Skip to content

Add Pathways health check to run_pathways_tests.yml #4697

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
SurbhiJainUSC wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

Add Pathways health check to run_pathways_tests.yml #4697

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 16 additions & 3 deletions .github/workflows/run_pathways_tests.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -104,6 +104,19 @@ jobs:
python3 -m pip freeze
- name: Copy test assets files
run : gcloud storage cp gs://maxtext-test-assets/* tests/assets
- name: Wait for Pathways Proxy Readiness
shell: bash
run: |
echo "Waiting for Pathways Proxy at localhost:29000..."
for i in {1..30}; do
if python3 -c "import socket; socket.create_connection(('localhost', 29000), timeout=1)" 2>/dev/null; then
echo "Pathways Proxy port is open and listening!"
sleep 2 # Allow gRPC server to complete internal handshakes
exit 0
fi
sleep 2
done
echo "ERROR: Pathways Proxy failed to start within 60s" && exit 1
- name: Run Tests
env:
TOTAL_WORKERS: ${{ inputs.total_workers }}
Expand Down Expand Up @@ -141,7 +154,7 @@ jobs:
- "29001:29001"
- "29002:29002"
options:
--entrypoint=[/usr/pathways/run/cloud_pathways_server_sanitized, --server_port=29001, --node_type=resource_manager, --enforce_kernel_ipv6_support=false, --instance_count=1, --instance_type=tpuv6e:2x2, --gcs_scratch_location=gs://cloud-pathways-staging/tmp]
--entrypoint=[/usr/pathways/run/cloud_pathways_server_sanitized, --server_port=29001, --node_type=resource_manager, --enforce_kernel_ipv6_support=false, --instance_count=1, --instance_type=tpuv6e:2x2, --gcs_scratch_location=gs://cloud-pathways-staging/maxtext-ci/${{ github.run_id }}_${{ github.run_attempt }}_${{ inputs.worker_group }}]
env:
TPU_SKIP_MDS_QUERY: true

Expand All @@ -153,7 +166,7 @@ jobs:
- "8471:8471"
- "8080:8080"
options:
--entrypoint=[/usr/pathways/run/cloud_pathways_server_sanitized, --server_port=29005, --resource_manager_address=localhost:29001, --enforce_kernel_ipv6_support=false, --gcs_scratch_location=gs://cloud-pathways-staging/tmp]
--entrypoint=[/usr/pathways/run/cloud_pathways_server_sanitized, --server_port=29005, --resource_manager_address=localhost:29001, --enforce_kernel_ipv6_support=false, --gcs_scratch_location=gs://cloud-pathways-staging/maxtext-ci/${{ github.run_id }}_${{ github.run_attempt }}_${{ inputs.worker_group }}]
--tpu=4

proxy:
Expand All @@ -164,4 +177,4 @@ jobs:
IFRT_PROXY_USE_INSECURE_GRPC_CREDENTIALS: true
XLA_FLAGS: "--xla_dump_to=/tmp/aot_test_dump --xla_dump_hlo_as_text --xla_dump_hlo_module_re=jit_train_step"
options:
--entrypoint=[/usr/pathways/run/cloud_proxy_server_sanitized, --server_port=29000, --resource_manager_address=localhost:29001, --enforce_kernel_ipv6_support=false, --gcs_scratch_location=gs://cloud-pathways-staging/tmp, --xla_tpu_scoped_vmem_limit_kib=65536, --xla_tpu_spmd_rng_bit_generator_unsafe=true]
--entrypoint=[/usr/pathways/run/cloud_proxy_server_sanitized, --server_port=29000, --resource_manager_address=localhost:29001, --enforce_kernel_ipv6_support=false, --gcs_scratch_location=gs://cloud-pathways-staging/maxtext-ci/${{ github.run_id }}_${{ github.run_attempt }}_${{ inputs.worker_group }}, --xla_tpu_scoped_vmem_limit_kib=65536, --xla_tpu_spmd_rng_bit_generator_unsafe=true]
Loading