From 2e5996f2281c312f6a4cbf12f698abc1e0c45a64 Mon Sep 17 00:00:00 2001
From: "Mads R. B. Kristensen" <madsbk@gmail.com>
Date: Tue, 12 Nov 2024 20:48:57 +0100
Subject: [PATCH 1/2] S3 benchmark: adding cudf-kvikio and cudf-fsspec (#509)

Authors:
  - Mads R. B. Kristensen (https://github.com/madsbk)

Approvers:
  - Lawrence Mitchell (https://github.com/wence-)

URL: https://github.com/rapidsai/kvikio/pull/509
---
 python/kvikio/kvikio/benchmarks/s3_io.py | 26 +++++++++++++++++++++++-
 1 file changed, 25 insertions(+), 1 deletion(-)

diff --git a/python/kvikio/kvikio/benchmarks/s3_io.py b/python/kvikio/kvikio/benchmarks/s3_io.py
index 7941462650..5e1846a1e5 100644
--- a/python/kvikio/kvikio/benchmarks/s3_io.py
+++ b/python/kvikio/kvikio/benchmarks/s3_io.py
@@ -99,9 +99,33 @@ def run() -> float:
         yield run()
 
 
+def run_cudf(args, kvikio_remote_io: bool):
+    import cudf
+
+    cudf.set_option("kvikio_remote_io", kvikio_remote_io)
+    url = f"s3://{args.bucket}/data"
+
+    # Upload data to S3 server
+    create_client_and_bucket()
+    data = cupy.random.rand(args.nelem).astype(args.dtype)
+    df = cudf.DataFrame({"a": data})
+    df.to_parquet(url)
+
+    def run() -> float:
+        t0 = time.perf_counter()
+        cudf.read_parquet(url)
+        t1 = time.perf_counter()
+        return t1 - t0
+
+    for _ in range(args.nruns):
+        yield run()
+
+
 API = {
     "cupy": partial(run_numpy_like, xp=cupy),
     "numpy": partial(run_numpy_like, xp=numpy),
+    "cudf-kvikio": partial(run_cudf, kvikio_remote_io=True),
+    "cudf-fsspec": partial(run_cudf, kvikio_remote_io=False),
 }
 
 
@@ -135,7 +159,7 @@ def main(args):
         def pprint_api_res(name, samples):
             samples = [args.nbytes / s for s in samples]  # Convert to throughput
             mean = statistics.harmonic_mean(samples) if len(samples) > 1 else samples[0]
-            ret = f"{api}-{name}".ljust(12)
+            ret = f"{api}-{name}".ljust(18)
             ret += f"| {format_bytes(mean).rjust(10)}/s".ljust(14)
             if len(samples) > 1:
                 stdev = statistics.stdev(samples) / mean * 100

From d40b7e4541a77842d0af911858b4f0708fe19225 Mon Sep 17 00:00:00 2001
From: James Lamb <jlamb@nvidia.com>
Date: Wed, 13 Nov 2024 09:11:32 -0600
Subject: [PATCH 2/2] enforce wheel size limits, README formatting in CI (#548)

Contributes to https://github.com/rapidsai/build-planning/issues/110

Proposes adding 2 types of validation on wheels in CI, to ensure we continue to produce wheels that are suitable for PyPI.

* checks on wheel size (compressed),
  - *to be sure they're under PyPI limits*
  - *and to prompt discussion on PRs that significantly increase wheel sizes*
* checks on README formatting
  - *to ensure they'll render properly as the PyPI project homepages*
  - *e.g. like how https://github.com/scikit-learn/scikit-learn/blob/main/README.rst becomes https://pypi.org/project/scikit-learn/*

Authors:
  - James Lamb (https://github.com/jameslamb)

Approvers:
  - Bradley Dice (https://github.com/bdice)

URL: https://github.com/rapidsai/kvikio/pull/548
---
 ci/build_wheel_cpp.sh           |  2 ++
 ci/build_wheel_python.sh        |  2 ++
 ci/validate_wheel.sh            | 21 +++++++++++++++++++++
 python/kvikio/pyproject.toml    |  8 ++++++++
 python/libkvikio/pyproject.toml |  8 ++++++++
 5 files changed, 41 insertions(+)
 create mode 100755 ci/validate_wheel.sh

diff --git a/ci/build_wheel_cpp.sh b/ci/build_wheel_cpp.sh
index 0367842a8c..ca27717769 100755
--- a/ci/build_wheel_cpp.sh
+++ b/ci/build_wheel_cpp.sh
@@ -36,4 +36,6 @@ python -m auditwheel repair \
     -w ${package_dir}/final_dist \
     ${package_dir}/dist/*
 
+./ci/validate_wheel.sh ${package_dir} final_dist
+
 RAPIDS_PY_WHEEL_NAME="${package_name}_${RAPIDS_PY_CUDA_SUFFIX}" rapids-upload-wheels-to-s3 cpp "${package_dir}/final_dist"
diff --git a/ci/build_wheel_python.sh b/ci/build_wheel_python.sh
index 0c709f2fe6..088e8e8e8f 100755
--- a/ci/build_wheel_python.sh
+++ b/ci/build_wheel_python.sh
@@ -25,4 +25,6 @@ python -m auditwheel repair \
     -w ${package_dir}/final_dist \
     ${package_dir}/dist/*
 
+./ci/validate_wheel.sh ${package_dir} final_dist
+
 RAPIDS_PY_WHEEL_NAME="${package_name}_${RAPIDS_PY_CUDA_SUFFIX}" rapids-upload-wheels-to-s3 python ${package_dir}/final_dist
diff --git a/ci/validate_wheel.sh b/ci/validate_wheel.sh
new file mode 100755
index 0000000000..5910a5c59f
--- /dev/null
+++ b/ci/validate_wheel.sh
@@ -0,0 +1,21 @@
+#!/bin/bash
+# Copyright (c) 2024, NVIDIA CORPORATION.
+
+set -euo pipefail
+
+package_dir=$1
+wheel_dir_relative_path=$2
+
+cd "${package_dir}"
+
+rapids-logger "validate packages with 'pydistcheck'"
+
+pydistcheck \
+    --inspect \
+    "$(echo ${wheel_dir_relative_path}/*.whl)"
+
+rapids-logger "validate packages with 'twine'"
+
+twine check \
+    --strict \
+    "$(echo ${wheel_dir_relative_path}/*.whl)"
diff --git a/python/kvikio/pyproject.toml b/python/kvikio/pyproject.toml
index b002569646..cafde598bd 100644
--- a/python/kvikio/pyproject.toml
+++ b/python/kvikio/pyproject.toml
@@ -139,6 +139,14 @@ provider = "scikit_build_core.metadata.regex"
 input = "kvikio/VERSION"
 regex = "(?P<value>.*)"
 
+[tool.pydistcheck]
+select = [
+    "distro-too-large-compressed",
+]
+
+# PyPI limit is 100 MiB, fail CI before we get too close to that
+max_allowed_size_compressed = '75M'
+
 [tool.pytest.ini_options]
 filterwarnings = [
     "error",
diff --git a/python/libkvikio/pyproject.toml b/python/libkvikio/pyproject.toml
index 3be7cbc0ae..9504cb3755 100644
--- a/python/libkvikio/pyproject.toml
+++ b/python/libkvikio/pyproject.toml
@@ -59,3 +59,11 @@ requires = [
 
 [project.entry-points."cmake.prefix"]
 libkvikio = "libkvikio"
+
+[tool.pydistcheck]
+select = [
+    "distro-too-large-compressed",
+]
+
+# PyPI limit is 100 MiB, fail CI before we get too close to that
+max_allowed_size_compressed = '75M'