You might need to understand cluster throughput in your Dell Isilon (network attached storage) NAS when doing the following:
Prerequisites
In order to execute this procedure in your environment, the following data, services, or apps are required:
Example
A bottleneck in an application’s throughput can produce latency spikes, meaning users can no longer interact with the storage system in real-time. A plateau in throughput usually indicates you’ve saturated your infrastructure in some respect. You would like an aggregation of the throughput being consumed by your Isilon cluster.
NOTE: To optimize the search shown below, you should specify an index and a time range.
- Run the following search:
sourcetype=emc:isilon:* stats.key=ifs.bytes.*.rate Cluster_Name="<name of cluster>"
| eval {stats.key}='stats.value'
| timechart span=15m p99(ifs.bytes.*) AS ifs.bytes.*
Search explanation
The table provides an explanation of what each part of this search achieves. You can adjust this query based on the specifics of your environment.
|
Splunk Search |
Explanation |
|
sourcetype=emc:isilon:* |
Search only EMC Isilon data. |
|
stats.key=ifs.bytes.*.rate |
Search for events where the stats key is set to "ifs.bytes.in.rate" or "ifs.bytes.out.rate", which describe the cumulative throughput rate on the Isilon file system (IFS). |
|
Cluster_Name="<name of cluster>" |
Enter the cluster name here to limit the search to a specific cluster. You can also omit this filter entirely and get the metric for all the clusters. |
|
| eval {stats.key}='stats.value' |
Assign the stats value to each unique stats.key. In this example we have two eval fields, one for in and one for the in.rate and one for the out.rate. |
|
| timechart span=15m p99(ifs.bytes.*) AS ifs.bytes.* |
Graph the results in fifteen minute increments. |
Result
This search produces a time chart that shows throughput values in the 99th percentile for both bytes in, which are writes, and bytes out, which are reads.
Comments
0 comments
Please sign in to leave a comment.