Retrieve NVMe protocol historical performance metrics
GET /protocols/nvme/services/{svm.uuid}/metrics
Introduced In: 9.7
Retrieves historical performance metrics for NVMe protocol of an SVM.
Parameters
Name | Type | In | Required | Description |
---|---|---|---|---|
status |
string |
query |
False |
Filter by status |
iops.other |
integer |
query |
False |
Filter by iops.other |
iops.read |
integer |
query |
False |
Filter by iops.read |
iops.write |
integer |
query |
False |
Filter by iops.write |
iops.total |
integer |
query |
False |
Filter by iops.total |
tcp.iops.other |
integer |
query |
False |
Filter by tcp.iops.other
|
tcp.iops.read |
integer |
query |
False |
Filter by tcp.iops.read
|
tcp.iops.write |
integer |
query |
False |
Filter by tcp.iops.write
|
tcp.iops.total |
integer |
query |
False |
Filter by tcp.iops.total
|
tcp.latency.other |
integer |
query |
False |
Filter by tcp.latency.other
|
tcp.latency.read |
integer |
query |
False |
Filter by tcp.latency.read
|
tcp.latency.write |
integer |
query |
False |
Filter by tcp.latency.write
|
tcp.latency.total |
integer |
query |
False |
Filter by tcp.latency.total
|
tcp.duration |
string |
query |
False |
Filter by tcp.duration
|
tcp.status |
string |
query |
False |
Filter by tcp.status
|
tcp.throughput.write |
integer |
query |
False |
Filter by tcp.throughput.write
|
tcp.throughput.total |
integer |
query |
False |
Filter by tcp.throughput.total
|
tcp.throughput.read |
integer |
query |
False |
Filter by tcp.throughput.read
|
fc.iops.other |
integer |
query |
False |
Filter by fc.iops.other
|
fc.iops.read |
integer |
query |
False |
Filter by fc.iops.read
|
fc.iops.write |
integer |
query |
False |
Filter by fc.iops.write
|
fc.iops.total |
integer |
query |
False |
Filter by fc.iops.total
|
fc.latency.other |
integer |
query |
False |
Filter by fc.latency.other
|
fc.latency.read |
integer |
query |
False |
Filter by fc.latency.read
|
fc.latency.write |
integer |
query |
False |
Filter by fc.latency.write
|
fc.latency.total |
integer |
query |
False |
Filter by fc.latency.total
|
fc.duration |
string |
query |
False |
Filter by fc.duration
|
fc.status |
string |
query |
False |
Filter by fc.status
|
fc.throughput.write |
integer |
query |
False |
Filter by fc.throughput.write
|
fc.throughput.total |
integer |
query |
False |
Filter by fc.throughput.total
|
fc.throughput.read |
integer |
query |
False |
Filter by fc.throughput.read
|
latency.other |
integer |
query |
False |
Filter by latency.other |
latency.read |
integer |
query |
False |
Filter by latency.read |
latency.write |
integer |
query |
False |
Filter by latency.write |
latency.total |
integer |
query |
False |
Filter by latency.total |
duration |
string |
query |
False |
Filter by duration |
throughput.write |
integer |
query |
False |
Filter by throughput.write |
throughput.total |
integer |
query |
False |
Filter by throughput.total |
throughput.read |
integer |
query |
False |
Filter by throughput.read |
timestamp |
string |
query |
False |
Filter by timestamp |
svm.uuid |
string |
path |
True |
Unique identifier of the SVM. |
interval |
string |
query |
False |
The time range for the data. Examples can be 1h, 1d, 1m, 1w, 1y. The period for each time range is as follows:
|
return_timeout |
integer |
query |
False |
The number of seconds to allow the call to execute before returning. When iterating over a collection, the default is 15 seconds. ONTAP returns earlier if either max records or the end of the collection is reached.
|
fields |
array[string] |
query |
False |
Specify the fields to return. |
max_records |
integer |
query |
False |
Limit the number of records returned. |
order_by |
array[string] |
query |
False |
Order results by specified fields and optional [asc |
desc] direction. Default direction is 'asc' for ascending. |
return_records |
boolean |
query |
False |
Response
Status: 200, Ok
Name | Type | Description |
---|---|---|
_links |
||
num_records |
integer |
Number of records |
records |
array[records] |
Example response
{
"_links": {
"next": {
"href": "/api/resourcelink"
},
"self": {
"href": "/api/resourcelink"
}
},
"records": [
{
"_links": {
"self": {
"href": "/api/resourcelink"
}
},
"duration": "PT15S",
"fc": {
"duration": "PT15S",
"iops": {
"read": 200,
"total": 1000,
"write": 100
},
"latency": {
"read": 200,
"total": 1000,
"write": 100
},
"status": "ok",
"throughput": {
"read": 200,
"total": 1000,
"write": 100
}
},
"iops": {
"read": 200,
"total": 1000,
"write": 100
},
"latency": {
"read": 200,
"total": 1000,
"write": 100
},
"status": "ok",
"svm": {
"uuid": "02c9e252-41be-11e9-81d5-00a0986138f7"
},
"tcp": {
"duration": "PT15S",
"iops": {
"read": 200,
"total": 1000,
"write": 100
},
"latency": {
"read": 200,
"total": 1000,
"write": 100
},
"status": "ok",
"throughput": {
"read": 200,
"total": 1000,
"write": 100
}
},
"throughput": {
"read": 200,
"total": 1000,
"write": 100
},
"timestamp": "2017-01-25T11:20:13Z"
}
]
}
Error
Status: Default, Error
Name | Type | Description |
---|---|---|
error |
Example error
{
"error": {
"arguments": [
{
"code": "string",
"message": "string"
}
],
"code": "4",
"message": "entry doesn't exist",
"target": "uuid"
}
}
Definitions
See Definitions
href
Name | Type | Description |
---|---|---|
href |
string |
_links
Name | Type | Description |
---|---|---|
next |
||
self |
_links
Name | Type | Description |
---|---|---|
self |
iops
The rate of I/O operations observed at the storage object.
Name | Type | Description |
---|---|---|
other |
integer |
Performance metric for other I/O operations. Other I/O operations can be metadata operations, such as directory lookups and so on. |
read |
integer |
Performance metric for read I/O operations. |
total |
integer |
Performance metric aggregated over all types of I/O operations. |
write |
integer |
Peformance metric for write I/O operations. |
latency
The round trip latency in microseconds observed at the storage object.
Name | Type | Description |
---|---|---|
other |
integer |
Performance metric for other I/O operations. Other I/O operations can be metadata operations, such as directory lookups and so on. |
read |
integer |
Performance metric for read I/O operations. |
total |
integer |
Performance metric aggregated over all types of I/O operations. |
write |
integer |
Peformance metric for write I/O operations. |
throughput
The rate of throughput bytes per second observed at the storage object.
Name | Type | Description |
---|---|---|
read |
integer |
Performance metric for read I/O operations. |
total |
integer |
Performance metric aggregated over all types of I/O operations. |
write |
integer |
Peformance metric for write I/O operations. |
fc
The NVMe/FC portion of the aggregated metrics.
Name | Type | Description |
---|---|---|
duration |
string |
The duration over which this sample is calculated. The time durations are represented in the ISO-8601 standard format. Samples can be calculated over the following durations: |
iops |
The rate of I/O operations observed at the storage object. |
|
latency |
The round trip latency in microseconds observed at the storage object. |
|
status |
string |
Any errors associated with the sample. For example, if the aggregation of data over multiple nodes fails then any of the partial errors might be returned, "ok" on success, or "error" on any internal uncategorized failure. Whenever a sample collection is missed but done at a later time, it is back filled to the previous 15 second timestamp and tagged with "backfilled_data". "Inconsistent_ delta_time" is encountered when the time between two collections is not the same for all nodes. Therefore, the aggregated value might be over or under inflated. "Negative_delta" is returned when an expected monotonically increasing value has decreased in value. "Inconsistent_old_data" is returned when one or more nodes do not have the latest data. |
throughput |
The rate of throughput bytes per second observed at the storage object. |
svm
Name | Type | Description |
---|---|---|
uuid |
string |
The unique identifier of the SVM. |
tcp
The NVMe/TCP portion of the aggregated metrics.
Name | Type | Description |
---|---|---|
duration |
string |
The duration over which this sample is calculated. The time durations are represented in the ISO-8601 standard format. Samples can be calculated over the following durations: |
iops |
The rate of I/O operations observed at the storage object. |
|
latency |
The round trip latency in microseconds observed at the storage object. |
|
status |
string |
Any errors associated with the sample. For example, if the aggregation of data over multiple nodes fails then any of the partial errors might be returned, "ok" on success, or "error" on any internal uncategorized failure. Whenever a sample collection is missed but done at a later time, it is back filled to the previous 15 second timestamp and tagged with "backfilled_data". "Inconsistent_ delta_time" is encountered when the time between two collections is not the same for all nodes. Therefore, the aggregated value might be over or under inflated. "Negative_delta" is returned when an expected monotonically increasing value has decreased in value. "Inconsistent_old_data" is returned when one or more nodes do not have the latest data. |
throughput |
The rate of throughput bytes per second observed at the storage object. |
records
Performance numbers, such as IOPS latency and throughput, for SVM protocols.
Name | Type | Description |
---|---|---|
_links |
||
duration |
string |
The duration over which this sample is calculated. The time durations are represented in the ISO-8601 standard format. Samples can be calculated over the following durations: |
fc |
The NVMe/FC portion of the aggregated metrics. |
|
iops |
The rate of I/O operations observed at the storage object. |
|
latency |
The round trip latency in microseconds observed at the storage object. |
|
status |
string |
Any errors associated with the sample. For example, if the aggregation of data over multiple nodes fails then any of the partial errors might be returned, "ok" on success, or "error" on any internal uncategorized failure. Whenever a sample collection is missed but done at a later time, it is back filled to the previous 15 second timestamp and tagged with "backfilled_data". "Inconsistent_ delta_time" is encountered when the time between two collections is not the same for all nodes. Therefore, the aggregated value might be over or under inflated. "Negative_delta" is returned when an expected monotonically increasing value has decreased in value. "Inconsistent_old_data" is returned when one or more nodes do not have the latest data. |
svm |
||
tcp |
The NVMe/TCP portion of the aggregated metrics. |
|
throughput |
The rate of throughput bytes per second observed at the storage object. |
|
timestamp |
string |
The timestamp of the performance data. |
error_arguments
Name | Type | Description |
---|---|---|
code |
string |
Argument code |
message |
string |
Message argument |
error
Name | Type | Description |
---|---|---|
arguments |
array[error_arguments] |
Message arguments |
code |
string |
Error code |
message |
string |
Error message |
target |
string |
The target parameter that caused the error. |