WD SN850 Slower than expected performance

[monkeyboy46800]

Trust me there's nothing wing with that drive. WD will send it back, as is to you.

So where do you think the issue lies then ?

 

[TheLostSwede]

I wish I remember what I did when I had a similar issue with one of my driver's, but it was so long ago now.

If you really think it's UEFI related, why not roll back to an older release and see if that helps?

You never said which Windows release you're on as well, but I presume you've updated that?

Regardless, a faulty drive doesn't behave like this. Yes, it might be some compatibility glitch, but if that's the case, a new drive won't help.

Did you have a look in the other thread I linked to earlier?

 

[monkeyboy46800]

Fresh Install:

I'm on 5950x, rolling back to older bios revision could cause this board not to boot with my CPU.
I don't have Zen2 lying around unfortunately.
Also tried the samsung NVME controller driver, same performance: Forum - Recommended AHCI/RAID and NVMe Drivers (win-raid.com)

 

[TheLostSwede]

Why would you install a Samsung driver for a WD drive? That driver is only for Samsung drives and isn't going to do squat in your case.

It might help taking a more scientific approach to fixing your problem, rather than throwing everything at it and hope it gets fixed.

Any chance you got another system or a friend who's system you can try the drive in?

 

[monkeyboy46800]

Any chance you got another system or a friend who's system you can try the drive in?

Why would I do that, you just said " Trust me, there is nothing wrong with the drive?"

 

[ThrashZone]

Hi,
It's always a good to confirm issues on another system.
Good argument for rma too.

 

[monkeyboy46800]

Hi,
It's always a good to confirm issues on another system.
Good argument for rma too.

Advanced RMA is authorised, replacement should be here in a couple of days.

 

[ThrashZone]

Advanced RMA is authorised, replacement should be here in a couple of days.

Hi,
Yes but you haven't ruled out the mother board as the issue.
Guess you will if the new one acts the same way.

 

[monkeyboy46800]

Hi,
Yes but you haven't ruled out the mother board as the issue.
Guess you will if the new one acts the same way.

Ticket open with Asrock 10 days ago, no reply yet. But they do have Software QC issues at the moment. Some reviews of this board on Zen2 show Gen4 SSD's running over 6GB/s so if a board issue hopefully a bios update can fix that.

 

[ThrashZone]

Hi,
10 work days ?

 

[monkeyboy46800]

Hi,
10 work days ?

No, 10 days.

 

[ThrashZone]

Hi,
Still a long time with no response :/

 

[TheLostSwede]

Ticket open with Asrock 10 days ago, no reply yet. But they do have Software QC issues at the moment. Some reviews of this board on Zen2 show Gen4 SSD's running over 6GB/s so if a board issue hopefully a bios update can fix that.

Because, guess what, it's Lunar New Year, so everyone in Taiwan is on holiday.

Normal test procedure is always to try and test things in a second system if something isn't working as it should. Nothing strange with that.

 

[monkeyboy46800]

So just downgraded bios stepping down each version as far back as I can go for Zen3 making sure to clear cmos each time, no change in performance.

EDIT

Managed to bump the performance a bit more using "nvme-cli" by using Namespace 1 Formatted LBA Size 4096 instead of 512

Rolling back the firmware by changing to non active firmware slot is a no go, it seems western digital dashboard pushes firmware to both slots.

Anyway got me a couple more hundred MB/s on reads & writes but something definitely wrong still :

smartctl 7.1 2019-12-30 r5022 [x86_64-linux-5.10.1-pmagic] (local build)
Copyright (C) 2002-19, Bruce Allen, Christian Franke, www.smartmontools.org

=== START OF INFORMATION SECTION ===
Model Number:                       WDS100T1X0E-00AFY0
Serial Number:                   
Firmware Version:                   611110WD
PCI Vendor/Subsystem ID:            0x15b7
IEEE OUI Identifier:                0x001b44
Total NVM Capacity:                 1,000,204,886,016 [1.00 TB]
Unallocated NVM Capacity:           0
Controller ID:                      8224
Number of Namespaces:               1
Namespace 1 Size/Capacity:          1,000,204,886,016 [1.00 TB]
Namespace 1 Formatted LBA Size:     4096
Namespace 1 IEEE EUI-64:            001b44 8b49d849b0
Local Time is:                      Sun Feb 14 00:17:50 2021 CST
Firmware Updates (0x14):            2 Slots, no Reset required
Optional Admin Commands (0x0017):   Security Format Frmw_DL Self_Test
Optional NVM Commands (0x005f):     Comp Wr_Unc DS_Mngmt Wr_Zero Sav/Sel_Feat Timestmp
Maximum Data Transfer Size:         128 Pages
Warning  Comp. Temp. Threshold:     84 Celsius
Critical Comp. Temp. Threshold:     88 Celsius
Namespace 1 Features (0x02):        NA_Fields

Supported Power States
St Op     Max   Active     Idle   RL RT WL WT  Ent_Lat  Ex_Lat
0 +     9.00W    9.00W       -    0  0  0  0        0       0

Supported LBA Sizes (NSID 0x1)
Id Fmt  Data  Metadt  Rel_Perf
0 -     512       0         2
1 +    4096       0         1

=== START OF SMART DATA SECTION ===
SMART overall-health self-assessment test result: PASSED

If anybody is interested in full characteristics:

root@PartedMagic:~# nvme id-ctrl /dev/nvme0n1 -H | more
NVME Identify Controller:
vid       : 0x15b7
ssvid     : 0x15b7
sn        : 
mn        : WDS100T1X0E-00AFY0                    
fr        : 611110WD
rab       : 4
ieee      : 001b44
cmic      : 0
  [3:3] : 0    ANA not supported
  [2:2] : 0    PCI
  [1:1] : 0    Single Controller
  [0:0] : 0    Single Port

mdts      : 7
cntlid    : 0x2020
ver       : 0x10400
rtd3r     : 0x7a120
rtd3e     : 0xf4240
oaes      : 0x200
[27:27] : 0    Zone Descriptor Changed Notices Not Supported
[14:14] : 0    Endurance Group Event Aggregate Log Page Change Notice Not Supported
[13:13] : 0    LBA Status Information Notices Not Supported
[12:12] : 0    Predictable Latency Event Aggregate Log Change Notices Not Supported
[11:11] : 0    Asymmetric Namespace Access Change Notices Not Supported
  [9:9] : 0x1    Firmware Activation Notices Supported
  [8:8] : 0    Namespace Attribute Changed Event Not Supported

ctratt    : 0x2
  [9:9] : 0    UUID List Not Supported
  [7:7] : 0    Namespace Granularity Not Supported
  [5:5] : 0    Predictable Latency Mode Not Supported
  [4:4] : 0    Endurance Groups Not Supported
  [3:3] : 0    Read Recovery Levels Not Supported
  [2:2] : 0    NVM Sets Not Supported
  [1:1] : 0x1    Non-Operational Power State Permissive Supported
  [0:0] : 0    128-bit Host Identifier Not Supported

rrls      : 0
cntrltype : 1
  [7:2] : 0    Reserved
  [1:0] : 0x1    I/O Controller
fguid     :
crdt1     : 0
crdt2     : 0
crdt3     : 0
oacs      : 0x17
  [9:9] : 0    Get LBA Status Capability Not Supported
  [8:8] : 0    Doorbell Buffer Config Not Supported
  [7:7] : 0    Virtualization Management Not Supported
  [6:6] : 0    NVMe-MI Send and Receive Not Supported
  [5:5] : 0    Directives Not Supported
  [4:4] : 0x1    Device Self-test Supported
  [3:3] : 0    NS Management and Attachment Not Supported
  [2:2] : 0x1    FW Commit and Download Supported
  [1:1] : 0x1    Format NVM Supported
  [0:0] : 0x1    Security Send and Receive Supported

acl       : 4
aerl      : 7
frmw      : 0x14
  [4:4] : 0x1    Firmware Activate Without Reset Supported
  [3:1] : 0x2    Number of Firmware Slots
  [0:0] : 0    Firmware Slot 1 Read/Write

lpa       : 0x1e
  [4:4] : 0x1    Persistent Event log Supported
  [3:3] : 0x1    Telemetry host/controller initiated log page Supported
  [2:2] : 0x1    Extended data for Get Log Page Supported
  [1:1] : 0x1    Command Effects Log Page Supported
  [0:0] : 0    SMART/Health Log Page per NS Not Supported

elpe      : 255
npss      : 0
avscc     : 0x1
  [0:0] : 0x1    Admin Vendor Specific Commands uses NVMe Format

apsta     : 0
  [0:0] : 0    Autonomous Power State Transitions Not Supported

wctemp    : 357
cctemp    : 361
mtfa      : 50
hmpre     : 0
hmmin     : 0
tnvmcap   : 1000204886016
unvmcap   : 0
rpmbs     : 0
[31:24]: 0    Access Size
[23:16]: 0    Total Size
  [5:3] : 0    Authentication Method
  [2:0] : 0    Number of RPMB Units

edstt     : 102
dsto      : 1
fwug      : 1
kas       : 0
hctma     : 0x1
  [0:0] : 0x1    Host Controlled Thermal Management Supported

mntmt     : 273
mxtmt     : 357
sanicap   : 0x60000002
  [31:30] : 0x1    Media is not additionally modified after sanitize operation completes successfully
  [29:29] : 0x1    No-Deallocate After Sanitize bit in Sanitize command Not Supported
    [2:2] : 0    Overwrite Sanitize Operation Not Supported
    [1:1] : 0x1    Block Erase Sanitize Operation Supported
    [0:0] : 0    Crypto Erase Sanitize Operation Not Supported

hmminds   : 0
hmmaxd    : 0
nsetidmax : 0
endgidmax : 0
anatt     : 0
anacap    : 0
  [7:7] : 0    Non-zero group ID Not Supported
  [6:6] : 0    Group ID does not change
  [4:4] : 0    ANA Change state Not Supported
  [3:3] : 0    ANA Persistent Loss state Not Supported
  [2:2] : 0    ANA Inaccessible state Not Supported
  [1:1] : 0    ANA Non-optimized state Not Supported
  [0:0] : 0    ANA Optimized state Not Supported

anagrpmax : 0
nanagrpid : 0
pels      : 1
sqes      : 0x66
  [7:4] : 0x6    Max SQ Entry Size (64)
  [3:0] : 0x6    Min SQ Entry Size (64)

cqes      : 0x44
  [7:4] : 0x4    Max CQ Entry Size (16)
  [3:0] : 0x4    Min CQ Entry Size (16)

maxcmd    : 0
nn        : 1
oncs      : 0x5f
  [8:8] : 0    Copy Not Supported
  [7:7] : 0    Verify Not Supported
  [6:6] : 0x1    Timestamp Supported
  [5:5] : 0    Reservations Not Supported
  [4:4] : 0x1    Save and Select Supported
  [3:3] : 0x1    Write Zeroes Supported
  [2:2] : 0x1    Data Set Management Supported
  [1:1] : 0x1    Write Uncorrectable Supported
  [0:0] : 0x1    Compare Supported

fuses     : 0
  [0:0] : 0    Fused Compare and Write Not Supported

fna       : 0
  [2:2] : 0    Crypto Erase Not Supported as part of Secure Erase
  [1:1] : 0    Crypto Erase Applies to Single Namespace(s)
  [0:0] : 0    Format Applies to Single Namespace(s)

vwc       : 0x7
  [2:1] : 0x3    The Flush command supports NSID set to FFFFFFFFh
  [0:0] : 0x1    Volatile Write Cache Present

awun      : 0
awupf     : 0
icsvscc     : 1
  [0:0] : 0x1    NVM Vendor Specific Commands uses NVMe Format

nwpc      : 0
  [2:2] : 0    Permanent Write Protect Not Supported
  [1:1] : 0    Write Protect Until Power Supply Not Supported
  [0:0] : 0    No Write Protect and Write Protect Namespace Not Supported

acwu      : 0
ocfs      : 0
sgls      : 0
[1:0]  : 0    Scatter-Gather Lists Not Supported

mnan      : 0
subnqn    : nqn.2018-01.com.wdc:nguid:E8238FA6BF53-0001-001B448B49D849B0
ioccsz    : 0
iorcsz    : 0
icdoff    : 0
ctrattr   : 0
  [0:0] : 0    Dynamic Controller Model

msdbd     : 0
ps    0 : mp:9.00W operational enlat:0 exlat:0 rrt:0 rrl:0
          rwt:0 rwl:0 idle_power:0.6300W active_power:9.00W

 

[monkeyboy46800]

Gotta love Asrocks feedback to my support request:

 

[GlitchKrieg]

I'm having the exact same problem with my SN850 on an MSI x570 Tomahawk w/a 5900x. Eager to see how things play out.

 

[RJARRRPCGP]

Still hitting a wall, the writes really do suck

View attachment 188005

Likely failing, if it keeps being absurdly slow. Like some faulty SSDs that I received.

 

[Hachi_Roku256563]

i find it funny how we are in a world where 3000mb/s is "horrible"
but i agree it does not sound like a drive failure feel like its a bottleneck somewhere else

 

[RJARRRPCGP]

but i agree it does not sound like a drive failure feel like its a bottleneck somewhere else

That doesn't strike me as an SSD failure. Symptoms to look for are the following for SSDs:

1. A high amount of latency, including random and severe lag, where it feels more like a fragmented spinner!
2. A game server (especially a Halo Custom Edition dedicated server) gives you a high ping warning, even when the internet isn't the cause.
3. Windows out of nowhere has a file integrity error.
4. A Windows update may look fine, but SFC fails it, more likely when SFC moans that it couldn't fix it.

i find it funny how we are in a world where 3000mb/s is "horrible"

3,000 MB/s is very good!

 

[phanbuey]

It's the ubuntu kernel most likely... they used to always have SSD issues a few years ago, updates to the OS fixed them.

That 3000 mb/s sounds like a driver issue and there are tons of threads from all points in time about this (both windows and Ubuntu), everyone seems to blame AMD drivers and wiping+reinstalling them seems to work.

Can you try uninstalling all of the nvme drivers and run again?

 

[DrCR]

^Actually, that has me wondering if testing from a current linux live cd/usb could be a good step to take.

 

[monkeyboy46800]

I already did the Linux install and tested multiple kernels, still bottlenecked with the SN850. RMA drive arrives tomorrow. Will report back with results. Still waiting for feedback from Asrock also.

 

[monkeyboy46800]

New Drive arrived, WD replaced my 1TB version with the 2TB version.

Still bottlenecked at just over 3 GB/s writes, not seeing the 7 GB/s reads or 5 GB/s writes reviewers were getting

 

[TheLostSwede]

New Drive arrived, WD replaced my 1TB version with the 2TB version.

Still bottlenecked at just over 3 GB/s writes, not seeing the 7 GB/s reads or 5 GB/s writes reviewers were getting

View attachment 188904

View attachment 188905

View attachment 188906

Didn't I say there was nothing wrong with your drive?
On the plus side, you got another terabyte of storage for free...

 

[GlitchKrieg]

Wow, they gave you an extra 1TB for free? That's a pretty sweet deal. Kind of figured it wasn't the drive though. FWIW I'm getting about the same speeds using the 1TB version of the SN850 on an X570 board. Guess I'll fiddle around with the BIOS and see if I can make any difference.