From 270446be27992e9c45eef165cde1f4ea49f8940d Mon Sep 17 00:00:00 2001
From: eugr <eugr@spark2.home.eugr.net>
Date: Fri, 5 Dec 2025 11:28:43 -0800
Subject: [PATCH] Add build-and-copy script for automated image building and
 deployment

---
 README.md         | 65 +++++++++++++++++++++++++++++++++++++++++++--
 build-and-copy.sh | 67 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 130 insertions(+), 2 deletions(-)
 create mode 100755 build-and-copy.sh

diff --git a/README.md b/README.md
index a0159a2..76e594e 100644
--- a/README.md
+++ b/README.md
@@ -48,9 +48,70 @@ docker build \
   -t vllm-node .
 ```
 
-### Copying the container to another Spark node
+### Option D: Using the Build Script (Recommended)
 
-To avoid extra network overhead, you can copy the image directly to your second Spark node via ConnectX 7 interface by using the following command:
+The `build-and-copy.sh` script automates the build process and optionally copies the image to another node. This is the recommended method for building and deploying to multiple Spark nodes.
+
+**Basic usage (build only):**
+
+```bash
+./build-and-copy.sh
+```
+
+**Build with a custom tag:**
+
+```bash
+./build-and-copy.sh --tag my-vllm-node
+```
+
+**Build and copy to another Spark node:**
+
+Using the same username as currently logged-in user:
+
+```bash
+./build-and-copy.sh --copy-to-host 192.168.177.12
+```
+
+Using a different username:
+
+```bash
+./build-and-copy.sh --copy-to-host 192.168.177.12 --user your_username
+```
+
+**Force rebuild vLLM source only:**
+
+```bash
+./build-and-copy.sh --rebuild-vllm
+```
+
+**Force rebuild all dependencies:**
+
+```bash
+./build-and-copy.sh --rebuild-deps
+```
+
+**Combined example (rebuild vLLM and copy to another node):**
+
+```bash
+./build-and-copy.sh --rebuild-vllm --copy-to-host 192.168.177.12
+```
+
+**Available options:**
+
+| Flag | Description |
+| :--- | :--- |
+| `-t, --tag <tag>` | Image tag (default: 'vllm-node') |
+| `--rebuild-deps` | Force rebuild all dependencies (sets CACHEBUST_DEPS) |
+| `--rebuild-vllm` | Force rebuild vLLM source only (sets CACHEBUST_VLLM) |
+| `-h, --copy-to-host <host>` | Host address to copy the image to after building |
+| `-u, --user <user>` | Username for SSH connection (default: current user) |
+| `--help` | Show help message |
+
+**IMPORTANT**: When copying to another node, make sure you use the Spark IP assigned to its ConnectX 7 interface (enp1s0f1np1), and not the 10G interface (enP7s7)!
+
+### Copying the container to another Spark node (Manual Method)
+
+Alternatively, you can manually copy the image directly to your second Spark node via ConnectX 7 interface by using the following command:
 
 ```bash
 docker save vllm-node | ssh your_username@another_spark_hostname_or_ip "docker load"
diff --git a/build-and-copy.sh b/build-and-copy.sh
new file mode 100755
index 0000000..7dbbf17
--- /dev/null
+++ b/build-and-copy.sh
@@ -0,0 +1,67 @@
+#!/bin/bash
+set -e
+
+# Default values
+IMAGE_TAG="vllm-node"
+REBUILD_DEPS=false
+REBUILD_VLLM=false
+COPY_HOST=""
+SSH_USER="$USER"
+
+# Help function
+usage() {
+    echo "Usage: $0 [OPTIONS]"
+    echo "  -t, --tag <tag>           : Image tag (default: 'vllm-node')"
+    echo "  --rebuild-deps            : Set cache bust for dependencies"
+    echo "  --rebuild-vllm            : Set cache bust for vllm"
+    echo "  -h, --copy-to-host <host> : Host address to copy the image to (if not set, don't copy)"
+    echo "  -u, --user <user>         : Username for ssh command (default: \$USER)"
+    echo "  --help                    : Show this help message"
+    exit 1
+}
+
+# Argument parsing
+while [[ "$#" -gt 0 ]]; do
+    case $1 in
+        -t|--tag) IMAGE_TAG="$2"; shift ;;
+        --rebuild-deps) REBUILD_DEPS=true ;;
+        --rebuild-vllm) REBUILD_VLLM=true ;;
+        -h|--copy-to-host) COPY_HOST="$2"; shift ;;
+        -u|--user) SSH_USER="$2"; shift ;;
+        --help) usage ;;
+        *) echo "Unknown parameter passed: $1"; usage ;;
+    esac
+    shift
+done
+
+# Construct build command
+CMD=("docker" "build" "-t" "$IMAGE_TAG")
+
+if [ "$REBUILD_DEPS" = true ]; then
+    echo "Setting CACHEBUST_DEPS..."
+    CMD+=("--build-arg" "CACHEBUST_DEPS=$(date +%s)")
+fi
+
+if [ "$REBUILD_VLLM" = true ]; then
+    echo "Setting CACHEBUST_VLLM..."
+    CMD+=("--build-arg" "CACHEBUST_VLLM=$(date +%s)")
+fi
+
+# Add build context
+CMD+=(".")
+
+# Execute build
+echo "Building image with command: ${CMD[*]}"
+"${CMD[@]}"
+
+# Copy to host if requested
+if [ -n "$COPY_HOST" ]; then
+    echo "Copying image '$IMAGE_TAG' to ${SSH_USER}@${COPY_HOST}..."
+    # Using the pipe method from README.md
+    docker save "$IMAGE_TAG" | ssh "${SSH_USER}@${COPY_HOST}" "docker load"
+    echo "Copy complete."
+else
+    echo "No host specified, skipping copy."
+fi
+
+echo "Done."