[proposal] Use rust based cp tool rather than busybox in autoinstrumentation images.

.chloggen/cputil.yaml

@@ -0,0 +1,16 @@
+# One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix'
+change_type: 'enhancement'
+
+# The name of the component, or a single word describing the area of concern, (e.g. operator, target allocator, github action)
+component: autoinstrumentation
+
+# A brief description of the change. Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: Replace busybox base image with cp binary in java autoinstrumentation dockerfile
+
+# One or more tracking issues related to the change
+issues: [1600]
+
+# (Optional) One or more lines of additional information to render under the primary note.
+# These lines will be padded with 2 spaces and then inserted directly into the document.
+# Use pipe (|) for multiline entries.
+subtext:

.github/CODEOWNERS

@@ -20,3 +20,6 @@
 
 # Target Allocator owners
 cmd/otel-allocator @open-telemetry/operator-ta-maintainers
+
+# cp-utility tool
+tools/cp-utility @rapphil @bryan-aguilar

.github/workflows/publish-autoinstrumentation-java.yaml

@@ -19,6 +19,10 @@ jobs:
 
     steps:
       - uses: actions/checkout@v3
+
+      # this is required so that the cp-utility binary is in included in the docker context. 
+      - name: copy cp-utility
+        run: cp -r tools/cp-utility autoinstrumentation/java/
 
       - name: Read version
         run: echo "VERSION=$(cat autoinstrumentation/java/version.txt)" >> $GITHUB_ENV

autoinstrumentation/java/Dockerfile

@@ -4,10 +4,43 @@
 #  - Grant the necessary access to the jar. `chmod -R go+r /javaagent.jar`
 #  - For auto-instrumentation by container injection, the Linux command cp is
 #    used and must be availabe in the image.
-FROM busybox
+
+# Stage 1: Build the cp-utility binary
+FROM rust:1.69 as builder
+
+WORKDIR /usr/src/cp-utility
+COPY ./cp-utility .
+
+## TARGETARCH is defined by buildx
+# https://docs.docker.com/engine/reference/builder/#automatic-platform-args-in-the-global-scope
+ARG TARGETARCH
+
+# Run validations and audit only on amd64 bacause it is faster and those two steps
+# are only used to validate the source code and don't require anything that is
+# architecture specific.
+
+# Validations
+## Validate formatting
+RUN if [ $TARGETARCH = "amd64" ]; then rustup component add rustfmt && cargo fmt --check ; fi
+
+## Audit dependencies
+RUN if [ $TARGETARCH = "amd64" ]; then cargo install cargo-audit && cargo audit ; fi
+
+
+# Cross-compile based on the target platform.
+RUN if [ $TARGETARCH = "amd64" ]; then export ARCH="x86_64" ; \
+    elif [ $TARGETARCH = "arm64" ]; then export ARCH="aarch64" ; \
+    else false; \
+    fi \
+    && rustup target add ${ARCH}-unknown-linux-musl \
+    && cargo test  --target ${ARCH}-unknown-linux-musl \
+    && cargo install --target ${ARCH}-unknown-linux-musl --path . --root .
+
+# Stage 2: Create distribution
+FROM scratch
 
 ARG version
 
-ADD https://github.com/open-telemetry/opentelemetry-java-instrumentation/releases/download/v$version/opentelemetry-javaagent.jar /javaagent.jar
+COPY --from=builder /usr/src/cp-utility/bin/cp-utility /bin/cp
 
-RUN chmod -R go+r /javaagent.jar
+ADD --chmod=go+r https://github.com/open-telemetry/opentelemetry-java-instrumentation/releases/download/v$version/opentelemetry-javaagent.jar /javaagent.jar

tools/cp-utility/.cargo/config.toml

@@ -0,0 +1,3 @@
+# Use git CLI to fetch the source code instead of relying on the rust git implementation
+[net]
+git-fetch-with-cli = true

tools/cp-utility/Cargo.toml

@@ -0,0 +1,22 @@
+[package]
+name = "cp-utility"
+version = "0.1.0"
+edition = "2021"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
+[dependencies]
+# No dependencies here
+
+[dev-dependencies]
+# dependencies only used during tests
+tempfile = "3.5.0"
+uuid = { version = "1.3.1", features = ["v4", "fast-rng"] }
+
+[profile.release]
+# Levers to optimize the binary for size
+strip = true # Strip symbols
+opt-level = "z" # Size optimization
+lto = true # linking time optimizations
+
+