We talked with Hedvig (@HedvigInc) at Storage Field Day 10 (SFD10), a month or so ago and had a detailed deep dive into their technology. (Check out the videos of their sessions here.)
Hedvig implements a software defined storage solution that runs on X86 or ARM processors and depends on a storage proxy operating in a hypervisor host (as a VM) and storage service nodes. Their proxy and the storage services can execute as separate VMs on the same host in a hyper-converged fashion or on different nodes as a separate storage cluster with hosts doing IO to the storage cluster.
Hedvig’s management team comes from hyper-scale environments (Amazon Dynamo/Facebook Cassandra) so they have lots of experience implementing distributed software defined storage at (hyper-)scale.
Continue reading “Hedvig storage system, Docker support & data protection that spans data centers” →
What does HAM look like to the open systems end user. We need to break this question up into two parts – one part for USP-V internal storage and the other part for external storage.
It appears that for internal storage first you need data replication services such as asynch or synchronous replication between the two USP-V storage subsystems. But here you still need some shared External storage used as a quorum disk. Then once all this is set up under HAM the two subsystems can automatically failover access to the replicated internal and shared external storage from one USP-V to the other.
For external storage it appears that this storage must be shared between the two USP-V systems and whenever the primary one fails the secondary one can take over (failover) data storage responsibilities for the failing USP-V frontend.
What does this do for data migration? Apparently, using automated failover with HAM one can migrate date between two different storage pools and then failover server access from one to the other non-disruptively.
Obviously all the servers accessing storage under HAM control would need to be able to access both USP-Vs in order for this to all work properly.
Continuous availability is a hard nut to crack. HDS seems to have taken a shot at doing this from a purely storage subsystem perspective. This might be very useful for data centers running heterogeneous server environments. Typically server clustering software is OS specific like MSCS. Symantec being the lone exception with VCS which supports multiple OSs. Such server clustering can handle storage outages but also depend on storage replication services to make this work.
Unclear to me which is preferable but when you add the non-disruptive data migration – it seems that HAM might make sense.