Add Aerial platform into CI

- create XML files for the Aerial pipeline - create docker-compose to automate deployment - add documentation - add to main Jenkinsfile Signed-off-by: Raphael Defosseux <raphael.defosseux@eurecom.fr> Co-authored-by: Jaroslava Fiedlerova <jaroslava.fiedlerova@openairinterface.org> Co-authored-by: Rúben Soares da Silva <rsilva@allbesmart.pt>
2024-03-08 16:15:18 +01:00
parent 4b3ea3f469
commit 1fadd7adb6
12 changed files with 703 additions and 17 deletions
@@ -0,0 +1,37 @@
+#!/bin/bash
+
+# Check if cuBB_SDK is defined, if not, use default path
+cuBB_Path="${cuBB_SDK:-/opt/nvidia/cuBB}"
+
+# Run gdrcopy insmod
+cd "$cuBB_Path"/cuPHY-CP/external/gdrcopy/ || exit 1
+
+./insmod.sh
+cd "$cuBB_Path" || exit 1
+# Add gdrcopy to LD_LIBRARY_PATH
+export LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/opt/mellanox/dpdk/lib/x86_64-linux-gnu:/opt/mellanox/doca/lib/x86_64-linux-gnu:/opt/nvidia/cuBB/cuPHY-CP/external/gdrcopy/build/x86_64/
+
+# Restart MPS
+# Export variables
+export CUDA_DEVICE_MAX_CONNECTIONS=8
+export CUDA_MPS_PIPE_DIRECTORY=/var
+export CUDA_MPS_LOG_DIRECTORY=/var
+
+# Stop existing MPS
+echo quit | nvidia-cuda-mps-control
+
+# Start MPS
+nvidia-cuda-mps-control -d
+echo start_server -uid 0 | nvidia-cuda-mps-control
+
+# Start cuphycontroller_scf
+# Check if an argument is provided
+if [ $# -eq 0 ]; then
+    # No argument provided, use default value
+    argument="P5G_SCF_FXN"
+else
+    # Argument provided, use it
+    argument="$1"
+fi
+
+"$cuBB_Path"/build/cuPHY-CP/cuphycontroller/examples/cuphycontroller_scf "$argument"
@@ -0,0 +1,65 @@
+version: "3.8"
+services:
+  nv-cubb:
+    container_name: nv-cubb
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities:
+                - gpu
+    network_mode: host
+    shm_size: 4096m
+    privileged: true
+    stdin_open: true
+    tty: true
+    volumes:
+      - /lib/modules:/lib/modules
+      - /dev/hugepages:/dev/hugepages
+      - /usr/src:/usr/src
+      - ./aerial_l1_entrypoint.sh:/opt/nvidia/cuBB/aerial_l1_entrypoint.sh
+      - /var/log/aerial:/var/log/aerial
+      - ../../../cmake_targets/share:/opt/cuBB/share
+    userns_mode: host
+    ipc: "shareable"
+    image: cubb-build:23-2
+    environment:
+      - cuBB_SDK=/opt/nvidia/cuBB
+    command: bash -c " rm -rf /tmp/phy.log && chmod +x /opt/nvidia/cuBB/aerial_l1_entrypoint.sh && /opt/nvidia/cuBB/aerial_l1_entrypoint.sh"
+    healthcheck:
+      test: ["CMD-SHELL",'grep -q "L1 is ready!" /tmp/phy.log && echo 0 || echo 1']
+      interval: 20s
+      timeout: 5s
+      retries: 5
+  oai-gnb-aerial:
+    cpuset: "13-20"
+    image: oai-gnb-aerial:latest
+    depends_on:
+      nv-cubb:
+        condition: service_healthy
+    privileged: true
+    ipc: "container:nv-cubb"
+    environment:
+      USE_ADDITIONAL_OPTIONS: --log_config.global_log_options level,nocolor,time
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities:
+                - gpu
+    network_mode: host
+    shm_size: 4096m
+    stdin_open: true
+    tty: true
+    volumes:
+      - ../../conf_files/gnb-vnf.sa.band78.273prb.aerial.conf:/opt/oai-gnb/etc/gnb.conf
+    container_name: oai-gnb-aerial
+    healthcheck:
+      test: /bin/bash -c "ps aux | grep -v grep | grep -c softmodem"
+      interval: 10s
+      timeout: 5s
+      retries: 5