Skip to content
View in the app

A better way to browse. Learn more.

Unraid

A full-screen app on your home screen with push notifications, badges and more.

To install this app on iOS and iPadOS
  1. Tap the Share icon in Safari
  2. Scroll the menu and tap Add to Home Screen.
  3. Tap Add in the top-right corner.
To install this app on Android
  1. Tap the 3-dot menu (⋮) in the top-right corner of the browser.
  2. Tap Add to Home screen or Install app.
  3. Confirm by tapping Install.

Upgrading 6.2.1->6.2.4->6.3-rc9 caused major performance issues with windows 10

Featured Replies

Team,

 

While trying to solve another issue, I upgraded to 6.3-rc9. This has caused my windows 10 vm performance to drop, specifcally while gaming, but I can see the latency issues in general OS and web browsing as well. The major drop in gaming is while using world of warcraft, loading into the game after character selection now takes 3x as long (feels like it used to when i was using horrible standard HDD), framerate has dropped by about half.

 

The VM image is stored on a user share, cache only. The cache drive is 2x 480GB SSD (btrfs)

 

System configuration is listed in my signature, VM configuration file is attached, legitimate windows license.

 

Steps I have taken:

 

1.) Graphics benchmarks with userbenchmark's tool, have me at 61% which is fine, the CPU benchmark is 17% (which is low, but typically I score low because I am only pinning 4 cpu's i think), Benchmarked disks (no previous benchmark to compare to)

-----------------------------------------------------------------------

CrystalDiskMark 5.2.1 x64 (UWP) © 2007-2017 hiyohiyo

                          Crystal Dew World : http://crystalmark.info/

-----------------------------------------------------------------------

* MB/s = 1,000,000 bytes/s [sATA/600 = 600,000,000 bytes/s]

* KB = 1000 bytes, KiB = 1024 bytes

 

  Sequential Read (Q= 32,T= 1) :  1046.275 MB/s

  Sequential Write (Q= 32,T= 1) :  586.129 MB/s

  Random Read 4KiB (Q= 32,T= 1) :    55.913 MB/s [ 13650.6 IOPS]

Random Write 4KiB (Q= 32,T= 1) :    37.448 MB/s [  9142.6 IOPS]

        Sequential Read (T= 1) :  1072.727 MB/s

        Sequential Write (T= 1) :  568.593 MB/s

  Random Read 4KiB (Q= 1,T= 1) :    15.660 MB/s [  3823.2 IOPS]

  Random Write 4KiB (Q= 1,T= 1) :    12.236 MB/s [  2987.3 IOPS]

 

  Test : 1024 MiB [C: 32.7% (65.2/199.4 GiB)] (x5)  [interval=5 sec]

  Date : 2017/01/29 13:50:10

    OS : Windows 10  [10.0 Build 14393] (x64)

 

2.) Updated the attached machine to use pc-i440fx-2.7 (instead of 2.5), did not fix the issue. did clear up a warning in the qemu logs though (2017-01-29T18:12:04.796334Z qemu-system-x86_64: warning: Unknown firmware file in legacy mode: etc/msr_feature_control)

 

 

Any help that can be provided would be great, I am willing to drop back down to 6.2.4 if I have to, but I would much rather solve the problem (or at least identify it)

 

Thanks

windows10.txt

  • Author

If it helps here is the Userbenchmark report (it isn't the best for troubleshooting or comparing VM performance though)

 

i440fx-2.5:

http://www.userbenchmark.com/UserRun/2695459

 

i440fx-2.7:

http://www.userbenchmark.com/UserRun/2696244

 

I'm not an expert on disk benchmarking but the overall sequential numbers look good to me, not sure what I should expect from random read/write though. It's possible that the issue is with CPU or drivers, so I am going to be working on those to see if I get any gains.

 

Update 1:

Downloaded nvidia 378.49 driver package, download took 30sec, unzipping took over 4minutes, then the initial system check took about 2 minutes (none of these are particularly incriminating, just providing info)

 

Update 2:

Newest nvidia drivers installed, no change, from the character select screen to having the game loaded, takes just about 60 seconds on my machine, this was previouly about 20sec before the 6.3 upgrade. For comparison sake,  my friends machine here (direct install not a VM) goes from character select to in game in 14 seconds

 

Thanks,

  • Author

Can anyone help me validate that the cache drive that my VM lives on is in fact reading and writing to the cache drive? If feels like it's not. The settings for the user share are set to cache only but I think something might be crossed.

 

Thanks...

post your xml

  • Author

1812: Its attached to the initial post, ill attach it here again

windows10.txt

Can anyone help me validate that the cache drive that my VM lives on is in fact reading and writing to the cache drive? If feels like it's not. The settings for the user share are set to cache only but I think something might be crossed.

 

Thanks...

 

there may be an easier way than this, but I don't know it:

 

make sure your array disks are spun down, either by time or by clicking spin down button on pain page.

 

launch vm.

 

if your vm img file is located on the cache only, then it should not spin up the array.

 

where is your app data folder located?

 

 

  • Author

1812,

 

In order to rule out any issues with the machine having been created under an early version of qemu, I created a brand new windows 10 install. After fully updating, and installing WoW, then benchmarking, the results were the same. 30ish FPS, 30-45sec to load (a little better), and subpar benchmarks (each about 15% higher than the previous). So after trying everything last night, I eventually gave up and reverted back to 6.2.4 (steps listed below). Immediately the VM performed crisply again, disk speed tests came back at 5x the speed, all of the benchmarks came back a 60+ percentile, and then the game returned to 100FPS, and loading <15sec. So there is clearly something wrong with libvert/qemu setup in 6.3-rc9.

 

For those that run into the need to revert from 6.3-rcX to 6.2.4 here are the steps I took:

1.) Backup your unraid flash before upgrading (I did NOT do this and regretted it immediately).

2.) Download a fresh 6.2.4, extract bzimage, bzroot and bzroot-gui

3.) Replace these on your flash drive and reboot unraid

4.) Fix Docker: Docker would not start due to a networking issue, while there may be another way to fix this, for me I removed ./config/network.cfq and restarted unRaid. This reset me from static IP to DHCP, then I just re-configured my network, rebooted one more time and docker started

5.) Fix any modified VM xml files saved during the time the server was at 6.3. The affected VMs would not show up in the list of VMs. I looked at the libvirt log (found in the VM settings page) to identify the problem lines, I then reverted those changes manually in /etc/libvirt/qemu. After a  reboot, the missing VMs showed back up, I clicked edit  on each, then saved them with 6.2.4, and they started with no issues.

 

This has me at the point I am now, I haven't found any other issues, but if this helps anyone then fantastic. And on that note, thank everyone for your help through this process.

 

Thanks,

Archived

This topic is now archived and is closed to further replies.

Account

Navigation

Search

Search

Configure browser push notifications

Chrome (Android)
  1. Tap the lock icon next to the address bar.
  2. Tap Permissions → Notifications.
  3. Adjust your preference.
Chrome (Desktop)
  1. Click the padlock icon in the address bar.
  2. Select Site settings.
  3. Find Notifications and adjust your preference.