Overclock.net - An Overclocking Community - View Single Post - What are good value SSDs in 2019? 1TB / Phison E12 + Toshiba

View Single Post
post #85 of (permalink) Old 07-23-2019, 10:23 AM
Sean Webster
Storage Nut
 
Sean Webster's Avatar
 
Join Date: Nov 2010
Location: Boca Raton, FL
Posts: 21,076
Rep: 1660 (Unique: 967)
Quote: Originally Posted by JackCY View Post
I can't really say for SSDs what other tests would be good to have. I know there is iometer and some companion program to it? And these can be customized for testing, never did it myself only have them saved.

It's good to see these for example:[*]Performance of empty vs full drive, or even a progress of performance as drive fills up, some reviews show this in some way.
First off, thanks a lot for the feedback. I hope you don't mind me commenting point by point in the discussion. Also, I just reread the OP. You mention 1TB drives are 953GB, as well some 1TB drives are 931.5GB too - Samsung 970 EVO series, WD Black SN750, Crucial P1, though I'm not aware of any E12 based SSDs at that 930GB.

I currently, test drives at 50% full rather than empty. Honestly, beyond 10% used, performance doesn't change much except for peak random IOPS or maybe a dynamic pseudo SLC cache will be smaller when more full. But, most real life applications won't change in performance much at all with a smaller dynamic cache.

Quote: Originally Posted by JackCY View Post
[*]Fependence of performance on available recovery time (moving data from SLC to storage, etc. time for maintenance tasks), can be dug out from reading the test descriptions/specifications when reviews do go beyond AS/ATTO/CDM.
Do you have any ideas on how this could be achieved? It's a great idea, but this is kinda tough to do, but I was thinking of building an iometer script to show how long it takes for the SLC buffer to recover, but with so many cache sizes and flushing patterns, this may take a while to develop. I would wind up doing interval'd time checks, but I would also be constantly refilling the cache and the time to carry out the test may be longer than it is worth - I can easily see it going for hours. Gotta make something I can easily fit into my already day-long testing. This is also something that challenges testing. You need to ensure that cache is clean before starting the next benchmark.

Quote: Originally Posted by JackCY View Post
[*]Size of RAM, size of SLC cache, how performance changes when these are exhausted, some reviews have graphs with progressive write filling up the drive, SLC/MLC stays up in speed, TLC often drops but stays usable, QLC tanks to HDD speeds, etc.
I mention this, but RAM doesn't really matter. Doubling the RAM or reducing it doesn't have much performance impact on most SSDs these days. DDR3 vs DDR4 also makes no difference. The other stuff is partially covered now, I figure just showing the size and behavior of the cache is good enough and from there most can see how it will perform under heavy writing with my 15min sequential write test. Most of the time the SLC cache clears within minutes. The 1TB Intel 660P takes like 20-30minutes to fold the SLC->QLC. But, remember, when the SLC cache is full, the data on the cache is also faster than the native TLC or QLC. So reads do get a small boost, folding out data isn't always something that is beneficial. Crucial's P1, for example, evacuates data from the cache faster than the 660P in favor of write performance, but that hurts it heavily in PCMark 8 and other application tests.

Quote: Originally Posted by JackCY View Post
[*]Temperature photos of the drive vs reported temperature, does it need a heatsink to maintain performance under heavy load and/or being stuck under a hot GPU, possibly what generic cheap heatsink does fit the drive and is low profile enough to not obstruct add in cards, is one sided motherboard heatsink (on the modern mobos) enough to cool it? Or is the controller for example on bottom side and remains uncooled.
Good stuff that I've been wanting to do, just don't have the $ to invest in one of those cameras/accessories. I've toyed with this every now and then, but I usually just plop a 120mm fan on the PSU aimed at my PCIe slots and temps of most drives stay under 60C - usually 45-50C at most underload like that. M.2 SSDs only consume 5-7W at most and average less, but I've been thinking about doing a heatsink vs non-heatsink head to head sometime putting those very ideas into play too. The VPN100 is one of the tallest heatsinked models I've used so far and it doesn't interfere with my GPU even in the highest M.2 slot. I think i mentioned that in my review, I try to at least. Also, motherboard heatsinks vary a lot. On my x470 system, it makes my OS drive idle at 60C, but temps never pass that either lol. (also, I don't think I've ever seen one M.2 with the controller on the bottom side)

Quote: Originally Posted by JackCY View Post
[*]What other drives have the same/similar specifications, such as a review of 1 Phison E12 drive would have links to all other E12 drives and their reviews when available. A mention of a comparable competing drive say with SM2262EN/WD and differences.
Very good point. I've recently started this when I started at Tom's too. Although, sometimes I don't go into deep details and just state entry-level/high-end competitor or something along those lines.


Quote: Originally Posted by JackCY View Post
[*]Some real worlds tests involving VMs, large Photoshop file processing (I got the drive for this too as I need a fast storage for cache and read/writing a 5GB+ PSB file, Photoshop is horribly optimized and will eat 16GB+ RAM and crap a ton of cache just to open it, editing 12k resolution image with a few layers is so much "fun" in Photoshop, it's like it has been made for editing 1080p images at best), game copy speed (modern games being nearly 100GB... kind of does have it's use), file search, ...
This x100000. So, PCMark 8 and sysmark do a decent job covering a broad range of applications representing the use cases most consumers would use, especially sysmark since it is application-based, not trace based. I started using Spec workstation 3, which goes further than PCMark 8 as a test for workstation users - aka - real pro workloads. It even breaks down IOPS and throughput, but, nothing really on VMs. Would be cool to do some VM load times and transfer performance within the VM. I'm just not sure how much that would be worth the effort, not many care about that honestly.


Quote: Originally Posted by JackCY View Post
[*]Is achieved level of performance worth paying for or does it fall into the category of: for normal user mainly gaming, streaming, ... there is almost no practical difference between 2GB/s and 6GB/s drive... certainly not worth paying +100% in price. But say for a pro use the very low latency offers excellent access times for... "databases", great endurance, stable performance under heavy use and load, ... In that case the drive is worth the high extra. For example.
Thats a good idea, I never thought to define and classify categories like that. I think I'll start in my recommendations.

Quote: Originally Posted by JackCY View Post
[*]There are often the usual varying Q depth and file size tests, which for non technical people will often be gibberish and all they can make of it is a "ranking" out of a graph.
You know what? I actually feel like varrying file size tests are meh. I just keep ATTO around for that reason. Otherwise, I just use iometer to see 4KB random and 128KB sequential at various QDs (mainly 1-8) and 1MB at QD1, which normally correlates to how Windows will perform a regular sequential file drag and drop. Although I back this up by testing transfers with diskbench - like fast copy, but basically just a timer for Windows file and folder transfers really. I do a 50GB file copy on the drive and a large file read in my main SSDs tests to cover that performance.

Quote: Originally Posted by JackCY View Post
For a regular home user I would say those CDM/AS/ATTO are helpful so one can check a performance of their own drive and see if they have some issue that needs resolving, if those benches are to be trusted and reliable that is, but then do mention it that a lower performance reported from these is normal under some specific circumstances or even why when known and not a fault of the drive but the bench is made that way.

Of course I do like to see more proper tests, custom tests made with iometer or custom programs etc. Not just PCmark or some other suite though.
I agree. I used to show off these tests when I was writing for The SSD Review. I think it is a great resource of comparison, but most actually prefer just to see data graphs instead and like I said, they have their quirks, so I've ditched that since. Also, test suites are very useful, much more so than iometer imo. It does more than just test a random datapoint. The tests are actually built off of real workloads.

Quote: Originally Posted by JackCY View Post
Level1Tech sometimes does interesting things with hardware, commenting on real world uses for regular person and a prosumer, checking Linux compatibility, ...
I've read others asking about linux compatibility check before too, but every drive should be fine in Linux until a bug is found. I don't have any protocol analyzers, so that's hard to do if you need a concrete answer. Otherwise, they are just standardized SATA or NVMe devices at the end of the day. Every SSD I test, however, has been secure erased within Parted Magic at one point or another. So, I'd say they are compatible after accessing them within that live OS. So, I could start mentioning that if you think it really would help.

Quote: Originally Posted by JackCY View Post
I have not seen or found that guide yet, looks nice. I've added it to OP.
Yeah, I just found it a few weeks ago. I wanna reach out to the dude and find out who he is lol.

Quote: Originally Posted by JackCY View Post
I see you've also updated the SSD guide on Tom'sHW. I think I only saw the MyDigitalSSD BPX Pro in a previous one there, which in my region is not available and many guides I found in June were still listing a lot of old drives. Anandtech: https://www.anandtech.com/show/9799/best-ssds still is outdated because prices have changed so much that the E12 drives there cost double and one will overlook them for example. Personally I think the QLC drives like P1, 660p should not be in these recommendations. Some of these older guides are filled with old drives and high prices, making them almost useless in the market that has moved on since both in performance and price. Rather than having a specific single product recommendation it would be nice to have a recommendation of a "drive design" with a list of drives that use it, especially when all the drives seem to be coming out of one factory anyway, same performance etc. That way one can search the drives in that list in their region and find which are available and for what price. That way it's less likely you will have a recommended drive that is region specific.

I did look up all the E12 and Adata/HP drives in shop aggregators and in shops, to be able to #1 buy one as they are not always available well, #2 buy at a good price.
Good point, I'll keep this in mind.

Quote: Originally Posted by JackCY View Post
Yes it's the same archive and files to a bit of the 12.3 update.

12.3 update on P34A80.
If you want, sure I would appreciate that. I did find I think that MP510 and P34A80 can be updated successfully and without data loss at least from v12+ but v11 = data loss.

My drive arrived with 12.2 and it has the sensor readout being at least 15C too low.
Just upated my P34A80 from 12.2 to 12.3 without an issue. Also updated my 1TB Patriot Viper VP100 and 512GB Gigabyte Aorus RGB from 12.1 to 12.3 too.

Quote: Originally Posted by AlphaC View Post
Thank you Sean for your insight and that very useful table.


One thing I would like to note is how reviewers often gloss over the SSD software's disk footprint and memory footprint. The software included may be antique-styled or extremely bloated (size used or memory use).


You noted in your MP510 review at Tom's hardware: It has a minimal few MB of disk usage though.

Sandisk's SSD dashboard is about half a GB in disk space per MajorGeeks' 7/17/2019 download size... AFAIK it doesn't have any amazing features, the manual only lists 3 tabs (performance in terms of speed and TRIM, tools such as secure erase and firmware update check, and status for health monitoring).
You're welcome. And wow, i didnt know its gotten that big. Last time i downloaded it, it was like 230MB or so. Crucial's storage executive was rather large too at about 200MB before, i think they shrunk it a bit recently tho. Those 3 are the main large software tools I know of. Most are usually 5-50MB. I'll keep this in mind. Thank you!

I AM THE SSD BENCHMARK GURU
Storage Essentials | My Build Logs | My Server Build Log | flickr | Steam | Depression and I
Some say he once took a backup of the entire NSA database. Others say he lays SSDs like chickens lay eggs. All we know is, it's Sean Webster!
Le Main Rig
(15 items)
Terrorbyte V2
(16 items)
Test Bench
(8 items)
CPU
i7-6700K
Motherboard
ASRock Z170 OC Formula
GPU
Gigabyte GTX 960 WindForce 2X OC
RAM
G.SKILL Ripjaws V
Hard Drive
480GB ADATA SX8200
Hard Drive
1TB Samsung 960 EVO
Hard Drive
2TB HP EX950
Power Supply
Corsair RM650
Cooling
Noctua NH-U12S
Case
Fractal Design R5
Operating System
Windows 10 Pro 64-Bit
Monitor
BenQ GW2765HT
Monitor
BenQ GW2765HT
Keyboard
Patriot Viper V760
Mouse
Patriot Viper V560
CPU
Intel i7 4790K
Motherboard
ASUS Maximux IV Extreme
RAM
Corsair Vengeance Pro
Hard Drive
128GB Samsung 830
Hard Drive
480GB SanDisk Extreme II
Hard Drive
2TB WD Red
Hard Drive
2TB Samung Spinpoint F4
Hard Drive
2TB Hitachi Deskstar 7K3000
Hard Drive
1TB Samsung Spinpoint F3
Hard Drive
3TB Toshiba DT01ACA300
Hard Drive
Seagate Barracuda 7200.14
Power Supply
Corsair 650TX
Case
Norco RPC 4224
Operating System
Windows 10 Pro
Other
LSI 9261-8i
Other
Intel RES2CV240
CPU
i5-4670k
Motherboard
Asrock Z97 Extreme6
RAM
32GB Kingston HyperX Beast 2400MHz
Hard Drive
128GB Samsung 850 Pro
Power Supply
850W Be Quiet! Dark Power Pro 10
Cooling
Thermaltake Water 3.0 Ultimate
Case
Thermaltake Urban T81
Operating System
Windows 8.1 Pro
▲ hide details ▲



Last edited by Sean Webster; 07-23-2019 at 10:49 AM.
Sean Webster is offline