Skip to content

Commit

Permalink
fix(system_monitor): disable gpu_monitor (#770)
Browse files Browse the repository at this point in the history
  • Loading branch information
h-ohta authored Aug 28, 2023
1 parent e60519c commit b21f684
Show file tree
Hide file tree
Showing 2 changed files with 41 additions and 38 deletions.
Original file line number Diff line number Diff line change
Expand Up @@ -68,33 +68,34 @@
contains: [": CPU Load Average"]
timeout: 3.0

gpu:
type: diagnostic_aggregator/AnalyzerGroup
path: gpu
analyzers:
temperature:
type: diagnostic_aggregator/GenericAnalyzer
path: temperature
contains: [": GPU Temperature"]
timeout: 3.0

usage:
type: diagnostic_aggregator/GenericAnalyzer
path: gpu_usage
contains: [": GPU Usage"]
timeout: 3.0

memory_usage:
type: diagnostic_aggregator/GenericAnalyzer
path: memory_usage
contains: [": GPU Memory Usage"]
timeout: 3.0

thermal_throttling:
type: diagnostic_aggregator/GenericAnalyzer
path: thermal_throttling
contains: [": GPU Thermal Throttling"]
timeout: 3.0
# Disable due to NVML error
# gpu:
# type: diagnostic_aggregator/AnalyzerGroup
# path: gpu
# analyzers:
# temperature:
# type: diagnostic_aggregator/GenericAnalyzer
# path: temperature
# contains: [": GPU Temperature"]
# timeout: 3.0

# usage:
# type: diagnostic_aggregator/GenericAnalyzer
# path: gpu_usage
# contains: [": GPU Usage"]
# timeout: 3.0

# memory_usage:
# type: diagnostic_aggregator/GenericAnalyzer
# path: memory_usage
# contains: [": GPU Memory Usage"]
# timeout: 3.0

# thermal_throttling:
# type: diagnostic_aggregator/GenericAnalyzer
# path: thermal_throttling
# contains: [": GPU Thermal Throttling"]
# timeout: 3.0

memory:
type: diagnostic_aggregator/AnalyzerGroup
Expand Down
24 changes: 13 additions & 11 deletions system/system_monitor/launch/system_monitor.launch.py
Original file line number Diff line number Diff line change
Expand Up @@ -86,16 +86,18 @@ def launch_setup(context, *args, **kwargs):
process_monitor_config,
],
)
with open(LaunchConfiguration("gpu_monitor_config_file").perform(context), "r") as f:
gpu_monitor_config = yaml.safe_load(f)["/**"]["ros__parameters"]
gpu_monitor = ComposableNode(
package="system_monitor",
plugin="GPUMonitor",
name="gpu_monitor",
parameters=[
gpu_monitor_config,
],
)

# Disable due to NVML error
# with open(LaunchConfiguration("gpu_monitor_config_file").perform(context), "r") as f:
# gpu_monitor_config = yaml.safe_load(f)["/**"]["ros__parameters"]
# gpu_monitor = ComposableNode(
# package="system_monitor",
# plugin="GPUMonitor",
# name="gpu_monitor",
# parameters=[
# gpu_monitor_config,
# ],
# )

# set container to run all required components in the same process
container = ComposableNodeContainer(
Expand All @@ -110,7 +112,7 @@ def launch_setup(context, *args, **kwargs):
net_monitor,
ntp_monitor,
process_monitor,
gpu_monitor,
# gpu_monitor,
],
output="screen",
)
Expand Down

0 comments on commit b21f684

Please sign in to comment.