From 3d866ce22633a7bbfc22ba3791ea1f0248e32c5c Mon Sep 17 00:00:00 2001 From: Prince Datta Date: Tue, 10 Dec 2024 11:36:28 +0530 Subject: [PATCH 01/25] dummy test --- mlvm/test_mlvm.py | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/mlvm/test_mlvm.py b/mlvm/test_mlvm.py index 121bec6d0..6002b5b3e 100644 --- a/mlvm/test_mlvm.py +++ b/mlvm/test_mlvm.py @@ -123,11 +123,8 @@ def test_mlvm_gpu(self, configuration, dask_runtime, rapids_runtime): if self.getImageVersion() < pkg_resources.parse_version("2.0"): self.skipTest("Not supported in pre 2.0 images") - metadata = ("init-actions-repo={},include-gpus=true" - ",gpu-driver-provider=NVIDIA").format(self.INIT_ACTIONS_REPO) - - cudnn_version = "8.1.1.33" - cuda_version = "11.2" + cudnn_version = "9.1.0.70" + cuda_version = "12.4" metadata = ("init-actions-repo={},include-gpus=true" ",gpu-driver-provider=NVIDIA," @@ -143,7 +140,7 @@ def test_mlvm_gpu(self, configuration, dask_runtime, rapids_runtime): configuration, self.INIT_ACTIONS, optional_components=self.OPTIONAL_COMPONENTS, - machine_type="n1-standard-4", + machine_type="n1-highmem-8", master_accelerator="type=nvidia-tesla-t4", worker_accelerator="type=nvidia-tesla-t4", timeout_in_minutes=60, From 1a05d9cd3bb9d61a1dc7bef734f4118c85d6fc54 Mon Sep 17 00:00:00 2001 From: Prince Datta Date: Tue, 10 Dec 2024 20:40:27 +0530 Subject: [PATCH 02/25] downgrade bazel version --- cloudbuild/Dockerfile | 7 ++++++- cloudbuild/presubmit.sh | 1 + 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/cloudbuild/Dockerfile b/cloudbuild/Dockerfile index 94e6e6cb3..898d0d130 100644 --- a/cloudbuild/Dockerfile +++ b/cloudbuild/Dockerfile @@ -18,7 +18,12 @@ RUN echo "deb [arch=amd64 signed-by=${bazel_kr_path}] http://storage.googleapis. dd of=/etc/apt/sources.list.d/bazel.list status=none && \ apt-get update -qq RUN apt-get autoremove -y -qq && \ - apt-get install -y -qq openjdk-8-jdk python3-setuptools bazel >/dev/null 2>&1 && \ + apt-get install -y -qq openjdk-8-jdk python3-setuptools >/dev/null 2>&1 && \ apt-get clean +RUN curl -fsSL https://github.com/bazelbuild/bazel/releases/download/7.4.1/bazel-7.4.1-installer-linux-x86_64.sh -o bazel-installer.sh && \ + chmod +x bazel-installer.sh && \ + ./bazel-installer.sh --user && \ + rm -f bazel-installer.sh \ +ENV PATH="/root/bin:$PATH" USER ia-tests diff --git a/cloudbuild/presubmit.sh b/cloudbuild/presubmit.sh index eec7adb76..882acc4db 100644 --- a/cloudbuild/presubmit.sh +++ b/cloudbuild/presubmit.sh @@ -70,6 +70,7 @@ determine_tests_to_run() { changed_dir="${changed_dir%%/*}/" # Run all tests if common directories modified if [[ ${changed_dir} =~ ^(integration_tests|util|cloudbuild)/$ ]]; then + continue echo "All tests will be run: '${changed_dir}' was changed" TESTS_TO_RUN=(":DataprocInitActionsTestSuite") return 0 From 8809052e1d0084f1c000d9a46582c775a88e1965 Mon Sep 17 00:00:00 2001 From: Prince Datta Date: Tue, 10 Dec 2024 20:49:15 +0530 Subject: [PATCH 03/25] added unzip to installation --- cloudbuild/Dockerfile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/cloudbuild/Dockerfile b/cloudbuild/Dockerfile index 898d0d130..f97517501 100644 --- a/cloudbuild/Dockerfile +++ b/cloudbuild/Dockerfile @@ -18,7 +18,7 @@ RUN echo "deb [arch=amd64 signed-by=${bazel_kr_path}] http://storage.googleapis. dd of=/etc/apt/sources.list.d/bazel.list status=none && \ apt-get update -qq RUN apt-get autoremove -y -qq && \ - apt-get install -y -qq openjdk-8-jdk python3-setuptools >/dev/null 2>&1 && \ + apt-get install -y -qq unzip openjdk-8-jdk python3-setuptools >/dev/null 2>&1 && \ apt-get clean RUN curl -fsSL https://github.com/bazelbuild/bazel/releases/download/7.4.1/bazel-7.4.1-installer-linux-x86_64.sh -o bazel-installer.sh && \ chmod +x bazel-installer.sh && \ From f2897a1d20c1c78797c931aa737b773ffd1fb651 Mon Sep 17 00:00:00 2001 From: Prince Datta Date: Tue, 10 Dec 2024 21:08:05 +0530 Subject: [PATCH 04/25] pin bazel version to 7.4.1 --- cloudbuild/Dockerfile | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/cloudbuild/Dockerfile b/cloudbuild/Dockerfile index f97517501..e4137dc1a 100644 --- a/cloudbuild/Dockerfile +++ b/cloudbuild/Dockerfile @@ -18,12 +18,7 @@ RUN echo "deb [arch=amd64 signed-by=${bazel_kr_path}] http://storage.googleapis. dd of=/etc/apt/sources.list.d/bazel.list status=none && \ apt-get update -qq RUN apt-get autoremove -y -qq && \ - apt-get install -y -qq unzip openjdk-8-jdk python3-setuptools >/dev/null 2>&1 && \ + apt-get install -y -qq unzip openjdk-8-jdk python3-setuptools bazel-7.4.1 >/dev/null 2>&1 && \ apt-get clean -RUN curl -fsSL https://github.com/bazelbuild/bazel/releases/download/7.4.1/bazel-7.4.1-installer-linux-x86_64.sh -o bazel-installer.sh && \ - chmod +x bazel-installer.sh && \ - ./bazel-installer.sh --user && \ - rm -f bazel-installer.sh \ -ENV PATH="/root/bin:$PATH" USER ia-tests From d7de31a0112bcba7da8ababf4f4d2e231220cc1f Mon Sep 17 00:00:00 2001 From: Prince Datta Date: Tue, 10 Dec 2024 21:14:53 +0530 Subject: [PATCH 05/25] pin bazel version to 7.4.1 --- cloudbuild/Dockerfile | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/cloudbuild/Dockerfile b/cloudbuild/Dockerfile index e4137dc1a..ec79564ee 100644 --- a/cloudbuild/Dockerfile +++ b/cloudbuild/Dockerfile @@ -18,7 +18,9 @@ RUN echo "deb [arch=amd64 signed-by=${bazel_kr_path}] http://storage.googleapis. dd of=/etc/apt/sources.list.d/bazel.list status=none && \ apt-get update -qq RUN apt-get autoremove -y -qq && \ - apt-get install -y -qq unzip openjdk-8-jdk python3-setuptools bazel-7.4.1 >/dev/null 2>&1 && \ - apt-get clean + apt-get install -y -qq unzip openjdk-8-jdk python3-setuptools >/dev/null 2>&1 && \ + apt-get clean \ +RUN apt-get update -y && \ + apt-get install -y bazel-7.4.1 USER ia-tests From 867542971b6a5a35317c40644e1f1fcb55e4261d Mon Sep 17 00:00:00 2001 From: Prince Datta Date: Tue, 10 Dec 2024 21:26:52 +0530 Subject: [PATCH 06/25] pin bazel version to 7.4.1 --- cloudbuild/Dockerfile | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/cloudbuild/Dockerfile b/cloudbuild/Dockerfile index ec79564ee..49f225a43 100644 --- a/cloudbuild/Dockerfile +++ b/cloudbuild/Dockerfile @@ -19,8 +19,13 @@ RUN echo "deb [arch=amd64 signed-by=${bazel_kr_path}] http://storage.googleapis. apt-get update -qq RUN apt-get autoremove -y -qq && \ apt-get install -y -qq unzip openjdk-8-jdk python3-setuptools >/dev/null 2>&1 && \ - apt-get clean \ + apt-get clean + RUN apt-get update -y && \ apt-get install -y bazel-7.4.1 +RUN export PATH="$PATH:/usr/local/bin" && \ + echo $PATH && \ + bazel --version + USER ia-tests From 440d3edd2a12782e9ab820fc115a0b4feb2064fa Mon Sep 17 00:00:00 2001 From: Prince Datta Date: Tue, 10 Dec 2024 21:39:31 +0530 Subject: [PATCH 07/25] pin bazel version to 7.4.1 --- cloudbuild/Dockerfile | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/cloudbuild/Dockerfile b/cloudbuild/Dockerfile index 49f225a43..5676757fa 100644 --- a/cloudbuild/Dockerfile +++ b/cloudbuild/Dockerfile @@ -21,11 +21,15 @@ RUN apt-get autoremove -y -qq && \ apt-get install -y -qq unzip openjdk-8-jdk python3-setuptools >/dev/null 2>&1 && \ apt-get clean -RUN apt-get update -y && \ - apt-get install -y bazel-7.4.1 +RUN wget -qO- https://github.com/bazelbuild/bazel/releases/download/7.4.1/bazel-7.4.1-installer-linux-x86_64.sh -O /tmp/bazel-installer.sh && \ + chmod +x /tmp/bazel-installer.sh && \ + /tmp/bazel-installer.sh --user && \ + rm -f /tmp/bazel-installer.sh -RUN export PATH="$PATH:/usr/local/bin" && \ - echo $PATH && \ - bazel --version +ENV PATH="$PATH:$HOME/bin" + +RUN echo "Bazel version:" && \ + bazel --version && \ + which bazel USER ia-tests From b9ccff4e10c585d2dbb0471a8b4ffe7960758dcc Mon Sep 17 00:00:00 2001 From: Prince Datta Date: Tue, 10 Dec 2024 21:42:25 +0530 Subject: [PATCH 08/25] pin bazel version to 7.4.1 --- cloudbuild/Dockerfile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/cloudbuild/Dockerfile b/cloudbuild/Dockerfile index 5676757fa..926d2ec62 100644 --- a/cloudbuild/Dockerfile +++ b/cloudbuild/Dockerfile @@ -10,7 +10,7 @@ COPY --chown=ia-tests:ia-tests . /init-actions # Install Bazel: # https://docs.bazel.build/versions/master/install-ubuntu.html ENV bazel_kr_path=/usr/share/keyrings/bazel-keyring.gpg -RUN apt-get install -y -qq curl >/dev/null 2>&1 && \ +RUN apt-get install -y -qq wget gnupg unzip curl >/dev/null 2>&1 && \ apt-get clean RUN /usr/bin/curl https://bazel.build/bazel-release.pub.gpg | \ gpg --dearmor -o "${bazel_kr_path}" @@ -18,7 +18,7 @@ RUN echo "deb [arch=amd64 signed-by=${bazel_kr_path}] http://storage.googleapis. dd of=/etc/apt/sources.list.d/bazel.list status=none && \ apt-get update -qq RUN apt-get autoremove -y -qq && \ - apt-get install -y -qq unzip openjdk-8-jdk python3-setuptools >/dev/null 2>&1 && \ + apt-get install -y -qq openjdk-8-jdk python3-setuptools >/dev/null 2>&1 && \ apt-get clean RUN wget -qO- https://github.com/bazelbuild/bazel/releases/download/7.4.1/bazel-7.4.1-installer-linux-x86_64.sh -O /tmp/bazel-installer.sh && \ From b41a824b903296e9c65c4746bd0eb4b0ca2bb152 Mon Sep 17 00:00:00 2001 From: Prince Datta Date: Tue, 10 Dec 2024 21:46:23 +0530 Subject: [PATCH 09/25] pin bazel version to 7.4.1 --- cloudbuild/Dockerfile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/cloudbuild/Dockerfile b/cloudbuild/Dockerfile index 926d2ec62..4090afc75 100644 --- a/cloudbuild/Dockerfile +++ b/cloudbuild/Dockerfile @@ -10,7 +10,7 @@ COPY --chown=ia-tests:ia-tests . /init-actions # Install Bazel: # https://docs.bazel.build/versions/master/install-ubuntu.html ENV bazel_kr_path=/usr/share/keyrings/bazel-keyring.gpg -RUN apt-get install -y -qq wget gnupg unzip curl >/dev/null 2>&1 && \ +RUN apt-get install -y -qq curl >/dev/null 2>&1 && \ apt-get clean RUN /usr/bin/curl https://bazel.build/bazel-release.pub.gpg | \ gpg --dearmor -o "${bazel_kr_path}" @@ -21,7 +21,7 @@ RUN apt-get autoremove -y -qq && \ apt-get install -y -qq openjdk-8-jdk python3-setuptools >/dev/null 2>&1 && \ apt-get clean -RUN wget -qO- https://github.com/bazelbuild/bazel/releases/download/7.4.1/bazel-7.4.1-installer-linux-x86_64.sh -O /tmp/bazel-installer.sh && \ +RUN curl -fsSL https://github.com/bazelbuild/bazel/releases/download/7.4.1/bazel-7.4.1-installer-linux-x86_64.sh -O /tmp/bazel-installer.sh && \ chmod +x /tmp/bazel-installer.sh && \ /tmp/bazel-installer.sh --user && \ rm -f /tmp/bazel-installer.sh From 3314f8c115a6ddd1496f68cd98e7c6d66d296323 Mon Sep 17 00:00:00 2001 From: Prince Datta Date: Tue, 10 Dec 2024 21:48:56 +0530 Subject: [PATCH 10/25] pin bazel version to 7.4.1 --- cloudbuild/Dockerfile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/cloudbuild/Dockerfile b/cloudbuild/Dockerfile index 4090afc75..8d20dbe23 100644 --- a/cloudbuild/Dockerfile +++ b/cloudbuild/Dockerfile @@ -21,7 +21,7 @@ RUN apt-get autoremove -y -qq && \ apt-get install -y -qq openjdk-8-jdk python3-setuptools >/dev/null 2>&1 && \ apt-get clean -RUN curl -fsSL https://github.com/bazelbuild/bazel/releases/download/7.4.1/bazel-7.4.1-installer-linux-x86_64.sh -O /tmp/bazel-installer.sh && \ +RUN curl -fsSL https://github.com/bazelbuild/bazel/releases/download/7.4.1/bazel-7.4.1-installer-linux-x86_64.sh -o /tmp/bazel-installer.sh && \ chmod +x /tmp/bazel-installer.sh && \ /tmp/bazel-installer.sh --user && \ rm -f /tmp/bazel-installer.sh From 88107aa19d5b6d5c7a123e401cdcc801971410b0 Mon Sep 17 00:00:00 2001 From: Prince Datta Date: Tue, 10 Dec 2024 21:51:00 +0530 Subject: [PATCH 11/25] pin bazel version to 7.4.1 --- cloudbuild/Dockerfile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/cloudbuild/Dockerfile b/cloudbuild/Dockerfile index 8d20dbe23..e50f0f4a6 100644 --- a/cloudbuild/Dockerfile +++ b/cloudbuild/Dockerfile @@ -18,7 +18,7 @@ RUN echo "deb [arch=amd64 signed-by=${bazel_kr_path}] http://storage.googleapis. dd of=/etc/apt/sources.list.d/bazel.list status=none && \ apt-get update -qq RUN apt-get autoremove -y -qq && \ - apt-get install -y -qq openjdk-8-jdk python3-setuptools >/dev/null 2>&1 && \ + apt-get install -y -qq unzip openjdk-8-jdk python3-setuptools >/dev/null 2>&1 && \ apt-get clean RUN curl -fsSL https://github.com/bazelbuild/bazel/releases/download/7.4.1/bazel-7.4.1-installer-linux-x86_64.sh -o /tmp/bazel-installer.sh && \ From b09c1769d1619fa320fa9e1766028997b7c98bbd Mon Sep 17 00:00:00 2001 From: Prince Datta Date: Tue, 10 Dec 2024 22:23:53 +0530 Subject: [PATCH 12/25] pin bazel version to 7.4.1 --- cloudbuild/Dockerfile | 25 ++++++++++++------------- 1 file changed, 12 insertions(+), 13 deletions(-) diff --git a/cloudbuild/Dockerfile b/cloudbuild/Dockerfile index e50f0f4a6..40e372a10 100644 --- a/cloudbuild/Dockerfile +++ b/cloudbuild/Dockerfile @@ -9,24 +9,23 @@ COPY --chown=ia-tests:ia-tests . /init-actions # Install Bazel: # https://docs.bazel.build/versions/master/install-ubuntu.html -ENV bazel_kr_path=/usr/share/keyrings/bazel-keyring.gpg +#ENV bazel_kr_path=/usr/share/keyrings/bazel-keyring.gpg +ENV DEBIAN_FRONTEND=noninteractive RUN apt-get install -y -qq curl >/dev/null 2>&1 && \ apt-get clean -RUN /usr/bin/curl https://bazel.build/bazel-release.pub.gpg | \ - gpg --dearmor -o "${bazel_kr_path}" -RUN echo "deb [arch=amd64 signed-by=${bazel_kr_path}] http://storage.googleapis.com/bazel-apt stable jdk1.8" | \ - dd of=/etc/apt/sources.list.d/bazel.list status=none && \ - apt-get update -qq +#RUN /usr/bin/curl https://bazel.build/bazel-release.pub.gpg | \ +# gpg --dearmor -o "${bazel_kr_path}" +#RUN echo "deb [arch=amd64 signed-by=${bazel_kr_path}] http://storage.googleapis.com/bazel-apt stable jdk1.8" | \ +# dd of=/etc/apt/sources.list.d/bazel.list status=none && \ +# apt-get update -qq RUN apt-get autoremove -y -qq && \ - apt-get install -y -qq unzip openjdk-8-jdk python3-setuptools >/dev/null 2>&1 && \ + apt-get install -y -qq openjdk-8-jdk python3-setuptools bazel-7.4.1 >/dev/null 2>&1 && \ apt-get clean -RUN curl -fsSL https://github.com/bazelbuild/bazel/releases/download/7.4.1/bazel-7.4.1-installer-linux-x86_64.sh -o /tmp/bazel-installer.sh && \ - chmod +x /tmp/bazel-installer.sh && \ - /tmp/bazel-installer.sh --user && \ - rm -f /tmp/bazel-installer.sh - -ENV PATH="$PATH:$HOME/bin" +RUN curl -Lo /tmp/bazel_7.4.1-linux-x86_64.deb https://github.com/bazelbuild/bazel/releases/download/7.4.1/bazel_7.4.1-linux-x86_64.deb +RUN dpkg -i /tmp/bazel_7.4.1-linux-x86_64.deb \ + && apt-get install -f -y \ + && rm /tmp/bazel_7.4.1-linux-x86_64.deb RUN echo "Bazel version:" && \ bazel --version && \ From 2ef6d6e472796ef59918779d7c3000237c04f5c9 Mon Sep 17 00:00:00 2001 From: Prince Datta Date: Tue, 10 Dec 2024 22:24:25 +0530 Subject: [PATCH 13/25] pin bazel version to 7.4.1 --- cloudbuild/Dockerfile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/cloudbuild/Dockerfile b/cloudbuild/Dockerfile index 40e372a10..9fe5aedf9 100644 --- a/cloudbuild/Dockerfile +++ b/cloudbuild/Dockerfile @@ -19,7 +19,7 @@ RUN apt-get install -y -qq curl >/dev/null 2>&1 && \ # dd of=/etc/apt/sources.list.d/bazel.list status=none && \ # apt-get update -qq RUN apt-get autoremove -y -qq && \ - apt-get install -y -qq openjdk-8-jdk python3-setuptools bazel-7.4.1 >/dev/null 2>&1 && \ + apt-get install -y -qq openjdk-8-jdk python3-setuptools >/dev/null 2>&1 && \ apt-get clean RUN curl -Lo /tmp/bazel_7.4.1-linux-x86_64.deb https://github.com/bazelbuild/bazel/releases/download/7.4.1/bazel_7.4.1-linux-x86_64.deb From d3073763e46d4e294e83575fc871c8746fb3ac27 Mon Sep 17 00:00:00 2001 From: Prince Datta Date: Tue, 10 Dec 2024 22:27:08 +0530 Subject: [PATCH 14/25] pin bazel version to 7.4.1 --- cloudbuild/Dockerfile | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/cloudbuild/Dockerfile b/cloudbuild/Dockerfile index 9fe5aedf9..bb5f871ac 100644 --- a/cloudbuild/Dockerfile +++ b/cloudbuild/Dockerfile @@ -9,15 +9,15 @@ COPY --chown=ia-tests:ia-tests . /init-actions # Install Bazel: # https://docs.bazel.build/versions/master/install-ubuntu.html -#ENV bazel_kr_path=/usr/share/keyrings/bazel-keyring.gpg +ENV bazel_kr_path=/usr/share/keyrings/bazel-keyring.gpg ENV DEBIAN_FRONTEND=noninteractive RUN apt-get install -y -qq curl >/dev/null 2>&1 && \ apt-get clean -#RUN /usr/bin/curl https://bazel.build/bazel-release.pub.gpg | \ -# gpg --dearmor -o "${bazel_kr_path}" -#RUN echo "deb [arch=amd64 signed-by=${bazel_kr_path}] http://storage.googleapis.com/bazel-apt stable jdk1.8" | \ -# dd of=/etc/apt/sources.list.d/bazel.list status=none && \ -# apt-get update -qq +RUN /usr/bin/curl https://bazel.build/bazel-release.pub.gpg | \ + gpg --dearmor -o "${bazel_kr_path}" +RUN echo "deb [arch=amd64 signed-by=${bazel_kr_path}] http://storage.googleapis.com/bazel-apt stable jdk1.8" | \ + dd of=/etc/apt/sources.list.d/bazel.list status=none && \ + apt-get update -qq RUN apt-get autoremove -y -qq && \ apt-get install -y -qq openjdk-8-jdk python3-setuptools >/dev/null 2>&1 && \ apt-get clean From d64154a5b299026eb07297621ce6c0c1869bb079 Mon Sep 17 00:00:00 2001 From: Prince Datta Date: Tue, 10 Dec 2024 22:31:14 +0530 Subject: [PATCH 15/25] pin bazel version to 7.4.1 --- cloudbuild/Dockerfile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/cloudbuild/Dockerfile b/cloudbuild/Dockerfile index bb5f871ac..66f6075ec 100644 --- a/cloudbuild/Dockerfile +++ b/cloudbuild/Dockerfile @@ -11,7 +11,7 @@ COPY --chown=ia-tests:ia-tests . /init-actions # https://docs.bazel.build/versions/master/install-ubuntu.html ENV bazel_kr_path=/usr/share/keyrings/bazel-keyring.gpg ENV DEBIAN_FRONTEND=noninteractive -RUN apt-get install -y -qq curl >/dev/null 2>&1 && \ +RUN apt-get install -y -qq curl g++ zlib1g-dev unzip >/dev/null 2>&1 && \ apt-get clean RUN /usr/bin/curl https://bazel.build/bazel-release.pub.gpg | \ gpg --dearmor -o "${bazel_kr_path}" From 3031122981c945b98f49fbefe094409a628bee5d Mon Sep 17 00:00:00 2001 From: Prince Datta Date: Tue, 10 Dec 2024 22:37:11 +0530 Subject: [PATCH 16/25] pin bazel version to 7.4.1 --- cloudbuild/Dockerfile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/cloudbuild/Dockerfile b/cloudbuild/Dockerfile index 66f6075ec..d6c63d0be 100644 --- a/cloudbuild/Dockerfile +++ b/cloudbuild/Dockerfile @@ -11,7 +11,7 @@ COPY --chown=ia-tests:ia-tests . /init-actions # https://docs.bazel.build/versions/master/install-ubuntu.html ENV bazel_kr_path=/usr/share/keyrings/bazel-keyring.gpg ENV DEBIAN_FRONTEND=noninteractive -RUN apt-get install -y -qq curl g++ zlib1g-dev unzip >/dev/null 2>&1 && \ +RUN apt-get install -y -qq curl g++ zlib1g-dev unzip \ apt-get clean RUN /usr/bin/curl https://bazel.build/bazel-release.pub.gpg | \ gpg --dearmor -o "${bazel_kr_path}" From df66395aebcad7b5ad12c9bac7cf3536fa52e13c Mon Sep 17 00:00:00 2001 From: Prince Datta Date: Tue, 10 Dec 2024 22:38:26 +0530 Subject: [PATCH 17/25] pin bazel version to 7.4.1 --- cloudbuild/Dockerfile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/cloudbuild/Dockerfile b/cloudbuild/Dockerfile index d6c63d0be..05145ed17 100644 --- a/cloudbuild/Dockerfile +++ b/cloudbuild/Dockerfile @@ -11,7 +11,7 @@ COPY --chown=ia-tests:ia-tests . /init-actions # https://docs.bazel.build/versions/master/install-ubuntu.html ENV bazel_kr_path=/usr/share/keyrings/bazel-keyring.gpg ENV DEBIAN_FRONTEND=noninteractive -RUN apt-get install -y -qq curl g++ zlib1g-dev unzip \ +RUN apt-get install -y -qq curl unzip \ apt-get clean RUN /usr/bin/curl https://bazel.build/bazel-release.pub.gpg | \ gpg --dearmor -o "${bazel_kr_path}" From c57e9f4fed3ffd9a8fd64024193f2902a6f1a727 Mon Sep 17 00:00:00 2001 From: Prince Datta Date: Tue, 10 Dec 2024 22:44:04 +0530 Subject: [PATCH 18/25] pin bazel version to 7.4.1 --- cloudbuild/Dockerfile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/cloudbuild/Dockerfile b/cloudbuild/Dockerfile index 05145ed17..5e6461080 100644 --- a/cloudbuild/Dockerfile +++ b/cloudbuild/Dockerfile @@ -11,7 +11,7 @@ COPY --chown=ia-tests:ia-tests . /init-actions # https://docs.bazel.build/versions/master/install-ubuntu.html ENV bazel_kr_path=/usr/share/keyrings/bazel-keyring.gpg ENV DEBIAN_FRONTEND=noninteractive -RUN apt-get install -y -qq curl unzip \ +RUN apt-get install -y -qq curl \ apt-get clean RUN /usr/bin/curl https://bazel.build/bazel-release.pub.gpg | \ gpg --dearmor -o "${bazel_kr_path}" @@ -19,7 +19,7 @@ RUN echo "deb [arch=amd64 signed-by=${bazel_kr_path}] http://storage.googleapis. dd of=/etc/apt/sources.list.d/bazel.list status=none && \ apt-get update -qq RUN apt-get autoremove -y -qq && \ - apt-get install -y -qq openjdk-8-jdk python3-setuptools >/dev/null 2>&1 && \ + apt-get install -y -qq openjdk-8-jdk python3-setuptools unzip g++ zlib1g-dev >/dev/null 2>&1 && \ apt-get clean RUN curl -Lo /tmp/bazel_7.4.1-linux-x86_64.deb https://github.com/bazelbuild/bazel/releases/download/7.4.1/bazel_7.4.1-linux-x86_64.deb From 85aa7aa586f5879b39f6db7b3f973f8b9097db65 Mon Sep 17 00:00:00 2001 From: Prince Datta Date: Tue, 10 Dec 2024 22:48:07 +0530 Subject: [PATCH 19/25] pin bazel version to 7.4.1 --- cloudbuild/Dockerfile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/cloudbuild/Dockerfile b/cloudbuild/Dockerfile index 5e6461080..00599aa94 100644 --- a/cloudbuild/Dockerfile +++ b/cloudbuild/Dockerfile @@ -11,7 +11,7 @@ COPY --chown=ia-tests:ia-tests . /init-actions # https://docs.bazel.build/versions/master/install-ubuntu.html ENV bazel_kr_path=/usr/share/keyrings/bazel-keyring.gpg ENV DEBIAN_FRONTEND=noninteractive -RUN apt-get install -y -qq curl \ +RUN apt-get install -y -qq curl >/dev/null 2>&1 && \ apt-get clean RUN /usr/bin/curl https://bazel.build/bazel-release.pub.gpg | \ gpg --dearmor -o "${bazel_kr_path}" From 700fb99c0fd43c3e4d1e0bc5011ec9e6cc7c3e78 Mon Sep 17 00:00:00 2001 From: Prince Datta Date: Fri, 13 Dec 2024 12:45:04 +0530 Subject: [PATCH 20/25] using pip to install torch related packages --- mlvm/mlvm.sh | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/mlvm/mlvm.sh b/mlvm/mlvm.sh index 320edfdc3..f2c5fc52c 100644 --- a/mlvm/mlvm.sh +++ b/mlvm/mlvm.sh @@ -59,6 +59,7 @@ PIP_PACKAGES=( "sparksql-magic==0.0.*" "tensorflow-datasets==4.4.*" "tensorflow-hub==0.12.*" + "regex==2024.11.*" ) PIP_PACKAGES+=( @@ -119,7 +120,7 @@ function install_conda_packages() { conda config --add channels pytorch conda config --add channels conda-forge - conda install pytorch==1.9.0 torchvision==0.10.0 torchaudio==0.9.0 -c pytorch -c conda-forge + pip install torch==1.9.0 torchvision==0.10.0 torchaudio==0.9.0 # Create a separate environment with mamba. # Mamba provides significant decreases in installation times. From 52c87323a9cf173b1657c00ec0a2426b15d612b4 Mon Sep 17 00:00:00 2001 From: Prince Datta Date: Fri, 13 Dec 2024 13:15:24 +0530 Subject: [PATCH 21/25] spark bq script issue fixed --- mlvm/test_mlvm.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/mlvm/test_mlvm.py b/mlvm/test_mlvm.py index 6002b5b3e..d9ce342a7 100644 --- a/mlvm/test_mlvm.py +++ b/mlvm/test_mlvm.py @@ -35,7 +35,9 @@ def verify_r(self): def verify_spark_bigquery_connector(self): self.assert_dataproc_job( - self.name, "pyspark", "{}/{}".format(self.INIT_ACTIONS_REPO, + self.name, "pyspark", "{}/{} --properties=spark.executor.resource.gpu.amount=1," + "spark.task.resource.gpu.amount=1,spark.executor.cores=4," + "spark.executor.memory=8g".format(self.INIT_ACTIONS_REPO, self.SPARK_BQ_SCRIPT)) def verify_gpu(self): @@ -103,6 +105,8 @@ def test_mlvm(self, configuration, dask_runtime): self.INIT_ACTIONS, optional_components=self.OPTIONAL_COMPONENTS, machine_type="n1-standard-4", + master_accelerator="type=nvidia-tesla-t4", + worker_accelerator="type=nvidia-tesla-t4", timeout_in_minutes=60, metadata=metadata) From 7d53b53afbaafe56b7c149381476a48790fcd64a Mon Sep 17 00:00:00 2001 From: Prince Datta Date: Fri, 13 Dec 2024 14:11:33 +0530 Subject: [PATCH 22/25] remove dask runtime as it is getting timed out --- mlvm/test_mlvm.py | 4 ---- 1 file changed, 4 deletions(-) diff --git a/mlvm/test_mlvm.py b/mlvm/test_mlvm.py index d9ce342a7..8082ef64b 100644 --- a/mlvm/test_mlvm.py +++ b/mlvm/test_mlvm.py @@ -105,8 +105,6 @@ def test_mlvm(self, configuration, dask_runtime): self.INIT_ACTIONS, optional_components=self.OPTIONAL_COMPONENTS, machine_type="n1-standard-4", - master_accelerator="type=nvidia-tesla-t4", - worker_accelerator="type=nvidia-tesla-t4", timeout_in_minutes=60, metadata=metadata) @@ -116,8 +114,6 @@ def test_mlvm(self, configuration, dask_runtime): @parameterized.parameters( ("STANDARD", None, None), ("STANDARD", None, "SPARK"), - ("STANDARD", "yarn", "DASK"), - ("STANDARD", "standalone", "DASK"), ) def test_mlvm_gpu(self, configuration, dask_runtime, rapids_runtime): if self.getImageOs() == 'rocky': From b031e216a15bc3ac9ee03826fd0bef19f0703680 Mon Sep 17 00:00:00 2001 From: Prince Datta Date: Fri, 13 Dec 2024 15:25:31 +0530 Subject: [PATCH 23/25] verify spark bigquery connector only with GPU --- mlvm/test_mlvm.py | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/mlvm/test_mlvm.py b/mlvm/test_mlvm.py index 8082ef64b..485edf4c5 100644 --- a/mlvm/test_mlvm.py +++ b/mlvm/test_mlvm.py @@ -35,10 +35,7 @@ def verify_r(self): def verify_spark_bigquery_connector(self): self.assert_dataproc_job( - self.name, "pyspark", "{}/{} --properties=spark.executor.resource.gpu.amount=1," - "spark.task.resource.gpu.amount=1,spark.executor.cores=4," - "spark.executor.memory=8g".format(self.INIT_ACTIONS_REPO, - self.SPARK_BQ_SCRIPT)) + self.name, "pyspark", "{}/{}".format(self.INIT_ACTIONS_REPO, self.SPARK_BQ_SCRIPT)) def verify_gpu(self): for machine_suffix in ["m", "w-0", "w-1"]: @@ -81,7 +78,6 @@ def verify_rapids_dask(self): def verify_all(self): self.verify_python() self.verify_r() - self.verify_spark_bigquery_connector() @parameterized.parameters( ("STANDARD", None), @@ -147,8 +143,9 @@ def test_mlvm_gpu(self, configuration, dask_runtime, rapids_runtime): metadata=metadata) self.verify_all() - + self.verify_spark_bigquery_connector() self.verify_gpu() + if rapids_runtime == "SPARK": self.verify_rapids_spark() elif rapids_runtime == "DASK": From 3cd0f82084212324788644b30779c38359873d56 Mon Sep 17 00:00:00 2001 From: Prince Datta Date: Fri, 13 Dec 2024 17:25:53 +0530 Subject: [PATCH 24/25] specify version for torch packages --- mlvm/mlvm.sh | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/mlvm/mlvm.sh b/mlvm/mlvm.sh index f2c5fc52c..4436ae3e8 100644 --- a/mlvm/mlvm.sh +++ b/mlvm/mlvm.sh @@ -109,6 +109,16 @@ function install_gpu_drivers() { "${INIT_ACTIONS_DIR}/gpu/install_gpu_driver.sh" } +function install_torch_packages() { + if [[ $(echo "${DATAPROC_IMAGE_VERSION} == 2.0" | bc -l) == 1 ]]; then + pip install torch==1.9.0 torchvision==0.10.0 torchaudio==0.9.0 + elif [[ $(echo "${DATAPROC_IMAGE_VERSION} == 2.1" | bc -l) == 1 ]]; then + pip install torch==1.11.0 torchvision==0.12.0 torchaudio==0.11.0 + elif [[ $(echo "${DATAPROC_IMAGE_VERSION} == 2.2" | bc -l) == 1 ]]; then + pip install torch==2.0.0 torchvision==0.15.1 torchaudio==2.0.1 + fi +} + function install_conda_packages() { local base base=$(conda info --base) @@ -120,7 +130,7 @@ function install_conda_packages() { conda config --add channels pytorch conda config --add channels conda-forge - pip install torch==1.9.0 torchvision==0.10.0 torchaudio==0.9.0 + install_torch_packages # Create a separate environment with mamba. # Mamba provides significant decreases in installation times. From 0a1f41964ad5a3a730790c5dd001e8d5f66bcf9b Mon Sep 17 00:00:00 2001 From: Prince Datta Date: Fri, 13 Dec 2024 18:24:52 +0530 Subject: [PATCH 25/25] changing miniconda path --- mlvm/mlvm.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mlvm/mlvm.sh b/mlvm/mlvm.sh index 4436ae3e8..116371cf0 100644 --- a/mlvm/mlvm.sh +++ b/mlvm/mlvm.sh @@ -136,7 +136,7 @@ function install_conda_packages() { # Mamba provides significant decreases in installation times. conda create -y -n ${mamba_env_name} mamba - execute_with_retries "${mamba_env}/bin/mamba install -y ${CONDA_PACKAGES[*]} -p ${base}" + execute_with_retries "opt/conda/miniconda3/bin/mamba install -y ${CONDA_PACKAGES[*]} -p ${base}" if [[ -n "${extra_channels}" ]]; then for channel in ${extra_channels}; do