HyperIP by NetEx Blog

Solving WAN Challenges of Workload Mobility Using HyperIP

Posted by Marketing

IBM released a whitepaper on Leveraging the Cloud to transform Test and Development. As companies implement software in the cloud on an on-premise platforms for workload sharing, challenges emerge in the movement of that workload between the customer premise and the offsite destination of that data. Does development become hindered if I move that workload offsite or does it have to be in my LAN? Can I move it offsite so workload mobility, flexible system and software configuration, and continuous provisioning be leveraged as a cost effective solution? IBM’s Smart Cloud solution and HyperIP’s WAN Acceleration Virtual Appliance ensures that customers can leverage workload mobility over the WAN, without suffering the performance problems caused by the WAN.
Customers leverage many techniques for moving the workload between the test/dev environment and the customer’s developers. vMotion, Live Migration, FTP, RSYNC, TSM, ProtecTier, etc. All of these applications require the workload to traverse the WAN. TCP/IP has limitations on the movement of big data. HyperIP removes those limitations to significantly improve performance of workload mobility, in excess of 10-12x faster by providing a WAN Acceleration technology that removes packet loss, latency, and out-of-order packets from task. HyperIP then implements block-level data reduction algorithms to significantly reduce the time to move that workload to or from the cloud hosting facility. This all translates to cost effective network transfers and connectivity.

For more information on HyperIP and to request a trial, go to http://www.netex.com .

This entry was posted in HyperIP, and tagged , , , , , , , , , Bookmark the permalink.

HyperIP Series – You Asked About vMotions Over Global Networks….

Posted by Marketing

Storage vMotion is different from “vMotion” where your storage stays the same and you change hosts, or “live storage vMotion” where the host is the same and you change the datastore. The storage vMotion I’m talking about is changing both the host and datastore. Storage vMotion works great on a LAN, but performing it over a WAN is a whole different story.

If you have ever tried to Storage vMotion your virtual machines over a WAN, I’m guessing it didn’t work so well. Most who try to do this are not able to. Why, you ask? Because over a WAN the native TCP stack on your ESX(i) hosts will start to back down. You’ll be lucky to complete a small storage vMotion over moderate distance in several hours, if at all. We have several customers who have tried this natively and have run into problems.  Now they use HyperIP WAN Optimization virtual appliance to mitigate performance issues making long distance vMotion a reality.

One of our customers, a large ‘financial’ enterprise level corporation, has been using HyperIP for their storage vMotions for well over a year now. When they first realized they had a need to migrate VM’s over their WAN, they would start a storage vMotion at the end of the day, expecting it to be completed when they came into the office the next day.  What they found is that in almost all attempts, the vMotion failed. They installed HyperIP and instantly they were vMotioning thousands of VM’s over their WAN between data centers. Last time we spoke to them, they had storage vMotioned over 1200 VM’s using HyperIP. They now do this on a regular basis. Before HyperIP they were lucky to get a single vMotion to finish.

Being able to move a VM at high speed anywhere in the world at anytime can have a profound impact on the way you do business and the way that your IT infrastructure is built and managed. You can build and configure VM’s locally at your corporate IT data center and HyperIP storage vMotion them out to where they need to go. If you are consolidating data centers or branch offices, you’ll need to move those VM’s over your WAN, or even a small internet link. If your organization is building dozens, hundreds, or thousands of VM’s, you’ll want to use HyperIP to move them.

In conclusion, HyperIP is downloadable, easy to implement, has a very small VM footprint, is inexpensive, and most important of all is absolutely necessary to storage vMotion your VM’s over a WAN. Download HyperIP now to start your free 30 day evaluation to take advantage your new ability to storage vMotion your VM’s anywhere in the world. Click the big orange box above to start the download process.

This entry was posted in HyperIP, and tagged , , , , , , , , , , , , Bookmark the permalink.

HyperIP Series – Works Great with IBM Tivoli Storage Manager (TSM)…

Posted by Marketing

Enterprise Remote Backup has become more of a reality than a perception with the advent of enterprise-class backup apps like Tivoli Storage Manager (TSM).  Building a central information archive using TSM Client to Server backups and restores can now be done over the WAN with the HyperIP WAN Optimization Virtual Appliance.  Case studies, such as this one, Triangle-Ireland, talk about reducing backup and recovery windows between 50%-90% over the existing WAN. Significant flexibility with software because HyperIP scales its virtual footprint from 1Mbs-800Mbs in the same virtual appliance.  This allows for a typical hub & spoke architecture from numerous remote sites back to a data center or offsite public or private cloud storage provider.  Whether there are 10 remote sites or 400, HyperIP scales to meet with the RTO’s of every site, cluster, or server, virtualized or not.

Tivoli Storage Manager Client or Server software has network tuning parameters and on-board compression as noted in: TSM Performance Tuning Guide.  TSM can offload TCP tuning and data compression to HyperIP to recover those precious cycles on their resident servers.  HyperIP has the ability to take over session management of the IP data stream and implement software-based, adaptive, block-level compression with no impact on the TSM servers.

For Best Practices for Deploying Tivoli Storage Manager over HyperIP, check out our documentation link: Best Practices for HyperIP Deployment.

Don’t just deploy Enterprise Remote Backup, but HyperIP it.
HyperIP is proud to be “Ready for IBM Tivoli” certified.

This entry was posted in HyperIP, and tagged , , , , , , , , Bookmark the permalink.

HyperIP Series – You Asked About Enabling Centralized Remote Backup

Posted by Marketing

A successful remote backup and recovery process depends on the right backup applications, the right management of those apps, and the network to support it. How can HyperIP WAN optimization virtual appliance enable this? Let’s look at a typical remote backup solution consisting of remote servers, residing in a branch, and a central repository of data for the backups, residing in a data center. These servers, virtualized in most cases, require remote backups to occur in a given backup window for each server. These backups are slave to the size of the WAN bandwidth to/from the branch. To reduce the backup windows or at worst, meet them, the WAN overhead has to be eliminated.

Typically, TCP overhead limits actual application throughput over these WAN links. The table below shows anticipated application throughput with HyperIP. Compare this to what you get now and the value proposition of HyperIP becomes evident.

HyperIP mitigates the effects of packet loss, latency, and out of order packets to more effectively drive near wire speed of the WAN link (~95%). Then, if needed, block-level compression, a feature of HyperIP, is applied to further reduce the amount of data traveling over the WAN link, dramatically increasing application throughput. This effectively turns the WAN into LAN-like performance from the backup client to the backup server destination.

Sounds interesting? Want to try HyperIP with your backup application? Go to our website at www.netex.com and click on the big orange download box. This will get you started on the right track. Our SE Team at NetEx will be glad to help size your bandwidth requirements for remote backup.Feel free to CONTACT US.

This entry was posted in HyperIP, and tagged , , , , , , , , Bookmark the permalink.

Goes together like PB & J

Posted by Marketing

Here is a brief success story about a Financial Services Company that uses HyperIP WAN Optimization virtual appliance to optimize their Veeam Backup & Replication.

The company uses a DS3 circuit between data centers and carves out an 8 Mb MPLS circuit for replication and SQL log file transfers. Packet loss and excessive latency was causing poor application performance.

From a high level standpoint, they wanted to improve Veeam Backup & Replication performance, reduce bandwidth costs by using their existing WAN more efficiently, and provide a disaster recovery program that they could rely upon.

HyperIP was downloaded from the VMware Virtual Appliance Marketplace (VAM) and installed on two existing VMware servers. In a very short period of time the customer’s IT architect installed HyperIP  and shortly thereafter was optimizing the Veeam Backup & Replication. Citrix WANscaler was also tested but the customer selected HyperIP for a variety of reasons:

Using a virtual infrastructure and virtual appliance provided ease of deployment, low cost of deployment, ease of integration into the existing infrastructure and the speed of deployment for newly created virtual machines.

For this customer it was extremely important that HyperIP was certified as VMware Ready versus other products. Customer Quotation – IT Infrastructure engineer:

“HyperIP did what I needed it to do at a fraction of the cost of the competition. Ease of implementation, good documentation, and pleasant experiences with support. HyperIP reduced the time to replicate VMware VMs by more than 80% while using less bandwidth. It was easy to implement due to good documentation and responsive tech support. The cost of increasing bandwidth was significantly higher than the cost of HyperIP.”

So with HyperIP and Veeam Backup & Replication this company has a replication (disaster recovery) solution they are happy with, are getting better WAN throughput and performance and are reducing costs by leveraging their existing infrastructure.

Download and test HyperIP for yourself at – http://www.netex.com/hyperip/evaluation-request

Portions of this case study are sourced from:
TechValidate Survey of a Medium Enterprise Financial Services Company
http://www.techvalidate.com/product-research/netex-hyperip/case-studies/FDC-B76-71E

 

This entry was posted in HyperIP, and tagged , , , , , , , , , , Bookmark the permalink.

HyperIP Series – You asked about Backup…

Posted by DaveHuhne

Backing up your data to a remote site is a business necessity. The method or design of your backup solution will be dependent on your requirements and whose system you own. Things like backup window, WAN, de-dupe, distance and incrementals all come into play when making purchase decisions for a backup solution. So why do I need a WAN Accelerator? My storage backup system de-dupes and compresses the data before sending it to its remote DR site. If I install a WAN Accelerator will it provide any additional value? Will data be further reduced after dedup and how much will my application throughput increase?

These are great questions but first you will have to determine if there is a bottleneck in your network. My backups don’t complete on time, why? My backup application throughput is low, why? I can only backup certain servers per night or my backup fills the window and I have new servers arriving as we speak. I can’t keep up so what should I do to solve the issue?

I can buy more bandwidth, increase the buffers in my switches, make the TCP windows bigger. Some of these remedies are expensive, take time or maybe I can’t make changes to the network? A plausible alternative is to test a WAN Accelerator.

HyperIP WAN Optimization virtual appliance helps alleviate many network issues that cause poor application performance and throughput over WANs. The software doesn’t care that your backup system data has been prior de-duped and/or compressed. The software uses an adaptive compression algorithm and will attempt to further reduce deduped data if at all possible. Compression is only one feature of the software that improves application performance. TCP transfers will also be affected by any number of network issues including congestion, jitter, latency, and packet loss. A minimal amount of packet loss can reduce effective throughput by half. Any resulting retransmits will further consume your bandwidth into making you believe your WAN utilization is high when in fact you are really only moving a fraction of the real data. HyperIP shields TCP applications from network issues allowing the maximize throughput.

So back to the question “What data reduction will I get with HyperIP”? The answer is HyperIP will manage the network so that the maximum throughput will be achieved as long as the application can deliver the required data to fill the pipe. As an example we have customers whose backup windows have gone from 24+ hours down to single digits. A recent Veeam customer reduced their backup window from 15 hours to 3 hours with HyperIP. CLICK HERE to see the Veeam / HyperIP success story.

Obviously every backup environment is different but downloading and testing HyperIP for yourself is quick and easy and could save you a lot of time.

This entry was posted in HyperIP, and tagged , , , , , , , , , , Bookmark the permalink.

HyperIP’s ‘Thin’ Virtual Appliance Footprint Comparison

Posted by Marketing

Building a virtual appliance to leverage the advantages of consolidation of server resources has obviously exploded. The idea of implementing WAN optimization in a virtual appliance has become more of a necessity than a luxury. VMware has created Best Practices for virtual appliance deployment including information for required processors, memory, disk space for the expanded image, NIC’s, etc. Is it cost effective to implement a virtual appliance versus a standalone WAN Optimization controller? Not always, so it pays to do some homework. HyperIP’s virtual footprint looks like this versus others.

The WAN Optimization footprints for Riverbed, Silver Peak and Blue Coat are so large they  almost negate the ability for the customer to deploy them in a remote or branch office just because of the sheer size. HyperIP has the smallest virtual machine footprint of any WAN Optimization virtual appliance which equates to a cost effective solution. The same ‘thin’ foot print scales from 1.5 Mb/s to 800 Mb/s which provides scalability and investment protection. Check it out for yourself. Download the OVF through VMware’s Virtual Appliance Marketplace or at www.netex.com.

Specifications for Virtualized WAN Optimizers:

Virtual Steelhead: http://www.riverbed.com/us/assets/media/documents/data_sheets/SpecSheet-Riverbed_VirtualSteelhead.pdf

Silver-Peak VX: http://www.silver-peak.com/assets/download/pdfpub/ds_SilverPeak_VX.pdf

Blue Coat Proxy-SG VA: http://bluecoat.com/products/sg/virtualappliance look under specifications.

This entry was posted in HyperIP, and tagged , , , , Bookmark the permalink.

Oh Canada, Bandwidth is Expensive – Eh?

Posted by Marketing

Recently a customer brought it to our attention that unlimited bandwidth pricing in Canada is up to 90 times more expensive than other countries.

“Despite Canadians ranking 33rd in broadband Internet speeds worldwide (speedtest.net), Canadian carriers cry foul; their networks are congested and unable to cope with the sheer volume of data that Canadians are consuming,” says the writer, Chris Stavropoulos.

In Japan, England, and the U.S, carriers provide account options for unlimited bandwidth. In Canada, there may be a standard rate for usage of 300 GB per month, with a per-GB charge for overage – an example of usage-based billing. Some Canadian DSL providers cap their overage fees, others do not. The article states cable internet providers are expected to adopt this same usage-based pricing model sometime this year.

In Africa, bandwidth prices remain high because of the expense of deploying necessary infrastructure (satellite versus Fibre optics), complicated and bureaucratic licensing policies, and profiteering.

For data-heavy operations like EMC SRDF, Celerra/Centera, NetApp SnapMirror, Symantec Volume Replicator, Dell EqualLogic, Veeam Backup & Replication, standard file sharing protocols like File Transfer Protocol (FTP), and many others, usage-based billing would quickly add up.

WAN optimization cuts bandwidth costs and resource consumption with minimal effort. Global users can reduce infrastructure costs and alleviate bandwidth constraints without sacrificing service quality, reliability or performance. For some service providers, savings are in the millions of dollars.

Compression is another way to significantly increase effective data throughput and save on overage costs. Compression ratios depend on the type of data that is being compressed. Production results have demonstrated a range of 2:1 up to 15:1. HyperIP WAN Optimization virtual appliance compresses data blocks (versus TCP packets) and efficiently aggregates data into blocks, before moving over the WAN. This puts more data into the HyperIP accelerated WAN. HyperIP’s block level compression feature is very effective, even at speeds up to OC3 (155 Mbps).

Since HyperIP WAN Optimization virtual appliance increases effective data throughput 3 to 10 times, organizations can get increased performance without increasing their usage of bandwidth. Simply put, it takes less bandwidth to replicate data with HyperIP than without it. Even in Canada.

This entry was posted in HyperIP, and tagged , , , , , , , Bookmark the permalink.

HyperIP WAN Optimization Virtual Appliance Solves Key Network Issues for Dell EqualLogic Replication

Posted by Marketing

A customer was recently experiencing slow replication of their databases using a Dell EqualLogic Replication application from their iSCSI SAN. They were concerned about replication windows so decided to research performance on the Dell website. In their investigation they found the following document on the Dell website.

Using Dell EqualLogic Auto Replication

This document explains use case scenarios and various configuration issues of Dell EqualLogic Replication in a typical DR scenario. A couple of the main network considerations when implementing Dell EqualLogic Auto Replication should be bandwidth and latency of the circuit. In high latency connections, replication will still work, but allow more time to complete. This is sound advice. From our experience, packet loss can also have a huge impact on application throughput.

HyperIP WAN Optimization virtual appliance, when configured with EqualLogic Replication, can reduce bandwidth requirements for replication by over 50% while maintaining high throughput. This brings the windows for replication into minutes instead of hours, allowing for the ease of testing the recovery plan, as well as recovering a node, server, cluster, or the entire site’s data volumes after a true disaster.

Simply, your current benchmark or replication assessment must take into consideration the average available bandwidth on a link with any packet loss or latency can be reduced to 40%-60%. HyperIP accelerates applications over WANs by time of day, to nearly 95% utilization. With a combination of block level compression, latency and packet loss mitigation, HyperIP can then improve EqualLogic replication throughput by 3X-6X .

Check out this TechValidate case study from one of our customers who uses Dell EqualLogic Replication and HyperIP. Click here to see case study.

This entry was posted in HyperIP, and tagged , , , , , , , , , , Bookmark the permalink.

Subscribe to our Blog

With RSS feeds, you don't have to visit our site everyday to keep up to date. Simply subscribe to our blog via RSS or Email and our posts will come to you!

Subscribe
via RSS

Search Blog Posts

Search

Subject

Visit our Website visit arrow