The Intel E810 network adapter is now fully certified for RDMA support in vSAN, I thought I would try it out and see what performance improvement I would get by enabling it. However I found that just installing the drivers is not enough to enable RDMA on the adapter itself.
At the time of writing this article, the driver versions that have been certified are as follows:
icen version 184.108.40.206
irdman version 220.127.116.11
E810 firmware 2.40
After installing the above drivers, I did not see any RDMA adapters listed in the vSphere UI:
So it would appear that the driver module has to be told to switch on RDMA, in order to do this you run the following two commands:
esxcli system module parameters set -m icen -p "RDMA=1,1"
esxcli system module parameters set -m irdman -p "ROCE=1,1"
The above two commands enable RDMA at the driver level, and then the version of RDMA at the RDMA driver level, for both ports. After a reboot of the host, you should now see an option in the UI for RDMA adapters:
Now going into the vSAN Services under network, you can now enable RDMA for your vSAN cluster:
In the networking section it should now show that RDMA Support is Enabled:
Now that RDMA is enabled there should be a performance boost due to the offload capabilities that RDMA offers. I will post some results as soon as my test cycles have completed.
As we all know there are a number of ways of scaling capacity in a vSAN environment, you can add disks to existing hosts and scale the storage independently of compute, or you can add nodes to the cluster and scale both the storage and compute together, but what if you are in a situation where you do not have any free disk slots available, and / or you are unable to add more nodes to the existing cluster? Well vSAN 7.0U1 comes with a new feature called vSAN HCI Mesh, so what does this mean and how does it work?
Let’s take the scenario below, we have two vSAN clusters in the same vCenter, Cluster A is nearing capacity from a storage perspective, but the compute is relatively under utilised, there are no available disk slots to expand out the storage. Cluster B on the other hand has a lot of free storage capacity but is more utilised on the compute side of things:
Now the vSAN HCI Mesh will allow you to consume storage on a remote vSAN cluster providing it exists within the same vCenter inventory, there are no special hardware / software requirements (apart from 7.0U1) and the traffic will leverage the existing vSAN network traffic configuration.
This cool feature adds an elastic capability to vSAN Clusters, especially if you need to have some additional temporary capacity for application refactoring or service upgrade where you want to deploy the new services but keep the old one operational until the transition is made.
VMware has not left the monitoring capabilities of such use out either, in the UI you can monitor the usage of “Remote VM” from a capacity perspective as well as within the performance service
So this clearly allows dissagregation of storage and compute in a vSAN environment and offers that flexibility and elasticity of storage consumption are there any limitations?
A vSAN cluster can only mount up to 5 remote vSAN Datastores
The vSAN Cluster must be able to access the other vSAN cluster(s) via the vSAN Network
vSphere and vCenter must be running 7.0U1 or later
Enterprise and Enterprise Plus editions of vSAN
Enough hosts / configuration to support storage policy, for example if your remote cluster has only four hosts, you cannot use a policy which requires RAID6
So this is a pretty cool feature and sort of elliminates the need for Storage Only vSAN nodes which was discussed in the past at many VMworlds
As the core density increases on a CPU it opens up the opportunity to consolidate the number of nodes required in any given cluster, but in a vSAN cluster, node consolidation has a negative effect on available IOPS, if you think about how each node provides a specific amount of IOPS, lowering the number of hosts in the cluster removes the IOPS capability of the nodes you are consolidating by, take the following for example:
Number of VMs : 200 vCPU Per VM : 4 Virtual Memory per VM : 32GB Storage per VM : 600GB vCPU to Core Ratio : 4 to 1
Now for the purpose of this sizing excersize I am going to use the vSAN Sizing tool and apply some cluster settings as per below:
So in the above scenario, the number of cores per CPU is 18, and I want to ensure that this is a two disk group configuration, if we then input the workload details as per below:
You will see when we click on recommendation that it shows a required node count of 8 (not taking into account any N+1 capability as we left that as 0 for the purpose of this sizing)
And we can see the disk config below:
However, if we increase the number of CPU Cores to 20 by clicking on the “+” in the sizing output we can see that it changes the number of nodes
And again if we increase the number of cores again to 22 we get a further reduction in the number of nodes to 6
The sizing tool will dynamically increase or decrease the number of disks required per host as well as the RAM per node that is required as you can see here:
But one thing we have not factored in here is the decrease in IOPS Capability that reducing by two nodes , if say for example each node was capable of 80K IOPS, reducing the node count by two means you have just lost 160K IOPS Capability, so what can we do to mitigate that?
Well instead of using SAS/SATA SSDs in your vSAN design, you could opt to use Intel Optane for Cache, and NAND based NVMe drives for capacity. For write operations, Intel Optane greatly improves on write performance as I have written about before, but also read performance is greatly accelerated because the capacity devices are NVMe, so therefore reducing your node count by two in this case and utilising this kind of technology means you still get similar levels of performance, the best part is, the overall solution will cost you less too, so your TCO comes down which is good for your finance department right?
One question I get asked frequently is what size Optane device is sufficient?
Well in all of my testing, I very rarely saturated the write buffer even with 375GB Optane drives as cache devices, the reason for this is because vSAN starts to perform de-staging from the cache tier to the capacity tier when the write buffer becomes around 30% Full, and because the capacity tier it NVMe based, the de-staging happens a lot quicker, especially since vSAN 6.7 U3 where the de-stage limits have been removed.
So when would a 750GB Optane be useful?
High write intensive workloads such as Video Surveilance and Databases, or when your capacity disks are much slower, Optane can still be used in vSAN Configurations where the Capacity Tier is SAS/SATA which of course are not as fast as most NVMe devices so the write buffer can get more full.
So just to re-cap, you can save money on your vSAN deployments by consolidating hosts with higher core count CPUs as well as leveraging newer technology such as Intel Optane in the Cache Tier and NVMe in the capacity tier thus saving money whilst maintaining same level of performance or better, what’s not to like?