• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

SATA III Limitations

dsplover

Member
I like benchmarks, they're good at measuring against another device.
SATA III bottlenecks are @ 590MBps.
Even though guys tell me they are getting 1GBPs using RAID 0.
They show increases in polyphony (real world tests for audio buffs) and the 1GBps seq. reads have oversaturated the bus, so this leaves to believe the random 4k-64k 160k IOps must be the reason.

Is there such a thing as a threshold of limitation of IOps over the SATA III Bus..?

Just curios as I can't seem to get an answer on this important issue.

Thanks
 
I am not sure how one would consistently surpass a BUS limitation.

I personally look forward to what M.2 will bring us and the SSD speeds that will come with it.
 
"Even though guys tell me they are getting 1GBPs using RAID 0."
That is multiple busses, A single SATA3 port is still limited to around 590MBps.

"Is there such a thing as a threshold of limitation of IOps over the SATA III Bus..?"
Yes, The command que calls still use bandwidth.
 
I like benchmarks, they're good at measuring against another device.
SATA III bottlenecks are @ 590MBps.
Usually lower. Anywhere that close to peak is going to be simple sequential data only. It usually tops out closer to 550MBps.
Even though guys tell me they are getting 1GBPs using RAID 0.
They show increases in polyphony (real world tests for audio buffs) and the 1GBps seq. reads have oversaturated the bus, so this leaves to believe the random 4k-64k 160k IOps must be the reason.

Is there such a thing as a threshold of limitation of IOps over the SATA III Bus..?
Yes. 32 in flight per device/port, and SATA is not duplex. There is not a hard limit per second, except the bandwidth, but there are several layers of overhead to add to the service time per operation, that it will never get too close to the bandwidth, on small IOs.

and the 1GBps seq. reads have oversaturated the bus
Nope. You won't get 1GB from a SATA 6Gbps port. You might get 500MBps each from two of them, however.

Also, it's IOPS, all caps, as the P is Per, and the S is Second, as lowercase was already in use to mean the simple plurality of IO operations.
 
Last edited:
Thanks Gents.

I am going to keep adding M.2 devices. While I only have 1 x 4x XP941, I like that better than using RAID 0/SATA III.
I have a 2x slot open on the ASRock so I will break down and get the Plextor M6e and not look back at SATA anymore.

Cheerz
 
Back
Top