Merged PR 3845699: [linkmgrd]: Introduce MUX cable linkmgrd

Linkmgrd monitors link status, mux status, and link state. Has
the link becomes unhealthy, linkmgrd will trigger mux switchover
on a standby ToR ensuring uninterrupted service to servers/blades.
This PR is initial implementation of linkmgrd.

Also, docker-mux container hold packages related to maintaining and managing
mux cable. It currently runs linkmgrd binary that monitor and switches
the mux if needed.
This PR also introduces mux-container and starts linkmgrd as startup when
build is configured with INCLUDE_MUX=y

Edit: linkmgrd PR will follow.

signed-off-by: Tamer Ahmed <tamer.ahmed@microsoft.com>

Related work items: #2315, #3146150
This commit is contained in:
Tamer Ahmed 2021-01-26 01:43:56 +00:00 committed by Ying Xie
parent 8138a34a0b
commit b8f70f8986
13 changed files with 189 additions and 1 deletions

View File

@ -10,6 +10,7 @@
# * ENABLE_ZTP: Enables zero touch provisioning.
# * SHUTDOWN_BGP_ON_START: Sets admin-down state for all bgp peerings after restart.
# * INCLUDE_KUBERNETES: Allows including Kubernetes
# * INCLUDE_MUX: Include MUX feature/services for TOR switch.
# * ENABLE_PFCWD_ON_START: Enable PFC Watchdog (PFCWD) on server-facing ports
# * by default for TOR switch.
# * ENABLE_SYNCD_RPC: Enables rpc-based syncd builds.
@ -267,6 +268,7 @@ SONIC_BUILD_INSTRUCTION := make \
HTTPS_PROXY=$(https_proxy) \
SONIC_INCLUDE_SYSTEM_TELEMETRY=$(INCLUDE_SYSTEM_TELEMETRY) \
SONIC_INCLUDE_RESTAPI=$(INCLUDE_RESTAPI) \
SONIC_INCLUDE_MUX=$(INCLUDE_MUX) \
TELEMETRY_WRITABLE=$(TELEMETRY_WRITABLE) \
EXTRA_DOCKER_TARGETS=$(EXTRA_DOCKER_TARGETS) \
BUILD_LOG_TIMESTAMP=$(BUILD_LOG_TIMESTAMP) \

View File

@ -0,0 +1,36 @@
{% from "dockers/dockerfile-macros.j2" import install_debian_packages, install_python_wheels, copy_files %}
FROM docker-config-engine-buster
ARG docker_container_name
RUN [ -f /etc/rsyslog.conf ] && sed -ri "s/%syslogtag%/$docker_container_name#%syslogtag%/;" /etc/rsyslog.conf
## Make apt-get non-interactive
ENV DEBIAN_FRONTEND=noninteractive
RUN apt-get update && \
apt-get install -f -y \
libmnl0
{% if docker_mux_debs.strip() -%}
# Copy locally-built Debian package dependencies
{{ copy_files("debs/", docker_mux_debs.split(' '), "/debs/") }}
# Install locally-built Debian packages and implicitly install their dependencies
{{ install_debian_packages(docker_mux_debs.split(' ')) }}
{%- endif %}
## Clean up
RUN apt-get clean -y && \
apt-get autoclean -y && \
apt-get autoremove -y && \
rm -rf /debs
COPY ["docker-init.sh", "/usr/bin/"]
COPY ["supervisord.conf", "/etc/supervisor/conf.d/"]
COPY ["files/supervisor-proc-exit-listener", "/usr/bin"]
COPY ["critical_processes", "/etc/supervisor/"]
## Copy all Jinja2 template files into the templates folder
COPY ["*.j2", "/usr/share/sonic/templates/"]
ENTRYPOINT ["/usr/bin/docker-init.sh"]

View File

@ -0,0 +1 @@
program:linkmgrd

View File

@ -0,0 +1,9 @@
#!/usr/bin/env bash
# Generate supervisord config file
mkdir -p /etc/supervisor/conf.d/
# The docker container should start this script as PID 1, so now that supervisord is
# properly configured, we exec supervisord so that it runs as PID 1 for the
# duration of the container's lifetime
exec /usr/local/bin/supervisord

View File

@ -0,0 +1,41 @@
[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=100
[eventlistener:supervisor-proc-exit-listener]
command=/usr/bin/supervisor-proc-exit-listener --container-name mux
events=PROCESS_STATE_EXITED,PROCESS_STATE_RUNNING
autostart=true
autorestart=unexpected
[program:rsyslogd]
command=/usr/sbin/rsyslogd -n -iNONE
priority=1
autostart=false
autorestart=unexpected
stdout_logfile=syslog
stderr_logfile=syslog
dependent_startup=true
[program:linkmgrd]
command=nice -n -20 /usr/sbin/linkmgrd -v warning
priority=2
autostart=false
autorestart=false
startsecs=0
startretries=0
stdout_logfile=syslog
stderr_logfile=syslog
dependent_startup=true
dependent_startup_wait_for=rsyslogd:running

View File

@ -31,6 +31,7 @@
{%- if sonic_asic_platform == "vs" %}{% do features.append(("gbsyncd", "enabled", false, "enabled")) %}{% endif %}
{%- if include_iccpd == "y" %}{% do features.append(("iccpd", "disabled", false, "enabled")) %}{% endif %}
{%- if include_mgmt_framework == "y" %}{% do features.append(("mgmt-framework", "enabled", true, "enabled")) %}{% endif %}
{%- if include_mux == "y" %}{% do features.append(("mux", "enabled", false, "enabled")) %}{% endif %}
{%- if include_nat == "y" %}{% do features.append(("nat", "disabled", false, "enabled")) %}{% endif %}
{%- if include_restapi == "y" %}{% do features.append(("restapi", "enabled", false, "enabled")) %}{% endif %}
{%- if include_sflow == "y" %}{% do features.append(("sflow", "disabled", false, "enabled")) %}{% endif %}

View File

@ -0,0 +1,17 @@
[Unit]
Description=MUX Cable Container
Requires=database.service updategraph.service pmon.service swss.service
After=pmon.service swss.service
StartLimitIntervalSec=1200
StartLimitBurst=3
[Service]
User={{ sonicadmin_user }}
ExecStartPre=/usr/bin/{{docker_container_name}}.sh start
ExecStart=/usr/bin/{{docker_container_name}}.sh wait
ExecStop=/usr/bin/{{docker_container_name}}.sh stop
Restart=always
RestartSec=30
[Install]
WantedBy=multi-user.target

View File

@ -191,3 +191,6 @@ SONIC_VERSION_CONTROL_COMPONENTS ?= none
# Set the env variable ENABLE_DOCKER_BASE_PULL = y to enable pulling sonic-slave docker from registry
REGISTRY_PORT ?= 443
REGISTRY_SERVER ?= sonicdev-microsoft.azurecr.io
# INCLUDE_MUX - build docker-mux for dual ToR (Gemini)
INCLUDE_MUX = y

12
rules/docker-mux.dep Normal file
View File

@ -0,0 +1,12 @@
DPATH := $($(DOCKER_MUX)_PATH)
DEP_FILES := $(SONIC_COMMON_FILES_LIST) rules/docker-mux.mk rules/docker-mux.dep
DEP_FILES += $(SONIC_COMMON_BASE_FILES_LIST)
DEP_FILES += $(shell git ls-files $(DPATH))
$(DOCKER_MUX)_CACHE_MODE := GIT_CONTENT_SHA
$(DOCKER_MUX)_DEP_FLAGS := $(SONIC_COMMON_FLAGS_LIST)
$(DOCKER_MUX)_DEP_FILES := $(DEP_FILES)
$(eval $(call add_dbg_docker,$(DOCKER_MUX),$(DOCKER_MUX_DBG)))

32
rules/docker-mux.mk Normal file
View File

@ -0,0 +1,32 @@
# Docker image for MUX
DOCKER_MUX_STEM = docker-mux
DOCKER_MUX = $(DOCKER_MUX_STEM).gz
DOCKER_MUX_DBG = $(DOCKER_MUX_STEM)-$(DBG_IMAGE_MARK).gz
$(DOCKER_MUX)_PATH = $(DOCKERS_PATH)/$(DOCKER_MUX_STEM)
$(DOCKER_MUX)_DEPENDS = $(SONIC_LINKMGRD) $(LIBSWSSCOMMON) $(LIBHIREDIS)
$(DOCKER_MUX)_DBG_DEPENDS = $($(DOCKER_CONFIG_ENGINE_BUSTER)_DBG_DEPENDS)
$(DOCKER_MUX)_DBG_DEPENDS += $(SONIC_LINKMGRD_DBG) $(LIBSWSSCOMMON_DBG) $(LIBHIREDIS_DBG)
$(DOCKER_MUX)_DBG_IMAGE_PACKAGES = $($(DOCKER_CONFIG_ENGINE_BUSTER)_DBG_IMAGE_PACKAGES)
$(DOCKER_MUX)_LOAD_DOCKERS = $(DOCKER_CONFIG_ENGINE_BUSTER)
ifeq ($(INCLUDE_MUX), y)
SONIC_DOCKER_IMAGES += $(DOCKER_MUX)
SONIC_INSTALL_DOCKER_IMAGES += $(DOCKER_MUX)
endif
ifeq ($(INCLUDE_MUX), y)
SONIC_DOCKER_DBG_IMAGES += $(DOCKER_MUX_DBG)
SONIC_INSTALL_DOCKER_DBG_IMAGES += $(DOCKER_MUX_DBG)
endif
$(DOCKER_MUX)_CONTAINER_NAME = mux
$(DOCKER_MUX)_RUN_OPT += --privileged -t
$(DOCKER_MUX)_RUN_OPT += -v /etc/sonic:/etc/sonic:ro
$(DOCKER_ORCHAGENT)_RUN_OPT += -v /var/log/mux:/var/log/mux:rw
$(DOCKER_MUX)_FILES += $(SUPERVISOR_PROC_EXIT_LISTENER_SCRIPT)

11
rules/linkmgrd.dep Normal file
View File

@ -0,0 +1,11 @@
SPATH := $($(SONIC_LINKMGRD)_SRC_PATH)
DEP_FILES := $(SONIC_COMMON_FILES_LIST) rules/linkmgrd.mk rules/linkmgrd.dep
DEP_FILES += $(SONIC_COMMON_BASE_FILES_LIST)
SMDEP_FILES := $(addprefix $(SPATH)/,$(shell cd $(SPATH) && git ls-files))
$(SONIC_LINKMGRD)_CACHE_MODE := GIT_CONTENT_SHA
$(SONIC_LINKMGRD)_DEP_FLAGS := $(SONIC_COMMON_FLAGS_LIST)
$(SONIC_LINKMGRD)_DEP_FILES := $(DEP_FILES)
$(SONIC_LINKMGRD)_SMDEP_FILES := $(SMDEP_FILES)
$(SONIC_LINKMGRD)_SMDEP_PATHS := $(SPATH)

18
rules/linkmgrd.mk Normal file
View File

@ -0,0 +1,18 @@
# SONiC LINK ManaGeR Daemon package
SONIC_LINKMGRD_VERSION = 1.0.0-1
SONIC_LINKMGRD_PKG_NAME = linkmgrd
export SONIC_LINKMGRD_VERSION SONIC_LINKMGRD_PKG_NAME
SONIC_LINKMGRD = sonic-$(SONIC_LINKMGRD_PKG_NAME)_$(SONIC_LINKMGRD_VERSION)_$(CONFIGURED_ARCH).deb
$(SONIC_LINKMGRD)_SRC_PATH = $(SRC_PATH)/$(SONIC_LINKMGRD_PKG_NAME)
$(SONIC_LINKMGRD)_DEPENDS = $(LIBSWSSCOMMON_DEV) $(LIBSWSSCOMMON) $(LIBHIREDIS_DEV) $(LIBHIREDIS)
SONIC_DPKG_DEBS += $(SONIC_LINKMGRD)
SONIC_LINKMGRD_DBG = sonic-$(SONIC_LINKMGRD_PKG_NAME)-dbgsym_$(SONIC_LINKMGRD_VERSION)_$(CONFIGURED_ARCH).deb
$(SONIC_LINKMGRD)_DBG_DEPENDS = $(LIBSWSSCOMMON_DEV) $(LIBSWSSCOMMON_DBG) $(LIBHIREDIS_DEV) $(LIBHIREDIS_DBG)
$(eval $(call add_derived_package,$(SONIC_LINKMGRD),$(SONIC_LINKMGRD_DBG)))
export SONIC_LINKMGRD SONIC_LINKMGRD_DBG

View File

@ -153,6 +153,10 @@ INCLUDE_NAT = y
endif
ifeq ($(SONIC_INCLUDE_MUX),y)
INCLUDE_MUX = y
endif
include $(RULES_PATH)/functions
ifeq ($(SONIC_USE_PDDF_FRAMEWORK),y)
@ -266,6 +270,7 @@ $(info "INCLUDE_RESTAPI" : "$(INCLUDE_RESTAPI)")
$(info "INCLUDE_SFLOW" : "$(INCLUDE_SFLOW)")
$(info "INCLUDE_NAT" : "$(INCLUDE_NAT)")
$(info "INCLUDE_KUBERNETES" : "$(INCLUDE_KUBERNETES)")
$(info "INCLUDE_MUX" : "$(INCLUDE_MUX)")
$(info "TELEMETRY_WRITABLE" : "$(TELEMETRY_WRITABLE)")
$(info "PDDF_SUPPORT" : "$(PDDF_SUPPORT)")
$(info "MULTIARCH_QEMU_ENVIRON" : "$(MULTIARCH_QEMU_ENVIRON)")
@ -944,7 +949,7 @@ $(addprefix $(TARGET_PATH)/, $(SONIC_INSTALLERS)) : $(TARGET_PATH)/% : \
export python_swss_debs+=" $(addprefix $(IMAGE_DISTRO_DEBS_PATH)/,$(LIBSWSSCOMMON)) $(addprefix $(IMAGE_DISTRO_DEBS_PATH)/,$(PYTHON_SWSSCOMMON)) $(addprefix $(IMAGE_DISTRO_DEBS_PATH)/,$(PYTHON3_SWSSCOMMON))"
export sonic_utilities_py3_wheel_path="$(addprefix $(PYTHON_WHEELS_PATH)/,$(SONIC_UTILITIES_PY3))"
export sonic_host_services_py3_wheel_path="$(addprefix $(PYTHON_WHEELS_PATH)/,$(SONIC_HOST_SERVICES_PY3))"
export include_mux="$(INCLUDE_MUX)"
$(foreach docker, $($*_DOCKERS),\
export docker_image="$(docker)"
export docker_image_name="$(basename $(docker))"