DiskSpeed, hard drive benchmarking (unRAID 6+), version 2.9.2


Recommended Posts

I felt compelled to post here and give you a HUGE thank you for putting this utility together. It is exactly what I didn't know I needed! I have a lot of 2TB drives of various ages, some over 7 years, and while they pass their monthly parity check and show no issues in SMART, your utility will help me monitor the actual performance of the drives and help catch any issues. I imagine it's only a matter of time before I'll need to replace a couple of the drives.

 

Thank you!

  • Thanks 1
Link to comment
  • 2 months later...
6 hours ago, TIE Fighter said:

getting an error while scanning for hardware in a new server setup.

Can you share the error screen? From the list of actions being taken to the error message - no need to include the long java stack, just the error message and where it occurred.

Link to comment
42 minutes ago, jbartlett said:

Can you share the error screen? From the list of actions being taken to the error message - no need to include the long java stack, just the error message and where it occurred.

 

interesting, it looks like i am unable to replicate the error message.

i restarted the docker and the server and now everything is working again.

if it happens again i will post the error message

 

thx for your reply

 

  • Thanks 1
Link to comment
  • 3 weeks later...

Pardon if this is a silly question, but how reliable are the figures provided by the benchmark?

 

I have two nvme SSDs and one has results which match its specs, while the other is horrible.

 

Samsung 970 Evo Plus shows between 2500-3000 MB/s which is expected

 

Samsung PM1733 shows between 700-850MB/s which is horrible compared to its claimed 7000MB/s spec. The odd thing is that I passed it through to a windows VM and ran AS ssd benchmark and showed reasonable results around 6700MB/s.

 

I am just curious to know whether its an error of the plugin and just ignore its result or not.

Thank you in advance

Link to comment
Posted (edited)

  

On 8/28/2021 at 7:57 PM, TheJudge said:

Pardon if this is a silly question, but how reliable are the figures provided by the benchmark?

 

NVME & SSD drives only provide normal benchmarks with the current DiskSpeed version if the drive has been written entirely (such as a single preclear write pass) or filled up. If a benchmark is read on a brand new SSD, it'll report reads off the chart because the drive knows if that spot has ever been written to previously and if not, returns null's without accessing the memory.

 

The next version will have a new method of testing the read/write speeds of solid state mediums by either finding and reading a large file or writing & reading back a large file.

 

When the next version will be released is anyone's guess. I'm a married man now, my development time is thus nipped. :)

Edited by jbartlett
Link to comment
3 hours ago, TheJudge said:

Thank you for your feedback :)

 

The pm1733 drive had been formatted prior to the test if that makes a difference. I'll just assume that the drive works as intended for now. 

Apologies, I misread your question and my brain flipped the numbers.

 

If you don't mind, let's try two tests against the drive. The first test duplicates how DiskSpeed performs a benchmark at the start. In these examples, I'm testing against /dev/sdd - change the drive reference to reflect your PM1733. This first test you will need to break out to stop.

Test 1: dd if=/dev/sdd of=/dev/null bs=1310720 skip=0 iflag=direct conv=noerror status=progress

 

Now let's do the same but against a file. Locate a large file and change the if= reference to point to it.

Test 2: dd if=/mnt/disks/SSD_327E/Cam1/OS.qcow2 of=/dev/null bs=1310720 skip=0 iflag=direct conv=noerror status=progress

 

Test 2 is how I plan to have version 3 of DiskSpeed to perform a benchmark. What are the transfer speeds?

Link to comment
11 hours ago, jbartlett said:

Apologies, I misread your question and my brain flipped the numbers.

 

If you don't mind, let's try two tests against the drive. The first test duplicates how DiskSpeed performs a benchmark at the start. In these examples, I'm testing against /dev/sdd - change the drive reference to reflect your PM1733. This first test you will need to break out to stop.

Test 1: dd if=/dev/sdd of=/dev/null bs=1310720 skip=0 iflag=direct conv=noerror status=progress

 

Now let's do the same but against a file. Locate a large file and change the if= reference to point to it.

Test 2: dd if=/mnt/disks/SSD_327E/Cam1/OS.qcow2 of=/dev/null bs=1310720 skip=0 iflag=direct conv=noerror status=progress

 

Test 2 is how I plan to have version 3 of DiskSpeed to perform a benchmark. What are the transfer speeds?


Ah, thank you for following up then! :)
 

I am not sure how long I needed to run the test so I stopped when there was no improvement.

Here are the results of test 1:
root@Tower:~# dd if=/dev/nvme0n1p1 of=/dev/null bs=1310720 skip=0 iflag=direct conv=noerror status=progress
43972034560 bytes (44 GB, 41 GiB) copied, 32 s, 1.4 GB/s^C
33920+0 records in
33919+0 records out
44458311680 bytes (44 GB, 41 GiB) copied, 32.3474 s, 1.4 GB/s

 

Here are the results of test 2:

root@Tower:~# dd if=/mnt/disks/Sam4tb/Test.mkv of=/dev/null bs=1310720 skip=0 iflag=direct conv=noerror status=progress
22972989440 bytes (23 GB, 21 GiB) copied, 11 s, 2.1 GB/s
18570+1 records in
18570+1 records out
24340223273 bytes (24 GB, 23 GiB) copied, 11.5635 s, 2.1 GB/s
 

Here is the drive listed using 'df'
/dev/nvme0n1p1 3748905808   49940604 3698965204   2% /mnt/disks/Sam4tb

 

I hope I ran these tests correctly. Please let me know if these results are expected or if there is anything else I can provide,

 

 

Link to comment
17 hours ago, TheJudge said:

44458311680 bytes (44 GB, 41 GiB) copied, 32.3474 s, 1.4 GB/s

24340223273 bytes (24 GB, 23 GiB) copied, 11.5635 s, 2.1 GB/s

 

It's odd that the drive reported different speeds. The Samsung PM1733 has a max read speed of 6,400 MB/s based on this spec video but your speeds are much slower for the SSD. Only recommendation I have is to verify that you have it connected to a PCIe Gen 4 interface. It kinda looks like a gen 3 speed.

Link to comment
3 hours ago, jbartlett said:

 

It's odd that the drive reported different speeds. The Samsung PM1733 has a max read speed of 6,400 MB/s based on this spec video but your speeds are much slower for the SSD. Only recommendation I have is to verify that you have it connected to a PCIe Gen 4 interface. It kinda looks like a gen 3 speed.

I found that odd as well that it had two different speeds.

 

To shed more light, I am using an ASRock RomeD8-2T motherboard, it has 7 PCie 4.0 slots. I have the Samsung PM1733 ssd connected to slot 1 using a U.2 to PCie adapter (https://www.amazon.com/gp/product/B01D2PXUAQ/ref=ppx_yo_dt_b_asin_title_o02_s00?ie=UTF8&psc=1) . It states it should support PCie 4.0 speeds if the slot supports it; and as previously mentioned, the windows VM reported the expected speeds so I wouldn't think the interface would be the limit.

I am conflicted with the results from the different tests ranging from 800MB/s in the disk speed docker, all the way to 6GB/s+ within a windows VM which makes it difficult to know which result to trust and use as a baseline to troubleshoot. I could potentially try another adapter if you have any solid recommendations.

Link to comment
14 hours ago, TheJudge said:

I am conflicted with the results from the different tests ranging from 800MB/s in the disk speed docker

Can you create a regular debug file and email it to me? Link and info is on the bottom of the DiskSpeed app screen. This way I can look at what the system is reporting for the drive.

Link to comment
9 hours ago, jbartlett said:

Can you create a regular debug file and email it to me? Link and info is on the bottom of the DiskSpeed app screen. This way I can look at what the system is reporting for the drive.

Email has been sent with the regular debug file.

 

 

  • Thanks 1
Link to comment
  • 3 weeks later...
On 9/2/2021 at 9:42 PM, TheJudge said:

Email has been sent with the regular debug file.

 

Sorry for the delay in responding, just haven't had much time for hobby programming of late.

 

I dug through the file you sent and the related hardware and so far I got nothing. I might be able to decern more using a full debug file but .... <shrug> Hard to tell unless I have the PCIe card & drive too.

 

It might be driver related in unraid/qemu (edit: Docker) in that it doesn't have one that supports this combo while the Windows VM does.

Edited by jbartlett
Link to comment

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.

Guest
Reply to this topic...

×   Pasted as rich text.   Restore formatting

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.