Jump to content

NVMe slower than SATA

WiiMAN
Go to solution Solved by BondiBlue,
1 minute ago, WiiMAN said:

Yeah the SATA is being boosted. But the NVMe is performing as expected? No need to adjust anything?

Yes, it looks fine to me. It's many times faster than the actual speeds of your SATA drive. 

Hi. Maybe I just don't know what I'm doing or something but different drive speed tests have

shown my Samsung 980 Pro NVMe M.2 to be slower than my Samsung 950 EVO SATA

Is there something I had to do to get its full performance?

C: is SATA and M: is NVMe

 

CPU: RYZEN 5 5600X

Motherboard: MSI MAG B550 Tomahawk

GPU: Radeon VEGA 56

RAM: 4 x 8 Corsair Vengance LPX (XMP enabled)

OS: Windows 10 19043.1237

BIOS version A.70

NVMe.png

SATA.png

Link to comment
Share on other sites

Link to post
Share on other sites

2 minutes ago, WiiMAN said:

Hi. Maybe I just don't know what I'm doing or something but different drive speed tests have

shown my Samsung 980 Pro NVMe M.2 to be slower than my Samsung 950 EVO SATA

Is there something I had to do to get its full performance?

C: is SATA and M: is NVMe

 

CPU: RYZEN 5 5600X

Motherboard: MSI MAG B550 Tomahawk

GPU: Radeon VEGA 56

RAM: 4 x 8 Corsair Vengance LPX (XMP enabled)

OS: Windows 10 19043.1237

BIOS version A.70

NVMe.png

SATA.png

What kind of sata do you have? Isnt sata limited to 6Gb/s? (600MB/s)

Link to comment
Share on other sites

Link to post
Share on other sites

You have some sort of ram cache on the SATA drive. It isn't the disks native performance. Those speeds on the SATA drive are not only beyond what SATA can do, it is beyond what PCIe 4.0 4x can do.

Gaming system: R7 7800X3D, Asus ROG Strix B650E-F Gaming Wifi, Thermalright Phantom Spirit 120 SE ARGB, Corsair Vengeance 2x 32GB 6000C30, RTX 4070, MSI MPG A850G, Fractal Design North, Samsung 990 Pro 2TB, Acer Predator XB241YU 24" 1440p 144Hz G-Sync + HP LP2475w 24" 1200p 60Hz wide gamut
Productivity system: i9-7980XE, Asus X299 TUF mark 2, Noctua D15, 64GB ram (mixed), RTX 3070, NZXT E850, GameMax Abyss, Samsung 980 Pro 2TB, random 1080p + 720p displays.
Gaming laptop: Lenovo Legion 5, 5800H, RTX 3070, Kingston DDR4 3200C22 2x16GB 2Rx8, Kingston Fury Renegade 1TB + Crucial P1 1TB SSD, 165 Hz IPS 1080p G-Sync Compatible

Link to comment
Share on other sites

Link to post
Share on other sites

1 minute ago, porina said:

You have some sort of ram cache on the SATA drive. It isn't the disks native performance. Those speeds on the SATA drive are not only beyond what SATA can do, it is beyond what PCIe 4.0 4x can do.

Well I’m not sure how that could’ve happened. I thought it was just showing the results in some other scale. Maybe Samsung Magician did something? Still not sure what’s with the NVMe performance tho

Link to comment
Share on other sites

Link to post
Share on other sites

8 minutes ago, WiiMAN said:

Well I’m not sure how that could’ve happened. I thought it was just showing the results in some other scale. Maybe Samsung Magician did something? Still not sure what’s with the NVMe performance tho

Turn off RAPID mode in Samsung Magician.

Main System (Byarlant): Ryzen 7 5800X | Asus B550-Creator ProArt | EK 240mm Basic AIO | 16GB G.Skill DDR4 3200MT/s CAS-14 | XFX Speedster SWFT 210 RX 6600 | Samsung 990 PRO 2TB / Samsung 960 PRO 512GB / 4× Crucial MX500 2TB (RAID-0) | Corsair RM750X | Mellanox ConnectX-3 10G NIC | Inateck USB 3.0 Card | Hyte Y60 Case | Dell U3415W Monitor | Keychron K4 Brown (white backlight)

 

Laptop (Narrative): Lenovo Flex 5 81X20005US | Ryzen 5 4500U | 16GB RAM (soldered) | Vega 6 Graphics | SKHynix P31 1TB NVMe SSD | Intel AX200 Wifi (all-around awesome machine)

 

Proxmox Server (Veda): Ryzen 7 3800XT | AsRock Rack X470D4U | Corsair H80i v2 | 64GB Micron DDR4 ECC 3200MT/s | 4x 10TB WD Whites / 4x 14TB Seagate Exos / 2× Samsung PM963a 960GB SSD | Seasonic Prime Fanless 500W | Intel X540-T2 10G NIC | LSI 9207-8i HBA | Fractal Design Node 804 Case (side panels swapped to show off drives) | VMs: TrueNAS Scale; Ubuntu Server (PiHole/PiVPN/NGINX?); Windows 10 Pro; Ubuntu Server (Apache/MySQL)


Media Center/Video Capture (Jesta Cannon): Ryzen 5 1600X | ASRock B450M Pro4 R2.0 | Noctua NH-L12S | 16GB Crucial DDR4 3200MT/s CAS-22 | EVGA GTX750Ti SC | UMIS NVMe SSD 256GB /

TEAMGROUP MS30 1TB | Corsair CX450M | Viewcast Osprey 260e Video Capture | Mellanox ConnectX-2 10G NIC | LG UH12NS30 BD-ROM | Silverstone Sugo SG-11 Case | Sony XR65A80K

 

Camera: Sony ɑ7II w/ Meike Grip | Sony SEL24240 | Samyang 35mm ƒ/2.8 | Sony SEL50F18F | Sony SEL2870 (kit lens) | PNY Elite Perfomance 512GB SDXC card

 

Network:

Spoiler
                           ┌─────────────── Office/Rack ────────────────────────────────────────────────────────────────────────────┐
Google Fiber Webpass ────── UniFi Security Gateway ─── UniFi Switch 8-60W ─┬─ UniFi Switch Flex XG ═╦═ Veda (Proxmox Virtual Switch)
(500Mbps↑/500Mbps↓)                             UniFi CloudKey Gen2 (PoE) ─┴─ Veda (IPMI)           ╠═ Veda-NAS (HW Passthrough NIC)
╔═══════════════════════════════════════════════════════════════════════════════════════════════════╩═ Narrative (Asus USB 2.5G NIC)
║ ┌────── Closet ──────┐   ┌─────────────── Bedroom ──────────────────────────────────────────────────────┐
╚═ UniFi Switch Flex XG ═╤═ UniFi Switch Flex XG ═╦═ Byarlant
   (PoE)                 │                        ╠═ Narrative (Cable Matters USB-PD 2.5G Ethernet Dongle)
                         │                        ╚═ Jesta Cannon*
                         │ ┌─────────────── Media Center ──────────────────────────────────┐
Notes:                   └─ UniFi Switch 8 ─────────┬─ UniFi Access Point nanoHD (PoE)
═══ is Multi-Gigabit                                ├─ Sony Playstation 4 
─── is Gigabit                                      ├─ Pioneer VSX-S520
* = cable passed to Bedroom from Media Center       ├─ Sony XR65A80K (Google TV)
** = cable passed from Media Center to Bedroom      └─ Work Laptop** (Startech USB-PD Dock)

Retired/Other:

Spoiler

Laptop (Rozen-Zulu): Sony VAIO VPCF13WFX | Core i7-740QM | 8GB Patriot DDR3 | GT 425M | Samsung 850EVO 250GB SSD | Blu-ray Drive | Intel 7260 Wifi (lived a good life, retired with honor)

Testbed/Old Desktop (Kshatriya): Xeon X5470 @ 4.0GHz | ZALMAN CNPS9500 | Gigabyte EP45-UD3L | 8GB Nanya DDR2 400MHz | XFX HD6870 DD | OCZ Vertex 3 Max-IOPS 120GB | Corsair CX430M | HooToo USB 3.0 PCIe Card | Osprey 230 Video Capture | NZXT H230 Case

TrueNAS Server (La Vie en Rose): Xeon E3-1241v3 | Supermicro X10SLL-F | Corsair H60 | 32GB Micron DDR3L ECC 1600MHz | 1x Kingston 16GB SSD / Crucial MX500 500GB

Link to comment
Share on other sites

Link to post
Share on other sites

1 minute ago, AbydosOne said:

Turn off RAPID mode in Samsung Magician.

That would make the SATA slower, right?

 

Also I probably should've mentioned, I'll be installing a brand new Windows on the NVMe to update to Windows 11. Which is why I'm asking if this behavior is normal or if there's something I need to verify before installing the new OS

 

My bad...

Link to comment
Share on other sites

Link to post
Share on other sites

Those speeds you're seeing from your SATA drive are literally impossible for the drive to achieve by itself. You've got a RAM cache enabled (I think Samsung calls it RAPID mode), and that's causing the result to be artificially high. Your NVMe SSD is already performing very well. 

Phobos: AMD Ryzen 7 2700, 16GB 3000MHz DDR4, ASRock B450 Steel Legend, 8GB Nvidia GeForce RTX 2070, 2GB Nvidia GeForce GT 1030, 1TB Samsung SSD 980, 450W Corsair CXM, Corsair Carbide 175R, Windows 10 Pro

 

Polaris: Intel Xeon E5-2697 v2, 32GB 1600MHz DDR3, ASRock X79 Extreme6, 12GB Nvidia GeForce RTX 3080, 6GB Nvidia GeForce GTX 1660 Ti, 1TB Crucial MX500, 750W Corsair RM750, Antec SX635, Windows 10 Pro

 

Pluto: Intel Core i7-2600, 32GB 1600MHz DDR3, ASUS P8Z68-V, 4GB XFX AMD Radeon RX 570, 8GB ASUS AMD Radeon RX 570, 1TB Samsung 860 EVO, 3TB Seagate BarraCuda, 750W EVGA BQ, Fractal Design Focus G, Windows 10 Pro for Workstations

 

York (NAS): Intel Core i5-2400, 16GB 1600MHz DDR3, HP Compaq OEM, 240GB Kingston V300 (boot), 3x2TB Seagate BarraCuda, 320W HP PSU, HP Compaq 6200 Pro, TrueNAS CORE (12.0)

Link to comment
Share on other sites

Link to post
Share on other sites

The SATA drive isn't actually being written to that fast. There's a RAM cache in play, so the data is being written into RAM, which, yeah, is going to be much faster than a 980 Pro, and then spooled to the drive in the background at *much* slower speeds. If you turn off the RAM cache, yes, the writes will *appear* slower. They'll really be just as fast as they always were. However, it will no longer be misreporting drive speed (i.e. you'll see how fast the drive actually is), and you also will have better data persistence. If the computer is abruptly restarted before any data that's been cache in RAM has finished spooling the drive, it's gone. Whereas, when you see the transfer complete without the RAM cache, it's all going to actually be on the drive.

 

CPU: AMD Ryzen 9 5900X · Cooler: Artic Liquid Freezer II 280 · Motherboard: MSI MEG X570 Unify · RAM: G.skill Ripjaws V 2x16GB 3600MHz CL16 (2Rx8) · Graphics Card: ASUS GeForce RTX 3060 Ti TUF Gaming · Boot Drive: 500GB WD Black SN750 M.2 NVMe SSD · Game Drive: 2TB Crucial MX500 SATA SSD · PSU: Corsair White RM850x 850W 80+ Gold · Case: Corsair 4000D Airflow · Monitor: MSI Optix MAG342CQR 34” UWQHD 3440x1440 144Hz · Keyboard: Corsair K100 RGB Optical-Mechanical Gaming Keyboard (OPX Switch) · Mouse: Corsair Ironclaw RGB Wireless Gaming Mouse

Link to comment
Share on other sites

Link to post
Share on other sites

4 minutes ago, BondiBlue said:

Those speeds you're seeing from your SATA drive are literally impossible for the drive to achieve by itself. You've got a RAM cache enabled (I think Samsung calls it RAPID mode), and that's causing the result to be artificially high. Your NVMe SSD is already performing very well. 

So the reported speed is accurate and all should be fine?

Link to comment
Share on other sites

Link to post
Share on other sites

Just now, WiiMAN said:

So the reported speed is accurate and all should be fine?

The speed you see right now from your SATA drive is not accurate at all. That drive cannot transfer data at speeds higher than 600MB/s (theoretical) in any scenario. What you're seeing is a RAM cache, as has been explained. 

Phobos: AMD Ryzen 7 2700, 16GB 3000MHz DDR4, ASRock B450 Steel Legend, 8GB Nvidia GeForce RTX 2070, 2GB Nvidia GeForce GT 1030, 1TB Samsung SSD 980, 450W Corsair CXM, Corsair Carbide 175R, Windows 10 Pro

 

Polaris: Intel Xeon E5-2697 v2, 32GB 1600MHz DDR3, ASRock X79 Extreme6, 12GB Nvidia GeForce RTX 3080, 6GB Nvidia GeForce GTX 1660 Ti, 1TB Crucial MX500, 750W Corsair RM750, Antec SX635, Windows 10 Pro

 

Pluto: Intel Core i7-2600, 32GB 1600MHz DDR3, ASUS P8Z68-V, 4GB XFX AMD Radeon RX 570, 8GB ASUS AMD Radeon RX 570, 1TB Samsung 860 EVO, 3TB Seagate BarraCuda, 750W EVGA BQ, Fractal Design Focus G, Windows 10 Pro for Workstations

 

York (NAS): Intel Core i5-2400, 16GB 1600MHz DDR3, HP Compaq OEM, 240GB Kingston V300 (boot), 3x2TB Seagate BarraCuda, 320W HP PSU, HP Compaq 6200 Pro, TrueNAS CORE (12.0)

Link to comment
Share on other sites

Link to post
Share on other sites

Just now, BondiBlue said:

The speed you see right now from your SATA drive is not accurate at all. That drive cannot transfer data at speeds higher than 600MB/s (theoretical) in any scenario. What you're seeing is a RAM cache, as has been explained. 

Yeah the SATA is being boosted. But the NVMe is performing as expected? No need to adjust anything?

Link to comment
Share on other sites

Link to post
Share on other sites

1 minute ago, WiiMAN said:

Yeah the SATA is being boosted. But the NVMe is performing as expected? No need to adjust anything?

Yes, it looks fine to me. It's many times faster than the actual speeds of your SATA drive. 

Phobos: AMD Ryzen 7 2700, 16GB 3000MHz DDR4, ASRock B450 Steel Legend, 8GB Nvidia GeForce RTX 2070, 2GB Nvidia GeForce GT 1030, 1TB Samsung SSD 980, 450W Corsair CXM, Corsair Carbide 175R, Windows 10 Pro

 

Polaris: Intel Xeon E5-2697 v2, 32GB 1600MHz DDR3, ASRock X79 Extreme6, 12GB Nvidia GeForce RTX 3080, 6GB Nvidia GeForce GTX 1660 Ti, 1TB Crucial MX500, 750W Corsair RM750, Antec SX635, Windows 10 Pro

 

Pluto: Intel Core i7-2600, 32GB 1600MHz DDR3, ASUS P8Z68-V, 4GB XFX AMD Radeon RX 570, 8GB ASUS AMD Radeon RX 570, 1TB Samsung 860 EVO, 3TB Seagate BarraCuda, 750W EVGA BQ, Fractal Design Focus G, Windows 10 Pro for Workstations

 

York (NAS): Intel Core i5-2400, 16GB 1600MHz DDR3, HP Compaq OEM, 240GB Kingston V300 (boot), 3x2TB Seagate BarraCuda, 320W HP PSU, HP Compaq 6200 Pro, TrueNAS CORE (12.0)

Link to comment
Share on other sites

Link to post
Share on other sites

Just now, BondiBlue said:

Yes, it looks fine to me. It's many times faster than the actual speeds of your SATA drive. 

Thanks a ton for the info 🙂

Link to comment
Share on other sites

Link to post
Share on other sites

Just now, WiiMAN said:

Thanks a ton for the info 🙂

Yep, no worries.

Phobos: AMD Ryzen 7 2700, 16GB 3000MHz DDR4, ASRock B450 Steel Legend, 8GB Nvidia GeForce RTX 2070, 2GB Nvidia GeForce GT 1030, 1TB Samsung SSD 980, 450W Corsair CXM, Corsair Carbide 175R, Windows 10 Pro

 

Polaris: Intel Xeon E5-2697 v2, 32GB 1600MHz DDR3, ASRock X79 Extreme6, 12GB Nvidia GeForce RTX 3080, 6GB Nvidia GeForce GTX 1660 Ti, 1TB Crucial MX500, 750W Corsair RM750, Antec SX635, Windows 10 Pro

 

Pluto: Intel Core i7-2600, 32GB 1600MHz DDR3, ASUS P8Z68-V, 4GB XFX AMD Radeon RX 570, 8GB ASUS AMD Radeon RX 570, 1TB Samsung 860 EVO, 3TB Seagate BarraCuda, 750W EVGA BQ, Fractal Design Focus G, Windows 10 Pro for Workstations

 

York (NAS): Intel Core i5-2400, 16GB 1600MHz DDR3, HP Compaq OEM, 240GB Kingston V300 (boot), 3x2TB Seagate BarraCuda, 320W HP PSU, HP Compaq 6200 Pro, TrueNAS CORE (12.0)

Link to comment
Share on other sites

Link to post
Share on other sites

16 minutes ago, WiiMAN said:

That would make the SATA slower, right?

 

Also I probably should've mentioned, I'll be installing a brand new Windows on the NVMe to update to Windows 11. Which is why I'm asking if this behavior is normal or if there's something I need to verify before installing the new OS

 

My bad...

Won't affect performance for almost all apps, as windows does this already.

 

Rapid caching just makes it fake the cache, so programs like crystal disk mark that tell the system to not use the cache still use it. This can lead to data loss, so leave it off.

Link to comment
Share on other sites

Link to post
Share on other sites

12 minutes ago, Electronics Wizardy said:

Won't affect performance for almost all apps, as windows does this already.

 

Rapid caching just makes it fake the cache, so programs like crystal disk mark that tell the system to not use the cache still use it. This can lead to data loss, so leave it off.

Roger!

Link to comment
Share on other sites

Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now

×