Citrix has revealed a desktop thin client based on the Raspberry Pi microcomputer – HDX Ready Pi, which is a Citrix-built box containing the Raspberry Pi 3 hardware and a ViewSonic Linux build designed specifically to run with the Citrix HDX virtual desktop platform. The device contains a Raspberry Pi 3 board, a power supply and ports for the Pi’s HDMI, ethernet and USB connections. It connects to a XenDesktop and XenApp server that hosts the virtual instances of each individual PC.
NUMA stands for Non Unified Memory Access and Nehalem was the first generation of Intel CPUs where NUMA was presented. However, the first commercial implementation of NUMA goes back to 1985, developed in Honeywell Information Systems Italy XPS-100 by Dan Gielan.
Solid-State-Drives are becoming widely implemented in ESXi hosts for caching (vFlash Read Cache, PernixData FVP), Virtual SAN or plain Datastores. Unfortunately, SSDs have limited lifetime per cell. Its value may range from 1.000 times in consumer TLC SSDs up to 100.000 times in enterprise SLC based SSDs. Lifetime can be estimated by device TBW parameters provided by vendor in its specification, It describes how many Terabytes can be written to the entire device, until the warranty expires.
As we know, Backblaze publishes the specifications its product – Storage Pods, and recently it has announced its sixth generation design, with the number of disks rising from 45 to 60 while reducing costs down even further.
With Windows Server 2012 Hyper-V became truly NUMA aware. A virtual NUMA topology is presented to the guest operating system. By default, the virtual NUMA topology is optimized by matching the NUMA topology of physical host. This enables Hyper-V to get the optimal performance for virtual machines with high performance, NUMA aware workloads where large numbers of vCPUs and lots of memory come into play. A great and well known example of this is SQL Server.
SanDisk is one of few companies currently offering 1TB of storage in a single-sided M.2 card – its product X400 SSD. X400 also comes in a 2.5″ 7mm-height form factor, but the M.2 configuration is the main selling point of this line. 1TB M.2 X400 card allows getting the most out of the ultra-thin notebooks in terms of storage, without sacrificing performance or battery life.
Google and Rackspace cooperate over creating a new server configuration based on IBM Power9 processors. The design is expected to be shared as part of the Open Compute Project. The hardware set will include 48V Open Compute racks by Google and Facebook collaborative development.
Personally, I am getting rather tired of the dismissive tone adopted by virtualization and cloud vendors when you raise the issue of disaster recovery. We previously discussed the limited scope of virtual systems clustering and failover: active-passive and active-active server clusters with data mirroring is generally inadequate for recovery from interruption events that have a footprint larger than a given equipment rack or subnetwork. Extending mirroring and cluster failover over distances greater than 80 kilometers is a dicey strategy, especially given the impact of latency and jitter on data transport over WAN links, which can create data deltas that can prevent successful application or database recovery altogether.
According to IDC quarterly report, EMC’s Data Domain leads in the purpose-built backup appliance market.
The need or perceived need for hard CPU processor affinity stems from a desire to offer the best possible guaranteed performance. The use cases for this do exist but the problems they try to solve or the needs they try to meet might be better served by a different design or architecture such as dedicated hardware. This is especially true when this requirement is limited to a single or only a few virtual machines needing lots of resources and high performance that are mixed into an environment where maximum density is a requirement. In such cases, the loss of flexibility by the Hyper-V CPU scheduler in regards to selecting where to source the time slices of CPU cycles is detrimental. The high performance requirements of such VMs also means turning of NUMA spanning. Combining processor affinity and high performance with maximum virtual machine density is a complex order to fulfill, no matter what.