From e45620793d902dded692b1250c610b747c41b9a7 Mon Sep 17 00:00:00 2001
From: Divye Gala <divyegala@gmail.com>
Date: Thu, 30 Mar 2023 14:38:50 -0400
Subject: [PATCH] Add Options to Generate Build Metrics Report (#1369)

This PR will also automatically generate an HTML report in `conda-cpp-build` CI runs under the task `Upload Additional Artifacts`

Authors:
  - Divye Gala (https://github.com/divyegala)

Approvers:
  - AJ Schmidt (https://github.com/ajschmidt8)
  - Corey J. Nolet (https://github.com/cjnolet)

URL: https://github.com/rapidsai/raft/pull/1369
---
 build.sh                               | 64 +++++++++++++++++++++++++-
 conda/recipes/libraft/build_libraft.sh |  2 +-
 conda/recipes/libraft/meta.yaml        |  1 +
 3 files changed, 64 insertions(+), 3 deletions(-)

diff --git a/build.sh b/build.sh
index 7e1a3e7e36..270c75de93 100755
--- a/build.sh
+++ b/build.sh
@@ -18,7 +18,7 @@ ARGS=$*
 # scripts, and that this script resides in the repo dir!
 REPODIR=$(cd $(dirname $0); pwd)
 
-VALIDARGS="clean libraft pylibraft raft-dask docs tests template bench-prims bench-ann clean --uninstall  -v -g -n --compile-lib --allgpuarch --no-nvtx --show_depr_warn --time -h"
+VALIDARGS="clean libraft pylibraft raft-dask docs tests template bench-prims bench-ann clean --uninstall  -v -g -n --compile-lib --allgpuarch --no-nvtx --show_depr_warn  --build-metrics --incl-cache-stats --time -h"
 HELP="$0 [<target> ...] [<flag> ...] [--cmake-args=\"<args>\"] [--cache-tool=<tool>] [--limit-tests=<targets>] [--limit-bench-prims=<targets>] [--limit-bench-ann=<targets>]
  where <target> is:
    clean            - remove all existing build artifacts and configuration (start over)
@@ -45,6 +45,8 @@ HELP="$0 [<target> ...] [<flag> ...] [--cmake-args=\"<args>\"] [--cache-tool=<to
    --allgpuarch                - build for all supported GPU architectures
    --no-nvtx                   - disable nvtx (profiling markers), but allow enabling it in downstream projects
    --show_depr_warn            - show cmake deprecation warnings
+   --build-metrics             - generate build metrics report for libraft
+   --incl-cache-stats          - include cache statistics in build metrics report
    --cmake-args=\\\"<args>\\\" - pass arbitrary list of CMake configuration options (escape all quotes in argument)
    --cache-tool=<tool>         - pass the build cache tool (eg: ccache, sccache, distcc) that will be used
                                  to speedup the build process.
@@ -71,6 +73,8 @@ BUILD_PRIMS_BENCH=OFF
 BUILD_ANN_BENCH=OFF
 COMPILE_LIBRARY=OFF
 INSTALL_TARGET=install
+BUILD_REPORT_METRICS=OFF
+BUILD_REPORT_INCL_CACHE_STATS=OFF
 
 TEST_TARGETS="CLUSTER_TEST;CORE_TEST;DISTANCE_TEST;LABEL_TEST;LINALG_TEST;MATRIX_TEST;RANDOM_TEST;SOLVERS_TEST;SPARSE_TEST;SPARSE_DIST_TEST;SPARSE_NEIGHBORS_TEST;NEIGHBORS_TEST;STATS_TEST;UTILS_TEST"
 BENCH_TARGETS="CLUSTER_BENCH;NEIGHBORS_BENCH;DISTANCE_BENCH;LINALG_BENCH;MATRIX_BENCH;SPARSE_BENCH;RANDOM_BENCH"
@@ -335,7 +339,12 @@ fi
 if hasArg clean; then
     CLEAN=1
 fi
-
+if hasArg --build-metrics; then
+    BUILD_REPORT_METRICS=ON
+fi
+if hasArg --incl-cache-stats; then
+    BUILD_REPORT_INCL_CACHE_STATS=ON
+fi
 if [[ ${CMAKE_TARGET} == "" ]]; then
     CMAKE_TARGET="all"
 fi
@@ -378,6 +387,12 @@ if (( ${NUMARGS} == 0 )) || hasArg libraft || hasArg docs || hasArg tests || has
         echo "Building for *ALL* supported GPU architectures..."
     fi
 
+    # get the current count before the compile starts
+    CACHE_TOOL=${CACHE_TOOL:-sccache}
+    if [[ "$BUILD_REPORT_INCL_CACHE_STATS" == "ON" && -x "$(command -v ${CACHE_TOOL})" ]]; then
+        "${CACHE_TOOL}" --zero-stats
+    fi
+
     mkdir -p ${LIBRAFT_BUILD_DIR}
     cd ${LIBRAFT_BUILD_DIR}
     cmake -S ${REPODIR}/cpp -B ${LIBRAFT_BUILD_DIR} \
@@ -395,6 +410,7 @@ if (( ${NUMARGS} == 0 )) || hasArg libraft || hasArg docs || hasArg tests || has
           ${CACHE_ARGS} \
           ${EXTRA_CMAKE_ARGS}
 
+  compile_start=$(date +%s)
   if [[ ${CMAKE_TARGET} != "" ]]; then
       echo "-- Compiling targets: ${CMAKE_TARGET}, verbose=${VERBOSE_FLAG}"
       if [[ ${INSTALL_TARGET} != "" ]]; then
@@ -403,6 +419,50 @@ if (( ${NUMARGS} == 0 )) || hasArg libraft || hasArg docs || hasArg tests || has
         cmake --build  "${LIBRAFT_BUILD_DIR}" ${VERBOSE_FLAG} -j${PARALLEL_LEVEL} --target ${CMAKE_TARGET}
       fi
   fi
+  compile_end=$(date +%s)
+  compile_total=$(( compile_end - compile_start ))
+
+  if [[ "$BUILD_REPORT_METRICS" == "ON" && -f "${LIBRAFT_BUILD_DIR}/.ninja_log" ]]; then
+      if ! rapids-build-metrics-reporter.py 2> /dev/null && [ ! -f rapids-build-metrics-reporter.py ]; then
+          echo "Downloading rapids-build-metrics-reporter.py"
+          curl -sO https://raw.githubusercontent.com/rapidsai/build-metrics-reporter/v1/rapids-build-metrics-reporter.py
+      fi
+
+      echo "Formatting build metrics"
+      MSG=""
+      # get some sccache/ccache stats after the compile
+      if [[ "$BUILD_REPORT_INCL_CACHE_STATS" == "ON" ]]; then
+          if [[ ${CACHE_TOOL} == "sccache" && -x "$(command -v sccache)" ]]; then
+              COMPILE_REQUESTS=$(sccache -s | grep "Compile requests \+ [0-9]\+$" | awk '{ print $NF }')
+              CACHE_HITS=$(sccache -s | grep "Cache hits \+ [0-9]\+$" | awk '{ print $NF }')
+              HIT_RATE=$(echo - | awk "{printf \"%.2f\n\", $CACHE_HITS / $COMPILE_REQUESTS * 100}")
+              MSG="${MSG}<br/>cache hit rate ${HIT_RATE} %"
+          elif [[ ${CACHE_TOOL} == "ccache" && -x "$(command -v ccache)" ]]; then
+              CACHE_STATS_LINE=$(ccache -s | grep "Hits: \+ [0-9]\+ / [0-9]\+" | tail -n1)
+              if [[ ! -z "$CACHE_STATS_LINE" ]]; then
+                  CACHE_HITS=$(echo "$CACHE_STATS_LINE" - | awk '{ print $2 }')
+                  COMPILE_REQUESTS=$(echo "$CACHE_STATS_LINE" - | awk '{ print $4 }')
+                  HIT_RATE=$(echo - | awk "{printf \"%.2f\n\", $CACHE_HITS / $COMPILE_REQUESTS * 100}")
+                  MSG="${MSG}<br/>cache hit rate ${HIT_RATE} %"
+              fi
+          fi
+      fi
+      MSG="${MSG}<br/>parallel setting: $PARALLEL_LEVEL"
+      MSG="${MSG}<br/>parallel build time: $compile_total seconds"
+      if [[ -f "${LIBRAFT_BUILD_DIR}/libraft.so" ]]; then
+          LIBRAFT_FS=$(ls -lh ${LIBRAFT_BUILD_DIR}/libraft.so | awk '{print $5}')
+          MSG="${MSG}<br/>libraft.so size: $LIBRAFT_FS"
+      fi
+      BMR_DIR=${RAPIDS_ARTIFACTS_DIR:-"${LIBRAFT_BUILD_DIR}"}
+      echo "The HTML report can be found at [${BMR_DIR}/ninja_log.html]. In CI, this report"
+      echo "will also be uploaded to the appropriate subdirectory of https://downloads.rapids.ai/ci/raft/, and"
+      echo "the entire URL can be found in \"conda-cpp-build\" runs under the task \"Upload additional artifacts\""
+      mkdir -p ${BMR_DIR}
+      MSG_OUTFILE="$(mktemp)"
+      echo "$MSG" > "${MSG_OUTFILE}"
+      PATH=".:$PATH" python rapids-build-metrics-reporter.py ${LIBRAFT_BUILD_DIR}/.ninja_log --fmt html --msg "${MSG_OUTFILE}" > ${BMR_DIR}/ninja_log.html
+      cp ${LIBRAFT_BUILD_DIR}/.ninja_log ${BMR_DIR}/ninja.log
+  fi
 fi
 
 # Build and (optionally) install the pylibraft Python package
diff --git a/conda/recipes/libraft/build_libraft.sh b/conda/recipes/libraft/build_libraft.sh
index 237e47eb26..2bf9b428cb 100644
--- a/conda/recipes/libraft/build_libraft.sh
+++ b/conda/recipes/libraft/build_libraft.sh
@@ -1,4 +1,4 @@
 #!/usr/bin/env bash
 # Copyright (c) 2022-2023, NVIDIA CORPORATION.
 
-./build.sh libraft --allgpuarch --compile-lib --no-nvtx
+./build.sh libraft --allgpuarch --compile-lib --build-metrics --incl-cache-stats --no-nvtx
diff --git a/conda/recipes/libraft/meta.yaml b/conda/recipes/libraft/meta.yaml
index 7859807777..ccd7314484 100644
--- a/conda/recipes/libraft/meta.yaml
+++ b/conda/recipes/libraft/meta.yaml
@@ -29,6 +29,7 @@ outputs:
         - CMAKE_CXX_COMPILER_LAUNCHER
         - CMAKE_GENERATOR
         - PARALLEL_LEVEL
+        - RAPIDS_ARTIFACTS_DIR
         - SCCACHE_BUCKET
         - SCCACHE_IDLE_TIMEOUT
         - SCCACHE_REGION