[Kevin Patrick]

I changed out two things.

First I tried the new 10Gtek SFP+ cable. This cable is supposed to be compatible with the Mellanox driver in the QNAP network card. No change at all.

Next I replaced the network card in the server with the QXG-10G1T card.

I connected this card to the RJ-45 port of the UniFi 10 Gbe switch. No change at all.

Finally, I connected the iMac Pro directly to the new network card in the server.

I set the IP address manually on the server and the iMac Pro. However, QNAP complained about not having any DNS server address. I rebooted anyway, since with my limited networking knowledge, I didn’t think this should matter for this test.

No change at all.

Of everything I’ve tried I simply cannot get the performance numbers to change.

However, when I went to check the Jumbo Frame settings the server I discovered that the only Jumbo Frame option for this new network card was 1500. No other option was available.

(insert you favorite frustration expletive here)

Am I missing something thats preventing me from changing the Jumbo Frames settings?

[Kevin Patrick]

Bob,

While waiting for the new card (coming today) I heard back from QNAP. Apparently, they have the same UniFi switch I have and their test results are the same as mine. In their words, “not good.”

They suggested connect direct and retest. (same suggestion as yours, they just have a higher latency response time)

Though I do have to connect up to other devices (both wired and wireless) to this server. So I will still need a 10 Gbe switch. I’ve nothing but success with Netgear, so I’m wondering what you opinion is of Netgear’s GS110MX switch?

[Kevin Patrick]

Done.

I get the card Monday, probably late.

I’ll post back with results.

Thanks Bob

[Kevin Patrick]

Hi Bob. Thanks for replying.

Given the volume of help you provide here on the Cow, you probably don’t recall helping me out a few weeks ago when I first set up our QNAP. (see my configuration below) I started this post to specifically discuss the SFP+ cable.

Interesting that the QXG-10G1T card you recomend has the same controller as my iMac Pro. I’d gladly replace the pre-installed card if this either addressed the performance
issue, or simply made the system happier.

While we probably can’t rule out the Ubiquiti switch as being an issue, it does allow write speeds much higher than read speeds. Could a switch even tell the difference?

QNAP checked to make sure that I had the correct MTU/Jumbo frames set correctly on both the iMac Pro and the server, which I did.

At this point, QNAP and Ubiquiti are esculating this performance issue. I hope to hear back from QNAP Monday.

I did order another SFP+ cable. This new version (from the same vendor) does state that it’s compatible with both Ubiquiti and the Mellanox controller. I don’t have a high level of confidence this will address the issue. I’d guess this is a works or doesn’t work issue, as opposed to a write is faster than read issue.

TS-873U-RP
Dual Port 10 Gbe SFP+ (preinstalled)
– I’m guessing it’s the LAN-10G2SF-MLX
– Mellanox MT27520
8 x Hitachi 8 TB Drives, HUH728080ALE600
One Static Volume
(no Storage Pool)

10Gtek Cable from QNAP to Switch
This is the cable in question, as 10Gtek says this is compatible with Ubiquiti but not compatible with the Mellanox chip in the QNAP 10Gbe card.

US‑16‑XG UniFi 10Gbe Switch

iMac Pro connected via RJ-45 Cat 6 to Switch

SMB:
I followed Apple’s published article about disabling SMB signing. It appears this is off by default on iMac Pro models, since I didn’t have to change anything.

Per Apple: (I made no change to this file, it was already set to no)
Open the /etc/nsmb.conf file.
Set the signing_required value to “no,” like this:
[default]
signing_required=no
Save the /etc/nsmb.conf file.
Disconnect and then reconnect any mounted SMB shares to make the changes take effect.

MTU Jumbo Frame:
iMac Pro (sys prefs)
– Configure Manually
– 10GbaseT
– full-duplex
– Jumbo (9000)
– (checked) AVB/EAV Mode
QNAP
– Jumbo Frame 9000

[Kevin Patrick]

Steve,

On a long call with QNAP, their tech guy did run iPerf. (something I’m not familiar with)

The iPerf results were basically the same as all the other basic tests. (Blackmagic and AJA)

Though I’m not sure if he ran it from the server to the iMac Pro. He’s esculating it to QNAP HQ. Any advice on how to run iPerf on the server side would be appreciated.

For reference:
~ 560 MB/sec Write (many test sources confirm)
~ 350 MB/sec Read (many test sources confirm)
~ 630 MB/sec Read (testing the HW only within the server, so this is basically max perf)

It’s odd that the read speeds are less (a lot too) than the write, as QNAP marketing posts the opposite.

I realize their is always overhead that keeps any real world results from getting anywhere near what the marketing guy says is theoretical maximum. But the read speeds are about half what they should be. Sadly read speed are rather important when editing.

[Kevin Patrick]

Both the iMac and the QNAP server needed to be changed to Jumbo frames, 9000 MTU. However, makeing the changes had no effect on performance.

[Kevin Patrick]

I created a single Static Volmume.
I created a shared folder.
I mounted the folder to my iMac Pro, using Qfinder Pro

I then ran AJA speed test and got the following results.

Speed Test – Write/Read MB/sec
iMac HD – 2,747/2,415
Promise T2 463/423
QNAP – 499/372

I ran Blackmagic’s speed test as well and I got similar results.

Then I realized I had not turned off SMB siging.

I followed Apple’s link: https://support.apple.com/en-us/HT205926

Though when I looked at the contents of nsmb.conf, is was already set to “no”.
[default]
signing_required=no

Just to be sure, I rebooted my iMac Pro, but I got the same results.

QNAP does state that the throughput of the TS-873U is 1353/1567. But, that’s with using both (2 x 10GBe, 64KB) ports.

So, I’m not really getting half of that speed, which is their theoretical speed.

Still, I want to make sure I’m getting the performace I should, for the setup I have. And, that I haven’t missed something in the setup.

[Kevin Patrick]

You’re suggestions works great for our edit station. iMac Pro, running FCPX. All media, projects and data is kept on the server. This was previously all on a direct attached Promise 8 drive thunderbolt device.

Now we’re moving to a QNAP device, I’m going to use it to make life easier for the various laptops users. They keep data on their laptops and need it backed up. They like Time Machine (I like Carbon Copy Cloner, bootable backups). Either way, using the server will be much better (for everyone) rather than external drives for random backups.

Also, we’re going to use the QNAP Apple TV app to view finished projects. As well as a shared folder for everyone to pass/share any files they need. (assuming that works as well as the marketing material says it does)

Reading QNAP’s material, it’s easy to head down a path of Storeage Pools and multiple Static and/or Thick Volumes. Which is why I’m here, because I don’t want to over think this. I don’t want to create something that’s more complicated, lower performance and/or difficult to expand.

I’m going to take your advice and go with one Static Volume with Shared Folders/Users.

I appreciate you taking the time to help me out. I actually had the opportunity to meet (and briefly talk) with you at NAB a few years ago. I think it was at OWC/Mac Sales booth? Again, thanks. Let me know if you have any other questions about our UniFi products. Which for the past year have been working great. (famous last words)

[Kevin Patrick]

The US-16-XG 10 GB has:
12 SFP+ Ports
4 10 GB RJ-45 Ports

I connected the QNAP to one of the SFP+ ports via a 10 G SFP+ Direct Attache Copper cable.
I iMac Pro to one of the 10 GBit RJ-45 ports.
I then connected the 16-XG 10G switch to the UniFi 48 port switch via another 10 G SFP+ Direct Attache Copper cable.

So, currenlty things are on one network. But then again, the QNAP has not been configured yet either.

Kevin

[Kevin Patrick]

[Bob Zelin] “I always create a single static volume”

It’s my understanding that this is the simplist solution that provides the best performance.

Though I was concerned about not being able to configure individual volumes for certain backups. Like cloning (CCC) a boot drive to a single volume. Or having a volume for just Time Machine backups.

I suppose I could do this with Shared Folders. Though I’m not sure if that would be an issue for some of those backup apps.

You don’t think have one Static Volume for Media and then several Thick Volumes for all the rest is a good idea? That’s not like have the best of both? Simplicity/speed and flexibility?

[Bob Zelin] “Two switches, 2 ports per computer. “

Not sure how I would have 2 ports on the laptops.