Pin dask and distributed for release (#11822)

This PR pins `dask` and `distributed` to `2022.9.2` for `22.10` release.

Authors:
  - GALI PREM SAGAR (https://github.com/galipremsagar)

Approvers:
  - Ray Douglass (https://github.com/raydouglass)
  - Lawrence Mitchell (https://github.com/wence-)
  - Ashwin Srinath (https://github.com/shwina)
  - https://github.com/jakirkham

URL: #11822

ci/benchmark/build.sh

@@ -37,10 +37,10 @@ export GBENCH_BENCHMARKS_DIR="$WORKSPACE/cpp/build/gbenchmarks/"
 export LIBCUDF_KERNEL_CACHE_PATH="$HOME/.jitify-cache"
 
 # Dask & Distributed option to install main(nightly) or `conda-forge` packages.
-export INSTALL_DASK_MAIN=1
+export INSTALL_DASK_MAIN=0
 
 # Dask version to install when `INSTALL_DASK_MAIN=0`
-export DASK_STABLE_VERSION="2022.7.1"
+export DASK_STABLE_VERSION="2022.9.2"
 
 function remove_libcudf_kernel_cache_dir {
     EXITCODE=$?

ci/cpu/build.sh

@@ -26,6 +26,10 @@ export GPUCI_CONDA_RETRY_SLEEP=30
 export CMAKE_GENERATOR="Ninja"
 export CONDA_BLD_DIR="$WORKSPACE/.conda-bld"
 
+# Whether to keep `dask/label/dev` channel in the env. If INSTALL_DASK_MAIN=0,
+# `dask/label/dev` channel is removed.
+export INSTALL_DASK_MAIN=0
+
 # Switch to project root; also root of repo checkout
 cd "$WORKSPACE"
 
@@ -49,6 +53,9 @@ conda activate rapids
 if [ "$SOURCE_BRANCH" = "main" ]; then
   conda config --system --remove channels rapidsai-nightly
   conda config --system --remove channels dask/label/dev
+elif [[ "${INSTALL_DASK_MAIN}" == 0 ]]; then
+  # Remove `dask/label/dev` channel if INSTALL_DASK_MAIN=0
+  conda config --system --remove channels dask/label/dev
 fi
 
 gpuci_logger "Check compiler versions"

ci/gpu/build.sh

@@ -32,10 +32,10 @@ export MINOR_VERSION=`echo $GIT_DESCRIBE_TAG | grep -o -E '([0-9]+\.[0-9]+)'`
 unset GIT_DESCRIBE_TAG
 
 # Dask & Distributed option to install main(nightly) or `conda-forge` packages.
-export INSTALL_DASK_MAIN=1
+export INSTALL_DASK_MAIN=0
 
 # Dask version to install when `INSTALL_DASK_MAIN=0`
-export DASK_STABLE_VERSION="2022.7.1"
+export DASK_STABLE_VERSION="2022.9.2"
 
 # ucx-py version
 export UCX_PY_VERSION='0.28.*'
@@ -78,6 +78,12 @@ gpuci_logger "Activate conda env"
 . /opt/conda/etc/profile.d/conda.sh
 conda activate rapids
 
+# Remove `dask/label/dev` channel if INSTALL_DASK_MAIN=0
+if [ "$SOURCE_BRANCH" != "main" ] && [[ "${INSTALL_DASK_MAIN}" == 0 ]]; then
+  conda config --system --remove channels dask/label/dev
+  gpuci_mamba_retry install conda-forge::dask==$DASK_STABLE_VERSION conda-forge::distributed==$DASK_STABLE_VERSION conda-forge::dask-core==$DASK_STABLE_VERSION --force-reinstall
+fi
+
 gpuci_logger "Check conda environment"
 conda info
 conda config --show-sources

conda/environments/cudf_dev_cuda11.5.yml

@@ -49,8 +49,8 @@ dependencies:
   - pydocstyle=6.1.1
   - typing_extensions
   - pre-commit
-  - dask>=2022.7.1
-  - distributed>=2022.7.1
+  - dask==2022.9.2
+  - distributed==2022.9.2
   - streamz
   - arrow-cpp=9
   - dlpack>=0.5,<0.6.0a0

conda/recipes/custreamz/meta.yaml

@@ -29,8 +29,8 @@ requirements:
     - python
     - streamz
     - cudf ={{ version }}
-    - dask>=2022.7.1
-    - distributed>=2022.7.1
+    - dask==2022.9.2
+    - distributed==2022.9.2
     - python-confluent-kafka >=1.7.0,<1.8.0a0
     - cudf_kafka ={{ version }}
 

conda/recipes/dask-cudf/meta.yaml

@@ -24,14 +24,14 @@ requirements:
   host:
     - python
     - cudf ={{ version }}
-    - dask>=2022.7.1
-    - distributed>=2022.7.1
+    - dask==2022.9.2
+    - distributed==2022.9.2
     - cudatoolkit ={{ cuda_version }}
   run:
     - python
     - cudf ={{ version }}
-    - dask>=2022.7.1
-    - distributed>=2022.7.1
+    - dask==2022.9.2
+    - distributed==2022.9.2
     - {{ pin_compatible('cudatoolkit', max_pin='x', min_pin='x') }}
 
 test:                                   # [linux64]

python/cudf/cudf/tests/test_orc.py

@@ -736,6 +736,7 @@ def test_orc_write_statistics(tmpdir, datadir, nrows, stats_freq):
 @pytest.mark.parametrize("stats_freq", ["STRIPE", "ROWGROUP"])
 @pytest.mark.parametrize("nrows", [2, 100, 6000000])
 def test_orc_chunked_write_statistics(tmpdir, datadir, nrows, stats_freq):
+    np.random.seed(0)
     supported_stat_types = supported_numpy_dtypes + ["str"]
     # Can't write random bool columns until issue #6763 is fixed
     if nrows == 6000000:

python/dask_cudf/setup.py

@@ -9,8 +9,8 @@
 
 install_requires = [
     "cudf",
-    "dask>=2022.7.1",
-    "distributed>=2022.7.1",
+    "dask==2022.9.2",
+    "distributed==2022.9.2",
     "fsspec>=0.6.0",
     "numpy",
     "pandas>=1.0,<1.6.0dev0",