From 79c12a75656431f3af000c2a8fdddb9220dff4e5 Mon Sep 17 00:00:00 2001 From: kk-inoue-esol <76925382+kk-inoue-esol@users.noreply.github.com> Date: Fri, 20 May 2022 10:37:30 +0900 Subject: [PATCH] fix(system_monitor): add some smart information to diagnostics (#708) Signed-off-by: kk-inoue-esol --- .../config/system_monitor/hdd_monitor.param.yaml | 3 +++ .../config/diagnostic_aggregator/system.param.yaml | 4 ++-- system/system_monitor/README.md | 2 ++ 3 files changed, 7 insertions(+), 2 deletions(-) diff --git a/launch/tier4_system_launch/config/system_monitor/hdd_monitor.param.yaml b/launch/tier4_system_launch/config/system_monitor/hdd_monitor.param.yaml index 32d3a425b1898..77a23eb0f9aa8 100644 --- a/launch/tier4_system_launch/config/system_monitor/hdd_monitor.param.yaml +++ b/launch/tier4_system_launch/config/system_monitor/hdd_monitor.param.yaml @@ -7,5 +7,8 @@ name: /dev/sda3 temp_warn: 55.0 temp_error: 70.0 + power_on_hours_warn: 3000000 + total_data_written_warn: 4915200 # =150TB (1unit=32MB) + total_data_written_safety_factor: 0.05 free_warn: 5120 # MB(8hour) free_error: 100 # MB(last 1 minute) diff --git a/system/system_error_monitor/config/diagnostic_aggregator/system.param.yaml b/system/system_error_monitor/config/diagnostic_aggregator/system.param.yaml index edea607c1bd1b..af6b9ab8a64c2 100644 --- a/system/system_error_monitor/config/diagnostic_aggregator/system.param.yaml +++ b/system/system_error_monitor/config/diagnostic_aggregator/system.param.yaml @@ -140,13 +140,13 @@ power_on_hours: type: diagnostic_aggregator/GenericAnalyzer - path: usage + path: power_on_hours contains: [": HDD PowerOnHours"] timeout: 3.0 total_data_written: type: diagnostic_aggregator/GenericAnalyzer - path: usage + path: total_data_written contains: [": HDD TotalDataWritten"] timeout: 3.0 diff --git a/system/system_monitor/README.md b/system/system_monitor/README.md index bd4eb3fb863c3..79f390a80d7e7 100644 --- a/system/system_monitor/README.md +++ b/system/system_monitor/README.md @@ -61,6 +61,8 @@ Every topic is published in 1 minute interval. | | CPU Thermal Throttling | ✓ | - | ✓ | | | | CPU Frequency | ✓ | ✓ | ✓ | Notification of frequency only, normally error not generated. | | HDD Monitor | HDD Temperature | ✓ | ✓ | ✓ | | +| | HDD PowerOnHours | ✓ | ✓ | ✓ | | +| | HDD TotalDataWritten | ✓ | ✓ | ✓ | | | | HDD Usage | ✓ | ✓ | ✓ | | | Memory Monitor | Memory Usage | ✓ | ✓ | ✓ | | | Net Monitor | Network Usage | ✓ | ✓ | ✓ | |