Random Performance – Iometer (IOPS/latency), YAPT (random)
We are trying something different here. Folks tend to not like to click through pages and pages of benchmarks, so I'm going to weed out those that show little to no delta across different units (PCMark). I'm also going to group results performance trait tested. Here are the random access results:
Iometer:
Iometer is an I/O subsystem measurement and characterization tool for single and clustered systems. It was originally developed by the Intel Corporation and announced at the Intel Developers Forum (IDF) on February 17, 1998 – since then it got wide spread within the industry. Intel later discontinued work on Iometer and passed it onto the Open Source Development Lab (OSDL). In November 2001, code was dropped on SourceForge.net. Since the relaunch in February 2003, the project is driven by an international group of individuals who are continuesly improving, porting and extend the product.
Iometer – IOPS
We don't normally see hybrid SLC cache SSDs run out of steam on the first test, but, well, these did. Not only did they, but the performance drops to a very low level almost immediately, not to mention being very inconsistent.
The Web Server test is read only, showing that so long as we are not writing, all three capacities of the Trion 100 had no issue here.
Well we got into the mixed read/write workloads and everything fell apart for the Trion 100's once again.
I'd like to say more, but I don't really have more to say other than don't plan on hitting a Trion 100 with any sort of mixed workload that involves writes.
Iometer – Average Transaction Time
For SSD reviews, HDD results are removed as they throw the scale too far to tell any meaningful difference in the results. Queue depth has been reduced to 8 to further clarify the results (especially as typical consumer workloads rarely exceed QD=8). Some notes for interpreting results:
- Times measured at QD=1 can double as a value of seek time (in HDD terms, that is).
- A 'flatter' line means that drive will scale better and ramp up its IOPS when hit with multiple requests simultaneously, especially if that line falls lower than competing units.
We can see in this 'zoomed in' QD 1-4 area that the Trion 100's approach ~2x the latency of competing SSDs wherever writes are included in the workload. This does not bode well for the Trion.
YAPT (random)
YAPT (yet another performance test) is a benchmark recommended by a pair of drive manufacturers and was incredibly difficult to locate as it hasn't been updated or used in quite some time. That doesn't make it irrelevant by any means though, as the benchmark is quite useful. It creates a test file of about 100 MB in size and runs both random and sequential read and write tests with it while changing the data I/O size in the process. The misaligned nature of this test exposes the read-modify-write performance of SSDs and Advanced Format HDDs.
Random reads – no problem for all SSDs tested, even the Trion 100's.
This test has no regard for 4k alignment, and it brings many SSDs to their knees rather quickly – especially the Trion 100's, but they fell apart even on our 4k aligned Iometer testing, so this was to be expected.
OCZ….Meh!
OCZ….Meh!
Not even Toshiba could save
Not even Toshiba could save them from the very bad habit of making crappy SSDs, lol.
Maybe they will come out with
Maybe they will come out with a NVME version!!!!?
OCZ in the name is deal
OCZ in the name is deal breaker for me. Lot of hype and nothing at the business end. 2nd deal breaker is TLC flash. Not a fan of it by long shot. I would be more optimistic if they come with pure TLC drive and like 4-5TB capacity for 400-500$.
If they want to take a stab at something, stab the region where no competition reached before. And that’s beefy SSDs for the masses intended as storage. You don’t need 500MB/s+ transfers here. Also random access/write/read is not major factor. I said as long as SSDs are around. Storage of rarely accessed data that’s the only good place for SSDs.
$.10 per GB I like that
$.10 per GB I like that idea
BackBlaze StoragePod made of only SSD
Only like $20k
Thanks for the solid write
Thanks for the solid write up, Allyn.
As I see it, OCZ continues to struggle. I thought with Toshiba acquiring them, allowing the access to Toshiba’s inventory “at cost,” they would provide some solid SSDs at affordable prices. Think Crucial. Instead we have prices higher than Samsung with subpar performance.
I’d love to support OCZ but they make it so darn hard! Unless they have some huge OEM contracts, I don’t see how they can stay relevant.
Perhaps Toshiba should ask
Perhaps Toshiba should ask their manufacturing partner Sandisk
for a little help here,as it’s possible the flash they are using
is exactly the same………………..
Haven’t seen write speeds that low since the 120GB-840……
Uphill battle-even if OCZ reduces prices by 30% they still have
the-“Friends don’t let friends OCZ” to contend with…………
It makes you wonder why OCZ
It makes you wonder why OCZ released this product when they could clearly see in their testing/validation that it couldn’t compete with the 850 Evo? Releasing a product after the competition that costs more that offers worse performance? *sigh*
My spoon is too big…
My spoon is too big…
*Sings in David Bowie’s
*Sings in David Bowie’s voice*
G-g-g-g-GAR-BAGE, G-g-GARBAGE. G-g-g-g-GAR-BAGE, Ga-ga-GARBAGE!
One major plus for me is that
One major plus for me is that OCZ offers a linux version of their “SSD Guru” utility. I’m wondering if some of the short comings in this review might be mitigated by an update.