Storage for cloud rendering and animation workflows

Cloud rendering is easy with a modern scalable file storage system like Qumulo

When the La La Land project came around it was make or break, and we were never down for a moment. QF2 is our rock, allowing us to focus on the visual effects with absolute confidence the data is safe

Tim LeDoux, Founder/VFX Supervisor Crafty Apes

Eliminate storage pains with a modern scale-out storage platform.

As movies and television become increasingly reliant on complex special effects, VFX studios are looking for file storage solutions that offer more capacity and better performance.

Qumulo File Fabric (QF2) provides the speed and scalability that VFX studios need to meet tight deadlines and keep costs down. With QF2, studios can render their most complex jobs without slowing down the artists who need to keep working on other frames.

Here’s a simple example of a rendering workflow that shows QF2 as the central file storage system. QF2 is used both by the artists and the rendering farm.

Try Qumulo for AWS

Ready for a test drive? You can try Qumulo for free! Find us in the AWS Marketplace.

See how it works

Enterprise-grade file in the cloud? Absolutely. Learn about cloud migration trends and see a live demo of rendering in the cloud.

Scalability

Each time customers add a node to a QF2 cluster, they scale up linearly, both in terms of capacity and performance.There is no practical limit to the number of files QF2 can store.

Lower TCO

QF2 costs less and has lower TCO than legacy storage appliances. QF2’s cost advantage comes from efficient use of storage capacity and from its use of standard hardware. With QF2, you can use 100% of provisioned capacity, not just the 70% or 80% that legacy systems recommend. This translates into more available disk space, a smaller data footprint and savings on infrastructure costs such as heating and cooling.

QF2’s cost efficiencies are also related to its reprotect times, or how long it takes to recover data if a disk fails. QF2 uses sophisticated data protection techniques that enable the fastest reprotect times in the industry. They are measured in hours, not days or weeks.

Real-time visibility and control

QF2’s real-time visibility and control provide information about what’s happening in the storage system, down to the file level. The capacity explorer and capacity trends tools give IT the information it needs to plan sensibly for the future and not worry about overprovisioning.

Simplicity

From the time you unbox QF2 to the time it’s a part of your production workflow is a matter of hours, not days. QF2 is so simple to manage that, once it’s installed, you can hand it over to junior staff members.

Multi-protocol support

QF2 supports SMB, NFS, REST, and FTP. Customers can easily set up NFS exports and SMB shares.

Simple subscription model

A single, simple subscription service covers everything, including all features, updates and support. There are no hidden costs and no surprises.

Great customer support

Customers get help fast from Qumulo’s team of storage experts. Each customer has a dedicated Slack channel with immediate access to their dedicated customer success engineer (CSM). Every CSM has deep experience working with file storage systems and understands the associated workflows and applications.

Rendering in the Cloud

For VFX studios, the need for more capacity and performance is complicated by the unpredictability of their workloads and the short delivery schedules. In particular, studios that work on episodic television programs need to complete a single episode in two to three weeks.

Given that deadlines are always tight, there is no time to build out the physical infrastructure when a studio outstrips the capacity of its on-premises render farm. Even renting equipment may not be feasible.

It might seem that the answer is obvious—move to the cloud—but until the advent of Qumulo File Fabric (QF2) for AWS, the solutions for file in the cloud have been limited, with poor scalability and performance as well as limited feature sets. QF2 for AWS is an enterprise-grade file storage system with the highest performance of any cloud-based solution.

Here is a simple example of a hybrid rendering workflow.


The on-prem render farm has been extended with additional resources in AWS. In this example, the QF2 cluster uses m4.16xlarge EC2 instances. The spot fleet is the collection of render nodes.

The pipeline uses EC2 Spot Instances for scalable, low-cost computing, Deadline for queue management and managing bids for the spot instances, and Thinkbox Marketplace usage-based licensing (UBL) for flexible licensing.

Performance

QF2 has the highest and most scalable performance of any file storage in the cloud. A standard four-node cluster that runs on m4.16xlarge AWS EC2 instances typically has a read throughput of 1.8GB/s and a write throughput of 1.3GB/s. FuseFX used a four-node cluster to support a rendering farm of 1000 compute EC2 instances (32,000 cores) and had a peak file system read throughput of 3.87GB/s and a peak IOPS of 40K.

Data Mobility

QF2 uses continuous replication to move data where it’s needed, when it’s needed. Continuous replication creates a copy of the data in a directory on your primary cluster and transfers it to a directory on a second, target cluster. Continuous replication is always running (unless you configure it not to). QF2 takes your latest changes and replicates them without you needing to worry about it.

Continuous replication means you can easily transfer data from your on-prem QF2 cluster to your QF2 cluster in AWS, perform your computations, and then transfer the results back to the on-prem storage.

Programmability

QF2 has the programmability that cloud architects and DevOps engineers expect. You can inspect and control the file system with a REST API. You can also use popular automation platforms, such as Terraform, to automatically deploy QF2 clusters.

We are building a fully orchestrated visual effects rendering solution that spans our on-premises data center and AWS. We now have a QF2 cluster on AWS and in our data center creating a unified fabric that enables us to share file data between these two operating environments, maintain workflow consistency, and meet the high performance requirements for heavy compute workloads in the cloud.

Jason Fotter — Co-founder and CTO FuseFX

Case study: FuseFx

Render jobs were sitting in the queue and stress levels were high. Qumulo + 32,000 cores saved the day.

Case study: Crafty Apes

Find out why Crafty Apes, a leading production studio, turned to Qumulo to complete their composition work on the film La La Land.

Want to learn more?

Give us 10 minutes of your time, and we’ll show you how to rethink data storage.