docker: fix /data ownership and permission (#7451)

* docker: fix /data ownership and permission

* chown if not owned by seaweed user

* fix github tests

* comments

* fix the unquoted variables in the case pattern matching

* Update docker/entrypoint.sh

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

* Update docker/entrypoint.sh

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

* Update entrypoint.sh

* Update entrypoint.sh

* Update docker/entrypoint.sh

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

---------

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

docker/Dockerfile.e2e

@@ -3,6 +3,10 @@ FROM ubuntu:22.04
 LABEL author="Chris Lu"
 
 # Use faster mirrors and optimize package installation
+# Note: This e2e test image intentionally runs as root for simplicity and compatibility.
+# Production images (Dockerfile.go_build) use proper user isolation with su-exec.
+# For testing purposes, running as root avoids permission complexities and dependency
+# on Alpine-specific tools like su-exec (not available in Ubuntu repos).
 RUN apt-get update && \
     DEBIAN_FRONTEND=noninteractive apt-get install -y \
     --no-install-recommends \
@@ -10,6 +14,7 @@ RUN apt-get update && \
     curl \
     fio \
     fuse \
+    ca-certificates \
     && apt-get clean \
     && rm -rf /var/lib/apt/lists/* \
     && rm -rf /tmp/* \
@@ -18,7 +23,7 @@ RUN mkdir -p /etc/seaweedfs /data/filerldb2
 
 COPY ./weed /usr/bin/
 COPY ./filer.toml /etc/seaweedfs/filer.toml
-COPY ./entrypoint.sh /entrypoint.sh
+COPY ./entrypoint_e2e.sh /entrypoint.sh
 
 # volume server grpc port
 EXPOSE 18080

docker/Dockerfile.go_build

@@ -17,7 +17,7 @@ COPY --from=builder /go/src/github.com/seaweedfs/seaweedfs/docker/filer.toml /et
 COPY --from=builder /go/src/github.com/seaweedfs/seaweedfs/docker/entrypoint.sh /entrypoint.sh
 
 # Install dependencies and create non-root user
-RUN apk add --no-cache fuse && \
+RUN apk add --no-cache fuse su-exec && \
     addgroup -g 1000 seaweed && \
     adduser -D -u 1000 -G seaweed seaweed
 
@@ -47,7 +47,5 @@ RUN mkdir -p /data/filerldb2 && \
 VOLUME /data
 WORKDIR /data
 
-# Switch to non-root user
-USER seaweed
-
+# Entrypoint will handle permission fixes and user switching
 ENTRYPOINT ["/entrypoint.sh"]

docker/Dockerfile.local

@@ -8,7 +8,7 @@ COPY ./filer.toml /etc/seaweedfs/filer.toml
 COPY ./entrypoint.sh /entrypoint.sh
 
 # Install dependencies and create non-root user
-RUN apk add --no-cache fuse curl && \
+RUN apk add --no-cache fuse curl su-exec && \
     addgroup -g 1000 seaweed && \
     adduser -D -u 1000 -G seaweed seaweed
 
@@ -38,7 +38,5 @@ RUN mkdir -p /data/filerldb2 && \
 VOLUME /data
 WORKDIR /data
 
-# Switch to non-root user
-USER seaweed
-
+# Entrypoint will handle permission fixes and user switching
 ENTRYPOINT ["/entrypoint.sh"]

docker/Dockerfile.rocksdb_large

@@ -34,7 +34,7 @@ COPY --from=builder /go/src/github.com/seaweedfs/seaweedfs/docker/filer_rocksdb.
 COPY --from=builder /go/src/github.com/seaweedfs/seaweedfs/docker/entrypoint.sh /entrypoint.sh
 
 # Install dependencies and create non-root user
-RUN apk add --no-cache fuse snappy gflags && \
+RUN apk add --no-cache fuse snappy gflags su-exec && \
     addgroup -g 1000 seaweed && \
     adduser -D -u 1000 -G seaweed seaweed
 
@@ -65,7 +65,5 @@ VOLUME /data
 
 WORKDIR /data
 
-# Switch to non-root user
-USER seaweed
-
+# Entrypoint will handle permission fixes and user switching
 ENTRYPOINT ["/entrypoint.sh"]

docker/Dockerfile.rocksdb_large_local

@@ -17,7 +17,7 @@ COPY --from=builder /go/src/github.com/seaweedfs/seaweedfs/docker/filer_rocksdb.
 COPY --from=builder /go/src/github.com/seaweedfs/seaweedfs/docker/entrypoint.sh /entrypoint.sh
 
 # Install dependencies and create non-root user
-RUN apk add --no-cache fuse snappy gflags tmux && \
+RUN apk add --no-cache fuse snappy gflags tmux su-exec && \
     addgroup -g 1000 seaweed && \
     adduser -D -u 1000 -G seaweed seaweed
 
@@ -48,7 +48,5 @@ VOLUME /data
 
 WORKDIR /data
 
-# Switch to non-root user
-USER seaweed
-
+# Entrypoint will handle permission fixes and user switching
 ENTRYPOINT ["/entrypoint.sh"]

docker/Makefile

@@ -5,15 +5,19 @@ all: gen
 gen: dev
 
 cgo ?= 0
+ldflags_extra ?= -extldflags -static
+
 binary:
 	export SWCOMMIT=$(shell git rev-parse --short HEAD)
 	export SWLDFLAGS="-X github.com/seaweedfs/seaweedfs/weed/util/version.COMMIT=$(SWCOMMIT)"
-	cd ../weed && CGO_ENABLED=$(cgo) GOOS=linux go build $(options) -tags "$(tags)" -ldflags "-s -w -extldflags -static $(SWLDFLAGS)" -o weed_binary && mv weed_binary ../docker/weed
+	cd ../weed && CGO_ENABLED=$(cgo) GOOS=linux go build $(options) -tags "$(tags)" -ldflags "-s -w $(ldflags_extra) $(SWLDFLAGS)" -o weed_binary && mv weed_binary ../docker/weed
 	cd ../other/mq_client_example/agent_pub_record && CGO_ENABLED=$(cgo) GOOS=linux go build && mv agent_pub_record ../../../docker/
 	cd ../other/mq_client_example/agent_sub_record && CGO_ENABLED=$(cgo) GOOS=linux go build && mv agent_sub_record ../../../docker/
 
+# Race detector requires CGO and dynamic linking - don't use -static
 binary_race: options = -race
 binary_race: cgo = 1
+binary_race: ldflags_extra =
 binary_race: binary
 
 build: binary

docker/entrypoint.sh

@@ -1,5 +1,33 @@
 #!/bin/sh
 
+# Fix permissions for mounted volumes
+# If /data is mounted from host, it might have different ownership
+# Fix this by ensuring seaweed user owns the directory
+if [ "$(id -u)" = "0" ]; then
+  # Running as root, check and fix permissions if needed
+  SEAWEED_UID=$(id -u seaweed)
+  SEAWEED_GID=$(id -g seaweed)
+  
+  # Verify seaweed user and group exist
+  if [ -z "$SEAWEED_UID" ] || [ -z "$SEAWEED_GID" ]; then
+    echo "Error: 'seaweed' user or group not found. Cannot fix permissions." >&2
+    exit 1
+  fi
+  
+  DATA_UID=$(stat -c '%u' /data 2>/dev/null)
+  DATA_GID=$(stat -c '%g' /data 2>/dev/null)
+  
+  # Only run chown -R if ownership doesn't match (much faster for subsequent starts)
+    echo "Fixing /data ownership for seaweed user (uid=$SEAWEED_UID, gid=$SEAWEED_GID)"
+    if ! chown -R seaweed:seaweed /data; then
+      echo "Warning: Failed to change ownership of /data. This may cause permission errors." >&2
+      echo "If /data is read-only or has mount issues, the application may fail to start." >&2
+    fi
+  
+  # Use su-exec to drop privileges and run as seaweed user
+  exec su-exec seaweed "$0" "$@"
+fi
+
 isArgPassed() {
   arg="$1"
   argWithEqualSign="$1="
@@ -8,10 +36,10 @@ isArgPassed() {
     passedArg="$1"
     shift
     case $passedArg in
-    $arg)
+    "$arg")
       return 0
       ;;
-    $argWithEqualSign*)
+    "$argWithEqualSign"*)
       return 0
       ;;
     esac

docker/entrypoint_e2e.sh

@@ -0,0 +1,86 @@
+#!/bin/bash
+set -e
+
+# Simplified entrypoint for e2e testing
+# 
+# This script intentionally runs as root for e2e test environments to:
+# 1. Simplify test setup and avoid permission-related test failures
+# 2. Eliminate dependency on Alpine-specific tools (su-exec) since we use Ubuntu base
+# 3. Focus testing on application logic rather than container security
+#
+# IMPORTANT: Production deployments should use Dockerfile.go_build with proper
+# user isolation via su-exec. This simplified approach is ONLY for testing.
+
+isArgPassed() {
+  arg="$1"
+  argWithEqualSign="$1="
+  shift
+  while [ $# -gt 0 ]; do
+    passedArg="$1"
+    shift
+    case $passedArg in
+    "$arg")
+      return 0
+      ;;
+    "$argWithEqualSign"*)
+      return 0
+      ;;
+    esac
+  done
+  return 1
+}
+
+case "$1" in
+
+  'master')
+  	ARGS="-mdir=/data -volumePreallocate -volumeSizeLimitMB=1024"
+  	shift
+  	exec /usr/bin/weed -logtostderr=true master $ARGS "$@"
+	;;
+
+  'volume')
+  	ARGS="-dir=/data -max=0"
+  	if isArgPassed "-max" "$@"; then
+  	  ARGS="-dir=/data"
+  	fi
+  	shift
+  	exec /usr/bin/weed -logtostderr=true volume $ARGS "$@"
+	;;
+
+  'server')
+  	ARGS="-dir=/data -volume.max=0 -master.volumePreallocate -master.volumeSizeLimitMB=1024"
+  	if isArgPassed "-volume.max" "$@"; then
+  	  ARGS="-dir=/data -master.volumePreallocate -master.volumeSizeLimitMB=1024"
+  	fi
+ 	shift
+  	exec /usr/bin/weed -logtostderr=true server $ARGS "$@"
+  	;;
+
+  'filer')
+  	ARGS=""
+  	shift
+  	exec /usr/bin/weed -logtostderr=true filer $ARGS "$@"
+	;;
+
+  's3')
+  	ARGS="-domainName=$S3_DOMAIN_NAME -key.file=$S3_KEY_FILE -cert.file=$S3_CERT_FILE"
+  	shift
+  	exec /usr/bin/weed -logtostderr=true s3 $ARGS "$@"
+	;;
+
+  'mount')
+  	shift
+  	exec /usr/bin/weed -logtostderr=true mount "$@"
+	;;
+
+  'shell')
+  	ARGS="-cluster=$SHELL_CLUSTER -filer=$SHELL_FILER -filerGroup=$SHELL_FILER_GROUP -master=$SHELL_MASTER -options=$SHELL_OPTIONS"
+  	shift
+  	exec echo "$@" | /usr/bin/weed -logtostderr=true shell $ARGS
+  ;;
+
+  *)
+  	exec /usr/bin/weed "$@"
+	;;
+esac
+