HPE m710x & Citrix – Next generation engineer workstation

Written by Thomas Poppelgaard. Posted in Citrix, Desktop Virtualization, Edgeline, End User Computing, GRID, HDX 3D Pro, HPE, Intel, M510, M710X, Microsoft, Moonshot, NVIDIA, Provisioning Services, Receiver, SCCM, Server 2012R2, vGPU, VMware, vSphere, Windows 10, Windows 7, Windows 8.1, Windows Server 2008R2, Windows Server 2012R2, Windows Server 2016, XenDesktop, XenServer

 

hpe_m710x_specs

 

 

HPE m710x & Citrix – Next gen engineer workstation

What is the m710x?

 

Which HPE appliance can you add the m710x in

Now HPE has a new server catridges available and a new appliance that targets a new business opportunity for SMB/medium customers. Previously you needed to buy a Moonshot 1500 solution that was a 4.3 U chassis, where you could add up to 45 server cartridges. This have changed and new offerings are now available from HPE. These include Edgeline. HPE Edgeline EL1000 Converged IoT System support one HPE Proliant server cartridge and HPE Edgeline EL4000 Converged IoT System, which support up to four HPE Proliant server cartridges. This is great for business that would like CPU/GPU/Fast storage and IO in small capacity but require fast performance. These appliances are also built for IoT systems. This means that HPE Edgeline is a more accessible solution for companies no matter their size or demand.

Testing Methology

I have been testing the m710x with Citrix XenDesktop 7.9 HDX 3D Pro and Windows 10 anniversary edition. I tested several applications from Autodesk, PTC, Siemens and Rheino.

The goal was to show the user experience how it is compared to NVIDIA GRID, which is industry standard of GPU enabled desktop/apps. This is not a benchmark measuring time to load, its simply testing the user responsiveness of one connection which is m710x (2GB video memory) vs NVIDIA GRID K2 K260Q profile (2GB video memory).

Test Setup

To the left the HPE m710x and to the right HPE DL 380Gen9 with NVIDIA GRID K2

m710xvsk240q_01

Latest OS + GPU driver + VDA at that current time was installed on HPE m710x

Latest Hypervisor + OS + vGPU driver + VDA at that current time was installed on HPE DL 380Gen9

m710xvsk240q_02

The GPU driver what is seen inside GPU-Z.

m710xvsk240q_03

Use case and user profiling CAD applications

Latest CAD applications from Autodesk was used such as AutoCAD, Revit, 3DSMax, VRED, Showcase, Fusion360 and Siemens FeMap, Rheino and PTC Creo.

m710xvsk240q_04

Methodology

This is the methodology I use. I am not using any automated scripts or software to simulate mouse moment, I am using a manual process so the human eye can judge the user experience.

m710xvsk240q_05

Below video shows the user experience on the left the m710x and on the right the NVIDIA GRID k260Q profile.

m710xvsk240q_06

User experience with Autodesk AutoCAD 2017 on m710x vs NVIDIA GRID K2 – K260Q

User experience with Autodesk Fusion 360 on m710x vs NVIDIA GRID K2 – K260Q

User experience with Autodesk Fusion 360 on m710x vs NVIDIA GRID K2 – K260Q

User experience with Autodesk Revit 2017 on m710x vs NVIDIA GRID K2 – K260Q

User experience with Autodesk Revit 2017 on m710x vs NVIDIA GRID K2 – K260Q

User experience with Autodesk Inventor 2017 on m710x vs NVIDIA GRID K2 – K260Q

User experience with Autodesk Inventor 2017 on m710x vs NVIDIA GRID K2 – K260Q

User experience with Autodesk Showcase 2016 on m710x vs NVIDIA GRID K2 – K260Q

User experience with Autodesk Showcase 2016 on m710x vs NVIDIA GRID K2 – K260Q

User experience with Siemens FeMap on m710x vs NVIDIA GRID K2 – K260Q

User experience with Rheino on m710x vs NVIDIA GRID K2 – K260Q

User experience with PTC Creo on m710x vs NVIDIA GRID K2 – K260Q

Summary of keyfindings with m710x for mainstream CAD requirements.

  • m710x works great and reduces the complexity of having virtualising with a hypervisor and having to virtualise a GPU, plus  it reduces the cost and you get bare metal performance. The advantage with intel is that the GPU instructions are send directly in the chip as CPU/GPU is 1 chip and GPU is not going through a PCIexpress board.
  • To install OS, Apps for persistent its recommended using Microsoft SCCM or RES Automation Manager, and if you would like to have a simplified image strategy Citrix Provisioning is the preferred option for HPE Moonshot, which also can do caching in memory and fallback to storage this could potentially speed up the IOPS even more than M.2.
  • Its recommend doing an assessment to see if you are below 2GB frame buffer to take advantage of the m710x, many companies that uses CAD is below this as of now, but if you required more GPU memory then NVIDIA/AMD is a better choice as they have Quadro/GRID that can give 3GB+ and above video memory+ lots of compute. The m710x can open 4Gb models but then it will put 1GB in CPU/GPU and 1GB in memory and 2GB in pagefile, where NVIDIA would put all in their GPU memory. This is why its recommended using assessment software such as UberAgent to understand how much GPU you are currently using.
  • User experience is king with HPE m710x, the cartridge with Windows 10 anniversary update and Citrix XenDesktop 7.9 HDX 3D Pro is ready for CAD vendors such as Siemens, PTC and Autodesk.
  • Applications performance is great, fast and no graphics elements are lost. Graphics are smooth, responsive and acceptable.
  • The performance of the CAD applications in these test are equal with Intel P580 vs GRID K2 K260Q.
  • Elements such as loading large files, zoom-in, rotating, working in layers and rendering works great with HPE m710x.
  • The new HPE m710x catridge is ready for mainstream CAD requirements.

I highly recommend you test your own models as above is samples I have found and customer data is always different, some samples are smaller others are larger.

How to get Involved – HPE Global Innovation Labs

hpelabs

Partner and customer engagement, interaction, assessment and colloboration on solution development and applications.

HPE can help with

  • Build, testing and pre-validation of Edgeline systems and end-to-end solutions
  • Integrated real-life “Edge Experience Zones“ to interact with and highlight industry applications
  • On-site access or secure remote access
  • Datacenter connectivity and testing

Try here https://www.hpe.com/us/en/servers/global-innovation-lab.html

Poppelgaard.com – Professional Services

Above article is written myself as an independent blogger/consultant and the results of the testing of the CAD applications was accomplished by Thomas Poppelgaard and sponsored by HPE. The methodology are as is and samples can be required if the readers would like the material to reproduce the same results.

if you are interested in testing your applications on the ProLiant Server Catridges – please dont hesitate to contact me a thomas@poppelgaard.com
I can also help with above value added tasks plus much more 🙂

Source

recommended articles to read about the new Moonshot/Edgeline productline

HPE Proliant server cartridge m510 and m710x building blocks for Citrix

HPE Moonshot Reinvented

HPE Proliant server cartridge m510 and m710x building blocks for Citrix

Written by Thomas Poppelgaard. Posted in Autodesk, Citrix, Cloud, Desktop Virtualization, Edgeline, End User Computing, HDX 3D Pro, HPE, Intel, M510, M710X, Microsoft, Moonshot, Provisioning, SCCM, VMware, vSphere, Windows 10, Windows 7, Windows 8.1, Windows Server 2008R2, Windows Server 2012R2, Windows Server 2016, XenApp, XenDesktop, XenServer

HPE have released new server cartridges m510 and m710x for HPE Moonshot and Edgeline. These new server cartridges are the first units that have built-in HPE iLO, so customers can easy manage each server cartridge.

Moonshot cartridge building blocks for Citrix workloads

Below chart describes what HPE Moonshot/Edgeline current strategy is for GPU enabled apps and desktops with Citrix XenDesktop and XenApp.

hpe_moonshot_edgeline2

Below chart describes which GPU enabled HPE Proliant server cartridges that can be used.

Interesting results is that density increases dramatically from m710p to m710x.

If companies requires non GPU enabled compute the m510-16 is a interesting server cartridge for Citrix XenApp

m710x_m510

 

Let’s look at the details of the two new server catridges.

m510 cartridge – hardware specifications

hpe_m510_specs

This server catridge is a beast, it have up to 16 core and 128GB memory and is also Windows Server 2016 ready 🙂

 M510 Citrix XenApp Office Worker with LoginVSI

Below shows some benchmark Citrix have accomplished with LoginVSI, interesting is that they get:

168 XenApp sessions per m510. <1/2 watt per session! 

m510-loginvsi

above chart is made by Tony Sanchez from Citrix

The average amount of users for Knowledge worker workloads Login VSI max was around 138 with 145 users being active at the time of the test. The baseline of 780 was consistent with  additional tests that were repeated. The High Scalability policy template was applied to the desktop group for all Login VSI users.

These test was made by Citrix internally, please read the blog here.

CPU performance of the m510 during the 145 user test. The max CPU utilization was around 93%

during the peak of the test without fully saturating the processor.

m710x catridge – hardware specifications

hpe_m710x_specs

m710x-storageoption1m710x-storageoption2

This server catridge is a beast, it have latest skylake core and 64GB memory and is also Windows 10, Windows Server 2016 and even RHEL, Ubunto ready 🙂

Then its also ready to be virtualized with Citrix XenServer and VMware vSphere and KVM, I will later blog how its working with these hypervisors.

M710x Citrix XenApp Knowledge Worker with LoginVSI

Below shows some benchmark Citrix have accomplished with LoginVSI, interesting is that they get:

67 XenApp Knowledge sessions per m710x

m510-loginvsi

These test was made by Citrix internally, please read the blog here.

 

Hardware Summary of HPE ProLiant m510 and m710x

summary_m510-m710x

I hope the above gives you a pretty good idea on where Moonshot & Edgeline is going – and this is just for Citrix XenDesktop and XenApp. I will cover how its used with Octoblu another time.

How to get Involved – HPE Global Innovation Labs

hpelabs

Partner and customer engagement, interaction, assessment and colloboration on solution development and applications.

HPE can help with

  • Build, testing and pre-validation of Edgeline systems and end-to-end solutions
  • Integrated real-life “Edge Experience Zones“ to interact with and highlight industry applications
  • On-site access or secure remote access
  • Datacenter connectivity and testing

Try here https://www.hpe.com/us/en/servers/global-innovation-lab.html

Poppelgaard.com – Professional Services

if you are interested in testing your applications on the ProLiant Server Catridges – please dont hesitate to contact me a thomas@poppelgaard.com
I can also help with above value added tasks plus much more 🙂

 

Source

Citrix Blogs – X Marks the Spot: XenApp, XenDesktop & XenServer with Intel Xeon & HPE Moonshot!

Citrix Blogs – We Choose to Go to the Moon!

 

Citrix XenDesktop 7.11 and XenApp 7.11

Written by Thomas Poppelgaard. Posted in AMD, Apple, Azure, Citrix, Cloud, Datacenter and Cloud, Desktop Virtualization, Director, End User Computing, FirePro, GRID, GRID 2.0, HDX, HDX 3D Pro, HTML5, iOS, Linux, Microsoft, NVENC, NVIDIA, OS X, Profile Management, Provisioning, Provisioning Services, Reciever, StoreFront, vGPU, Virtualization Ready, Windows 10, Windows Server 2016, XenApp, XenDesktop

7-11-logo

Citrix have released a new version of Citrix XenDesktop 7.11 and XenApp 7.11 and is now available for download.

Citrix raises the bar of for user experience and new product release of following technologies

  • Virtual Delivery Agents 7.11 for ServerOS and ClientOS
  • AppDNA 7.11
  • Storefront 3.7
  • Provisioning Services 7.11
  • Profile Management 5.5
  • License Server 11.14
  • Citrix Receiver 15.0 for Windows
  • HDX RealTime Optimization Pack 2.1.1 for Microsoft Skype® for Busines
  • Citrix SCOM Management Bundle for XenApp and XenDesktop (2016_08_24)
  • Linux Virtual Delivery Agent 1.4
  • Tech preview for HTML5 redirection

This release is an important release no matter if you are working daily with Office application such as Excel, Word or Browsers and even highend applications such as CAD. The features in 7.11 have important improved user experience from the VDA to the Receiver that improves dramtically the user experience. NVIDIA NVENC technology is now part of VDA and supports even multiple monitors. The admin can now monitor RTT within Director this feature have been something I have asked for very long time and now finally its in the product, customer will love this new feature so its fast to see where the issue is in a infrastructure with which users that have latency issues. Version 7.11 is the release that fully supports Microsoft Windows Server 2016 that is soon GA, this means you can install Delivery components on Windows Server 2016, VDA on Server 2016, use Azure N-series with support for Windows Server 2016 Hyper-V Discrete Device Assignment (DDA) or you can use it onpremises with Hyper-V. Support for UWP is HUGE and I am very excited about this technology and this also used in Microsoft Hololens so cant wait to a Receiver for hololens so you can publish UWP apps to Hololens 😉 Imagine that. I can keep going on with all these new features lets dig in below and learn whats new, its incredible that Citrix raises the bar and comes with huge improvements and they this each 3 months 🙂 yes each 3months, you read it correct. If you dont have a plan for this in your company I highly recommend you build a strategy on how you upgrade you Citrix environment frequently to get these awesome new features.

Microsoft Hololens Commercial Edition

Written by Thomas Poppelgaard. Posted in Augmented Reality, Citrix, Cloud, Datacenter and Cloud, Desktop Virtualization, End User Computing, Microsoft, Virtualization Ready

Hi All

I have been having the Microsoft Hololens developer edition for some weeks now and I am amazed how a great product it is, when I got unbox the package I could quickly see that this was not a typical “developer” product aka “beta” product it seem finish and ready for shipping for the masses.

IMG_9017

I created a video of how great Citrix is working together with Hololens, you can see it below

In the nearest future you will be able to run Published applications from Azure such as the new announced service Citrix XenApp “express” instead of the discontinued “Azure RemoteApp” – read more about this annoncement here

Below video gives you an idea how it might look like working on either a Word document or heavy GPU CAD application such as Autodesk AutoCAD from the Hololens. The applications are not installed on the Microsoft Hololens, they are running from servers securely and pixels are only streamed to the Microsoft Hololens, this is what is called remote graphics, and now possible in Augmented Reality. Powerful technology and many use cases for this new workstyle.

 

Today Microsoft is now shipping the Hololens Commercial edition.

 

The Commercial Suite includes the Development Edition, enterprise features for added security and device management, and a warranty. Transform your business with Microsoft HoloLens.

Contact your Microsoft account representative or email mpcsales@microsoft.com.

hololens

Unboxing Microsoft HoloLens Development Edition

IMG_8904

IMG_8905IMG_8906IMG_8907

What’s in the box

  • Microsoft HoloLens Development Edition
  • Clicker
  • Carrying case
  • Microfiber cloth
  • Charger
  • Micro-USB 2.0 cable

Enterprise features

  • Kiosk mode. With HoloLens kiosk mode, you can limit which apps to run to enable demo or showcase experiences.
  • Mobile Device Management (MDM) for HoloLens. Your IT department can manage multiple HoloLens devices simultaneously using solutions like Microsoft InTune. You will be able to manage settings, select apps to install and set security configurations tailored to your organization’s need.
  • Identity. Azure Active Directory and next generation credentials with PIN unlock.
  • Windows Update for Business. Controlled operating system updates to devices and support for long term servicing branch.
  • Data security. BitLocker data encryption and secure boot is enabled on HoloLens to provide the same level of security protection as any other Windows device.
  • Work access. Anyone in your organization can remotely connect to the corporate network through a virtual private network on a HoloLens. HoloLens can also access Wi-Fi networks that require credentials.
  • Windows Store for Business. Your IT department can also set up an enterprise private store, containing only your company’s apps for your specific HoloLens usage. Securely distribute your enterprise software to selected group of enterprise users.

Source

https://www.microsoft.com/microsoft-hololens/en-us/commercial-suite

 

NVIDIA GRID – AppGuide (AutoCAD)

Written by Thomas Poppelgaard. Posted in AutoCAD, Autodesk, Best Practise, Desktop Virtualization, End User Computing, GRID, Horizon, NVIDIA, VMware, vSphere

Hi All.

I want to share this with you all, Luke Wignall and his team from NVIDIA have created some great AppGuides, that helps with understanding how many users can you put on a NVIDIA GRID system with either K1/K2 in a VMware environment. These guides are made together with vendors such as Autodesk. The guides focus on following apps Autodesk AutoCAD.

In this blogpost my goal is to highlight the great work NVIDIA have done creating the scalability app guides and these guides helps you if you want to virtualize Autodesk AutoCAD 2015 with NVIDIA GRID and VMware Horizon. The guides are great – cause they give an idea what you would require in a virtualized environment and these can be reused for other virtualized platforms such as Citrix and Microsoft – keep in mind that results might be different. If you would like to get more informations about how the setup is configured and which methodology i recommend you read the AppGuide, you can download it in under source in the end of this article.

The appguides gives a great idea to understand the impact of CPU and how the GPU are giving value.

Autodesk-Logo-2013

AutoCAD_2016

About AutoCAD 2015

Autodesk AutoCAD is one of the most globally used software platforms for CAD design and documentation.  AutoCAD leverages both CPU and GPU to deliver a high quality user experience, and as a result, there are several things that need to be considered in architecting your GRID vGPU solution: the size of your map data, the concurrency of your users, and the level of interaction with primary 2D and some 3D data.

Results NVIDIA Appguide for Autodesk AutoCAD 2015

autodesk-nvidia-vmware

The following are results of our testing, looking for the greatest scalability while still within performance expectations.  It’s important to note that your users, your data, and your hardware will impact these results, and you may decide a different level of performance or scalability is required to meet your individual business needs. As the Catalyst benchmark does not push AutoCAD’s GPU capabilities, and was built to push the limits of dedicated hardware versus the shared resources of VDI, the decision was made to stop testing once the CPU was approaching 100% utilized and test times had climbed past twice what we were finding on the a single physical workstation with dedicated resources.  We then met with the Autodesk AutoCAD team, discussed the results, reviewed the tests in action, and physically verified that this was still within what a typical user would deem acceptable and usable. When running AutoCAD, anything higher than 20 FPS is awesome, but users generally don’t notice the difference once you exceed 30 FPS.  However, once you drop below 10 FPS, the software is going to feel very sluggish and become unusable by the time you hit 5 FPS. • 20 fps above is good • Below 10fps – sluggish • 5 fps – unusable

  • 32VM : K220Q perform better than K120Q but K120Q is still maintain avg 31FPS. 
  • 40VM : Due to vGPU configuration, need K120Q, avg FPS is 24 FPS
  • 48VM : one you hit 40 VM running, avg FPS is dropping below 10 FPS. 

AutoCAD requires significant CPU resources, so investing in higher CPU speeds and more cores will pay off on performance and scalability.  For medium to large models, K240Q performance might be better for a real use scenario. Since your own situation is different, you must test with your own models to ensure the most accurate results. The chart below shows a comparison between two different sets of VDI guests, one using the K2 and its K220Q profile, the other a K1 and its similarly sized frame buffer profile, the K120Q:

äutocad2015_scaling-01

Notice that as scale, the number of concurrent VM’s increases, there is an obvious drop in performance, and logs will show this is the CPU becoming 100% utilized.  This is a “peak workload” test as all sessions are started in unison, we would expect humans to be more staggered in their workflow.

The next chart shows results when we add that synthetic human behavior, we delay the launching of each session by 5 seconds, this offsets the tests and prevents all tests hitting the same function and impacting the CPU in unison.

äutocad2015_scaling-02
Notice that with delayed launching, or staggered starts, the performance remains high to a much greater scale of concurrent sessions.

Additional findings from this testing:
vCPU –  2 vCPU are sufficient for this benchmark, however increasing model size and complexity will change this. 
• Virtual System Memory – 2 GB is sufficient for this benchmark, however increasing model size and complexity will change this.  
• K220Q/K120Q  : both show capped FPS caused by frame rate limiting (FRL) 
• vGPU has 45 fps frame limiter for performance balancing across multiple VM

AutoCAD 2015 Users per server

Based on the NVIDIA GRID™ Performance Engineering Lab (GRID P.E.L.) findings, NVIDIA GRID provides the following performance and scalability metrics for Autodesk AutoCAD 2015. These metrics are based on tests with the lab equipment shown in the graphic below, using the Cadalyst benchmark, and in working with Autodesk and their emphasis on end user usability.  Of course, your usage will depend on your models and equipment, so this Application Guide is intended to be used as a starting point for your implementation.

autocad-users-per-server

 

Source

Download the NVIDIA GRID vGPU APPLICATION GUIDE FOR AUTODESK AUTOCAD 2015 ON VMWARE HORIZON here

 

Recent Comments

Alex

|

So how come version 3.11 doesn’t work for application switching?

John

|

Hello, how to allow SR-IOV for the Intel P580 in a m710x? (unable to find any settings in BIOS)

I get the following error: Dismount-VmHostAssignableDevice : The operation failed.
The device cannot be assigned to a virtual machine as the firmware (BIOS or UEFI) on this host computer system indicates that the device must remain in
contact with the firmware running in the host. The device can only be used in the management operating system. You should contact your OEM to determ
ine if a firmware upgrade is available, or if the PCI Express device can be reconfigured to be independent of the host firmware.

Aza

|

Great article Thomas.

Can you tell more about the difference in user density between M510 and M710x?
Citrix published an article with a LoginVSI test related to the M510 9https://www.citrix.com/blogs/2016/06/30/we-choose-to-go-to-the-moon/), but I’m more interested in the M170x because of its Iris Pro P580.

Olivier

|

Thank you! Thats the solution i needed.