From a6f69968e446d6fc1fa3e0e4d07733d2e0a667e0 Mon Sep 17 00:00:00 2001 From: Zhanghao Wu Date: Tue, 21 May 2024 21:47:19 +0000 Subject: [PATCH] add system site-packages --- sky/skylet/constants.py | 2 +- tests/kubernetes/README.md | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/sky/skylet/constants.py b/sky/skylet/constants.py index 467cff4c432..1b1636907b3 100644 --- a/sky/skylet/constants.py +++ b/sky/skylet/constants.py @@ -105,7 +105,7 @@ '{ conda init && source ~/.bashrc; };' # Create a separate conda environment for SkyPilot dependencies. f'[ -d {SKY_REMOTE_PYTHON_ENV} ] || ' - f'{{ {SKY_PYTHON_CMD} -m venv {SKY_REMOTE_PYTHON_ENV} && ' + f'{{ {SKY_PYTHON_CMD} -m venv {SKY_REMOTE_PYTHON_ENV} --system-site-packages && ' f'echo $(echo {SKY_REMOTE_PYTHON_ENV})/bin/python > {SKY_PYTHON_PATH_FILE}; }};' ) diff --git a/tests/kubernetes/README.md b/tests/kubernetes/README.md index 4a882352703..655daf55b55 100644 --- a/tests/kubernetes/README.md +++ b/tests/kubernetes/README.md @@ -32,13 +32,13 @@ sky local up ```bash PROJECT_ID=$(gcloud config get-value project) CLUSTER_NAME=testclusterromil - gcloud beta container --project "${PROJECT_ID}" clusters create "${CLUSTER_NAME}" --zone "us-central1-c" --no-enable-basic-auth --cluster-version "1.29.0-gke.1381000" --release-channel "regular" --machine-type "n1-standard-8" --accelerator "type=nvidia-tesla-t4,count=1" --image-type "COS_CONTAINERD" --disk-type "pd-balanced" --disk-size "100" --metadata disable-legacy-endpoints=true --scopes "https://www.googleapis.com/auth/devstorage.read_only","https://www.googleapis.com/auth/logging.write","https://www.googleapis.com/auth/monitoring","https://www.googleapis.com/auth/servicecontrol","https://www.googleapis.com/auth/service.management.readonly","https://www.googleapis.com/auth/trace.append" --num-nodes "2" --logging=SYSTEM,WORKLOAD --monitoring=SYSTEM --enable-ip-alias --network "projects/${PROJECT_ID}/global/networks/default" --subnetwork "projects/${PROJECT_ID}/regions/us-central1/subnetworks/default" --no-enable-intra-node-visibility --default-max-pods-per-node "110" --security-posture=standard --workload-vulnerability-scanning=disabled --no-enable-master-authorized-networks --addons HorizontalPodAutoscaling,HttpLoadBalancing,GcePersistentDiskCsiDriver --enable-autoupgrade --enable-autorepair --max-surge-upgrade 1 --max-unavailable-upgrade 0 --enable-managed-prometheus --enable-shielded-nodes --node-locations "us-central1-c" && gcloud beta container --project "${PROJECT_ID}" node-pools create "v100" --cluster "${CLUSTER_NAME}" --zone "us-central1-c" --machine-type "n1-standard-8" --accelerator "type=nvidia-tesla-v100,count=1" --image-type "COS_CONTAINERD" --disk-type "pd-balanced" --disk-size "100" --metadata disable-legacy-endpoints=true --scopes "https://www.googleapis.com/auth/devstorage.read_only","https://www.googleapis.com/auth/logging.write","https://www.googleapis.com/auth/monitoring","https://www.googleapis.com/auth/servicecontrol","https://www.googleapis.com/auth/service.management.readonly","https://www.googleapis.com/auth/trace.append" --num-nodes "2" --enable-autoupgrade --enable-autorepair --max-surge-upgrade 1 --max-unavailable-upgrade 0 --node-locations "us-central1-c" && gcloud beta container --project "${PROJECT_ID}" node-pools create "largecpu" --cluster "${CLUSTER_NAME}" --zone "us-central1-c" --machine-type "n1-standard-16" --image-type "COS_CONTAINERD" --disk-type "pd-balanced" --disk-size "100" --metadata disable-legacy-endpoints=true --scopes "https://www.googleapis.com/auth/devstorage.read_only","https://www.googleapis.com/auth/logging.write","https://www.googleapis.com/auth/monitoring","https://www.googleapis.com/auth/servicecontrol","https://www.googleapis.com/auth/service.management.readonly","https://www.googleapis.com/auth/trace.append" --num-nodes "2" --enable-autoupgrade --enable-autorepair --max-surge-upgrade 1 --max-unavailable-upgrade 0 --node-locations "us-central1-c" + gcloud beta container --project "${PROJECT_ID}" clusters create "${CLUSTER_NAME}" --zone "us-central1-c" --no-enable-basic-auth --cluster-version "1.29.1-gke.1589020" --release-channel "regular" --machine-type "n1-standard-8" --accelerator "type=nvidia-tesla-t4,count=1" --image-type "COS_CONTAINERD" --disk-type "pd-balanced" --disk-size "100" --metadata disable-legacy-endpoints=true --scopes "https://www.googleapis.com/auth/devstorage.read_only","https://www.googleapis.com/auth/logging.write","https://www.googleapis.com/auth/monitoring","https://www.googleapis.com/auth/servicecontrol","https://www.googleapis.com/auth/service.management.readonly","https://www.googleapis.com/auth/trace.append" --num-nodes "2" --logging=SYSTEM,WORKLOAD --monitoring=SYSTEM --enable-ip-alias --network "projects/${PROJECT_ID}/global/networks/default" --subnetwork "projects/${PROJECT_ID}/regions/us-central1/subnetworks/default" --no-enable-intra-node-visibility --default-max-pods-per-node "110" --security-posture=standard --workload-vulnerability-scanning=disabled --no-enable-master-authorized-networks --addons HorizontalPodAutoscaling,HttpLoadBalancing,GcePersistentDiskCsiDriver --enable-autoupgrade --enable-autorepair --max-surge-upgrade 1 --max-unavailable-upgrade 0 --enable-managed-prometheus --enable-shielded-nodes --node-locations "us-central1-c" && gcloud beta container --project "${PROJECT_ID}" node-pools create "v100" --cluster "${CLUSTER_NAME}" --zone "us-central1-c" --machine-type "n1-standard-8" --accelerator "type=nvidia-tesla-v100,count=1" --image-type "COS_CONTAINERD" --disk-type "pd-balanced" --disk-size "100" --metadata disable-legacy-endpoints=true --scopes "https://www.googleapis.com/auth/devstorage.read_only","https://www.googleapis.com/auth/logging.write","https://www.googleapis.com/auth/monitoring","https://www.googleapis.com/auth/servicecontrol","https://www.googleapis.com/auth/service.management.readonly","https://www.googleapis.com/auth/trace.append" --num-nodes "2" --enable-autoupgrade --enable-autorepair --max-surge-upgrade 1 --max-unavailable-upgrade 0 --node-locations "us-central1-c" && gcloud beta container --project "${PROJECT_ID}" node-pools create "largecpu" --cluster "${CLUSTER_NAME}" --zone "us-central1-c" --machine-type "n1-standard-16" --image-type "COS_CONTAINERD" --disk-type "pd-balanced" --disk-size "100" --metadata disable-legacy-endpoints=true --scopes "https://www.googleapis.com/auth/devstorage.read_only","https://www.googleapis.com/auth/logging.write","https://www.googleapis.com/auth/monitoring","https://www.googleapis.com/auth/servicecontrol","https://www.googleapis.com/auth/service.management.readonly","https://www.googleapis.com/auth/trace.append" --num-nodes "2" --enable-autoupgrade --enable-autorepair --max-surge-upgrade 1 --max-unavailable-upgrade 0 --node-locations "us-central1-c" ``` 2. Get the kubeconfig for your cluster and place it in `~/.kube/config`: ```bash gcloud container clusters get-credentials --region # Example: - # gcloud container clusters get-credentials testcluster --region us-central1-c + # gcloud container clusters get-credentials $CLUSTER_NAME --region us-central1-c ``` 3. Verify by running `kubectl get nodes`. You should see your nodes. 4. **If you want GPU support**, make sure you install GPU drivers by running: