At Pure//Accelerate 2018 Cody Hosterman and I delivered a session on “Moving Data Between Cloud and On-Premises Virtualized Environments“. The focus of this session was on data mobility and how Pure Storage customers and partners will be able to use different features and integrations to move data from on-premises, extending into the cloud, backing up using Snap To NFS (now) and converting Pure Storage volumes into cloud native format via our Tech Preview of CloudSnap.
If you attended Pure//Accelerate 2018 you saw the below diagram which outlines our data portability vision from on-premises to the cloud.
We will be doing a 5-part blog series that walks through each of the individual stages, which includes:
Stage 1 — VMware Virtual Volumes
In the first stage of the demo we set the scene with VVols. VVols allows you to non-disruptively convert VMFS-based virtual machines into the open format that VVols providers. Through a totally non-disruptive, VAAI-offloaded Storage vMotion, a VMFS VM will be converted into a VVol-based VM. Furthermore, using VM storage policies through the VVols Storage Policy Based Management engine, we can assign FlashArray replication to the specific VVols to replicate it to a remote FlashArray.
Stage 2 — Microsoft Hyper-V
Using the VVols from Stage 1 we use asynchronous replication of the SQL Server VVol data volume to our Equinix deployment. Once replicated, I connect to a Microsoft Hyper-V host and present that data volume to a Hyper-V virtual machine to perform additional data manipulation.
Stage 3 — AWS Direct Connect
In this stage we continue to use the same SQL Server data volume which we started with in Stage 1 by creating a crash consistent snapshot and connecting it to an EC2 instance over Direct Connect using iSCSI connectivity from the Pure Storage FlashArray.
Stage 4 — Snap To NFS
One of the critical steps with any workload is to create backups. In Stage 4 we use Snap To NFS to create a backup of the SQL Server data volume. After taking a backup we then restore that snapshot into an EC2 instance.
Stage 5 — CloudSnap
At Accelerate we said the Multi-Cloud model is important for data mobility regardless of what cloud provider someone may have chosen. Using our Tech Preview of CloudSnap we will take the SQL Server data volume and rehydrate into a cloud native format (EBS) that can be connected to an EC2. Think dev/test.
The below diagram illustrates each of the stages we demonstrated at our session.
This should set the stage for the 5 part series. Cody will be posting Stage 1 details very soon on his blog at https://codyhosterman.com.