Find Communities by: Category | Product

PowerMax

May 2018 Previous month Next month

Customers has told us the heat map is still popular and they like a physical representation of how busy the array is like we see here below. The variance in colors represents utilization levels. Clicking on a square will give you further metrics relevant to that object and you can drill down further on this if you wish.

 

17.PNG.png

 

In this release we have included a planning ability whereby you can project potentially how busy an object will be based on current usage out to 6 months, this will allow customers to place their workload on ports that are not expected to be busy over the coming months which should stop performance problems from even occurring.

 

18.PNG.png

 

Additionally we have allowed you to filter based on storage group. In a troubleshooting scenario you can easily select your storage group such as irco2sd15 here and filter the heat map based on the Fa’s that storage group is mapped down just as we see here:

 

19.PNG.png

 

20.PNG.png

 

Finally we allow users to drill down on specific objects within the heat map as required, here that director 2B is turning red and is quite busy so if we hover over and select it we get a picture of how busy it has been over the last 4 hours. If we wish to navigate to analyse or charts we can so from here and it lands us here in context with that particular director already selected.

 

The Reports section has not changed much in terms of content but it’s presented in a more consumable format. You can produce a report on demand on items such as capacity or you can choose to schedule it to be run at a certain time. Finally if you want a report to be emailed to you or a colleague you can also configure this.

 

21.PNG.png

 

The plan section displays predicted future data, based on linear projection. You can use the information contained in the projection dashboard to assist when planning and to avoid potential problems. It allows you to estimate and chart capacity growth based on your SRP or your thin pool.

 

It will give you a days to full value and a capacity figure over the course of 1 week, 1 month, 3 months and 6 months. You do require 10 days of performance data in order to generate this chart but it is a really powerful tool for storage administrators who want to view and chart their capacity consumption.

 

22.PNG.png

 

Here we are focused on SRP1 and a 6 month time frame, in the chart the yellow line represents the projected capacity growth for this box based on current capacity usage. Also highlighted in red we see are given a days to full value based on current trends.

 

For a video outlying these properties see here: https://www.youtube.com/edit?o=U&video_id=ZIBbvDULdhQ

 

I hope you found this useful and if you have any questions please let me know.

The Analyse section provides 3 views into your storage data. You can use real time and diagnostic views to debug and find causes for performance problems. You can then use historical to show long term trends and plan for future needs.

 

  • Real Time – Collects Data between 2 and 5 seconds for a limited set of metrics at an array level and is available for 1 hour.
  • Diagnostic – Collects data every 5 minutes for Root cause analysis and is available for the previous 7 days.
  • Historical – Collects data every 15 minutes and is available for the previous year.

 

Real Time is focused on an array level view where your focus is on FE/BE Directors and RDF Directors, you can also look at external directors if desired.

 

11.PNG.png

 

As highlighted in red you have the ability to capture a trace if required and display it in the charts section so you have a visual picture of your performance. Bear in mind this is displaying metrics at between 2-5 seconds so it offers you an insight into how the box is behaving at present in a really granular format. To capture the trace you merely select the individual director or all of the directors and then select capture trace.


12.PNG.png


To display this trace in a chart you merely change views to the charting section and select real time and then trace and you have the option to select 9 KPI’s related to directors so you can focus on metrics like BE IO’s per sec and % Cache WP.

Diagnostic provides high-level data about all the storage systems. The specific information depends on the models of the selected storage arrays.

 

13.PNG.png

 

Highlighted in red to the left we have the category of objects that we can select and drill down on. The list is ranked in terms of how busy the SG based across the values displayed. To the right you have the ability to change the time frame from 4 out to 24 hours. Additionally with this list having over 500 objects you have the ability to filter on it if you require.

 

I wanted to go over some of the potential use cases also here which will aid you in your troubleshooting. Typically when a storage administrator begins a performance troubleshooting task their starting point from an application perspective is the host.

 

14.PNG.png

 

To do this quickly we can leverage the Analyze section to select hosts and our scope is the last 12 hours, in this particular example the application owner is running on host irco2sd15 and although the host IO’s/Sec and host MBs/Sec are high the host is meeting its response time as we are green in the 3rd column.

A very useful section here is the events and alerts piece if selected it gives you a view into what events and alerts occurred in the last 24 hours.

 

15.PNG.png

 

Here we have the ability to go back to the last 24 hours and also customize the view so if we have a large number of configuration changes we can select a certain timeframe such as 2:00 to 2:30 last night. For this example I have received a call that someone has lost access to their host CA and so I can look back to the changes and I notice that someone ran a delete operation on the port group CA which might explain the loss of service.

 

Finally we have the Historical view which provides high-level data about all storage systems. This allows you to take a more long term view of how certain elements in your storage array have been performing over a longer time frame going back to 12 months. I just wanted to show you 1 potential use case here for a host.

 

16.PNG.png

 

You can see by the breadcrumb selection that I have drilled to focus on the initiator ports 1D and 3D as while investigating a performance problem with a host the application owner mentioned that performance has been slow for some time. Focusing on the response time for these FA’s we can see that over the course of the last 12 months it has been within expected parameters.

 

I hope you found this helpful, if you have any questions please let me know.

With HTML5 we have made significant improvements in the charting section which offers our customers a greater deal of functionality in allowing more flexibility in how they interact with the product combined with a reduction in the time spent identifying potential Array performance problems.

 

This release is significantly different from the previous in terms of layout and usage so I wanted to touch on certain key elements before I delved into some of the potential use cases.

 

6.PNG.png

 

You have the ability to name the chart if you wish but it’s optional, in the timeframe drop down you have the following options:

Realtime – the last hour at 30 second granularity for up to 5 SG’s at a time on 1 array covering certain KPI’s or run a trace at the system level.

 

Diagnostic – 1, 2, 4, 8, 12, 24 hours or customizable allowing you to focus on a certain timeframe such as 03:15 – 03:45 a.m. last night.

 

Historical – last 24 hours, last week, last month, last 6 months, last 12 months or customizable allowing you to focus on a certain timeframe such as 12:00 – 05:00 on the 24th of last month.

 

In Objects you have the ability to select from Array, Storage & Hosts, Directors & Ports, Storage Resources, Data Protection and System internals where by you can focus on the specific category you need to target.

If you notice the radio button highlighted in red we have given you the ability to toggle between average and max values here. Also in the metric list section you can choose just to display KPI Metrics or all metrics.

 

Additionally for the icons below the default tab I wanted to outline and explain what their function is:

 

7.PNG.png

 

  • Save as Template – allows you to save it as a template if you need to focus on certain KPI Metrics for a particular object like metadata usage on an array.
  • Save as PDF – Charts – This allows you to save a chart and send it to a colleague in a visual format if you want to illustrate a certain pattern like capacity growth in a the last month.
  • Save as PDF – Charts & Data – like above this gives you back the visual charts and also the figures behind that.
  • Copy Charts to a Tab – allows you to copy charts over to a different tab while retaining the originals in the current tab
  • Move Charts to a Tab – allows you to move charts completely over to a different tab

 

8.PNG.png

 

In the previous version of the software the navigation was along the top of the screen but we have changed this to a left hand side navigation view so customers can more easily interact with the product. In this example I have created a chart called PerfIssue03/20 whereby I have selected the timeframe of the last 4 hours for the array 0647 and selected the KPI’s % reads and % Writes and drew my chart accordingly.

 

As a potential use case let’s say we were focusing on a potential issue from last night and we began by checking the last 4 hours and we found nothing of note so we decided to expand our scope.  To do this we copied out chart with the pencil icon and we changed the time frame to the last 8 hours and added 2 additional metrics called BE IO’s Per Sec and BE READ Req’s Per Sec and then draw a new chart.

 

charts2.PNG.png

 

 

Some of this functionality was in the previous product but we have reduced the input required from the end user and allowed them to merely copy a chart and edit it if required.

 

Additionally we have allowed you to add more tabs in the same way you do with a web browser so if you were comparing performance over a couple of days similar to what you see in the screenshot you can label charts by day and group accordingly.

 

For a video on this please see here: https://www.youtube.com/edit?o=U&video_id=9192_w1iwco


I hope you found this overview helpful and if you would like to see more focus on certain areas please let us know.

This series of blog posts are dedicated to the performance section for Unisphere for PowerMax 9.0. We have made significant improvements in this particular area in terms of usability and functionality and I wanted to take some time to explain the new functionality and user flows.

I wanted to begin with the Dashboard section where we have our “Pre-Canned” Dashboards which provides you with the ability to interrogate across a certain range of objects which will allow you to troubleshoot a potential performance issue on an array with specific KPI’s concentrating on the most common areas of focus. In total we have 12 Dashboards including Array, Storage Groups, Hosts, Thin Pools, Storage Containers, Port Groups, FE Directors, BE Directors, RDF Directors, Disk Groups, Disk Technology and External Directors. The great thing about dashboards is it takes the hard work out of troubleshooting for customers in that it presents you with a set of charts that will help you identify a potential problem if there is one.

 

I wanted to focus on the Array and Storage Group Dashboard here and talk a little more about them in greater detail.

 

1.PNG.png

 

For this dashboard the timeframe is set for the last 4 hours in the upper right hand corner but the time range can be expanded as you wish if you need to see earlier timeframe over the last hours, days or months going back over the last 12 months. You can also change the graph style as you wish. These are average values but there is a toggle button whereby you can select a Maximum value if desired.

Also in the upper right hand corner we have some useful functionality including the following:

  • Ability to save this dashboard as a custom dashboard or as a template.
  • Schedule array report or schedule array overview report
  • Run PDF report now, Run PDF report now with data and Run array overview PDF report now.
  • Navigate to the charts or analyse section

 

 

There are 3 separate views for this dashboard across the upper left hand side including Array Workload, Array Efficiency and Performance thresholds. These have been chose in order to give you a broad picture of how the array is performing at present in terms of its workload and performance.

In the previous screenshot you were looking at an array workload view looking at Host and BE Reqs/sec, Host MB’s/sec, % Cache WP and Host and BE IO’s/sec. In the array efficiency we focus on Subscribed and Usable capacity, Snapshot Capacity and % Metadata usage in order to give you a view into consumption patterns on the array.

 

2.PNG.png

 

3.PNG.png

In the next example I have selected the Storage Group Dashboard and selected a SG which has been seeing heavy Read and Write activity over the last 4 hours. This dashboard you can see 4 separate tiles our current View SG Workload, I/O Profile, Performance Thresholds and SG Noisy Neighbour. The SG Workload tile gives you an indication of read and write activity that is going to the SG across 6 different charts.

 

I wanted to spend some time on the new functionality we have introduced in 9.0 with the Noisy Neighbor Dashboard in order to represent potential FA contention.

 

4.PNG.png

 

In our conversations with customers one of the most common issues they encounter in their environments is the Noisy Neighbour scenario. For a given Storage Group the Dashboard will chart key performance metrics, and also detail the relationship between the storage group and the associated front end director and ports. The Dashboard will also show other SG’s that are sharing the same ports and could be contributing to performance issues.

There are 6 charts here with 3 graphs on the top which focus on Reads and Writes. Along the bottom we see the FE Directors and FE Ports that this SG is mapped down. Also we have a complete list of all SG’s that share these mappings so if there were a “rogue” SG which was consuming a lot of resources and causing a knock on performance problem you could easily see who the offender was on this list.

 

5.PNG.png

Finally I just wanted to show you templates and custom dashboards. The template I’m displaying here is called MetaData Usage and in my case it’s something I need to monitor closely so I have created a chart with all of our Meta Data metrics and saved this is as a template so I can easily view it any time.

 

Also in the custom dashboard I can save specific objects such as SG “Tier 1 Trading Application” as it is one of my mission critical SG’s that I need to keep a close eye on so by saving it as a custom dashboard I can access it easily.

 

This concludes this blog on the dashboard section, next I will cover the charting section where we have made huge improvements in the functionality and usability of the product.

 

Noisy Neighbor Video Example

 

https://www.youtube.com/watch?v=GHGcDHboR7c