Ever since Windows Server 2012 we have SMB Direct capabilities in the OS and Windows Server 2012 R2 added more use cases such as live migration for example. In Windows Server 2016, even more, workloads leverage SMB Direct, such as S2D and Storage Replication. SMB Direct leverages the RDMA capabilities of a NIC which delivers high throughput at low latency combined with CPU offloading to the NIC. The latter save CPU cycles for the other workloads on the hosts such as virtual machines.
We’ve reviewed several times about the large supremacy around AWS and Azure regarding cloud services market share (more details about recent surveys can be found here: “AWS Bigger in SMBs but Azure is the Service Most Likely to Renew or Purchase”) and Google Cloud lands in third place for most of the services. Now they are implementing new NVIDIA GPUs for their virtual machines and sustained discounts for customers using the new NVIDIA VMs.
Before we have started our journey through the storage world, I would like to begin with a side note on what is hyperconverged infrastructure and which problems this cool word combination really solves. Folks who already took the grip on hyperconvergence can just skip the first paragraph where I’ll describe HCI components plus a backstory about this tech. Hyperconverged infrastructure (HCI) is a term coined by two great guys: Steve Chambers and Forrester Research (at least Wiki said so). They’ve created this word combination in order to describe a fully software-defined IT infrastructure that is capable of virtualizing all the components of conventional ‘hardware-defined’ systems.
This article describes the deployment of a Ceph cluster in one instance or as it’s called “Ceph-all-in-one”. As you may know, Ceph is a unified Software-Defined Storage system designed for great performance, reliability, and scalability. With the help of Ceph, you can build an environment with the desired size. You can start with a one-node system and there are no limits in its sizing. I will show you how to build the Ceph cluster on top of one virtual machine (or instance). You should never use such scenario in production, only for testing purposes. The series of articles will guide you through the deployment and configuration of different Ceph cluster builds.
Sooner or later every single IT guy comes to the idea of having some lab. There are a million reasons why you would need a lab: learning new technologies, improving skills, trying crazy ideas you would never dare to try in the production network, you name it. Even though it is a work-related activity for most home labbers this is just another hobby for many of us. That’s why people spend so many hours of their personal time building the homelab, investing significant funds into new hardware, thoroughly planning its setup, looking for a help in online communities or sharing their experience to help others. There is a whole universe of home labbers and I am happy to be part of this community. In this post, I would like to share my experience with 3 generations of home labs I have had so far and the thoughts about next generation.
Many IT administrators or virtualization guys run their homelabs at home. It is a good way to learn new technologies, be able to break things in a lab to get stronger skills. It is sometimes a challenge, to squeeze as much RAM as possible from it. The main challenge is always a memory utilization. VMware VMs are getting memory hungry all the time and they are not “optimized” for Homelab use, but rather for production environments. Yes, it is the main purpose of those VMs after all.
As written in the previous post, for ROBO scenario the most interesting HCI (Hyper-Converged Infrastructure) configuration is a two nodes configuration, considering that two nodes could be enough to run dozen VMs (or also more). For this reason, not all hyperconverged solutions could be suitable for this case (for example Nutanix or Simplivity need at least 3 nodes). And is not simple scale down an enterprise solution to a small size, due to the architecture constraints.
Anyone who has configured and used SMB Direct with RoCE RDMA Mellanox cards appreciates the excellent diagnostic counters Mellanox provides for use with Windows Performance Monitor. They are instrumental when it comes to finding issues and verifying everything is working correctly.
The reason for writing this article was the goal of eliminating any possible confusion in the process of configuring the StarWind Virtual Tape Library in pair with the Microsoft System Center Data Protection Manager. The integration of SCDPM provides a benefit of consolidating the view of alerts across all your DPM 2016 servers. Alerts are grouped by disk or tape, data source, protection group and replica volumes, which simplifies troubleshooting. The grouping functionality is further completed with the console capable of separating issues that only affect one data source from problems that impact multiple data sources. Alerts are also separated into backup failure or infrastructure problems.
These days, more and more companies need high-quality, reliable and efficient server hardware. Home labs used by enthusiasts and professionals in the IT sphere for software developing and testing, studying for an IT certification, and configuring virtual environments became popular as well. Small companies are also interested in cheap and compact servers, the production of which is based on a couple of virtual machines or networking applications. Supermicro company ranks one of the leading positions in server development for a long time. Supermicro products range from the Hi-End clusters to microservers. Recently the company released two compact servers: SuperServer E200-8D and its younger model – SuperServer E300-8D.