Welcome To OVIS LDMS Documentation!

LDMS is a lightweight framework for collecting, aggregating, and transporting system metrics in HPC environments. It gathers data from diverse sources like hardware counters and system logs, enabling real-time monitoring with low overhead and scalability for large systems.

Introduction To LDMS

• LDMS Quick Start
  • Installation
    • AlmaLinux8
    • RHEL 9
    • LDMS Source Installation Instructions
    • Basic Configuration and Running

LDMS Streams

• Streams-enabled Application Data Collectors
  • Caliper
    • Setup & Configuration
    • LDMS Expected Output
  • Darshan
    • Compile and Build with LDMS
    • Run an LDMS Streams Daemon
    • Test the Darshan-LDMS Integrated Code (Multi Node)
    • Test the Darshan-LDMS Integrated Code (Single Node)
    • Pre-Installed Darshan-LDMS
    • Check Results
  • Kokkos
    • Setup and Configuration
  • How To Make A Data Connector
    • Include the following LDMS files
    • Initialize All Necessary Variables
    • Copy “Hello Sampler” Streams API Functions
    • Initialize and Connect to LDMSD
    • Publish Event Data to LDMSD

ASF

• AppSysFusion
  • Quick Start
    • Create A Simple Analysis
    • Test Analysis via Terminal Window
    • Test Analysis via Grafana Dashboard
  • Additional ASF Tutorial Material
  • Grafana Panel Creation with DSOS Plugin
    • Configuring the Query and Visualization
    • Dashboard Variables and Advanced Settings
  • Basic Grafana Usage
  • Python Analysis Creation
    • Analysis I/O
    • Example Analysis Module
    • Testing an Analysis Module

Deployment

• Deployment
  • Github Repository for LDMS Functional Testing

Man Pages

• LDMS
  • ldms-plugins
    • Display information on installed LDMSD plugins.
  • ldms-reverse-conf
    • Generate a tear-down configuration file
  • ldms_authentication
    • Authentication in LDMS transports
  • ldms_build_install
    • Instructions for building and installing ldms
  • lsdate
    • List directory contents with UTC timestamp suffix translation
  • ldms_msg
    • publish/subscribe data in LDMS message service
  • ldms_msg_chan
    • Resilient Publish/Subscribe LDMS Message Channel Service
  • LDMS Python API Threading Model and Callback Contract
    • Section 1: The Threading Model
    • Section 2: Two Rules for Every Callback
    • Section 3: Blocking and Non-Blocking Mode
    • Section 4: Transport API Callbacks
    • Section 5: Message API Callbacks
    • Section 6: Summary
    • SEE ALSO
  • ldms_quickstart
    • Man page for Quick Start of LDMS
  • LDMS Transport Threading Model and Callback Safety
    • Section 1: Overview
    • Section 2: Threading Guarantees
    • Section 3: Creating and Connecting
    • Section 4: Passive Side (Listener)
    • Section 5: The Event Callback
    • Section 6: Reference Counting
    • Section 7: Lifecycle Sketch
    • Section 8: Summary of Safety Rules
    • SEE ALSO
  • ldmsctl
    • Issue control commands to ldmsd.
  • ldms_ls
    • Query an ldmsd for metric set values
  • auth
    • ldms_auth_munge
    • ldms_auth_naive
    • ldms_auth_none
    • ldms_auth_ovis
  • test
    • ldms-run-static-tests
    • ldms-static-test
    • pll-ldms-static-test
• LDMSD
  • ldmsd_communicator Module
    • A python program to communicator via Python with a LDMS daemon
  • ldmsd Configuration File Reference
    • Manual for LDMSD Configuration Files
  • ldmsd Configuration Threading Model
    • Configuration Command Pipeline
    • SEE ALSO
  • ldmsd_controller
    • A python program to configure an ldms daemon.
  • LDMSD Event-Based Storage
    • Event-Driven Storage with Worker Thread Pool
  • ldmsd_peer_daemon_advertisement
    • Manual for LDMSD Peer Daemon Advertisement
  • ldmsd_qgroup
    • Quota Group Feature in LDMSD
  • Sampler Plugin Developer Documentation
    • Section 1: Threading Overview
    • Section 2: API Threading Guarantees
    • Section 3: Concurrency Scenarios
    • Section 4: Synchronization Mechanism
    • Section 5: Plugin Lifecycle
    • Section 6: Using the LDMS Message Service in Sampler Plugins
    • Section 7: LDMSD Internal Implementation Details (For Maintainers Only)
    • SEE ALSO
  • Storage Plugin Developer Documentation
    • Section 1: Threading Overview
    • Section 2: Storage Paths
    • Section 3: API Threading Guarantees
    • Section 4: Concurrency Scenarios
    • Section 5: Synchronization Mechanism
    • Section 6: Plugin Lifecycle
    • Section 7: Using the LDMS Message Service in Storage Plugins
    • Section 8: LDMSD Internal Implementation Details (For Maintainers Only)
    • SEE ALSO
  • ldmsd_stream to ldms_msg
    • conversion guide
  • ldmsd_yaml_parser
    • A python program to parse a YAML configuration file into a v4 LDMS configuration.
  • ldmsd
    • Start an ldms daemon
  • ldmsd_failover
    • Explanation, configuration, and commands for ldmsd failover
  • ldmsd_setgroup
    • Explanation, configuration, and commands for ldmsd set group
  • ldmsd_smplrp
    • LDMSD Sampler Policy
  • ldmsd_decomposition
    • Manual for LDMSD decomposition
  • test
    • ldms_msg_publish
    • ldmsd_stream_publish
    • ldmsd_stream_subscribe
• Plugins
  • store
    • store_avro_kafka
    • darshan_stream_store
    • store_kafka
    • store_csv
    • store_function_csv
    • store_rabbitkw
    • store_rabbitv3
    • store_sos
    • store_papi
    • store_slurm
    • ldmsd_store_app
    • store_flatfile
    • stream_csv_store
    • ldms_csv_time_drops
    • ldms-csv-anonymize
    • ldms-csv-export-sos
  • sampler
    • app_sampler
    • linux_proc_sampler
    • aries_linkstatus
    • aries_mmr
    • aries_mmr_configurable
    • blob_msg_writer
    • blob_stream_writer
    • ldms-csv-from-blobs
    • clock
    • coretemp
    • cray_dvs_sampler
    • cray_system_sampler_variants
    • cxi_sampler
    • dcgm_sampler
    • dstat
    • ldms_dstat_schema_name
    • all_example
    • array_example
    • synthetic
    • file_importer
    • filesingle
    • ldms-sensors-config
    • fptrans
    • ldms_msg_sampler
    • hello_sampler
    • hweventpapi
    • ibmad_records_sampler
    • ibmad_sampler
    • ldms-ibnet-sampler-gen
    • ibnet
    • ldms_ibnet_schema_name
    • json_stream_sampler
    • kgnilnd
    • jobid
    • ldms_sampler_base
    • edac
    • lnet_stats
    • loadavg
    • lustre2_client
    • lustre_mdc
    • lustre_client
    • lustre_mdt
    • lustre_ost
    • meminfo
    • msr_interlagos
    • netlink-notifier
    • opa2
    • papi_sampler
    • For perfevent2 example
    • perfevent
    • perfevent2
    • procdiskstats
    • procinterrupts
    • procnet
    • procnetdev
    • procnetdev2
    • procnfs
    • procstat
    • procstat2
    • rapl
    • rdc_sampler
    • ldms_rdc_schema_name
    • sampler_atasmart
    • shm_sampler
    • slingshot_info
    • slingshot_metrics
    • slurm_sampler
    • slurm_notifier
    • sysclassib
    • syspapi_sampler
    • tx2mon
    • variable
    • vmstat
    • zfs_leafvdevs
    • zfs_topvdevs
    • zfs_zpool
• Contributing
  • store
    • store_timescale
    • store_tutorial
  • sampler
    • daos_sampler
    • geopm_sampler
    • ipmireader
    • ipmisensors
    • tutorial_sampler
    • variorum_sampler
• Third-plugins
  • my_plugin
    • Man page for the LDMS my_plugin plugin

Contributing to LDMS

• How to write an LDMS Sampler Plugin
• How to write an LDMS Store Plugin
• Documentation For RST Generation
  • Man Pages
  • Test Your Changes
  • Edits To Other Files

To join the LDMS Users Group Mailing List: https://github.com/ovis-hpc/ovis-wiki/wiki/Mailing-Lists

OVIS Subproject Github Repositories

• ldms

• ovis-publications

• maestro

• sos

• baler

• containers

• ovis-publications