# Copyright 2024 Google Inc. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. apiVersion: v1 kind: Service metadata: name: nccl-host-1 spec: selector: name: nccl-host-1 clusterIP: None --- apiVersion: v1 kind: Service metadata: name: nccl-host-2 spec: selector: name: nccl-host-2 clusterIP: None --- apiVersion: v1 kind: Pod metadata: name: nccl-test-host-1 labels: name: nccl-host-1 annotations: networking.gke.io/default-interface: 'eth0' networking.gke.io/interfaces: | [ {"interfaceName":"eth0","network":"default"}, {"interfaceName":"eth1","network":"vpc1"}, {"interfaceName":"eth2","network":"vpc2"}, {"interfaceName":"eth3","network":"vpc3"}, {"interfaceName":"eth4","network":"vpc4"} ] devices.gke.io/container.tcpx-daemon: |+ - path: /dev/nvidia0 - path: /dev/nvidia1 - path: /dev/nvidia2 - path: /dev/nvidia3 - path: /dev/nvidia4 - path: /dev/nvidia5 - path: /dev/nvidia6 - path: /dev/nvidia7 - path: /dev/nvidiactl - path: /dev/nvidia-uvm spec: containers: - name: tcpx-daemon image: us-docker.pkg.dev/gce-ai-infra/gpudirect-tcpx/tcpgpudmarxd-dev:v2.0.12 imagePullPolicy: Always command: - /tcpgpudmarxd/build/app/tcpgpudmarxd - --gpu_nic_preset - a3vm - --gpu_shmem_type - fd - --uds_path - /run/tcpx - --setup_param - \"--verbose 128 2 0 \" securityContext: capabilities: add: - NET_ADMIN volumeMounts: - name: libraries mountPath: /usr/local/nvidia/lib64 - name: tcpx-socket mountPath: /run/tcpx - name: sys mountPath: /hostsysfs - name: proc mountPath: /hostprocsysfs env: - name: LD_LIBRARY_PATH value: /usr/local/nvidia/lib64 - name: nccl-test image: us-docker.pkg.dev/gce-ai-infra/gpudirect-tcpx/nccl-plugin-gpudirecttcpx-dev:v3.1.9 imagePullPolicy: Always command: - /bin/sh - -c - | service ssh restart; sleep infinity; env: - name: LD_LIBRARY_PATH value: /usr/local/nvidia/lib64 securityContext: capabilities: add: - IPC_LOCK volumeMounts: - name: tcpx-socket mountPath: /tmp - name: libraries mountPath: /usr/local/nvidia/lib64 - name: config-volume mountPath: /configs resources: limits: nvidia.com/gpu: 8 volumes: - name: config-volume configMap: name: nccl-configmap defaultMode: 0777 - name: libraries hostPath: path: /home/kubernetes/bin/nvidia/lib64 - name: tcpx-socket hostPath: path: /run/tcpx - name: sys hostPath: path: /sys - name: proc hostPath: path: /proc/sys --- apiVersion: v1 kind: Pod metadata: name: nccl-test-host-2 labels: name: nccl-host-2 annotations: networking.gke.io/default-interface: 'eth0' networking.gke.io/interfaces: | [ {"interfaceName":"eth0","network":"default"}, {"interfaceName":"eth1","network":"vpc1"}, {"interfaceName":"eth2","network":"vpc2"}, {"interfaceName":"eth3","network":"vpc3"}, {"interfaceName":"eth4","network":"vpc4"} ] devices.gke.io/container.tcpx-daemon: |+ - path: /dev/nvidia0 - path: /dev/nvidia1 - path: /dev/nvidia2 - path: /dev/nvidia3 - path: /dev/nvidia4 - path: /dev/nvidia5 - path: /dev/nvidia6 - path: /dev/nvidia7 - path: /dev/nvidiactl - path: /dev/nvidia-uvm spec: containers: - name: tcpx-daemon image: us-docker.pkg.dev/gce-ai-infra/gpudirect-tcpx/tcpgpudmarxd-dev:v2.0.12 imagePullPolicy: Always command: - /tcpgpudmarxd/build/app/tcpgpudmarxd - --gpu_nic_preset - a3vm - --gpu_shmem_type - fd - --uds_path - /run/tcpx - --setup_param - \"--verbose 128 2 0 \" securityContext: capabilities: add: - NET_ADMIN volumeMounts: - name: libraries mountPath: /usr/local/nvidia/lib64 - name: tcpx-socket mountPath: /run/tcpx - name: sys mountPath: /hostsysfs - name: proc-sys mountPath: /hostprocsysfs env: - name: LD_LIBRARY_PATH value: /usr/local/nvidia/lib64 - name: nccl-test image: us-docker.pkg.dev/gce-ai-infra/gpudirect-tcpx/nccl-plugin-gpudirecttcpx-dev:v3.1.9 imagePullPolicy: Always command: - /bin/sh - -c - | service ssh restart; sleep infinity; env: - name: LD_LIBRARY_PATH value: /usr/local/nvidia/lib64 securityContext: capabilities: add: - IPC_LOCK volumeMounts: - name: tcpx-socket mountPath: /tmp - name: libraries mountPath: /usr/local/nvidia/lib64 - name: config-volume mountPath: /configs resources: limits: nvidia.com/gpu: 8 volumes: - name: config-volume configMap: name: nccl-configmap defaultMode: 0777 - name: libraries hostPath: path: /home/kubernetes/bin/nvidia/lib64 - name: tcpx-socket hostPath: path: /run/tcpx - name: sys hostPath: path: /sys - name: proc-sys hostPath: path: /proc/sys