Rackable Systems and their Microslice Clustered 1U Servers

I think there has been a lot of negative press towards Rackable Systems.  We will give their new solution credit that it is marketed very well, and comes prepackaged and ready to go.

But let's cut through the hype of both sides, the people who love this concept and the people who hate it.

What Rackable Systems have done is a first, to minimize space, power and costs into small servers.  This is great, and many companies have already built their own servers based on small depth Supermicro Chassis and using Desktop components.

The downside is that it seems they must be using Desktop components to achieve this since server motherboards don't typically come with single socket CPU options.  As some have pointed out, the concern is not with the RAM or even CPU chips, but if the motherboards are from Desktop Units.

Server Motherboards will always be tougher and more reliable than a Desktop board, but with that said, the idea in our minds is Rackable Systems is saying it doesn't matter.  You will have multiple systems operating in a load balanced cluster situation (at least this is the only sane minded use case assumption), so the failure of a number of servers is irrelevant.

One thing we don't buy is the "Virtualization doesn't always make senes", Virtualization allows more flexibiity and leverage, although it may pose a threat to hardware vendors which is where this rhetoric has come from.

If I were to use MicroSlice, I would make sure each server is virtualized so we can add RAM hard disk and live migrate them at any point.

In short, this practice of MicroSlice is a lot of hype, but it does offer an excellent cost and reduced power benefit.  People shouldn't be put off on the kind of hardware being used so long as they're operating in a clustered and load balanced environment.

We think Rackable Systems and their opponents both make excellent points and I hope we've walked you through the smoke and mirrors of what's being said.


Tags:

rackable, microslice, clustered, serversi, marketed, prepackaged, hype, minimize, servers, depth, supermicro, chassis, desktop, components, downside, achieve, server, motherboards, typically, socket, cpu, pointed, ram, tougher, reliable, doesn, multiple, operating, balanced, cluster, sane, minded, assumption, irrelevant, quot, virtualization, senes, allows, flexibiity, leverage, pose, hardware, vendors, rhetoric, virtualized, disk, migrate, reduced, shouldn, opponents, ve, mirrors,

Latest Articles

  • How To Force Flash an AMD Instinct GPU To Another Model Using Debian Ubuntu Mint Linux
  • How To compile ollama from source to use unsupported AMD GPU with rocm in Ubuntu Debian
  • QEMU KVM Virtio GPU Windows Cannot Select 1080P
  • Linux Gnome Desktop Ubuntu Mint Debian Gets Slower After Weeks
  • Firefox How to Save Full Page As Screenshot/PDF
  • Nvidia Datacenter Driver Tesla Slow nvidia-smi response and high utilization with 0 usage
  • ffmpeg how to normalize / increase the volume of your audio
  • kdenlive audio blips pops cracks artifacts solution fix
  • haproxy / nginx certbot SSL issues
  • nginx how to see the real IP when behind a CDN
  • Docker how to find real container child process ID
  • Alibaba Aliyun how to reset password solution 'Setup does not meet the requirements, please resetting'
  • RTL88X Series 80Mhz hostapd mode for Linux Debian Kali
  • How To Deploy Your Own Mastodon Server in Docker
  • ffmpeg burning subtitles in non-English errors [Parsed_subtitles_0 @ 0x561d3a0b3b80] Glyph 0x6709 not found, selecting one more font for (Sans, 700, 0)
  • rsyslog in container config
  • Interesting Whisper AI CPU vs GPU Test
  • How to install pytorch with cuda capability for AI acceleration with Nvidia Tesla etc.. GPUs
  • How to Spider the web archive.org to recover your old website/webpage
  • Debian 10 /etc/apt/sources.list