mirror of
https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git
synced 2025-08-10 19:18:57 +08:00
Consolidate entrypoint to support broader deployment scenarios (#6566)
### What problem does this PR solve? This PR gives better control over how we distribute which service will be loaded. With this approach, we can create containers to run only the web server and others to run the task executor. It also introduces the unique ID per task executor host, this will be important when scaling task executors horizontally, considering unique task executor ids will be required. This new `entrypoint.sh` maintains the default behavior of starting the web server and task executor in the same host. ### Type of change - [ ] Bug Fix (non-breaking change which fixes an issue) - [X] New Feature (non-breaking change which adds functionality) - [ ] Documentation Update - [ ] Refactoring - [ ] Performance Improvement - [ ] Other (please describe):
This commit is contained in:
Wanderson Pinto dos Santos
GitHub
parent
c61df5dd25
commit
2632493c8b
@ -201,7 +201,7 @@ COPY agentic_reasoning agentic_reasoning
|
||||
COPY pyproject.toml uv.lock ./
|
||||
|
||||
COPY docker/service_conf.yaml.template ./conf/service_conf.yaml.template
|
||||
COPY docker/entrypoint.sh docker/entrypoint-parser.sh ./
|
||||
COPY docker/entrypoint.sh ./
|
||||
RUN chmod +x ./entrypoint*.sh
|
||||
|
||||
# Copy compiled web pages
|
||||
|
||||
@ -1,29 +0,0 @@
|
||||
#!/bin/bash
|
||||
|
||||
# replace env variables in the service_conf.yaml file
|
||||
rm -rf /ragflow/conf/service_conf.yaml
|
||||
while IFS= read -r line || [[ -n "$line" ]]; do
|
||||
# Use eval to interpret the variable with default values
|
||||
eval "echo \"$line\"" >> /ragflow/conf/service_conf.yaml
|
||||
done < /ragflow/conf/service_conf.yaml.template
|
||||
|
||||
export LD_LIBRARY_PATH=/usr/lib/x86_64-linux-gnu/
|
||||
|
||||
PY=python3
|
||||
|
||||
CONSUMER_NO_BEG=$1
|
||||
CONSUMER_NO_END=$2
|
||||
|
||||
function task_exe(){
|
||||
JEMALLOC_PATH=$(pkg-config --variable=libdir jemalloc)/libjemalloc.so
|
||||
while [ 1 -eq 1 ]; do
|
||||
LD_PRELOAD=$JEMALLOC_PATH $PY rag/svr/task_executor.py $1;
|
||||
done
|
||||
}
|
||||
|
||||
for ((i=CONSUMER_NO_BEG; i<CONSUMER_NO_END; i++))
|
||||
do
|
||||
task_exe $i &
|
||||
done
|
||||
|
||||
wait;
|
||||
152
docker/entrypoint.sh
Executable file → Normal file
152
docker/entrypoint.sh
Executable file → Normal file
@ -1,35 +1,139 @@
|
||||
#!/bin/bash
|
||||
#!/usr/bin/env bash
|
||||
|
||||
# replace env variables in the service_conf.yaml file
|
||||
rm -rf /ragflow/conf/service_conf.yaml
|
||||
while IFS= read -r line || [[ -n "$line" ]]; do
|
||||
# Use eval to interpret the variable with default values
|
||||
eval "echo \"$line\"" >> /ragflow/conf/service_conf.yaml
|
||||
done < /ragflow/conf/service_conf.yaml.template
|
||||
set -e
|
||||
|
||||
/usr/sbin/nginx
|
||||
# -----------------------------------------------------------------------------
|
||||
# Usage and command-line argument parsing
|
||||
# -----------------------------------------------------------------------------
|
||||
function usage() {
|
||||
echo "Usage: $0 [--disable-webserver] [--disable-taskexecutor] [--consumer-no-beg=<num>] [--consumer-no-end=<num>] [--workers=<num>] [--host-id=<string>]"
|
||||
echo
|
||||
echo " --disable-webserver Disables the web server (nginx + ragflow_server)."
|
||||
echo " --disable-taskexecutor Disables task executor workers."
|
||||
echo " --consumer-no-beg=<num> Start range for consumers (if using range-based)."
|
||||
echo " --consumer-no-end=<num> End range for consumers (if using range-based)."
|
||||
echo " --workers=<num> Number of task executors to run (if range is not used)."
|
||||
echo " --host-id=<string> Unique ID for the host (defaults to \`hostname\`)."
|
||||
echo
|
||||
echo "Examples:"
|
||||
echo " $0 --disable-taskexecutor"
|
||||
echo " $0 --disable-webserver --consumer-no-beg=0 --consumer-no-end=5"
|
||||
echo " $0 --disable-webserver --workers=2 --host-id=myhost123"
|
||||
exit 1
|
||||
}
|
||||
|
||||
export LD_LIBRARY_PATH=/usr/lib/x86_64-linux-gnu/
|
||||
ENABLE_WEBSERVER=1 # Default to enable web server
|
||||
ENABLE_TASKEXECUTOR=1 # Default to enable task executor
|
||||
CONSUMER_NO_BEG=0
|
||||
CONSUMER_NO_END=0
|
||||
WORKERS=1
|
||||
|
||||
PY=python3
|
||||
if [[ -z "$WS" || $WS -lt 1 ]]; then
|
||||
WS=1
|
||||
# -----------------------------------------------------------------------------
|
||||
# Host ID logic:
|
||||
# 1. By default, use the system hostname if length <= 32
|
||||
# 2. Otherwise, use the full MD5 hash of the hostname (32 hex chars)
|
||||
# -----------------------------------------------------------------------------
|
||||
CURRENT_HOSTNAME="$(hostname)"
|
||||
if [ ${#CURRENT_HOSTNAME} -le 32 ]; then
|
||||
DEFAULT_HOST_ID="$CURRENT_HOSTNAME"
|
||||
else
|
||||
DEFAULT_HOST_ID="$(echo -n "$CURRENT_HOSTNAME" | md5sum | cut -d ' ' -f 1)"
|
||||
fi
|
||||
|
||||
function task_exe(){
|
||||
JEMALLOC_PATH=$(pkg-config --variable=libdir jemalloc)/libjemalloc.so
|
||||
while [ 1 -eq 1 ];do
|
||||
LD_PRELOAD=$JEMALLOC_PATH $PY rag/svr/task_executor.py $1;
|
||||
HOST_ID="$DEFAULT_HOST_ID"
|
||||
|
||||
# Parse arguments
|
||||
for arg in "$@"; do
|
||||
case $arg in
|
||||
--disable-webserver)
|
||||
ENABLE_WEBSERVER=0
|
||||
shift
|
||||
;;
|
||||
--disable-taskexecutor)
|
||||
ENABLE_TASKEXECUTOR=0
|
||||
shift
|
||||
;;
|
||||
--consumer-no-beg=*)
|
||||
CONSUMER_NO_BEG="${arg#*=}"
|
||||
shift
|
||||
;;
|
||||
--consumer-no-end=*)
|
||||
CONSUMER_NO_END="${arg#*=}"
|
||||
shift
|
||||
;;
|
||||
--workers=*)
|
||||
WORKERS="${arg#*=}"
|
||||
shift
|
||||
;;
|
||||
--host-id=*)
|
||||
HOST_ID="${arg#*=}"
|
||||
shift
|
||||
;;
|
||||
*)
|
||||
usage
|
||||
;;
|
||||
esac
|
||||
done
|
||||
|
||||
# -----------------------------------------------------------------------------
|
||||
# Replace env variables in the service_conf.yaml file
|
||||
# -----------------------------------------------------------------------------
|
||||
CONF_DIR="/ragflow/conf"
|
||||
TEMPLATE_FILE="${CONF_DIR}/service_conf.yaml.template"
|
||||
CONF_FILE="${CONF_DIR}/service_conf.yaml"
|
||||
|
||||
rm -f "${CONF_FILE}"
|
||||
while IFS= read -r line || [[ -n "$line" ]]; do
|
||||
eval "echo \"$line\"" >> "${CONF_FILE}"
|
||||
done < "${TEMPLATE_FILE}"
|
||||
|
||||
export LD_LIBRARY_PATH="/usr/lib/x86_64-linux-gnu/"
|
||||
PY=python3
|
||||
|
||||
# -----------------------------------------------------------------------------
|
||||
# Function(s)
|
||||
# -----------------------------------------------------------------------------
|
||||
|
||||
function task_exe() {
|
||||
local consumer_id="$1"
|
||||
local host_id="$2"
|
||||
|
||||
JEMALLOC_PATH="$(pkg-config --variable=libdir jemalloc)/libjemalloc.so"
|
||||
while true; do
|
||||
LD_PRELOAD="$JEMALLOC_PATH" \
|
||||
"$PY" rag/svr/task_executor.py "${host_id}_${consumer_id}"
|
||||
done
|
||||
}
|
||||
|
||||
for ((i=0;i<WS;i++))
|
||||
do
|
||||
task_exe $i &
|
||||
done
|
||||
# -----------------------------------------------------------------------------
|
||||
# Start components based on flags
|
||||
# -----------------------------------------------------------------------------
|
||||
|
||||
while [ 1 -eq 1 ];do
|
||||
$PY api/ragflow_server.py
|
||||
done
|
||||
if [[ "${ENABLE_WEBSERVER}" -eq 1 ]]; then
|
||||
echo "Starting nginx..."
|
||||
/usr/sbin/nginx
|
||||
|
||||
wait;
|
||||
echo "Starting ragflow_server..."
|
||||
while true; do
|
||||
"$PY" api/ragflow_server.py
|
||||
done &
|
||||
fi
|
||||
|
||||
if [[ "${ENABLE_TASKEXECUTOR}" -eq 1 ]]; then
|
||||
if [[ "${CONSUMER_NO_END}" -gt "${CONSUMER_NO_BEG}" ]]; then
|
||||
echo "Starting task executors on host '${HOST_ID}' for IDs in [${CONSUMER_NO_BEG}, ${CONSUMER_NO_END})..."
|
||||
for (( i=CONSUMER_NO_BEG; i<CONSUMER_NO_END; i++ ))
|
||||
do
|
||||
task_exe "${i}" "${HOST_ID}" &
|
||||
done
|
||||
else
|
||||
# Otherwise, start a fixed number of workers
|
||||
echo "Starting ${WORKERS} task executor(s) on host '${HOST_ID}'..."
|
||||
for (( i=0; i<WORKERS; i++ ))
|
||||
do
|
||||
task_exe "${i}" "${HOST_ID}" &
|
||||
done
|
||||
fi
|
||||
fi
|
||||
|
||||
wait
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user