diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/playbook.yaml b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/playbook.yaml index b5c4f88..060f7c1 100644 --- a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/playbook.yaml +++ b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/playbook.yaml @@ -7,11 +7,10 @@ # 보고 mc-o11y-manager가 "linux" / "windows" 둘 중 하나로 채움. # default "linux" 로 두는 이유: 옛 호출자(직접 Semaphore template 호출 등)에 대한 호환 + Telegraf/FluentBit/Beyla 기존 케이스. os_type: "{{ os_type | default('linux') }}" - # enable_gpu: NVIDIA GPU 노드에서 DCGM Exporter를 함께 설치/제거할지 여부. - # telegraf 에이전트 설치 시에만 의미가 있으며, telegraf의 prometheus input이 - # localhost:9400(DCGM Exporter)을 스크랩해 GPU 메트릭을 수집한다. + # enable_gpu: telegraf config에 GPU 수집(nvidia_smi input)을 넣을지 여부. + # 노드에 설치할 것은 없다 - nvidia-smi는 NVIDIA 드라이버에 동봉되므로, + # 이 값은 mc-o11y-manager가 config를 조립할 때만 쓰인다. enable_gpu: "{{ enable_gpu | default(false) }}" - NVIDIA_CONTAINER_TOOLKIT_VERSION: "1.19.0-1" tasks: - name: Check variables include_role: @@ -41,13 +40,6 @@ no_log: true when: os_type == 'windows' - # DCGM Exporter (GPU 메트릭): Linux + telegraf + enable_gpu 인 경우에만 수행. - # (o11y-infra dcgm role 포팅 — podman으로 dcgm-exporter 컨테이너 구동, 포트 9400) - - name: DCGM Exporter Operation - include_role: - name: dcgm - when: os_type == 'linux' and agent == 'telegraf' and (enable_gpu | bool) - - name: Agent Operation (Linux) include_role: name: agent diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent-windows/agent-install-files/amd64/telegraf/bin/cmp-telegraf.exe.tar.gz_00 b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent-windows/agent-install-files/amd64/telegraf/bin/cmp-telegraf.exe.tar.gz_00 index a11167a..d3aa2ea 100644 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent-windows/agent-install-files/amd64/telegraf/bin/cmp-telegraf.exe.tar.gz_00 and b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent-windows/agent-install-files/amd64/telegraf/bin/cmp-telegraf.exe.tar.gz_00 differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent-windows/agent-install-files/amd64/telegraf/bin/cmp-telegraf.exe.tar.gz_01 b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent-windows/agent-install-files/amd64/telegraf/bin/cmp-telegraf.exe.tar.gz_01 deleted file mode 100644 index 96de4d7..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent-windows/agent-install-files/amd64/telegraf/bin/cmp-telegraf.exe.tar.gz_01 and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent-windows/agent-install-files/amd64/telegraf/bin/cmp-telegraf.exe.tar.gz_02 b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent-windows/agent-install-files/amd64/telegraf/bin/cmp-telegraf.exe.tar.gz_02 deleted file mode 100644 index 1338c31..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent-windows/agent-install-files/amd64/telegraf/bin/cmp-telegraf.exe.tar.gz_02 and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent/agent-install-files/amd64/telegraf/bin/cmp-telegraf.tar.gz_00 b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent/agent-install-files/amd64/telegraf/bin/cmp-telegraf.tar.gz_00 index 48cac6e..fa05699 100644 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent/agent-install-files/amd64/telegraf/bin/cmp-telegraf.tar.gz_00 and b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent/agent-install-files/amd64/telegraf/bin/cmp-telegraf.tar.gz_00 differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent/agent-install-files/amd64/telegraf/bin/cmp-telegraf.tar.gz_01 b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent/agent-install-files/amd64/telegraf/bin/cmp-telegraf.tar.gz_01 index 5a2a9a4..e50f683 100644 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent/agent-install-files/amd64/telegraf/bin/cmp-telegraf.tar.gz_01 and b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent/agent-install-files/amd64/telegraf/bin/cmp-telegraf.tar.gz_01 differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent/agent-install-files/amd64/telegraf/bin/cmp-telegraf.tar.gz_02 b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent/agent-install-files/amd64/telegraf/bin/cmp-telegraf.tar.gz_02 deleted file mode 100644 index bddff3f..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent/agent-install-files/amd64/telegraf/bin/cmp-telegraf.tar.gz_02 and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent/agent-install-files/arm64/telegraf/bin/cmp-telegraf.tar.gz_00 b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent/agent-install-files/arm64/telegraf/bin/cmp-telegraf.tar.gz_00 index 4630152..c25a43d 100644 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent/agent-install-files/arm64/telegraf/bin/cmp-telegraf.tar.gz_00 and b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent/agent-install-files/arm64/telegraf/bin/cmp-telegraf.tar.gz_00 differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent/agent-install-files/arm64/telegraf/bin/cmp-telegraf.tar.gz_01 b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent/agent-install-files/arm64/telegraf/bin/cmp-telegraf.tar.gz_01 index 257641f..0e4c7ad 100644 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent/agent-install-files/arm64/telegraf/bin/cmp-telegraf.tar.gz_01 and b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent/agent-install-files/arm64/telegraf/bin/cmp-telegraf.tar.gz_01 differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent/agent-install-files/arm64/telegraf/bin/cmp-telegraf.tar.gz_02 b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent/agent-install-files/arm64/telegraf/bin/cmp-telegraf.tar.gz_02 deleted file mode 100644 index 2a03845..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/agent/agent-install-files/arm64/telegraf/bin/cmp-telegraf.tar.gz_02 and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/cmp-dcgm-exporter.service b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/cmp-dcgm-exporter.service deleted file mode 100644 index 0a632fa..0000000 --- a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/cmp-dcgm-exporter.service +++ /dev/null @@ -1,41 +0,0 @@ -[Unit] -Description=CMP DCGM Exporter Service -Wants=network-online.target -After=network-online.target -RequiresMountsFor=%t/containers - -[Service] -Type=notify -NotifyAccess=all -User=root - - -Environment=TIME_DIFF_SECONDS=0 -Environment=PODMAN_SYSTEMD_UNIT=%n - -ExecStart=/cmp-agent/common/podman/bin/run-podman run \ - --pid=host \ - --cgroups=no-conmon \ - --env TIME_DIFF_SECONDS \ - --env HOSTNAME=%H \ - --sdnotify=conmon \ - --replace \ - -d \ - --restart=always \ - --tz=Asia/Seoul \ - --network=host \ - --device=nvidia.com/gpu=all \ - --name cmp-dcgm \ - -p 9400:9400 \ - --mount type=bind,src=/cmp-agent/dcgm-exporter-custom.csv,dst=/cmp-agent/dcgm-exporter-custom.csv,ro=true \ - nvcr.io/nvidia/k8s/dcgm-exporter:4.4.2-4.7.0-ubuntu22.04 \ - -f /cmp-agent/dcgm-exporter-custom.csv - -ExecStop=/cmp-agent/common/podman/bin/run-podman stop cmp-dcgm - -Restart=on-failure -RestartPreventExitStatus=100 -TimeoutStopSec=30 - -[Install] -WantedBy=multi-user.target diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/dcgm-exporter-custom.csv b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/dcgm-exporter-custom.csv deleted file mode 100644 index 0a0bb67..0000000 --- a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/dcgm-exporter-custom.csv +++ /dev/null @@ -1,92 +0,0 @@ -# Format -# If line starts with a '#' it is considered a comment -# DCGM FIELD, Prometheus metric type, help message - -# Clocks -DCGM_FI_DEV_SM_CLOCK, gauge, SM clock frequency (in MHz). -DCGM_FI_DEV_MEM_CLOCK, gauge, Memory clock frequency (in MHz). -# DCGM_EXP_CLOCK_EVENTS_COUNT, gauge, Count of clock events within the user-specified time window (see clock-events-count-window-size param). - -# Temperature -DCGM_FI_DEV_MEMORY_TEMP, gauge, Memory temperature (in C). -DCGM_FI_DEV_GPU_TEMP, gauge, GPU temperature (in C). -DCGM_FI_DEV_FAN_SPEED, gauge, Fan speed for the device in percent(in %). - -# Power -DCGM_FI_DEV_POWER_USAGE, gauge, Power draw (in W). -DCGM_FI_DEV_TOTAL_ENERGY_CONSUMPTION, counter, Total energy consumption since boot (in mJ). -DCGM_FI_DEV_PSTATE, gauge, Performance state. - -# PCIE -DCGM_FI_DEV_PCIE_TX_THROUGHPUT, counter, Total number of bytes transmitted through PCIe TX (in KB) via NVML. -DCGM_FI_DEV_PCIE_RX_THROUGHPUT, counter, Total number of bytes received through PCIe RX (in KB) via NVML. -DCGM_FI_DEV_PCIE_REPLAY_COUNTER, counter, Total number of PCIe retries. - -# Utilization (the sample period varies depending on the product) -DCGM_FI_DEV_GPU_UTIL, gauge, GPU utilization (in %). -DCGM_FI_DEV_MEM_COPY_UTIL, gauge, Memory utilization (in %). -DCGM_FI_DEV_ENC_UTIL, gauge, Encoder utilization (in %). -DCGM_FI_DEV_DEC_UTIL , gauge, Decoder utilization (in %). - -# Errors and violations -DCGM_FI_DEV_XID_ERRORS, gauge, Value of the last XID error encountered. -DCGM_FI_DEV_CLOCKS_EVENT_REASONS, gauge, Clock throttle reasons -DCGM_EXP_XID_ERRORS_COUNT, gauge, Count of XID Errors within user-specified time window (see xid-count-window-size param). - -# DCGM_FI_DEV_POWER_VIOLATION, counter, Throttling duration due to power constraints (in us). -# DCGM_FI_DEV_THERMAL_VIOLATION, counter, Throttling duration due to thermal constraints (in us). -# DCGM_FI_DEV_SYNC_BOOST_VIOLATION, counter, Throttling duration due to sync-boost constraints (in us). -# DCGM_FI_DEV_BOARD_LIMIT_VIOLATION, counter, Throttling duration due to board limit constraints (in us). -# DCGM_FI_DEV_LOW_UTIL_VIOLATION, counter, Throttling duration due to low utilization (in us). -# DCGM_FI_DEV_RELIABILITY_VIOLATION, counter, Throttling duration due to reliability constraints (in us). - -# Memory usage -DCGM_FI_DEV_FB_FREE, gauge, Frame buffer memory free (in MB). -DCGM_FI_DEV_FB_USED, gauge, Frame buffer memory used (in MB). -DCGM_FI_DEV_FB_TOTAL, gauge, Frame buffer memory (in MB). - -# ECC (Datacenter GPU only, A100, H100, V100, T4) -DCGM_FI_DEV_ECC_SBE_VOL_TOTAL, counter, Total number of single-bit volatile ECC errors. -DCGM_FI_DEV_ECC_DBE_VOL_TOTAL, counter, Total number of double-bit volatile ECC errors. -DCGM_FI_DEV_ECC_SBE_AGG_TOTAL, counter, Total number of single-bit persistent ECC errors. -DCGM_FI_DEV_ECC_DBE_AGG_TOTAL, counter, Total number of double-bit persistent ECC errors. - -# Retired pages -# DCGM_FI_DEV_RETIRED_SBE, counter, Total number of retired pages due to single-bit errors. -# DCGM_FI_DEV_RETIRED_DBE, counter, Total number of retired pages due to double-bit errors. -# DCGM_FI_DEV_RETIRED_PENDING, counter, Total number of pages pending retirement. - -# NVLink -# DCGM_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_TOTAL, counter, Total number of NVLink flow-control CRC errors. -# DCGM_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_TOTAL, counter, Total number of NVLink data CRC errors. -# DCGM_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_TOTAL, counter, Total number of NVLink retries. -# DCGM_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_TOTAL, counter, Total number of NVLink recovery errors. -DCGM_FI_DEV_NVLINK_BANDWIDTH_TOTAL, counter, Total number of NVLink bandwidth counters for all lanes - -# MIG (Multi-Instance GPU) -DCGM_FI_DEV_MIG_MODE, gauge, MIG mode status (0=disabled / 1=enabled) -DCGM_FI_DEV_MIG_MAX_SLICES, gauge, Maximum number of MIG slices supported - -# VGPU License status -DCGM_FI_DEV_VGPU_LICENSE_STATUS, gauge, vGPU License status - -# Remapped rows -DCGM_FI_DEV_UNCORRECTABLE_REMAPPED_ROWS, counter, Number of remapped rows for uncorrectable errors -DCGM_FI_DEV_CORRECTABLE_REMAPPED_ROWS, counter, Number of remapped rows for correctable errors -DCGM_FI_DEV_ROW_REMAP_FAILURE, gauge, Whether remapping of rows has failed - -# Static configuration information. These appear as labels on the other metrics -DCGM_FI_DRIVER_VERSION, label, Driver Version -DCGM_FI_DEV_PCI_BUSID, label, PCI attributes for the device -DCGM_FI_CUDA_DRIVER_VERSION, label, CUDA Driver Version -DCGM_FI_DEV_VBIOS_VERSION, label, VBIOS version of the device -DCGM_FI_NVML_VERSION, label, NVML Version -# DCGM_FI_DEV_BRAND, label, Device Brand -# DCGM_FI_DEV_SERIAL, label, Device Serial Number -# DCGM_FI_DEV_OEM_INFOROM_VER, label, OEM inforom version -# DCGM_FI_DEV_ECC_INFOROM_VER, label, ECC inforom version -# DCGM_FI_DEV_POWER_INFOROM_VER, label, Power management object inforom version -# DCGM_FI_DEV_INFOROM_IMAGE_VER, label, Inforom image version - -# Process identifier -DCGM_FI_PROCESS_NAME, label, Process name diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_00 b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_00 deleted file mode 100644 index 8efd1af..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_00 and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_01 b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_01 deleted file mode 100644 index 506193c..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_01 and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_02 b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_02 deleted file mode 100644 index ba64b9a..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_02 and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_03 b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_03 deleted file mode 100644 index 7f8e05b..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_03 and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_04 b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_04 deleted file mode 100644 index e7dd57e..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_04 and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_05 b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_05 deleted file mode 100644 index 7f9fccd..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_05 and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/deb/libnvidia-container-tools_1.19.0-1_amd64.deb b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/deb/libnvidia-container-tools_1.19.0-1_amd64.deb deleted file mode 100644 index d9f0f10..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/deb/libnvidia-container-tools_1.19.0-1_amd64.deb and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/deb/libnvidia-container1_1.19.0-1_amd64.deb b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/deb/libnvidia-container1_1.19.0-1_amd64.deb deleted file mode 100644 index 8b0983c..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/deb/libnvidia-container1_1.19.0-1_amd64.deb and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/deb/nvidia-container-toolkit-base_1.19.0-1_amd64.deb b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/deb/nvidia-container-toolkit-base_1.19.0-1_amd64.deb deleted file mode 100644 index 498e483..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/deb/nvidia-container-toolkit-base_1.19.0-1_amd64.deb and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/deb/nvidia-container-toolkit_1.19.0-1_amd64.deb b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/deb/nvidia-container-toolkit_1.19.0-1_amd64.deb deleted file mode 100644 index bc0b4ce..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/deb/nvidia-container-toolkit_1.19.0-1_amd64.deb and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/rpm/libnvidia-container-tools-1.19.0-1.x86_64.rpm b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/rpm/libnvidia-container-tools-1.19.0-1.x86_64.rpm deleted file mode 100644 index 5c9bd30..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/rpm/libnvidia-container-tools-1.19.0-1.x86_64.rpm and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/rpm/libnvidia-container1-1.19.0-1.x86_64.rpm b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/rpm/libnvidia-container1-1.19.0-1.x86_64.rpm deleted file mode 100644 index e4ab169..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/rpm/libnvidia-container1-1.19.0-1.x86_64.rpm and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/rpm/nvidia-container-toolkit-1.19.0-1.x86_64.rpm b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/rpm/nvidia-container-toolkit-1.19.0-1.x86_64.rpm deleted file mode 100644 index 16aba76..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/rpm/nvidia-container-toolkit-1.19.0-1.x86_64.rpm and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/rpm/nvidia-container-toolkit-base-1.19.0-1.x86_64.rpm b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/rpm/nvidia-container-toolkit-base-1.19.0-1.x86_64.rpm deleted file mode 100644 index a9c1914..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/amd64/rpm/nvidia-container-toolkit-base-1.19.0-1.x86_64.rpm and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/cmp-dcgm-exporter.service b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/cmp-dcgm-exporter.service deleted file mode 100644 index 0a632fa..0000000 --- a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/cmp-dcgm-exporter.service +++ /dev/null @@ -1,41 +0,0 @@ -[Unit] -Description=CMP DCGM Exporter Service -Wants=network-online.target -After=network-online.target -RequiresMountsFor=%t/containers - -[Service] -Type=notify -NotifyAccess=all -User=root - - -Environment=TIME_DIFF_SECONDS=0 -Environment=PODMAN_SYSTEMD_UNIT=%n - -ExecStart=/cmp-agent/common/podman/bin/run-podman run \ - --pid=host \ - --cgroups=no-conmon \ - --env TIME_DIFF_SECONDS \ - --env HOSTNAME=%H \ - --sdnotify=conmon \ - --replace \ - -d \ - --restart=always \ - --tz=Asia/Seoul \ - --network=host \ - --device=nvidia.com/gpu=all \ - --name cmp-dcgm \ - -p 9400:9400 \ - --mount type=bind,src=/cmp-agent/dcgm-exporter-custom.csv,dst=/cmp-agent/dcgm-exporter-custom.csv,ro=true \ - nvcr.io/nvidia/k8s/dcgm-exporter:4.4.2-4.7.0-ubuntu22.04 \ - -f /cmp-agent/dcgm-exporter-custom.csv - -ExecStop=/cmp-agent/common/podman/bin/run-podman stop cmp-dcgm - -Restart=on-failure -RestartPreventExitStatus=100 -TimeoutStopSec=30 - -[Install] -WantedBy=multi-user.target diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/dcgm-exporter-custom.csv b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/dcgm-exporter-custom.csv deleted file mode 100644 index 1529b6a..0000000 --- a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/dcgm-exporter-custom.csv +++ /dev/null @@ -1,92 +0,0 @@ -# Format -# If line starts with a '#' it is considered a comment -# DCGM FIELD, Prometheus metric type, help message - -# Clocks -DCGM_FI_DEV_SM_CLOCK, gauge, SM clock frequency (in MHz). -DCGM_FI_DEV_MEM_CLOCK, gauge, Memory clock frequency (in MHz). -# DCGM_EXP_CLOCK_EVENTS_COUNT, gauge, Count of clock events within the user-specified time window (see clock-events-count-window-size param). - -# Temperature -DCGM_FI_DEV_MEMORY_TEMP, gauge, Memory temperature (in C). -DCGM_FI_DEV_GPU_TEMP, gauge, GPU temperature (in C). -DCGM_FI_DEV_FAN_SPEED, gauge, Fan speed for the device in percent(in %). - -# Power -DCGM_FI_DEV_POWER_USAGE, gauge, Power draw (in W). -DCGM_FI_DEV_TOTAL_ENERGY_CONSUMPTION, counter, Total energy consumption since boot (in mJ). -DCGM_FI_DEV_PSTATE, gauge, Performance state. - -# PCIE -DCGM_FI_DEV_PCIE_TX_THROUGHPUT, counter, Total number of bytes transmitted through PCIe TX (in KB) via NVML. -DCGM_FI_DEV_PCIE_RX_THROUGHPUT, counter, Total number of bytes received through PCIe RX (in KB) via NVML. -DCGM_FI_DEV_PCIE_REPLAY_COUNTER, counter, Total number of PCIe retries. - -# Utilization (the sample period varies depending on the product) -DCGM_FI_DEV_GPU_UTIL, gauge, GPU utilization (in %). -DCGM_FI_DEV_MEM_COPY_UTIL, gauge, Memory utilization (in %). -DCGM_FI_DEV_ENC_UTIL, gauge, Encoder utilization (in %). -DCGM_FI_DEV_DEC_UTIL , gauge, Decoder utilization (in %). - -# Errors and violations -DCGM_FI_DEV_XID_ERRORS, gauge, Value of the last XID error encountered. -DCGM_FI_DEV_CLOCKS_EVENT_REASONS, gauge, Clock throttle reasons -DCGM_EXP_XID_ERRORS_COUNT, gauge, Count of XID Errors within user-specified time window (see xid-count-window-size param). - -# DCGM_FI_DEV_POWER_VIOLATION, counter, Throttling duration due to power constraints (in us). -# DCGM_FI_DEV_THERMAL_VIOLATION, counter, Throttling duration due to thermal constraints (in us). -# DCGM_FI_DEV_SYNC_BOOST_VIOLATION, counter, Throttling duration due to sync-boost constraints (in us). -# DCGM_FI_DEV_BOARD_LIMIT_VIOLATION, counter, Throttling duration due to board limit constraints (in us). -# DCGM_FI_DEV_LOW_UTIL_VIOLATION, counter, Throttling duration due to low utilization (in us). -# DCGM_FI_DEV_RELIABILITY_VIOLATION, counter, Throttling duration due to reliability constraints (in us). - -# Memory usage -DCGM_FI_DEV_FB_FREE, gauge, Frame buffer memory free (in MB). -DCGM_FI_DEV_FB_USED, gauge, Frame buffer memory used (in MB). -DCGM_FI_DEV_FB_TOTAL, gauge, Frame buffer memory (in MB). - -# ECC (Datacenter GPU only, A100, H100, V100, T4) -DCGM_FI_DEV_ECC_SBE_VOL_TOTAL, counter, Total number of single-bit volatile ECC errors. -DCGM_FI_DEV_ECC_DBE_VOL_TOTAL, counter, Total number of double-bit volatile ECC errors. -DCGM_FI_DEV_ECC_SBE_AGG_TOTAL, counter, Total number of single-bit persistent ECC errors. -DCGM_FI_DEV_ECC_DBE_AGG_TOTAL, counter, Total number of double-bit persistent ECC errors. - -# Retired pages -# DCGM_FI_DEV_RETIRED_SBE, counter, Total number of retired pages due to single-bit errors. -# DCGM_FI_DEV_RETIRED_DBE, counter, Total number of retired pages due to double-bit errors. -# DCGM_FI_DEV_RETIRED_PENDING, counter, Total number of pages pending retirement. - -# NVLink -# DCGM_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_TOTAL, counter, Total number of NVLink flow-control CRC errors. -# DCGM_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_TOTAL, counter, Total number of NVLink data CRC errors. -# DCGM_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_TOTAL, counter, Total number of NVLink retries. -# DCGM_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_TOTAL, counter, Total number of NVLink recovery errors. -DCGM_FI_DEV_NVLINK_BANDWIDTH_TOTAL, counter, Total number of NVLink bandwidth counters for all lanes - -# MIG (Multi-Instance GPU) -DCGM_FI_DEV_MIG_MODE, gauge, MIG mode status (0=disabled / 1=enabled) -DCGM_FI_DEV_MIG_MAX_SLICES, gauge, Maximum number of MIG slices supported - -# VGPU License status -DCGM_FI_DEV_VGPU_LICENSE_STATUS, gauge, vGPU License status - -# Remapped rows -DCGM_FI_DEV_UNCORRECTABLE_REMAPPED_ROWS, counter, Number of remapped rows for uncorrectable errors -DCGM_FI_DEV_CORRECTABLE_REMAPPED_ROWS, counter, Number of remapped rows for correctable errors -DCGM_FI_DEV_ROW_REMAP_FAILURE, gauge, Whether remapping of rows has failed - -# Static configuration information. These appear as labels on the other metrics -DCGM_FI_DRIVER_VERSION, label, Driver Version -DCGM_FI_DEV_PCI_BUSID, label, PCI attributes for the device -DCGM_FI_CUDA_DRIVER_VERSION, label, CUDA Driver Version -DCGM_FI_DEV_VBIOS_VERSION, label, VBIOS version of the device -DCGM_FI_NVML_VERSION, label, NVML Version -# DCGM_FI_DEV_BRAND, label, Device Brand -# DCGM_FI_DEV_SERIAL, label, Device Serial Number -# DCGM_FI_DEV_OEM_INFOROM_VER, label, OEM inforom version -# DCGM_FI_DEV_ECC_INFOROM_VER, label, ECC inforom version -# DCGM_FI_DEV_POWER_INFOROM_VER, label, Power management object inforom version -# DCGM_FI_DEV_INFOROM_IMAGE_VER, label, Inforom image version - -# Process identifier -DCGM_FI_PROCESS_NAME, label, Process name diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_00 b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_00 deleted file mode 100644 index 8efd1af..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_00 and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_01 b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_01 deleted file mode 100644 index 506193c..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_01 and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_02 b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_02 deleted file mode 100644 index ba64b9a..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_02 and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_03 b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_03 deleted file mode 100644 index 7f8e05b..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_03 and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_04 b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_04 deleted file mode 100644 index e7dd57e..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_04 and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_05 b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_05 deleted file mode 100644 index 7f9fccd..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_05 and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/deb/libnvidia-container-tools_1.19.0-1_arm64.deb b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/deb/libnvidia-container-tools_1.19.0-1_arm64.deb deleted file mode 100644 index 9beaf54..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/deb/libnvidia-container-tools_1.19.0-1_arm64.deb and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/deb/libnvidia-container1_1.19.0-1_arm64.deb b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/deb/libnvidia-container1_1.19.0-1_arm64.deb deleted file mode 100644 index 2bc1a35..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/deb/libnvidia-container1_1.19.0-1_arm64.deb and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/deb/nvidia-container-toolkit-base_1.19.0-1_arm64.deb b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/deb/nvidia-container-toolkit-base_1.19.0-1_arm64.deb deleted file mode 100644 index 3e31602..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/deb/nvidia-container-toolkit-base_1.19.0-1_arm64.deb and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/deb/nvidia-container-toolkit_1.19.0-1_arm64.deb b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/deb/nvidia-container-toolkit_1.19.0-1_arm64.deb deleted file mode 100644 index 69b41f3..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/deb/nvidia-container-toolkit_1.19.0-1_arm64.deb and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/rpm/libnvidia-container-tools-1.19.0-1.aarch64.rpm b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/rpm/libnvidia-container-tools-1.19.0-1.aarch64.rpm deleted file mode 100644 index fa24b58..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/rpm/libnvidia-container-tools-1.19.0-1.aarch64.rpm and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/rpm/libnvidia-container1-1.19.0-1.aarch64.rpm b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/rpm/libnvidia-container1-1.19.0-1.aarch64.rpm deleted file mode 100644 index 60fa9c0..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/rpm/libnvidia-container1-1.19.0-1.aarch64.rpm and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/rpm/nvidia-container-toolkit-1.19.0-1.aarch64.rpm b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/rpm/nvidia-container-toolkit-1.19.0-1.aarch64.rpm deleted file mode 100644 index 26abd58..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/rpm/nvidia-container-toolkit-1.19.0-1.aarch64.rpm and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/rpm/nvidia-container-toolkit-base-1.19.0-1.aarch64.rpm b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/rpm/nvidia-container-toolkit-base-1.19.0-1.aarch64.rpm deleted file mode 100644 index 6f6a68a..0000000 Binary files a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/dcgm-install-files/arm64/rpm/nvidia-container-toolkit-base-1.19.0-1.aarch64.rpm and /dev/null differ diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/tasks/dcgm_common_begin.yaml b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/tasks/dcgm_common_begin.yaml deleted file mode 100644 index 3bf06de..0000000 --- a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/tasks/dcgm_common_begin.yaml +++ /dev/null @@ -1,40 +0,0 @@ -# 공통 부트스트랩: busybox + cmp-agent-common(podman 정적 바이너리 포함) 설치. -# agent role의 agent_common_begin.yaml과 동일한 공통 설치 흐름을 dcgm role 단독 실행 시에도 보장한다. -- name: Copy temporary busybox - include_tasks: send_file.yaml - vars: - input_file_path: "{{ playbook_dir }}/roles/agent/agent-install-files/{{ arch }}/busybox" - output_file_path: "/tmp/busybox_{{ request_id }}" - output_file_owner: "root" - output_file_group: "root" - output_file_chmod: "755" - -- name: Copy Common Agent Install File - include_tasks: send_file.yaml - vars: - input_file_path: "{{ playbook_dir }}/roles/agent/agent-install-files/{{ arch }}/cmp-agent-common.tar.gz" - output_file_path: "/tmp/cmp-agent-common_{{ request_id }}.tar.gz" - output_file_owner: "root" - output_file_group: "root" - output_file_chmod: "644" - -- name: Copy Common Agent Install Script File - include_tasks: send_file.yaml - vars: - input_file_path: "{{ playbook_dir }}/roles/agent/agent-install-files/{{ arch }}/cmp-agent_install_common" - output_file_path: "/tmp/cmp-agent_install_common_{{ request_id }}" - output_file_owner: "root" - output_file_group: "root" - output_file_chmod: "755" - -- name: Run Common Agent Install Script File - become: true - become_method: sudo - become_user: root - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: "flock -x /tmp/cmp-agent_install_common.lock /tmp/cmp-agent_install_common_{{ request_id }} {{ request_id }}" diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/tasks/dcgm_common_end.yaml b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/tasks/dcgm_common_end.yaml deleted file mode 100644 index 223c719..0000000 --- a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/tasks/dcgm_common_end.yaml +++ /dev/null @@ -1,35 +0,0 @@ -- name: Remove temporary busybox - become: true - become_method: sudo - become_user: root - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: "rm -f /tmp/busybox_{{ request_id }}" - -- name: Remove Remote Common Agent Install File - become: true - become_method: sudo - become_user: root - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: "rm -f /tmp/cmp-agent-common_{{ request_id }}.tar.gz" - -- name: Remove Remote Common Agent Script File - become: true - become_method: sudo - become_user: root - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: "rm -f /tmp/cmp-agent_install_common_{{ request_id }}" diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/tasks/dcgm_install.yaml b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/tasks/dcgm_install.yaml deleted file mode 100644 index a42e522..0000000 --- a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/tasks/dcgm_install.yaml +++ /dev/null @@ -1,308 +0,0 @@ -# 1. Common bootstrap (podman static 설치) -- name: Begin Agent Common Tasks - include_tasks: "{{ role_path }}/tasks/dcgm_common_begin.yaml" - -- name: Detect OS family - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: grep '^ID=' /etc/os-release | head -n1 | cut -d'=' -f2 | tr -d '"' - register: os_id_raw - changed_when: false - failed_when: false - -- name: Debug OS ID - debug: - msg: "OS ID is {{ os_id_raw.stdout | trim }}" - -- name: Set OS family for RedHat-based - set_fact: - os_family: "redhat" - when: os_id_raw.stdout | trim in ['rhel', 'centos', 'rocky', 'almalinux', 'fedora'] - -- name: Set OS family for Debian-based - set_fact: - os_family: "debian" - when: os_id_raw.stdout | trim in ['ubuntu', 'debian'] - -- name: Set OS family as unknown - set_fact: - os_family: "unknown" - when: os_family is not defined - -- name: Display OS family - debug: - msg: "Detected os family is {{ os_family }}" - -# 2. Install NVIDIA Container Toolkit -- name: Create NVIDIA Container Toolkit Package Temporary Folder - become: true - become_method: sudo - become_user: root - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: "mkdir -p /tmp/dcgm-install-files_{{ request_id }}/" - -- name: Copy NVIDIA Container Toolkit DEB Packages - include_tasks: send_file.yaml - vars: - input_file_path: "{{ role_path }}/dcgm-install-files/{{ arch }}/deb/{{ item }}" - output_file_path: "/tmp/dcgm-install-files_{{ request_id }}/{{ item }}" - output_file_owner: "root" - output_file_group: "root" - output_file_chmod: "644" - loop: - - "libnvidia-container1_{{ NVIDIA_CONTAINER_TOOLKIT_VERSION }}_{{ arch }}.deb" - - "libnvidia-container-tools_{{ NVIDIA_CONTAINER_TOOLKIT_VERSION }}_{{ arch }}.deb" - - "nvidia-container-toolkit-base_{{ NVIDIA_CONTAINER_TOOLKIT_VERSION }}_{{ arch }}.deb" - - "nvidia-container-toolkit_{{ NVIDIA_CONTAINER_TOOLKIT_VERSION }}_{{ arch }}.deb" - when: os_family == "debian" - -- name: Copy NVIDIA Container Toolkit RPM Packages - include_tasks: send_file.yaml - vars: - input_file_path: "{{ role_path }}/dcgm-install-files/{{ arch }}/rpm/{{ item }}" - output_file_path: "/tmp/dcgm-install-files_{{ request_id }}/{{ item }}" - output_file_owner: "root" - output_file_group: "root" - output_file_chmod: "644" - loop: - - "libnvidia-container1-{{ NVIDIA_CONTAINER_TOOLKIT_VERSION }}.{{ arch_raw.stdout | trim }}.rpm" - - "libnvidia-container-tools-{{ NVIDIA_CONTAINER_TOOLKIT_VERSION }}.{{ arch_raw.stdout | trim }}.rpm" - - "nvidia-container-toolkit-base-{{ NVIDIA_CONTAINER_TOOLKIT_VERSION }}.{{ arch_raw.stdout | trim }}.rpm" - - "nvidia-container-toolkit-{{ NVIDIA_CONTAINER_TOOLKIT_VERSION }}.{{ arch_raw.stdout | trim }}.rpm" - when: os_family == "redhat" - -- name: Install NVIDIA Container Toolkit Package (Debian/Ubuntu) - become: true - become_method: sudo - become_user: root - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: "dpkg -i /tmp/dcgm-install-files_{{ request_id }}/*.deb" - when: os_family == "debian" - -- name: Install NVIDIA Container Toolkit Package (RHEL/CentOS) - become: true - become_method: sudo - become_user: root - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: "rpm -ivh --force /tmp/dcgm-install-files_{{ request_id }}/*.rpm" - when: os_family == "redhat" - -- name: Fix nvidia-cdi-refresh.service for compressed kernel modules (.ko.zst) - become: true - become_method: sudo - become_user: root - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: | - sed -i 's/nvidia|nvidia-current)\\\.ko\[:\]/nvidia|nvidia-current)\\.ko[^:]*:/g' /etc/systemd/system/nvidia-cdi-refresh.service && systemctl daemon-reload && systemctl restart nvidia-cdi-refresh - ignore_errors: true - -- name: Remove Temporary NVIDIA Container Toolkit Package Files - become: true - become_method: sudo - become_user: root - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: "rm -rf /tmp/dcgm-install-files_{{ request_id }}" - -# 3. DCGM Exporter 이미지 로드 -# 이미지(273MB)는 GitHub 100MB 제한 때문에 50MB 단위(_00.._05)로 분할 저장되어 있다. -# (telegraf의 cmp-telegraf.tar.gz_* 분할 방식과 동일) -- name: Merge split DCGM Exporter Image (local) - raw: "cat {{ role_path }}/dcgm-install-files/{{ arch }}/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04.tar.gz_* > /tmp/dcgm-exporter_{{ request_id }}.tar.gz" - delegate_to: 127.0.0.1 - -- name: Copy DCGM Exporter Image - include_tasks: send_file.yaml - vars: - input_file_path: "/tmp/dcgm-exporter_{{ request_id }}.tar.gz" - output_file_path: "/tmp/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04-{{ site_code }}.tar.gz" - output_file_owner: "root" - output_file_group: "root" - output_file_chmod: "644" - -- name: Remove Local Merged DCGM Exporter Image - raw: "rm -f /tmp/dcgm-exporter_{{ request_id }}.tar.gz" - delegate_to: 127.0.0.1 - -- name: Load DCGM Exporter Image - become: true - become_method: sudo - become_user: root - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: "/cmp-agent/common/podman/bin/run-podman load -i /tmp/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04-{{ site_code }}.tar.gz" - -- name: Remove Temporary DCGM Exporter Image File - become: true - become_method: sudo - become_user: root - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: "rm -rf /tmp/dcgm-exporter_4.4.2-4.7.0-ubuntu22.04-{{ site_code }}.tar.gz" - changed_when: true - -# 4. systemd 적용 및 시작 -- name: Install DCGM Exporter Service File - include_tasks: send_file.yaml - vars: - input_file_path: "{{ role_path }}/dcgm-install-files/{{ arch }}/cmp-dcgm-exporter.service" - output_file_path: "/lib/systemd/system/cmp-dcgm-exporter.service" - output_file_owner: "root" - output_file_group: "root" - output_file_chmod: "644" - -- name: Copy DCGM Exporter Custom Config File - include_tasks: send_file.yaml - vars: - input_file_path: "{{ role_path }}/dcgm-install-files/{{ arch }}/dcgm-exporter-custom.csv" - output_file_path: "/cmp-agent/dcgm-exporter-custom.csv" - output_file_owner: "root" - output_file_group: "root" - output_file_chmod: "644" - -- name: Check if nvidia-persistenced service exists - become: true - become_method: sudo - become_user: root - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: "systemctl list-unit-files nvidia-persistenced.service --no-legend | grep -c nvidia-persistenced" - register: nvidia_persistenced_exists - changed_when: false - failed_when: false - -- name: Remove --no-persistence-mode from nvidia-persistenced service file - become: true - become_method: sudo - become_user: root - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: "sed -i 's/--no-persistence-mode//g' /lib/systemd/system/nvidia-persistenced.service" - when: nvidia_persistenced_exists.stdout | trim | int > 0 - ignore_errors: true - -- name: Fix DCGM Exporter Service File SELinux Permission - become: true - become_method: sudo - become_user: root - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: "chcon system_u:object_r:systemd_unit_file_t:s0 /lib/systemd/system/cmp-dcgm-exporter.service" - ignore_errors: true - -- name: Fix DCGM Exporter Custom Config File SELinux Permission - become: true - become_method: sudo - become_user: root - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: "chcon system_u:object_r:systemd_unit_file_t:s0 /cmp-agent/dcgm-exporter-custom.csv" - ignore_errors: true - -- name: Fix NVIDIA Persistenced Service File SELinux Permission - become: true - become_method: sudo - become_user: root - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: "chcon system_u:object_r:systemd_unit_file_t:s0 /lib/systemd/system/nvidia-persistenced.service" - when: nvidia_persistenced_exists.stdout | trim | int > 0 - ignore_errors: true - -- name: Reload systemd daemon - become: true - become_method: sudo - become_user: root - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: "systemctl daemon-reload" - -- name: Start and Enable DCGM Exporter service - become: true - become_method: sudo - become_user: root - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: "systemctl enable --now cmp-dcgm-exporter.service" - -- name: Restart NVIDIA Persistenced Service - become: true - become_method: sudo - become_user: root - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: "systemctl restart nvidia-persistenced.service" - when: nvidia_persistenced_exists.stdout | trim | int > 0 - ignore_errors: true - -# 5. 공통 작업 종료 -- name: End Agent Common Tasks - include_tasks: "{{ role_path }}/tasks/dcgm_common_end.yaml" diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/tasks/dcgm_uninstall.yaml b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/tasks/dcgm_uninstall.yaml deleted file mode 100644 index fe40c6e..0000000 --- a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/tasks/dcgm_uninstall.yaml +++ /dev/null @@ -1,125 +0,0 @@ -- name: Stop and Disable DCGM Exporter service - become: true - become_method: sudo - become_user: root - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: "systemctl disable --now cmp-dcgm-exporter.service 2>&1 | true && /cmp-agent/common/podman/bin/run-podman rm -f cmp-dcgm 2>&1 | true" - -- name: Detect OS family - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: grep '^ID=' /etc/os-release | head -n1 | cut -d'=' -f2 | tr -d '"' - register: os_id_raw - changed_when: false - failed_when: false - -- name: Debug OS ID - debug: - msg: "OS ID is {{ os_id_raw.stdout | trim }}" - -- name: Set OS family for RedHat-based - set_fact: - os_family: "redhat" - when: os_id_raw.stdout | trim in ['rhel', 'centos', 'rocky', 'almalinux', 'fedora'] - -- name: Set OS family for Debian-based - set_fact: - os_family: "debian" - when: os_id_raw.stdout | trim in ['ubuntu', 'debian'] - -- name: Set OS family as unknown - set_fact: - os_family: "unknown" - when: os_family is not defined - -- name: Display OS family - debug: - msg: "Detected os family is {{ os_family }}" - -# 2. Remove NVIDIA Container Toolkit -- name: Remove NVIDIA Container Toolkit DEB Packages - become: true - become_method: sudo - become_user: root - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: "apt purge -y libnvidia-container1 libnvidia-container-tools nvidia-container-toolkit-base nvidia-container-toolkit" - when: os_family == "debian" - -- name: Remove NVIDIA Container Toolkit RPM Packages - become: true - become_method: sudo - become_user: root - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: "yum remove -y libnvidia-container1 libnvidia-container-tools nvidia-container-toolkit-base nvidia-container-toolkit" - when: os_family == "redhat" - -# 3. DCGM Exporter 이미지 삭제 -- name: Remove DCGM Exporter Image - become: true - become_method: sudo - become_user: root - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: "/cmp-agent/common/podman/bin/run-podman rmi nvcr.io/nvidia/k8s/dcgm-exporter:4.4.2-4.7.0-ubuntu22.04 2>&1 | true" - -# 4. systemd 서비스 삭제 -- name: Remove DCGM Exporter Service File - become: true - become_method: sudo - become_user: root - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: "rm -f /lib/systemd/system/cmp-dcgm-exporter.service" - ignore_errors: true - -- name: Remove DCGM Exporter Custom Config File - become: true - become_method: sudo - become_user: root - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: "rm -f /cmp-agent/dcgm-exporter-custom.csv" - ignore_errors: true - -- name: Reload systemd daemon - become: true - become_method: sudo - become_user: root - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: "systemctl daemon-reload" diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/tasks/main.yaml b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/tasks/main.yaml deleted file mode 100644 index c87f52a..0000000 --- a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/tasks/main.yaml +++ /dev/null @@ -1,24 +0,0 @@ -- name: Detect Remote's architecture - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: uname -m - register: arch_raw - changed_when: false - failed_when: false - -- name: Set architecture variable - set_fact: - arch: "{{ 'amd64' if arch_raw.stdout | trim == 'x86_64' else 'arm64' if arch_raw.stdout | trim == 'aarch64' else arch_raw.stdout | trim }}" - -- name: Debug architecture - debug: - msg: "Architecture is {{ arch }}" - -# DCGM Exporter는 install / uninstall만 지원 (update/restart는 telegraf 에이전트만 해당) -- name: Run DCGM Exporter task based on install method - include_tasks: "dcgm_{{ install_method | default('install') }}.yaml" - when: install_method | default('install') in ['install', 'uninstall'] diff --git a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/tasks/send_file.yaml b/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/tasks/send_file.yaml deleted file mode 100644 index 1b40d7e..0000000 --- a/conf/docker/conf/mc-observability/mc-observability-infra/ansible/playbooks/install-agent/roles/dcgm/tasks/send_file.yaml +++ /dev/null @@ -1,19 +0,0 @@ -- name: Copy file to remote temp location - raw: | - scp -r -o StrictHostKeyChecking=no -P {{ target_port }} {% if target_sshkey_path | default('') | length > 0 %}-i {{ target_sshkey_path }} {% endif %}{{ input_file_path }} {{ target_user }}@{{ target_host }}:/tmp/temp_file_{{ request_id }} - delegate_to: 127.0.0.1 - -- name: Move file to final location with proper permissions - become: true - become_method: sudo - become_user: root - vars: - ansible_connection: ssh - ansible_host: "{{ target_host }}" - ansible_port: "{{ target_port }}" - ansible_user: "{{ target_user }}" - ansible_ssh_private_key_file: "{{ target_sshkey_path }}" - raw: | - mv -f /tmp/temp_file_{{ request_id }} {{ output_file_path }} - chmod {{ output_file_chmod }} {{ output_file_path }} - chown {{ output_file_owner }}:{{ output_file_group }} {{ output_file_path }} diff --git a/conf/docker/docker-compose.yaml b/conf/docker/docker-compose.yaml index afd4951..4402993 100644 --- a/conf/docker/docker-compose.yaml +++ b/conf/docker/docker-compose.yaml @@ -1222,7 +1222,7 @@ services: <<: *default-health-check ##### MC-OBSERVABILITY ######################################################################################################################### mc-observability-manager: - image: cloudbaristaorg/mc-observability:0.6.0 + image: cloudbaristaorg/mc-observability:0.6.1 container_name: mc-observability-manager restart: unless-stopped networks: @@ -1262,7 +1262,7 @@ services: start_period: 5m mc-observability-front: - image: cloudbaristaorg/mc-observability-front:0.6.0 + image: cloudbaristaorg/mc-observability-front:0.6.1 container_name: mc-observability-front restart: unless-stopped networks: @@ -1274,7 +1274,7 @@ services: condition: service_started mc-observability-infra: - image: cloudbaristaorg/mc-observability-infra:0.6.0 + image: cloudbaristaorg/mc-observability-infra:0.6.1 container_name: mc-observability-infra restart: unless-stopped networks: @@ -1399,7 +1399,7 @@ services: init: true mc-observability-influx: - image: cloudbaristaorg/mc-observability-influx:0.6.0 + image: cloudbaristaorg/mc-observability-influx:0.6.1 container_name: mc-observability-influx restart: unless-stopped networks: @@ -1441,7 +1441,7 @@ services: - mc-observability-network mc-observability-influx-2: - image: cloudbaristaorg/mc-observability-influx:0.6.0 + image: cloudbaristaorg/mc-observability-influx:0.6.1 container_name: mc-observability-influx-2 restart: unless-stopped networks: @@ -1617,7 +1617,7 @@ services: init: true mc-observability-grafana: - image: cloudbaristaorg/mc-observability-grafana:0.6.0 + image: cloudbaristaorg/mc-observability-grafana:0.6.1 container_name: mc-observability-grafana restart: unless-stopped networks: @@ -1652,7 +1652,7 @@ services: fi mc-observability-insight: - image: cloudbaristaorg/mc-observability-insight:0.6.0 + image: cloudbaristaorg/mc-observability-insight:0.6.1 container_name: mc-observability-insight restart: always networks: @@ -1679,7 +1679,7 @@ services: start_period: 10s mc-observability-insight-scheduler: - image: cloudbaristaorg/mc-observability-insight-scheduler:0.6.0 + image: cloudbaristaorg/mc-observability-insight-scheduler:0.6.1 container_name: mc-observability-insight-scheduler restart: always ports: @@ -1758,7 +1758,7 @@ services: - mc-observability-network mc-observability-mcp-maria: - image: cloudbaristaorg/mc-observability-mcp-mariadb:0.6.0 + image: cloudbaristaorg/mc-observability-mcp-mariadb:0.6.1 container_name: mc-observability-mcp-maria restart: always networks: @@ -1782,7 +1782,7 @@ services: - OPENAI_API_KEY=${OPENAI_API_KEY:-} mc-observability-mcp-influx: - image: cloudbaristaorg/mc-observability-mcp-influxdb:0.6.0 + image: cloudbaristaorg/mc-observability-mcp-influxdb:0.6.1 container_name: mc-observability-mcp-influx restart: always ports: