1
0
Fork 0
nvme-cli/Documentation/nvme-solidigm-workload-tracker.txt
Daniel Baumann 65508f0a28
Adding upstream version 2.11.
Signed-off-by: Daniel Baumann <daniel@debian.org>
2025-02-16 12:28:14 +01:00

104 lines
No EOL
3.2 KiB
Text

nvme-solidigm-workload-tracker(1)
=================================
NAME
----
nvme-solidigm-workload-tracker - Real-time capture of Workload Tracker samples
SYNOPSIS
--------
[verse]
'nvme solidigm workload-tracker' <device> [--enable | -e] [--disable | -d]
[--sample-time=<time> | -s <time>]
[--type=<type> | -t <type>]
[--run-time=<seconds> | -r <seconds>]
[--flush-freq=<count> | -f <count>]
[--wall-clock | -w]
[--trigger-field=<field> | -T <field>]
[--trigger-threshold=<value> | -V <value>]
[--trigger-on-delta | -D]
[--trigger-on-latency | -L]
[--verbose | -v]
DESCRIPTION
-----------
Captures and displays real-time workload tracker samples for the given Solidigm
NVMe device. This command allows for monitoring and analysis of the device's
workload characteristics.
The <device> parameter is mandatory and may be either the NVMe character
device (ex: /dev/nvme0), or a namespace block device (ex: /dev/nvme0n1).
OPTIONS
-------
-e, --enable::
Enable the workload tracker before capturing samples.
-d, --disable::
Disable the workload tracker after capturing samples.
-s <time>, --sample-time=<time>::
Set the sample interval. Valid values are: default, 1ms, 5ms, 10ms, 50ms, 100ms, 500ms, 1s, 5s, 10s, 30s, 1m, 5m, 10m, 30m, 1h.
-t <type>, --type=<type>::
Set the tracker type. Valid types are: Base, CmdQ, Pattern, RandSeq, Throttle, Power, Defrag.
-r <seconds>, --run-time=<seconds>::
Limit runtime capture time in seconds.
-f <count>, --flush-freq=<count>::
Number of samples (1 to 126) to wait before extracting data. Default is 100 samples.
-w, --wall-clock::
Log current wall timestamp when entry was retrieved.
-T <field>, --trigger-field=<field>::
Field name to stop trigger on.
-V <value>, --trigger-threshold=<value>::
Field value to trigger stop sampling.
-D, --trigger-on-delta::
Trigger on delta to stop sampling.
-L, --trigger-on-latency::
Use latency tracker to trigger stop sampling.
-v, --verbose::
Increase logging verbosity. Can be used multiple times.
EXAMPLES
--------
* Enable the workload tracker and capture samples:
+
------------
# nvme solidigm workload-tracker /dev/nvme0 --enable
------------
* Capture workload tracker samples with a 1ms interval for 60 seconds:
+
------------
# nvme solidigm workload-tracker /dev/nvme0 --enable --sample-time=1ms --run-time=60
------------
* Disable the workload tracker:
+
------------
# nvme solidigm workload-tracker /dev/nvme0 --disable
------------
* Enable the workload tracker and capture samples with a specific sample time and type:
+
------------
# nvme solidigm workload-tracker /dev/nvme0 --enable --sample-time=1ms --type=Base
------------
* Capture Power tracker samples with a 10-second interval for 5 minutes:
+
------------
# nvme solidigm workload-tracker /dev/nvme0 --enable --type=Power --sample-time=10s --run-time=300
------------
NVME
----
Part of the nvme-user suite