL))"
 	export include_system_telemetry="$(INCLUDE_SYSTEM_TELEMETRY)"
+	export include_system_otel="$(INCLUDE_SYSTEM_OTEL)"
 	export include_system_gnmi="$(INCLUDE_SYSTEM_GNMI)"
 	export include_system_bmp="$(INCLUDE_SYSTEM_BMP)"
 	export include_system_eventd="$(INCLUDE_SYSTEM_EVENTD)"