Tag Archives: VMware

Why vSAN is the storage of choice for VMware Cloud Foundation

December 4, 2019 MrVSAN Leave a comment

Recently VMware annouced that Cloud Foundation would support external storage connectivity, when I first heard this I thought to myself are VMware out of their minds? Amongst customers who I meet and talk to more or less on a daily basis, I also spoke to a lot of customers at VMworld about this but the stance or direction from VMware has not changed, if you want a truly Software Defined Data-Center then vSAN is the storage of choice.

So why have VMware decided to allow external storage in Cloud Foundation?

Many customers who are either about to start or have already started their journey to a Software Defined Data Center and/or Hybrid Cloud are still using existing assets that they wish to continue to sweat out, it may well be that their traditional storage is only a couple of years old and VMware are not expecting customers to simply throw out existing infrastructure that was either recently purchased or still being sweat out as that would be a tall ask right?

Customers also still have workloads that can’t simply be migrated to the full SDDC, they take some time to plan the migration, maybe there is a re-architecture of the workload that needs to be performed, or maybe there’s a specific need where a traditional storage array has to be used until any obstacles have been overcome, VMware recognises this hence the support for external storage in Cloud Foundation.

There are also specific use cases where Hyper Converged powered by vSAN isn’t an ideal fit, cold storage or archive storage is one of these, so supporting an array that can provide a suplemental storage architecture to meet these requirements is also a plus point.

Will I lose any functionality by leveraging traditional storage with Cloud Foundation? Simple answer is yes for the following reasons:

No lifecycle management for external storage through SDDC Manager which means patching and updating of the storage is still a manual task.
No single pane of glass management out of the box for external storage without installing third party plugins which in my experience have a tendancy to break other things.
No automation of stretched cluster deployment on external storage, all the replication etc has to be configured manually.
Day-2 operations such as Capacity Reporting, Health Check and Performance Monitoring are lost without installing any third party software for the external storage.
Auto deployment of the storage during a Workload Domain deployment, all the external storage has to be prepared beforehand.
Losing the true “Software Defined Storage” aspect and granular object control, currently external storage support for VVOLS is not there right now either.

Also remember that with Cloud Foundation, the Management Workload Domain has to run on vSAN, you can not use external storage for this.

So if you want a truly Software Defined Data Center with all the automation of deployment, all the nice built in features for day-2 operations then vSAN is the first choice of storage, if you have existing storage you wish to sweat out whilst you migrate to a full SDDC then that’s supported too, and yes you can have a vSAN cluster co-exist with external storage too, which makes migrations so much easier.

The other aspect to look at this is in a Hybrid Cloud or Multi Cloud strategy, Cloud Foundation is all about providing a consistent infrastructure between your private and public clouds, so if your public cloud is using Cloud Foundation with vSAN then the logical choice is to have vSAN as your storage for your Cloud Foundation Private Cloud to have that consistent infrastructure for your workloads no matter where they may run.

Informational

Linear scaling is anything but a myth

March 20, 2019 MrVSAN Leave a comment

I have many conversations with many people, whether they be customers, friends, colleagues, potential customers but the question is always the same, does vSAN really scale linearly?

So to answer this question, I have access to an 8-Node cluster which I essentially removed four of the nodes and ran a performance test usinc HCI Bench, for the 4-Node cluster I ran a total of 120 VMs and for scalability reasons 240 VMs in the 8-Node cluster.

For the purpose of the test, I wanted to run all the performance tests I have ran previously so all block sizes up to 128K as well as Read/Write percentages of 0%, 30%, 70% and 100%, so let us take a look at the 4-Node performance:

As you can see even the four node cluster was pretty performant and we can see that the four node cluster can quite easily achieve in excess of 200K IOPS on reads, and 150K IOPS on 70/30 split, so what happens when we add another 4 nodes to the cluster?

So as you can see from both the tests, latency was pretty much similar in both sets of tests indicating it was a pretty comparable test, so the IOPS and Throughput was more or less double when doubling the size of the cluster proving that vSAN does scale linearly. I would have liked to have had an additional 8-nodes to show further scaling, but in all the customers who I have spoken to about increasing their cluster sizes, they confirm that it scales linearly.

Informational

Oracle performance on HPE Synergy, vSAN and Intel Optane

March 11, 2019 MrVSAN Leave a comment

I had the privilege recently to work with a customer who had asked HPE to perform some performance benchmarks not just with HCI Bench, but because they run quite a lot of Oracle workloads they wanted to determine if the performance of vSAN on HPe Synergy would be sufficient in order to run their workloads.

Whilst agreeing on the hardware specification, the customer had referenced my previous post on Optane™ Performance and had asked HPE to perform the tests using Optane™ as the cache tier in the Synergy configuration, this was not only to provide a superior performance experience, but it also would free up two capacity slots in the disk tray of the chassis per Synergy compute node meaning the customer could have more capacity.

Synergy Specification:

HPE Virtual Connect SE 40Gb F8 Module for Synergy
HPE Synergy D3940 Storage Module with SAS expanders
3x HPE Synergy 480 Gen10 nodes, each equipped with:
2x Intel® Xeon® Gold 6154 CPU @ 3.00GHz
2x Intel® Optane™ 750 GB SSD DC P4800X Series PCIe (x4)
768 GB Memory (24x 32 GB RDIMM @ 2666 MHz)
2x Disk Group config with 1x Optane + 3x 800GB SAS per Disk Group
LACP based 40GbE interconnection between Compute Nodes

Please note: At the time of writing the 750GB U.2 Optane drives were undergoing certification for HPE Synergy.

In order to perform the Oracle workload testing HPE engaged with their own internal Oracle specialists to determine the correct workloads that needed to be performed, and with a target of <2ms specified by the customer they decided to use Kevin Closson’s SLOB tool, SLOB was configured in the following way:

128 SLOB Schemas
Each Schema was 8GB in Size
Total of 1TB Test data

For the purpose of testing HPE decided that they would perform different tests in the following way:

(A) Single Oracle VM Instance with 128 Schemas, 70% Read, 30% Write
(B) Single Oracle VM Instance with 128 Schemas, 50% Read, 50% Write
(C&D) Single Oracle VM Instance with Heavy REDO activity and Large SGA and REDO_STRESS=Heavy, 50% Read, 50% Write, with 128 Schemas and 32 Schemas
(E) Single Oracle VM Instance
(F & G) 2 Parallel Oracle VM Instances with 64 / 128 Schemas Each, 70% Read, 30% Write

Test	SGA	PGA	Schemas	Scale	REDO_STRESS
A	5G	1G	128	8G	Lite
B	5G	1G	128	8G	Lite
C	256G	100G	128	8G	Heavy
D	256G	100G	32	8G	Heavy
E	5G	1G	128	8G	Lite
F	5G	1G	64	8G	Lite
G	5G	1G	128	8G	Lite

Before the tests were performed, and Oracle I/O Calibration was performed which is a feature of Oracle Databases and is used to assess the performance of the I/O subsystem by issuing an I/O intensive read-only workload in order to determine the maximum IOPS and throughput whilst maintaining close to 0ms latency.

Each test ran for 60 minutes in order to ensure enough data was filling up the write buffer, so let’s take a look at the results:

As you can see from the results, the target of <2ms was achieved successfully and at one point with two oracle VMs achieveing a staggering 250k IOPS at 1.305ms latency is very impressive across a 3-Node cluster, not only was the customer pleased with the results, but the Oracle Specialist within HPE said that the results exceeded their expectations also.

So as you can see, a composable infrastructure deployment of vSAN such as HPE Synergy with Intel Optane™ can still deliver the same levels of performance as standard rack mount servers, combined with VMware Cloud Foundation delivering a full SDDC package from both a hardware and software perspective.

It's all about VMware vSAN