• Some users have recently had their accounts hijacked. It seems that the now defunct EVGA forums might have compromised your password there and seems many are using the same PW here. We would suggest you UPDATE YOUR PASSWORD and TURN ON 2FA for your account here to further secure it. None of the compromised accounts had 2FA turned on.
    Once you have enabled 2FA, your account will be updated soon to show a badge, letting other members know that you use 2FA to protect your account. This should be beneficial for everyone that uses FSFT.

ProLiant E200 Write Performance Oddities

bigdogchris

bigdogchris

Fully [H]
Joined
Feb 19, 2008
Messages
19,080
I have 8x 146GB 10k SAS drives in a RAID 5 array on a E200 w/128MB BBC on 2008R2. I am using CrystalDiskmark and ATTO Disk Benchmark to test.

I'm having bizarre write speed issues. Using ATTO, it will read around 450MB/s, which is expected. However the write speed is around 15MB/s. CrystalDiskMark shows around the same results. If I disable Direct I/O in ATTO the write speed jumps to around 400MB/s. Real world testing nets me about 15MB/s write and about 5MB/s if copying amongst the same array. There's obviously an issue.

Is there a way to get the cached performance I see by disabling Direct I/O at all times in real world writes?

I've made sure that my controller and hard drive firmwares are up to date as well as using the most recent controller driver. I've also tried different cache ratios, disabled the cache, as well as tested local disk caching on and off.

I've read online many other people with E200 controllers with this issue but have not yet found a solution. Thinking of the vast difference in results regarding Direct I/O on/off, I'm wondering if this is a write-back / write-through issue but thought toggling the cache and cache ratio would help that, but it doesn't.
 
Last edited:
E200's are a piece o %&*# controller

from what I remember

you have to setup the controller something like
0% Read
100% write caching in the Smartarray advanced setup section
then enable HDD onboard cache.

to get any performance at all

Best option is to bypass it and grab another card P400 P600 P800 etc.

.
 
I've tried numerous combinations without any success at all. The cache does not seem to make any difference at all so I can't even tell if it's working, though the diagnostic says it is.

One thing I noticed while watching resource mon is that when I'm copying large, single files to the server with the e200, the servers memory usage will drastically increase as a cache, giving a temporary boost to write speeds. As the file is wrote to disk the memory returns to normal levels. If you delete the file before it's "wrote" the memory instantly clears, so I know it's being used as a cache. I've never seen this before, is it a 2k8R2 thing?

If I replace the e200 with a P400, will the raid array still be in tact? I don't know if the e200 is an LSI chip like the p400.
 
Snip

The short answer = ENABLE the write cache BUT set the WRITE CACHE to 0% via the HP CLI. [ctrl slot=0 modify cacheratio=100/0 | ctrl slot=0 modify dwc=enable] Turn it on, but don't use it, go figure!

I just set up an Open-e DSS V6 server on an HP ML350 G5 with a E200i RAID controller, 128MB BBWC, and 6 x 1.5 TB 7200 RPM drives in a RAID 10 array. I was getting very bad performance, less than 100 iostats on an iSCSI file I/O volume high initialize rate. I have similar configurations using 3Ware 9550 cards producing well over 1000 iostats so I was trying to figure out what the ??? was going wrong.

A bit of research directed me here and to an Experts-Exchange article (http://www.experts-exchange.com/Storage/Hard_Drives/Q_24947953.html). It would appear the RAID 5 processor and write cache are troublesome components to this controller. I wasn't using RAID 5 so I experimented with the read/write cache through the HP controller CLI that Open-e conveniently puts in their software.

The CLI was running VERY SLOW, commands took a minute to respond. Finally the above command made the array perform closer to expectation. I am now seeing almost 1000 iostats and the CLI is responding normally. Yes, you have to enable the write cache and set it to 0%. No other combination seems to work. Even using the disable write cache option failed to provide acceptable performance.

snip

From Here
http://serverfault.com/questions/150419/raid-array-performance-on-an-hp-proliant-ml350-g5-smart-array-e200i

Code: 
http://serverfault.com/questions/150419/raid-array-performance-on-an-hp-proliant-ml350-g5-smart-array-e200i
 
Just to update this.

I found that the write cache does almost nothing for sequential reads and writes but does help tremendously with random and queued depth performance. It's still not great overall performance but the difference with and without the cache is quite substantial. I'm just disappointed that with 8 drives, the performance is not better.

I'm considering upgrading to the SA P400 512 but I read that the RAID 5 performance is still not going to be great.

Does anyone have a P400? If so, what do you guys think of it?
 
Upgraded to the P400 - 512MB. Quite a significant performance boost. Even working with large data sets the performance is quiet a nice boost. IO is significantly better. Well worth the $30 it cost. ATTO, with Direct I/O was really improved. 300MB/s writes and 600MB/s reads, which is much closer to what this array should be at.
 
Last edited:
You must log in or register to reply here.
Back
Top