Solved

Sizing SSD capacity to HDD capacity in a node

  • 11 June 2021
  • 2 replies
  • 56 views

Just a quick question about sizing SSD capacity to HDD capacity in a node (in a new homogenous cluster). When specifying drive space in a node, what is the percentage SSD to HDD per node at a minimum. Is there a best practice guide that someone can point me towards? I’m not asking about the number of HDDs vs the number of SSDs.

The question is around capacity and not number or drives. e.g. I configure a node with 4TB of SSD (2x1.92TB) and 60TB of HDD (10 x 6TB) and Nutanix Sizer says this is fine. This is roughly 6.25% SSD But what should I have as a minimum SSD capacity of of a hybrid node is 6% Okay, or should it be more like 10% or 20% (or more)?

icon

Best answer by Sergei Ivanov 11 June 2021, 10:45

Hi @tcourtney-72782 

The problem there may possibly be with the performance of the cluster. It will greatly depend on what kind of workload you run there. If you want to run OLTP databases or any heavy IOPS workload with low latency expectations, it might be a good idea to size more SSD. If you plan to have a lot of cold data and latency is not that important, smaller SSD tier size will do. We generally recommend to never size the SSD tier below 10% of the total capacity, but overall the higher SSD ratio, the better performance you will get.

You should also check your working set size and it should fit into the SSD tier. Check with the application owners how much new data do their applications write per day. You can also check the incremental backup sizes. Incremental daily backups will have the data from the last day only, so it will provide some indication of how much new data is generated daily. Aim to make sure that the working set will fit into the 75% of the SSD tier and don’t forget about the RF2/RF3. And of course leave some free space for the future growth.

View original

This topic has been closed for comments

2 replies

Userlevel 4
Badge +5

Hi @tcourtney-72782 

The problem there may possibly be with the performance of the cluster. It will greatly depend on what kind of workload you run there. If you want to run OLTP databases or any heavy IOPS workload with low latency expectations, it might be a good idea to size more SSD. If you plan to have a lot of cold data and latency is not that important, smaller SSD tier size will do. We generally recommend to never size the SSD tier below 10% of the total capacity, but overall the higher SSD ratio, the better performance you will get.

You should also check your working set size and it should fit into the SSD tier. Check with the application owners how much new data do their applications write per day. You can also check the incremental backup sizes. Incremental daily backups will have the data from the last day only, so it will provide some indication of how much new data is generated daily. Aim to make sure that the working set will fit into the 75% of the SSD tier and don’t forget about the RF2/RF3. And of course leave some free space for the future growth.

Hey @tcourtney-72782,

if you some kind migrating from Hyper-V or ESXi, take nutanix collector to check how many working data you have. this size plus 25% is your SSD tier size.

As @Sergei Ivanov mentioned 10% is absolute minimum, i would recommend to size at 20%.

 

Kind regards,

SergeR