From 8eb84b73e6c439b5ab9530c253eec48ac6082627 Mon Sep 17 00:00:00 2001
From: "C.J. Collier" <cjac@google.com>
Date: Fri, 20 Jun 2025 22:18:17 +0000
Subject: [PATCH] feat: Add no-customization.sh for disk usage metrics

This commit introduces `examples/secure-boot/no-customization.sh`, a
new script designed primarily for collecting disk usage metrics during
custom image builds. This script directly addresses the need for
detailed disk analysis, a critical component in ensuring Dataproc
images remain lightweight and optimized, as emphasized in the recent
Dataproc 2.3 release which focused on reduced CVEs and smaller image
footprints Dataproc on GCE image version 2.3 (optimized for FedRAMP _
Compliance).pdf].

During the development and review of the Dataproc 2.3 custom images,
this `no-customization.sh` script, along with similar disk metric
collection logic in `install_gpu_driver.sh`, was instrumental. These
tools allowed for precise measurement of disk consumption at various
stages of image creation. The data gathered directly informed
decisions regarding package inclusions and default disk sizes,
contributing significantly to the ~70% reduction in open-source
software components and ~50% reduction in total CVEs observed in
Dataproc 2.3 images Dataproc on GCE image version 2.3 (optimized for
FedRAMP _ Compliance).pdf].

The metrics captured by this script (and the `install_gpu_driver.sh`
exit handler) were fed back into `pre-init.sh` and other image
generation orchestrators, allowing for iterative refinement and
validation of the image size. This continuous feedback loop was
crucial for achieving the lightweight and compliant image goals for
Dataproc 2.3. The inclusion of this script in the repository makes
this valuable diagnostic tool available for future image optimization
efforts, especially relevant for new AI/ML images or subsequent
releases.

The `no-customization.sh` script leverages existing patterns for disk
usage monitoring and cleanup within the custom images repository,
including the use of `df`, `perl` for metric calculation, and the `dd`
command for zeroing free space when `creating-image` metadata is
present.
---
 examples/secure-boot/no-customization.sh | 53 ++++++++++++++++++++++++
 1 file changed, 53 insertions(+)
 create mode 100644 examples/secure-boot/no-customization.sh

diff --git a/examples/secure-boot/no-customization.sh b/examples/secure-boot/no-customization.sh
new file mode 100644
index 0000000..5ad17b0
--- /dev/null
+++ b/examples/secure-boot/no-customization.sh
@@ -0,0 +1,53 @@
+#!/bin/bash
+
+function exit_handler() {
+  set +ex
+  echo "Exit handler invoked"
+
+  # Process disk usage logs from installation period
+  rm -f /run/keep-running-df
+  sync
+  sleep 5.01s
+  # compute maximum size of disk during installation
+  # Log file contains logs like the following (minus the preceeding #):
+#Filesystem     1K-blocks    Used Available Use% Mounted on
+#/dev/vda2        7096908 2611344   4182932  39% /
+  df / | tee -a "/run/disk-usage.log"
+
+  perl -e '($first, @samples) = grep { m:^/: } <STDIN>;
+           unshift(@samples,$first); $final=$samples[-1];
+           ($starting)=(split(/\s+/,$first))[2] =~ /^(\d+)/;
+             ($ending)=(split(/\s+/,$final))[2] =~ /^(\d+)/;
+           @siz=( sort { $a => $b }
+                   map { (split)[2] =~ /^(\d+)/ } @samples );
+$max=$siz[0]; $min=$siz[-1]; $inc=$max-$starting;
+print( "     samples-taken: ", scalar @siz, $/,
+       "starting-disk-used: $starting", $/,
+       "  ending-disk-used: $ending", $/,
+       " maximum-disk-used: $max", $/,
+       " minimum-disk-used: $min", $/,
+       "      increased-by: $inc", $/ )' < "/run/disk-usage.log"
+
+  # zero free disk space
+  if [[ -n "$(get_metadata_attribute creating-image)" ]]; then
+    dd if=/dev/zero of=/zero
+    sync
+    sleep 3s
+    rm -f /zero
+  fi
+
+  echo "exit_handler has completed"
+  return 0
+}
+
+# Monitor disk usage in a screen session
+df / | tee "/run/disk-usage.log"
+touch "/run/keep-running-df"
+screen -d -m -LUS keep-running-df \
+  bash -c "while [[ -f /run/keep-running-df ]] ; do df / | tee -a /run/disk-usage.log ; sleep 5s ; done"
+
+trap exit_handler EXIT
+
+apt-get update -y -qq > /dev/null 2>&1
+
+echo "exit handler will be triggered after this operation."