-
G Speed Q ESATA Write Speeds in Raid5
-
The biggest deciding factor to E-Sata Multiplexing bay performance is the E-Sata controller cards. I have tested this extensively from very cheap Marvell Startech controllers to Silicon image controllers and even Highpoint. This is one instance where what you pay for is what you get. This works the same with SAS controllers. Higher end LSI SAS controllers have far greater performance especially with rebuild rates than much cheaper Highpoint SAS controllers. The best E-Sata card that I have seen is Sonnet’s. That card will give you close to peak bandwidth performance for your E-Sata multibay regardless of the manufacturer especially on HFS+ arrays. However this is a $250+ expense. The only decent cheaper controllers that I have seen were Marvell and only with the latest firmware and drivers. Keep in mind Caching models on the controllers for command queuing along with the controller firmware initializing with Windows 7 cache policy correctly is what decides this. So the overall here is if you want the 200Mb/s a sec on these 4 and 5 bay E-sata units expect to get a $300 controller card. If 185MB/s Read 150MB/s writes is ok then look at highpoint or Marvell controllers.
Eric-ADK
Tech Manager -
I’ve just run the Blackmagic Speed test on my G-Speed Q 8 TB (RAID5 – 6 TB) with 1.15 TB free. I’ve connected it to a MacPro 8-core through a Sonnet 2-port SATA card. I’m seeing about 230 MB/sec write and 250 MB/sec read.
———————————–
Neil Sadwelkar
neilsadwelkar.blogspot.com
twitter: fcpguru
FCP Editor, Edit systems consultant
Mumbai India -
EricBowen writes: The biggest deciding factor to E-Sata Multiplexing bay performance is the E-Sata controller cards.
I’ll speculate that this is due to the difference in switching method used by the controller. Command based causes the controller to communicate discreetly to each drive via the multiplier, one drive at a time and no outstanding commands are permitted. FIS based enables the controller to, in a sense, communicate to all of the drives at the same time, with multiple outstanding requests per drive. Obviously FIS is a lot more complicated, but also a lot more efficient.
What I’m not sure of about the G-Speed Q is how this relates to its internal raid controller, since I don’t think it’s up to the computer SATA controller to talk to the drives. The G-Speed Q controller presents a logical drive to the computer SATA controller which should just spit out a stream of data to the G-Speed Q. And then it’s up to the G-Speed Q controller to divvy that up into data and parity chunks, and deliver them to the proper drives. So I’m a bit puzzled why the controller matters in this case.
-
I have seen where the Multiplexor controller on the bay slows the performance down with controllers that have better performance on others. Likely due to what you reference. Firmware updates for the bays have changed this. Very similar to what I see with USb3 multibays. However the caching policy is at the E-Sata controller level and that is where the largest performance difference is made. I have also seen this with onboard Intel controllers and raid. They often change their caching policy and the raid 0 performance changes because of that. Sonnet just seems to have a much better caching policy than the other controllers.
Eric-ADK
Tech Manager -
Eric, can you list the exact model of Sonnet card that you’re using? Is it the H680 SAS card or one of the SATA cards like the Tempo?
Reply to this Discussion! Login or Sign Up