Archive

Posts Tagged ‘system’

True Scale Out Shared Nothing Architecture – #Compute, #Storage, #Nutanix via @josh_odgers

October 26, 2013 Leave a comment

This is yet another great blog post by Josh! Great work and keep it up! 😉

I love this statement:

I think this really highlights what VMware and players like Google, Facebook & Twitter have been saying for a long time, scaling out not up, and shared nothing architecture is the way of the future.

At VMware vForum Sydney this week I presented “Taking vSphere to the next level with converged infrastructure”.

Firstly, I wanted to thank everyone who attended the session, it was a great turnout and during the Q&A there were a ton of great questions.

I got a lot of feedback at the session and when meeting people at vForum about how the Nutanix scale out shared nothing architecture tolerates failures.

I thought I would summarize this capability as I believe its quite impressive and should put everyone’s mind at ease when moving to this kind of architecture.

So lets take a look at a 5 node Nutanix cluster, and for this example, we have one running VM. The VM has all its data locally, represented by the “A” , “B” and “C” and this data is also distributed across the Nutanix cluster to provide data protection / resiliency etc.

Nutanix5NodeCluster

So, what happens when an ESXi host failure, which results in the Nutanix Controller VM (CVM) going offline and the storage which is locally connected to the Nutanix CVM being unavailable?

Firstly, VMware HA restarts the VM onto another ESXi host in the vSphere Cluster and it runs as normal, accessing data both locally where it is available (in this case, the “A” data is local) and remotely (if required) to get data “B” and “C”.

Nutanix5nodecluster1failed

Secondly, when data which is not local (in this example “B” and “C”) is accessed via other Nutanix CVMs in the cluster, it will be “localized” onto the host where the VM resides for faster future access.

It is importaint to note, if data which is not local is not accessed by the VM, it will remain remote, as there is no benefit in relocating it and this reduces the workload on the network and cluster.

The end result is the VM restarts the same as it would using traditional storage, then the Nutanix cluster “curator” detects if any data only has one copy, and replicates the required data throughout the cluster to ensure full resiliency.

The cluster will then look like a fully functioning 4 node cluster as show below.

5NodeCluster1FailedRebuild

The process of repairing the cluster from a failure is commonly incorrectly compared to a RAID pack rebuild. With a raid rebuild, a small number of disks, say 8, are under heavy load re striping data across a hot spare or a replacement drive. During this time the performance of everything on the RAID pack is significantly impacted.

With Nutanix, the data is distributed across the entire cluster, which even with a 5 node cluster will be at least 20 SATA drives, but with all data being written to SSD then sequentially offloaded to SATA.

The impact of this process is much less than a RAID…

Continue reading here!

//Richard

Monitoring #Netscaler with Operations Manager 2012 – #SCOM – via @msandbu

August 8, 2013 1 comment

Another great blog post by msandbu!!

This guide has been written with Netscaler build 73 and Operations Manager 2012 SP1 (on WS2012) with the management pack from Citrix.

Operations Manager 2012 supports monitoring network devices either through SNMP (v1, 2 and 3) or through just basic ICMP.
Citrix has made a management pack solution, which you can use to enhance the monitoring capabilities in SCOM.
The pack also includes VMM PRO management pack (Which is not gone through in this guide, just the basic management pack)

The management pack can be downloaded from mycitrix (Requires login)
https://www.citrix.com/downloads/netscaler-adc/components/netscaler-management-pack-for-operations-manager-2012.html

(Just a side note: Comtrade is a Citrix Partner who is currently making a new management pack for Netscaler so stay tuned for the new release )

So when we have a functional Operations Manager server up and running we have to install the SNMP service on one of the servers.
This can be done via Server Manager.

After that is installed go into services.msc and choose “Accept SNMP packets from any host” or just enter the IP of the Netscaler server.
Make sure that firewall on the OpsMgr server allows for SNMP traffic in…

Continue reading here!

//Richard

#Sanbolic Brings Public Cloud Economics to the Enterprise – #Melio

March 18, 2013 1 comment

Ok, I must say that this product is great!!! If you haven’t looked at it before then please do! And contact us at EnvokeIT if you want more details!

Sanbolic Enables Distributed Flash, SSD and HDD to Achieve Enterprise Systems Capability and Scale-Out In Server-Side and Commodity Storage Deployments

Waltham, MA – (March 18, 2013) – Sanbolic® today announced the general availability of its Melio version 5 (Melio5™) software – delivering distributed scale-out, high-availability and enterprise data services through software. Server-side flash has seen rapid adoption for applications such as hyperscale web serving, but limited adoption in general purpose enterprise applications. With the launch of Melio5, Sanbolic enables enterprise customers to dramatically improve their storage infrastructure economics by enabling server-side flash, SSD and HDD as primary persistent storage. Melio5 aggregates across nodes for scale-out and availability while providing RAID, remote replication, quality of Service (QoS), snapshots and systems functionality through a software layer on commodity hardware. This provides customers with the ability to deploy commodity and server-based storage architecture with similar economics and flexibility as public cloud data centers such as Google and Facebook.

With validation by hundreds of enterprise and government organizations running in production, Melio volume management and file system technology addresses the needs of high performing cost effective storage infrastructure on-premise. Melio5’s architecture is designed to scale up to 2,048 nodes and up to 65,000 storage devices enabling linear performance scalability in a cluster.

Melio5 also eliminates the need to deploy a redundant flash caching layer in front of legacy storage area network (SAN) hardware by directly incorporating flash into hybrid volumes and intelligently placing data based on file system access profiles. A hybrid volume will place random access data such as file system metadata on flash sectors while placing sequential data on low cost hard disk drives to greatly reduce the cost of capacity. The result is a highly scalable, high performance storage system, with a much lower cost than legacy storage arrays.

“Typically, server and disk drive vendors operate on gross margins in the 20-30% range. Storage array vendors, on the other hand, are often twice that or more,” said Eric Slack, Senior Analyst,Storage Switzerland. “Sanbolic’s approach leverages the architecture that the big social media and public cloud companies use, to fix this problem. By replacing storage arrays (and storage array margins) with commodity server and disk drive hardware and enabling it with intelligence through software, companies can significantly reduce storage infrastructure costs.”

Terri McClure, Senior Analyst, Enterprise Strategy Group (ESG), stated, “Sanbolic’s Melio5 software enables corporate users to take advantage of flash and SSD in conjunction with commodity hardware to create an intelligent, cost effective, and high performance storage architecture like the huge public cloud companies run, while still ensuring enterprise workload scalability and high availability.”

“Melio5 lets us solve one of the biggest challenges for our customers today – the upfront and management cost for storage – without sacrificing systems capability or performance. The Lego-like modular capability of Melio allows our customers to scale-out their storage and servers based on off-the-self commodity components, without downtime,” said Mattias Tornblom, CEO, EnvokeIT.

“LSI and Sanbolic’s shared vision and complementary products help customers to dramatically improve the performance, flexibility and economics of their on-premise storage infrastructure,” said Brent Blanchard, Senior Director of Worldwide Channel Sales and Marketing, LSI Corporation. “LSI’s Nytro™ family of server-side flash acceleration cards and leading SAS-based server storage connectivity solutions…

Continue reading here or here!

//Richard

%d bloggers like this: