Requirement
Name | |
1.0 | Uses APIs available with libpmwapi in Intel® PMWatch v3.0 or above |
| 2.0 | Uses libipmctl v01.00.00.3262 or above |
| 3.0 | Uses DCPMM DIMM firmware v01.00.00.5127 or above |
| 4.0 | Should have configurable metrics group selection |
| 5.0 | Should have configurable collection interval |
Overview
Collectd DCPMM plugin monitors Intel® Optane™ DC Persistent Memory and provides memory performance and health information metrics.
Design
dcpmm plugin
The dcpmm plugin collects memory performance, health information metrics and timestamp information listed below.
Name | Type | Type Instance | Description | Comment |
|---|---|---|---|---|
| Memory performance metrics | ||||
| total_bytes_read | media | total_bytes_read | Number of bytes transacted by the read operations | |
| total_bytes_written | media | total_bytes_written | Number of bytes transacted by the write operations | |
| read_64B_ops_rcvd | media | read_64B_ops_rcvd | Number of read operations performed to the physical media in 64 bytes granularity | |
| write_64B_ops_rcvd | media | write_64B_ops_rcvd | Number of write operations performed to the physical media in 64 bytes granularity | |
| media_read_ops | media | media_read_ops | Number of read operations performed to the physical media | |
| media_write_ops | media | media_write_ops | Number of write operations performed to the physical media | |
| host_reads | controller | host_reads | Number of read operations received from the CPU (memory controller) | |
| host_writes | controller | host_writes | Number of write operations received from the CPU (memory controller) | |
| read_hit_ratio | buffer | read_hit_ratio | Measures the efficiency of the buffer in the read path. Range of 0.0 - 1.0 | |
| write_hit_ratio | buffer | write_hit_ratio | Measures the efficiency of the buffer in the write path. Range of 0.0 - 1.0 | |
| Health information metrics | ||||
| health_status | health | health_status | Overall health summary (0: normal | 1: non-critical | 2: critical | 3: fatal) | |
| lifespan_remaining | health | lifespan_remaining | The module’s remaining life as a percentage value of factory expected life span | |
| lifespan_used | health | lifespan_used | The module’s used life as a percentage value of factory expected life span | |
| power_on_time | health | power_on_time | The lifetime the DIMM has been powered on in seconds | |
| uptime | health | uptime | The current uptime of the DIMM for the current power cycle in seconds | |
| last_shutdown_time | health | last_shutdown_time | The time the system was last shutdown. The time is represented in epoch (seconds) | |
| media_temperature | health | media_temperature | The media’s current temperature in degrees Celsius | |
| controller_temperature | health | controller_temperature | The controller’s current temperature in degrees Celsius | |
| max_media_temperature | health | max_media_temperature | The media’s the highest temperature reported in degrees Celsius | |
| max_controller_temperature | health | max_controller_temperature | The controller’s highest temperature reported in degrees Celsius | |
| Timestamp | ||||
| tsc_cycles | timestamp | tsc_cycles | The number of tsc cycles during each interval | |
| epoch | timestamp | epoch | The timestamp in seconds at which the metrics are collected from DCPMM DIMMs | |
Plugin configuration
The following configuration options should be supported by dcpmm collectd plugin:
Name | Description | Comment |
|---|---|---|
Interval | The collection interval in seconds at which the metric counts are collected | Defaults to global Interval value. This will override the global Interval value for dcpmm plugin. None of the other plugins will be affected. |
CollectHealth | Health information metrics will be collected if set to true | Default value is false. |
CollectdPerfMetrics | Memory performance metrics will be collected if set to true | Default value is true. |
EnableDispatchAll | This parameter helps to seamlessly enable simultaneous health and memory performance metrics collection in future. | This is unused at the moment and must always be false. |
Here is an example of the plugin configuration section of collectd.conf file:
<Plugin dcpmm> Interval 10.0 CollectHealth false CollectPerfMetrics true EnableDispatchAll false</Plugin>
Implementation details
To enable monitoring of Intel® Optane™ DC Persistent Memory, APIs provided by Intel® PMWatch is used. This is an open source tool and is available at https://github.com/intel/intel-pmwatch.
The following diagram shows the high level architecture of dcpmm plugin.
plugin API | libpmwapi API | Description |
|---|---|---|
dcpmm_config | Parse configuration provided in collectd.conf and register read callback if the correct configuration is provided | |
dcpmm_init | PMWAPIGetDIMMCount | Obtain the number of DCPMM DIMMs |
PMWAPIStart | Passes the configuration and starts the collection | |
dcpmm_read | PMWAPIRead | Reads the metric values |
dcpmm_shutdown | PMWAPIStop | Stops the collection |
Considerations
Configuration Considerations
The recommended collection interval is 1 second or above.
Deployment Considerations
If Intel® Optane™ DC Persistent Memory (DCPMM) is not available in the system, the plugin will be unloaded during initialization callback.
API/GUI/CLI Considerations
Equivalence Considerations
Security Considerations
Alarms, events, statistics considerations
Redundancy Considerations
Performance Considerations
The recommended collection interval is 1 second or above.
Testing Consideration
The timing interval requirement needs to be taken into consideration when conducting tests.
The Tests should be carried out on a system underload as well as a relatively idle system.
Other Considerations
Impact
The following table outlines possible impact(s) the deployment of this deliverable may have on the current system.
Ref | System Impact Description | Recommendation / Comments |
1 |
Key Assumptions
The following assumptions apply to the scope specified in this document.
Ref | Assumption | Status |
1 |
Key Exclusions
The following exclusions apply to the scope discussed in this document.
Ref | Exclusion | Status |
1 |