New LSI 9200 series controllers: 6Gb/s, 2.88 GB/s seq. reads, 1.87 GB/s seq. writes

[Biker]

0.22 on reads for adaptec. 0.095 onboard. I dont remember the write access times TBH, but those aren't too important anyway.

...and Areca is somewhere in the middle with .013 - .017 reads..... hmmmmm.

[justin.kerr]

Well after 3 days, it seems that the classified and the LSI don't play well together.... LSI tech support seemed decent, but the end result is wait for bios/firmware updates, or return it.. lol what to do with all the x25m's?

[Biker]

Well after 3 days, it seems that the classified and the LSI don't play well together.... LSI tech support seemed decent, but the end result is wait for bios/firmware updates, or return it.. lol what to do with all the x25m's?

Please elaborate on "don't play well"...

Also which Classified?

759, 760 or 761?

[justin.kerr]

LSI tech said that my board was designed for GPU's not RAID cards, so the performance would be low.....and have a lot of problems, like all SLI MOBOs have with their RAID cards..........I think she was just fed with with all my calling, trying to get some performance out of it. lol...But any way, I seem have pretty great write performance, but read is stupid low, I am going to keep trying different combinations, trying to get decent results.

[justin.kerr]

760

[Spoiler]

LSI tech said that my board was designed for GPU's not RAID cards, so the performance would be low.....and have a lot of problems, like all SLI MOBOs have with their RAID cards..........I think she was just fed with with all my calling, trying to get some performance out of it. lol...But any way, I seem have pretty great write performance, but read is stupid low, I am going to keep trying different combinations, trying to get decent results.

Hmm, thats odd. The guy form that OCZ forums link was running a Classified mobo. He seems to have no problems with the LSI card.

[Biker]

Hmm, thats odd. The guy form that OCZ forums link was running a Classified mobo. He seems to have no problems with the LSI card.

Hmmmm....

True "no probs" but define no probs

On the OCZ guys setup he was getting .3 read latency with Read Ahead switched on and .27 with it off....

Not very fast at all....

Writes however were spot on

Similar results with your Classified and this card justin.kerr?

[justin.kerr]

so far, writes are scaling very well, reads are just crap, hopefully with new drivers/FW updates this will change...

[Biker]

so far, writes are scaling very well, reads are just crap, hopefully with new drivers/FW updates this will change...

Lowest read latency I can achieve with an LSI card is .024 - amd that is an 8708ELP, not the new ones...

[Mic]

Been looking a bit at the test at tomshardware http://www.tomshardware.com/reviews/...780a,2374.html where he compaires the 9260 to onboard raid. Might just be me reading the charts wrong but it doesn't look to impressive there as far as I can tell. Kinda expected a bit more, but ok its just benchmarks.

[XS Janus]

Read access time:


Write access time:

[lowfat]

Been looking a bit at the test at tomshardware http://www.tomshardware.com/reviews/...780a,2374.html where he compaires the 9260 to onboard raid. Might just be me reading the charts wrong but it doesn't look to impressive there as far as I can tell. Kinda expected a bit more, but ok its just benchmarks.

It doesn't look impressive at all.

[WonderSausage]

It doesn't look impressive at all.

Tom's has no idea how to configure hardware RAID, and they tested the LSI on the ATI board, not the Core i7.

[WonderSausage]

I'm waiting for the Intel Gen2 SSDs to become available again, but in the meantime, my LSI 9260-8i arrived and I decided to do some initial testing to make sure that it's getting allocated enough lanes and so forth.

I just threw on a couple of ancient Raptor 36GB in RAID 0 and set up benches with small working sets to test cached performance only (with write-back forced on because my battery hasn't arrived yet).

In my previous experience with X58 and other RAID controllers, they tend to get 4 lanes allocated. Of course, all previous controllers have been PCI-e 1.0 and the 9260 is 2.0. There is no way to tell the difference between 4 lanes @ 2.0 and 8 lanes @ 1.0 but due to the previous experience I'm going to assume 4 lanes.

Clearly the LSI 9260-8i is getting 4 lanes @ 2.0 on the P6T Deluxe given these benches. Hell, it's above the theoretical real-world maximum (theoretical ultimate maximum is 2000, real-world is suppoed to be ~1800). It's in the bottom X16 slot on the P6T Deluxe. I put an Intel PCI-e x1 NIC in the top x1 slot as well as a 4870X2 in the first x16 slot.

Let me just say in caps for those skimming this thread, THIS IS INTENTIONALLY TESTING CACHED PERFORMANCE.



It's obvious that the card has enough throughput for any drive configuration, and that the cache is fast enough to not hold back any SSD RAID0 setup.

I'm not going to bother to post the ATTO results which as you probably know are all over the place once you get over a few hundred MBps, but the max reached was similar in that bench.

WS

[F.E.A.R.]

Hi, WonderSausage!
Please make a run with HDTune 3.5 (normal Benchmark and Random Access) and with IOmeter - Workstation-Pattern too.
Which drives do you use?

[lowfat]

Hi, WonderSausage!
Please make a run with HDTune 3.5 (normal Benchmark and Random Access) and with IOmeter - Workstation-Pattern too.
Which drives do you use?

In the post above yours he says he is using a pair of old 36GB raptors.

[F.E.A.R.]

Ups...

[XS Janus]

nice through put!

I was disappointed how the same sds worked way slower on LSi than on ICH10, the endemic Ati board could be the culprit...
Stupid toms, always fails in some regard...

[Mic]

Yeah most likely some non optimal configuration.. With 6x Intel X25-E those transfer rates should be a bit higher.

[Serra]

LSI controllers seem to generally have issues with first release drivers/firmware, I wouldn't be surprised if that was an issue as well. Roll that into what others were saying about issues on SLI boards and I'm not surprised - perhaps a tape mod is needed?

I can't wait until Dell gets on board with a PERC 7, that's when I'll jump in. There's nothing like paying half price or less for a new controller because a system admin doesn't need it in his new system. Plus at that point the firmware issues have generally been worked out and you get a lot of support for issues from Dell.

[Biker]

Ok.

Computard (OCZ & [H] forums) is definitely getting to grips with his new 9260-8i card now:

Anyone for 1.7gb/s+ throughput?

8x Vertex 30GB running on Classified 759 (with an overclocked PCI-e bus):



Just PM'd him to see if he managed to beat down on the read latency any... will report back when I get a response....

[Baron_Davis]

Nice

[F.E.A.R.]

I would like to see a bench with maximum raw power (without cache).
HDtune and HDtach.

[F.E.A.R.]

nice through put!

I was disappointed how the same sds worked way slower on LSi than on ICH10, the endemic Ati board could be the culprit...
Stupid toms, always fails in some regard...

This shows only seq. transfer rates.
I´m sure the LSI is faster with ramdom reads/writes

[Biker]

Well i've ordered a 9260-8i to play with....

I only have 110mb/s read drives for testing right now but apart from future proofing and speed etc i'm after only one thing...... X58 compatibility