Claude
0cb7605afa
The Dockerfile installs openjdk-17-jre-headless and sets JAVA_HOME=/usr/lib/jvm/java-17-openjdk-amd64, but the entrypoint default was still /usr/lib/jvm/java-11-openjdk-amd64. The validation caught the mismatch at container start: [entrypoint] FATAL: JAVA_HOME=/usr/lib/jvm/java-11-openjdk-amd64 but /usr/lib/jvm/java-11-openjdk-amd64/bin/java is missing or not executable That's exactly the failure mode the validation is designed to catch - the deployment config got out of sync. Aligning all four files (Dockerfile, entrypoint, .env.example, docker-compose.yml) to java-17-openjdk-amd64. No app code touched. 165/165 still pass.
63 lines
2.6 KiB
Bash
Executable File
63 lines
2.6 KiB
Bash
Executable File
#!/bin/sh
|
|
# docker-entrypoint.sh
|
|
#
|
|
# Spark 3.1.2 + JDK 11 container entrypoint.
|
|
#
|
|
# Three responsibilities, in order:
|
|
# 1. Resolve JAVA_HOME and SPARK_HOME from env (with sensible defaults
|
|
# matching the Dockerfile).
|
|
# 2. Validate the resolved paths exist and contain the expected
|
|
# binaries. Fail fast at container start with a clear error
|
|
# message, instead of letting a job submission die later with an
|
|
# opaque "no such file" or "command not found".
|
|
# 3. Update PATH so the (possibly overridden) JAVA_HOME/bin and
|
|
# SPARK_HOME/bin are prepended — overrides via docker-compose / .env
|
|
# take effect on the very next container start, without rebuilding
|
|
# the image.
|
|
#
|
|
# Compared to the previous version this drops the awk-based PATH
|
|
# stripping (too brittle — would also strip the new JAVA_HOME/bin if
|
|
# it happened to be under /usr/lib/jvm/) and instead just prepends.
|
|
# Whatever was in the old PATH is preserved; the new paths win
|
|
# because they come first.
|
|
set -e
|
|
|
|
# Defaults match the Dockerfile's build-time ENV
|
|
# (openjdk-17-jre-headless + Spark 3.5.8)
|
|
: "${JAVA_HOME:=/usr/lib/jvm/java-17-openjdk-amd64}"
|
|
: "${SPARK_HOME:=/opt/spark}"
|
|
|
|
# --- Validation (fail fast with a clear error) ---
|
|
if [ ! -x "${JAVA_HOME}/bin/java" ]; then
|
|
echo "[entrypoint] FATAL: JAVA_HOME=${JAVA_HOME} but ${JAVA_HOME}/bin/java is missing or not executable" >&2
|
|
echo "[entrypoint] Hint: set JAVA_HOME to a directory containing bin/java (e.g. /usr/lib/jvm/java-11-openjdk-amd64)" >&2
|
|
exit 1
|
|
fi
|
|
|
|
if [ ! -x "${SPARK_HOME}/bin/spark-submit" ]; then
|
|
echo "[entrypoint] FATAL: SPARK_HOME=${SPARK_HOME} but ${SPARK_HOME}/bin/spark-submit is missing or not executable" >&2
|
|
echo "[entrypoint] Hint: set SPARK_HOME to the Spark install root (e.g. /opt/spark)" >&2
|
|
exit 1
|
|
fi
|
|
|
|
# Export the resolved values (so subprocesses see them)
|
|
export JAVA_HOME
|
|
export SPARK_HOME
|
|
|
|
# --- Update PATH ---
|
|
# Prepend the project venv and the (possibly overridden) JDK + Spark
|
|
# bin dirs. Order matters: /app/.venv/bin first (project tools win),
|
|
# then JAVA_HOME/bin (overrides any system java), then SPARK_HOME/bin,
|
|
# then whatever was already on PATH.
|
|
export PATH="/app/.venv/bin:${JAVA_HOME}/bin:${SPARK_HOME}/bin:${PATH}"
|
|
|
|
# --- Log the effective resolution so docker logs show what was picked ---
|
|
echo "[entrypoint] JAVA_HOME=${JAVA_HOME}" >&2
|
|
echo "[entrypoint] SPARK_HOME=${SPARK_HOME}" >&2
|
|
echo "[entrypoint] java: $(command -v java)" >&2
|
|
echo "[entrypoint] spark-submit: $(command -v spark-submit)" >&2
|
|
echo "[entrypoint] java version: $(java -version 2>&1 | head -1)" >&2
|
|
|
|
# Run whatever CMD was passed (gunicorn main:app, or python main.py, etc.)
|
|
exec "$@"
|