Disclaimer: I recently attended Storage Field Day 19. My flights, accommodation and other expenses were paid for by Tech Field Day. There is no requirement for me to blog about any of the content presented and I am not compensated in any way for my time at the event. Some materials presented were discussed under NDA and don’t form part of my blog posts, but could influence future discussions.
NetApp recently presented at Storage Field Day 19. You can see videos of the presentation here, and download my rough notes from here.
StorageGRID
If you haven’t heard of it before, StorageGRID is NetApp’s object storage platform. It offers a lot of the features you’d expect from an object storage platform. The latest version of the offering, 11.3, was released a little while ago, and includes a number of enhancements, as well as some new hardware models.
Workloads Are Changing
Object storage has been around a bit longer than you might think, and its capabilities and use cases have changed over that time. Some of the newer object workloads don’t just need a scale out bucket to store old archive data. Instead, they want more performance and flexibility.
Higher performance
- Ingest / Retrieve
- Delete
Flexibility
- Support mixed workloads and multiple tenants
- Granular data protection policies
- Optimise data placement and retention
- Adapt to new requirements and regulations
Agility / Simplicity
- Leverage resources across multiple clouds – Move data to and from public cloud
- Open standards for data portability
- Low touch operations
New Hardware
SG1000
- Load Balancer
- Can run Admin node
| Description | Compute Appliance – Gateway Node |
| Performance | High performance load balancer and optional Admin node function |
| Key Features | 1U
Dual-socket Intel platform 768GB memory Two dual-port 100GbE Mellanox NICs (10/25/40/100GbE) Dual 1GBase-T ports for management Redundant power and cooling Two internal NVMe SSDs |
Multi-shelf SG6060
[image courtesy of NetApp]
The SG6060 is mighty dense, offering 2PB in a single node.
SGF6024
[image courtesy of NetApp]
The SGF6024 is an All-Flash Storage Node.
| Description | All-Flash 24 SSD Appliance |
| Performance | High performance, low latency, small object workloads |
| Key Features | · 2U (3U with compute node)
· 40 2.4 GHz CPU cores (compute node) · 192 GB memory (compute node) · 4x10GbE/4x25GbENICs · 24 SSD drives |
| Max capacity | 367.2 TB RAW (15.3 TB SSDs) |
| SSD drive support | NON-FDE: 800Gb, 3.8TB, 7.6TB, 15.3TB FIPS: 1.6TB; SED: 3.8TB |
Architecture
Flexible Deployment Options
- Appliance-based
- VMware-based
- Software only
Storage Nodes
Manages metadata
Manages storage
- Disk
- Cloud
Policy Engine
- Applies policy at ingest
- Continual data integrity checks
- Applies new policy if applicable
Minimum 3 storage nodes required per site
Admin Nodes
Admin / Tenant portal
- Create tenants
- Define grid configuration
- Create ILM policies
Audit
- Granular audit log of tenant actions
Metrics
- Collect and store metrics via Prometheus
Load balancer
- Create HA groups for Storage Nodes and optionally Admin portal
Service Provider Model
Separation between GRID admin and Tenant admin
Grid administration
- Manages infrastructure
- Creates data management policies
- Creates tenant accounts – No data access
Tenant administration
- Storage User administration
- Tenant data is isolated by default
- Use standard S3 IAM and Bucket Policy
- Leverage multi-cloud Platform Services (Cloud mirror, SNS, ElasticSearch)
Thoughts and Further Reading
I’ve been a fan of StorageGRID for some time, and not just because I work at a service provider that sells it as a consumable service. NetApp has a good grasp of what’s required to make an object storage platform do what it needs to do to satisfy most requirements, and it also understands what’s required to ensure that the platform delivers on its promise of reliability and durability. I’m a big fan of the flexible deployment models, and the focus on service providers and multi-tenancy is a big plus.
The new hardware introduced in this update helps remove the requirement for a hypervisor to run admin VMs to keep the whole shooting match going. This is particularly appealing if you really just want to run a storage as a service offering and don’t want to mess about with all that pesky compute. Or you might want to be wanting to use this as a backup repository for one of the many products that can use it.
NetApp has owned Bycast for around 10 years now, and continues to evolve the StorageGRID platform in terms of resiliency, performance, and capabilities. I’m really quite keen to see what the next 10 years have in store. You can read more about what’s new with StorageGRID 11.3 here.