Tag Archives: NPX

The Key to performance is Consistency

Posted on by
Reply

In recent weeks I have been doing lots of proof of concepts and performance testing using tools such as Jetstress (with great success I might add).

What I have always told customers is to focus on choosing a solution which comfortably meets their performance requirements while also delivering consistent performance.

The key word here is consistency.

Many solutions can achieve very high peak performance especially when only testing cache performance, but this isn’t real world as I discussed in Peak Performance vs Real World Performance.

So with two Jetstress VMs on a 3 node Nutanix cluster (N+1 configuration) I configured Jetstress to create multiple databases which used about 85% of the available capacity per node. The nodes used were hybrid, meaning some SSD and some SATA drives.

What this means is the nodes have ~20% of data within the SSD tier and the bulk of the data residing within the SATA tier as shown in the Nutanix PRISM UI on the Storage tab as shown below.

Tierusage

As Jetstress performs I/O across all data concurrently, it means that things like caching and tiering become much less effective.

For this testing no tricks have been used such as de-duplicating Jetstress DBs, which are by design duplicates. Doing this would result in unrealistically high dedupe ratios where all data would be served from SSD/cache resulting in artificially high performance and low latency. That’s not how I roll, I only talk real performance numbers which customers can achieve in the real world.

In this post I am not going to talk about the actual IOPS result, the latency figures or the time it took to create the databases as I’m not interested in getting into performance bake offs. What I am going to talk about is the percentage difference in the following metrics between the nodes observed during these tests:

1. Time to create the databases : 1.73%

2. IOPS achieved : 0.44%

3. Avg Read Latency : 4.2%

As you can see the percentage difference between the nodes for these metrics is very low, meaning performance is very consistent across a Nutanix cluster.

Note: All testing was performed concurrently and background tasks performed by Nutanix “Curator” function such as ILM (Tiering) and Disk Balancing were all running during these tests.

What does this mean?

Running business critical workloads on the same Nutanix cluster does not cause any significant noisy neighbour types issues which can and do occur in traditional centralised shared storage solutions.

VMware have attempted to mitigate against this issue with technology such as Storage I/O Control (SIOC) and Storage DRS (SDRS) but these issues are natively eliminated thanks to the Nutanix scale out shared nothing architecture. (Nutanix Xtreme Computing Platform or XCP)

Customers can be confident that performance achieved on one node is repeatable as Nutanix clusters are scaled even with Business Critical applications with large working sets which easily exceed the SSD tier.

It also means performance doesn’t “fall of the cache cliff” and become inconsistent, which has long been a fear with systems dependant on cache for performance.

Nutanix has chosen not to rely on caching to achieve high read/write performance, instead we to tune our defaults for consistent performance across large working sets and to ensure data integrity which means we commit the writes to persistent media before acknowledging writes and perform checksums on all read and write I/O. This is key for business critical applications such as MS SQL, MS Exchange and Oracle.

My NPX Journey

Posted on by
12

I have had an amazing learning experience in the last few months, expanding my skills into a second hypervisor being Kernel Virtual Machine (KVM) as well as continuing to enhance my knowledge on the ever increasing functionality of the Nutanix platform itself.

This past week I have been in Miami with some of the most talented guys in the industry who I have the pleasure to work with. We have been bootstrapping the Nutanix Platform Expert (NPX) program and have had numerous people submit comprehensive documentation sets which have been reviewed, and those who met the (very) high bar, were invited to the in-person, panel based Nutanix Design Review (NDR).

I was lucky enough to be asked to be part of the NDR panel as well as being invited to the NDR to attempt my NPX.

Being on the panel was a great learning experience in itself as I was privileged to observe many candidates who presented expert level architecture, design and troubleshooting abilities across multiple hypervisors.

I presented a design based on KVM for a customer which I have been working with over the last few months who is deploying a large scale vBCA solution on Nutanix.

I had an All-Star panel made up entirely of experienced Nutant’s who all happen to also be VCDXs, its safe to say it was not an easy experience.

The Design Review section was 90 mins which went by in a heart beat where I presented my vBCA KVM design, followed by a 30 min troubleshooting session and 60 min design scenario also based on vSphere.

Its a serious challenge having to present at an expert level on one Hypervisor, then swap into troubleshooting and designing a second hypervisor, so by the end of the examination it was safe to say I went to the bar.

As this is a bootstrap process I was asked to leave the room while the panel performed the final scores, then I was invited back in the room and told I was

Congratulations NPX #001

I am over the moon to be a part of an amazing company and to be honoured with the being #001 of such an challenging certification. I intend to continue to pursue deeper level knowledge on multiple hypervisors and everything Nutanix related to ensure I do justice to being NPX #001.

I am also pleased to say we have crowned several other NPX’s but I won’t steal there thunder by announcing their names and numbers.

For more information on the NPX program see http://go.nutanix.com/npx-application.html

Looking forward to .NEXT conference which is on this week!

My Journey to Double-VCDX

Posted on by
Reply

It was back in 2011 when I started my journey to VCDX which was a fantastic learning experience which has helped improve my skills as an Enterprise Architect.

After achieving VCDX-DCV in May 2012, I have continued to put the skills and experience I gained during my VCDX journey into practice, and came to the realization, of how little I actually know, and how much more there is learn.

I was looking for another certification challenge however there was no additional VCDX certification tracks at the time. Then VCDX-Cloud and VCDX-Desktop were released, I figured I should attempt VCDX-Cloud since my VCDX-DCV submission was actually based on a vCloud design.

At the time I didn’t have my VCAPs for Cloud, so as per my VCAP-CID Exam Experience and VCAP-CIA Exam Experience posts explain, I formed a study group and sat and passed both exams over a period of a few months.

Next came the VCDX application phase, I prepared my design in a similar fashion to my original application which basically meant reviewing the VCDX-Cloud Blueprint and ensuring all sections have been covered.

I sad part about submitting a second VCDX is that there is no requirement to redefend in person. As a result I suspect the impression is that achieving a second VCDX is easier. While I think this is somewhat true as the defence is no walk in the park, the VCDX submission still must be of an expert standard.

I suspect for first time VCDX applicants, the candidate may be given the benefit of the doubt if the documentation is not clear, has mistakes or contradicts itself in some areas as these points can be clarified or tested by the panellists during the design defence.

In the case of subsequent applications,  I suspect that Double-X candidates may not get the benefit of the doubt, as these points cannot be clarified. As a result, It could be argued the quality of the documentation needs to be of a higher standard so that everything in the design is clear and does not require clarification.

My tips for Double-X Candidates:

In addition to the tips in my original VCDX Journey Post:

  1. Ensure your documentation is of a level which could be handed to a competent engineer and implemented with minimal or no assistance.
  2. Ensure you have covered all items in the blueprint to a standard which is higher than your previous successful VCDX submission
  3. Make your design decisions clear and concise and ensure you have cross referenced relevant sections back to detailed customer requirements.
  4. Treat your Double-VCDX submission equally if not more seriously than your first applications. Ensure you dot all your “I”s and cross your “T”s.

I was lucky enough to have existing Double-VCDX Magnus Andersson (@magander3) and Nutanix colleague review my submission and give some excellent advice. So a big thanks Magnus!

What next?

Well just like when I completed my first VCDX, I was already looking for another challenge. Luckily I have already found the next certification and am well on the way to submitting my application for the Nutanix Platform Expert (NPX).

The VCDX-DCV and VCDX-Cloud have both been awesome learning experiences and I think both have proven to be great preparation for my NPX attempt, so stay tuned and with a bit of luck, you’ll be reading my NPX Journey in the not to distant future.