Adam_a

Seagate 1200.2/Micron S600DC Enterprise SAS SSD Review

4 posts in this topic

The Seagate 1200.2/Micron S600DC families of drives offer a SAS interface, capacities up to nearly 4TB and four different endurance ratings designed to meet most enterprise needs. The drives are identical down to the firmware (the functional portion of the firmware, drive identification within the firmware is unique to each brand), which is a unique development and marketing strategy for the two companies. Out of the gate the 1200.2/S600DC is clearly the best SAS SSD either company has produced on its own, so the early dividends of the partnership appear to be paying well. The long-term will be interesting though, as this conjoined strategy is great for launch, but will likely prove untenable over time if both Seagate and Micron fancy themselves as SSD vendors going forward.

Seagate 1200.2/Micron S600DC Enterprise SAS SSD Review

Share this post


Link to post
Share on other sites

I'm trying to replicate your results from above review with the "Scalable Endurance" model (S610DC) but I'm having issues getting the results even close to the spec'd performance on sequential writes and even see extreme latency spikes with 4k random read/write, even after preconditioning the drive to the Micron Specs. I have a very small suspicion that the controller (MegaRAID 9271-8i) might have issues performing when the host is doing things in parallel. I'm getting proper 4k reads (130k) and 4k writes (22k) without O_DSYNC but with O_DIRECT. 

I've been experimenting for a few days and I'm a bit at a loss what to try. As the drive is SAS I'm currently also trying to find a different controller - connecting directly to the board isn't an option as with SATA drives unfortunately.

I wonder whether you may have any suggestions. I'm also contacting Micron to see whether they can explain this or have suggestions. Unfortunately their SSD tool doesn't seem to properly work with MegaRAID to access the drives even though the manual says it does.

My next step is to compare individual and mixed-mode performance. I'll use an Avago 9271-8i (which we currently have in production) and compare that to the Avago SAS III HBA 9300-8i and the Adaptec SAS III HBA 1000-8i. I'm specifically interested to see how performance is impacted when either only this drive is used or other drives (SATA HDDs and other SATA SSDs) are getting traffic at the same time.

Cheers and thanks for the well-written and documented review.

Share this post


Link to post
Share on other sites

I think part of the issue you describe is flowing through the RAID card, I'm assuming in RAID0 for that drive, versus pass-through/HBA mode. If that's the case, its the hardware RAID holding that SSD back.

Share this post


Link to post
Share on other sites

Thanks, that is my suspicion as well. I just received a shipment of said controllers and I'll also include the 9271 in JBOD mode (it can't do a pass-through on individual devices AFAICT). I'll let you know my findings here.

Share this post


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