View NetApp Storage Real-time performance statistics using the statistics command

Cluster-mode, new command-line tools are introduced to view detailed storage system performance metrics that are especially useful for storage system diagnostics.

650) this.width=650; "title=" lamp "style=" border-top:0px; border-right:0px; Background-image:none; border-bottom:0px; padding-top:0px; padding-left:0px; border-left:0px; padding-right:0px "border=" 0 "alt=" lamp "src=" http://s3.51cto.com/wyfs02/M01/8F/99/  Wkiom1jmd0egpowhaaae7zufeim380.png "" "height="/> Note: Use this command to enter advanced mode, SSH login storage CLI Environment, execute command: Set–privilege Advanced Reference 1:

650) this.width=650; "title=" image "style=" border-top:0px; border-right:0px; Background-image:none; border-bottom:0px; padding-top:0px; padding-left:0px; border-left:0px; padding-right:0px "border=" 0 "alt=" image "src=" http://s3.51cto.com/wyfs02/M01/8F/99/wKiom1jmD0fSBI_ Jaab9cgkg-m0065.png "" 883 "height=" 118 "/>

Figure 1

Overview of how commands are used

You can use the command statistics show-periodic to view an overview of the current system's performance metrics in real time.

650) this.width=650; "title=" image "style=" border-top:0px; border-right:0px; Background-image:none; border-bottom:0px; padding-top:0px; padding-left:0px; border-left:0px; margin:0px; padding-right:0px "border=" 0 "alt=" image "src=" http://s3.51cto.com/wyfs02/M01/8F/97/ Wkiol1jmd0qixdaaaaoh7ozdzh4025.png "" 1189 "height=" 561 "/>

Figure 2

Sample Collection

You can also use the command statistics start |stop to collect performance parameters for a period of time, and then output the collected sample performance parameters through the statistics show command.

Example 1: Collect CPU utilization. by command:

Statistics Start–object Processor–sample-id smp_1

Statistics Start–object Disk–sample-id smp_2

Starts collecting performance parameters for processor objects. -sample-id to collect sample numbers, the system can collect multiple samples at the same time. If you do not specify this parameter manually, the system will automatically specify the number. In Example 1 above, a performance collection of 2 samples for 2 objects was started, and multiple object performance indicators, such as commands, can be collected in one sample:

Statistics Start–object Processor|disk–sample-id smp_1

Collection of performance metrics for processor and disk objects at the same time in sample Smp_1

Sample Show

by command:

Statistics Show–object Processor

Can show the collected sample data, such as 3

650) this.width=650; "title=" image "style=" border-top:0px; border-right:0px; Background-image:none; border-bottom:0px; padding-top:0px; padding-left:0px; border-left:0px; padding-right:0px "border=" 0 "alt=" image "src=" http://s3.51cto.com/wyfs02/M02/8F/99/ Wkiom1jmd0rquun9aaee4qdgq0g015.png "" 1017 "height=" 484 "/>

Figure 3

You can even add filter conditions:

Statistics Show–object processor–filter "node_name=cluster1-01"

Filter out CPU performance data for node "cluster1-01"

Statistics Show–object processor–filter "processor_busy>80"

Filter out performance data with CPU utilization above 80%

Stop Sample Collection

Sample collection needs to consume system performance and not stop collection after use.

Statistics Stop–sample-id smp_1

Statistics Stop–sample-id smp_2

command StructureObject

statistics show is able to show the performance parameters of each object in the storage system. The Statistics Catalog object show lets you list the objects contained in the system, such as processor (each core of the CPU), disk (each physical disk), and so on.

Instance

Statistics Catalog Instance show–object "objectname" lists the running instances of the object.

Example 4: If 4, run the command:

Statistics Catalog Instance Show–object processor

The Display object processor has four instances running, that is, the storage system has 4 cores.

650) this.width=650; "title=" image "style=" border-top:0px; border-right:0px; Background-image:none; border-bottom:0px; padding-top:0px; padding-left:0px; border-left:0px; padding-right:0px "border=" 0 "alt=" image "src=" http://s3.51cto.com/wyfs02/M02/8F/97/ Wkiol1jmd0vggkiqaacjkvhnslg580.png "" 923 "height=" 222 "/>

Figure 4

Example 5: If 5, run the command:

Statistics Catalog Instance Show–object disk

Display object disk has 20 instances running, that is, the storage system has 20 of disks.

650) this.width=650; "title=" image "style=" border-top:0px; border-right:0px; Background-image:none; border-bottom:0px; padding-top:0px; padding-left:0px; border-left:0px; padding-right:0px "border=" 0 "alt=" image "src=" http://s3.51cto.com/wyfs02/M02/8F/99/wKiom1jmEEzQKY__ Aaewxnmdsg0477.png "" 777 "height=" 626 "/>

Figure 5

Counter

There are multiple performance counters for each object, and you can list performance counters for related objects by command statistics catalog counter show–object "objectname"

Example 6: If 6, run the command:

Statistics Catalog Counter Show–object processor

Display Object processor has 8 performance counters

650) this.width=650; "title=" image "style=" border-top:0px; border-right:0px; Background-image:none; border-bottom:0px; padding-top:0px; padding-left:0px; border-left:0px; padding-right:0px "border=" 0 "alt=" image "src=" http://s3.51cto.com/wyfs02/M00/8F/97/ Wkiol1jmd07btkv1aaghwteyswa461.png "" 917 "height=" 381 "/>

Figure 6

Example 7:

Statistics Show–object processor–instance processor0–counter processor_busy|sk_switches

such as 7, the command lists the performance indicators of the Processor0 processor_busy and sk_switches counters

650) this.width=650; "title=" image "style=" border-top:0px; border-right:0px; Background-image:none; border-bottom:0px; padding-top:0px; padding-left:0px; border-left:0px; padding-right:0px "border=" 0 "alt=" image "src=" http://s3.51cto.com/wyfs02/M01/8F/99/ Wkiom1jmd06jzes4aadnxq8gg1o706.png "" 868 "height=" 436 "/>

Figure 7

CPU Usage

Refer to Figure 3 and Figure 7

Latency

Use the command:

Statistics Disk Show

To query the latency of each disk, refer to Figure 8

You can also view the delay for a Aggregate/volume/lun

Collect samples of Aggregate/volume/lun:

Statistics Start–object Aggregate|volume|lun

Query sample data, you can see the deferred data

650) this.width=650; "title=" image "style=" border-top:0px; border-right:0px; Background-image:none; border-bottom:0px; padding-top:0px; padding-left:0px; border-left:0px; padding-right:0px "border=" 0 "alt=" image "src=" http://s3.51cto.com/wyfs02/M02/8F/99/ Wkiom1jmd0-yp0ataafxwhhrejk323.png "" 748 "height=" 543 "/>

Figure 8

Disk Busy level

Use the Statistics Disk Show command to view the throughput and latency metrics for the disk, which will continue to output disk performance metrics, and the following are the related columns for command line output:

disk	disk name
node	disk belongs to storage node name
busy "(%)	disk has a time ratio of IO operations to measure the disk's busy level
total Ops	Total disk operations over the sampling time, approximate iops
read Ops	disk read operation during sampling time
write Ops	disk write operation during sampling time
read" (Bps)	Read bytes per second
write" (Bps)
latency" (US)	delay (subtle)

This command does not require sample data collection

The following is the result output of the command run

650) this.width=650; "title=" image "style=" border-top:0px; border-right:0px; Background-image:none; border-bottom:0px; padding-top:0px; padding-left:0px; border-left:0px; padding-right:0px "border=" 0 "alt=" image "src=" http://s3.51cto.com/wyfs02/M02/8F/99/ Wkiom1jmee2t6bjeaait8ewgkku228.png "" 711 "height=" 594 "/>

Figure 9

IOPS

Refer to Figure 2, 8, 9, query ioPS

Cifs/nfs operation

Querying the most active users (Cifs/nfs read and write operations with the largest number of users)

Cluster1::* > Statistics Top client Show
cluster1:12/27/2016 01:33:56
*total
Client Vserver Node Protocol Ops
------------- ------------ -----------                    --------  ------
192.168.0.253 CIFS_NFS_SVM cluster1-01 CIFS 5145
192.168.0.61 CIFS_NFS_SVM cluster1-02 CIFS 815
192.168.0.70 CIFS_NFS_SVM cluster1-02 CIFS 200

Query the most accessed files (10 by default)

650) this.width=650; "title=" image "style=" border-top:0px; border-right:0px; Background-image:none; border-bottom:0px; padding-top:0px; padding-left:0px; border-left:0px;  padding-right:0px "border=" 0 "alt=" image "src=" http://s3.51cto.com/wyfs02/M00/8F/98/ Wkiol1jmehthhlcmaagy6cyeliu377.png "" 1130 "height=" 322 "/>

System Background Process resource consumption

by command:

Statistics workload Show

can query to which load the current system resources are primarily consumed

650) this.width=650; "title=" image "style=" border-top:0px; border-right:0px; Background-image:none; border-bottom:0px; padding-top:0px; padding-left:0px; border-left:0px; padding-right:0px "border=" 0 "alt=" image "src=" http://s3.51cto.com/wyfs02/M01/8F/97/ Wkiol1jmd1gs0keeaagqcgkhge4649.png "" 573 "height=" 783 "/>

View NetApp Storage Real-time performance statistics using the statistics command