Amazon FSx for NetApp ONTAP file systems can now be created up to 9 times faster than previously. The file systems are completely managed, as is already the case with this service, with latency to primary storage being in the sub-millisecond range and latency to the capacity pool being in the tens of milliseconds. You’ll be able to move even more of your most taxing workloads in statistical computing, visual effects, and electronic design automation (EDA) to the cloud thanks to this improved performance.
Scaling Success with Amazon FSx Strategies
Current FSx for ONTAP scale-up file systems have a maximum throughput of 4 GBps and 192 TiB of SSD storage. They are powered by a single pair of servers in an active/passive high availability (HA) arrangement. To provide continuous availability even in the event that an Availability Zone is unavailable, the server pair can be placed in two different Availability Zones or across different fault domains within a single Availability Zone.
With today’s release, ONTAP file systems powered by two to six HA pairs can now have scale-out FSx created for them. The following are the specifications for the scale-out and scale-up file systems (all of which are marked as “up to” since you can set the values you want for each when you construct your file system):
|Up to 4 GBps
|Up to 1.8 GBps
|Up to 160K
|Up to 192 TiB
|Single or Multiple
|Up to 36 GBps
|Up to 6.6 GBps
|Up to 1.2M
|Up to 1 PiB
The real server configuration will depend on the throughput your file system requires, which will be as follows:
|4 GBps or less
|Up to 4 GBps Read
Up to 1.1 GBps Write (Single-AZ)
Up to 1.8 GBps Write (Multi-AZ)
|Up to 160K
|More than 4 GBps
|Up to 6
|Up to 6 GBps Read
Up to 1.1 GBps Write
|Up to 200K
Building a File System for Scaling Out
Using the AWS Management Console, AWS Command Line Interface (AWS CLI), or by creating code that invokes the Amazon FSx CreateFileSystem function, You can construct a scale-out file system. Using the console, you will first select Amazon FSx for NetApp ONTAP.
You select a Single-AZ deployment, type in a name, select Standard create, and enter the amount of SSD storage you want. You have three alternatives (more on that in a moment): accept the suggested throughput capacity, select a value from the menu, or enter a value to see my possibilities.
There’s a handy magical feature in the dropdown. It will display one or more options based on your input of the required throughput capacity:
Occasionally, the console may present you with multiple choices for the same required throughput capacity. The following suggestions will assist you in selecting a solution that will perform well for your workload.
Low Throughput: You will only be able to use one HA pair if you select a plan that offers 4 GBps or less. Choosing this option is the easiest if you don’t want a high throughput.
High Storage and/or Throughput: The maximum throughput varies depending on how many HA pairs you supply. Additionally, selecting a solution with more pairs will increase your headroom for potential future increases in allocated storage.
You make your choices, input the typical values for the remaining options, and then click Next to see my settings again. After making sure that my selections for any attributes that cannot be changed after creation are correct, you click Create file system.
You have the ability to alter the supplied IOPS up to once every six hours and to expand the storage capacity.
Currently, if the file system uses multiple HA pairs, the provisioned throughput capacity cannot be altered after formation.
Accessible Right Now
You can begin developing and utilizing scale-out file systems right now in the US East (Ohio, N. Virginia), US West (Oregon), Asia Pacific (Sydney), and Europe (Ireland) Regions.