RAID-5 performance of LSI SAS 2008m-8i in C240 M3?

Can anybody speak to the performance of the mezzanine RAID controller option in the C240, particularly in a RAID-5 configuration? I have need to configure a C240 with all 5 PCIe slots consumed with interface cards, so I will need to use the mezzanine card option. The 2008m does not support a BBU, but from what I understand, it does support write caching and does have an onboard processor for XOR offload so I would expect it has decent RAID-5/50 performance. I can't seem to find any benchmarks or documentation to confirm that.

Hi Brad,
Please find the document for RAID controllers in C 240 M2 ,link mentioned below may be this can help you out.
http://www.cisco.com/en/US/docs/unified_computing/ucs/c/hw/C240/install/raid.pdf
Syed

Similar Messages

Cisco UCS RAID SAS 2008M-8i Mezzanine Card Performance?

I recently purchased a UCS C220 bundle, which includes a Cisco UCS RAID SAS 2008M-8i Mezzanine Card. I'm planning on deploying this as a standalone server running XenServer 6.2 in the near future.
I'm happy with the unit and testing is good, but for one aspect. The disk IO throughput on it seems to be far short of what I expected. I have a desktop PC with an Intel DZ77GA-70K motherboard as a lab spare, and the disk IO I can achieve from that server with the same disks exceeds what the C220 seems to be able to achieve, on a consistent repeatable basis.
The testing I am doing is based around two benchmarks:
1. A 400G file copy between the two machines, over the network back-to-back to note the maximum sustained throughput, and
2. A mix of runs with 'sysbench' to mix of tests of local IO, of sequential and random reads and writes, with the command: "sysbench --test=fileio --file-total-size=150G --file-test-mode=seqrd --init-rng=on --max-time=300 --max-requests=0 run"
For #1, I run a copy to/from an HP MicroServer Gen8, which has 12TB of disk space on it in a Linux RAID0 configuration (4x3TB Seagate drives). If I copy files to or from this HP Server to the Intel DZ77GA-70K I am able to easily saturate the 1G network, achieving a sustained 960MBit/s for an hour or more at a time. If I then take the exact same SATA disks from the DZ77GA-70K, connect these into the UCS box and do the exact same network copy with the exact same OS, I'm only about to get around ~400-500MBit/sec of sustained throughput.
For #2, the test results of which are entirely local to the C220, come in around 105-110 MByte/sec on a sequential read, which drops to around 2 MByte/sec on a random read or write test. No surprise of the enormous drop - because random reads/writes are a pretty tough IO load, but I would expect sequential reading should be much better. I can get consistent sysbench seqrd results from the MicroServer of around 300 MByte/sec, for example.
I can consistently replicate this with Redhat 6.5, as well as Gentoo (running the latest linux kernel) as well as from a Xen 6.2SP1 Hypervisor install on the C220 (tested from the Dom0 domain itself, as well as a Linux guest) all 64 bit. Jumbo frames are enabled end-to-end also, and CPU is not bottlenecking. Latest firmware is installed on all components. The ucs-cxxx-drivers.1.5.4a.iso image states that for the Redhat and Xen systems, that the required drivers are included in the OS, so I don't need to worry about installing them separately. Presumably the Gentoo system has even newer drivers again because it has a very new kernel, but alas the throughputs are the same on all of those systems.
I have tried with SATA as well as a SAS drive, and the test results are also practically the same. All disks in all servers are Seagate 6.0 Gb/s units, and none of the servers are swapping to disk at any stage.
I am happy with network IO - I can completely saturate the 1G ports easily, and I'm convinced that's not a part of the problem here.
What could cause this sort of performance? Storage card logs in CIMC don't indicate anything is wrong and none of the OS's are indicating issues of any sort, but it certainly does seem something isn't right in that I'm getting significantly superior performance from a desktop motherboard and the MicroServer, than an enterprise grade server, when testing with the exact same hard drives.
Questions:
- Is the 2008M-8i card considered a low-end RAID card or should I be getting reasonable throughput from it? I was anticipating performance at least as good as a desktop motherboard, but this doesn't seem to be the case. The RAID card as a component is more expensive than an entire MicroServer or Intel Motherboard so it should run much better, yes?
- What sort of performance should I expect out of this card on a single sequential read or write?
- Can this RAID card run drives just as JBOD's or do all disks have to be initialised in an array (even if just a RAID0 array with 1 disk)? It seems if they are added to the server they do not show up to any OS until they are initialised as part of an array, although I haven't delved into the BIOS settings of the card itself (only from CIMC so far).
- I recall seeing something about best practice of having two virtual drives on these cards, what is the impact in running more, given the card certainly allows more to be created (I currently have 4 while I am testing)
- I noticed on Cacti graphs while rebuilding a RAID1 array that the CPU ran hotter while the array was being rebuilt, and cooled down once the rebuild had completed, which indicates the rebuild was using up CPU on the host hardware. Should this not have been entirely transparent to the system if the RAID activity is offloaded to this card, or is an increase in CPU to be expected?
I'm very keen to find out others experiences of this card, what people have done to get good throughput out of it, or if I should go back to a whitebox server with an Intel board :-)
Thanks,
Reuben

Hello Reuben,
I reached out to colleagues who are more knowledge on this topic and here is their response.
- Is the 2008M-8i card considered a low-end RAID card or should I be getting reasonable throughput from it? I was anticipating performance at least as good as a desktop motherboard, but this doesn't seem to be the case. The RAID card as a component is more expensive than an entire MicroServer or Intel Motherboard so it should run much better, yes? -
2008M-8i card is a entry/value card with an expected performance which is better than a software RAID. This card doesn’t utilise memory in a standard RAID 0/1 configuration.
- What sort of performance should I expect out of this card on a single sequential read or write? - We should expect around 1GB sequential read (refer link http://www.cisco.com/c/en/us/solutions/collateral/data-center-virtualization/unified-computing/whitepaper_c11-728200.html)
- Can this RAID card run drives just as JBOD's or do all disks have to be initialised in an array (even if just a RAID0 array with 1 disk)? It seems if they are added to the server they do not show up to any OS until they are initialised as part of an array, although I haven't delved into the BIOS settings of the card itself (only from CIMC so far). -
This card can be used in JBOD mode. To enable JBOD mode you need to use MegaCLI commands. This option is not present as a default configuration.
Please note: Once we enable the JBOD mode – it cannot be reverted back to the default RAID mode setting.
- I recall seeing something about best practice of having two virtual drives on these cards, what is the impact in running more, given the card certainly allows more to be created (I currently have 4 while I am testing) -
This doesn’t apply for this card as it does not have any cache. Can you please point us to the document about best practice of having two virtual drives ?
- I noticed on Cacti graphs while rebuilding a RAID1 array that the CPU ran hotter while the array was being rebuilt, and cooled down once the rebuild had completed, which indicates the rebuild was using up CPU on the host hardware. Should this not have been entirely transparent to the system if the RAID activity is offloaded to this card, or is an increase in CPU to be expected? - Creating/Deleting/Modifying a RAID volume is a CPU independent operation.

C240 M3S can't setup first boot with Cisco UCSC RAID SAS 2008M-8i Mezzanine in BIOS

Hi all,
I have a problem with C240 M3S with boot device.
1. There is a Cisco UCSC RAID SAS 2008M-8i Mezzanine in the C240 M3S
2. I set up the raid5 for four SAS disks with Cisco UCSC RAID SAS 2008M-8i Mezzanine
3. When I install the ESXi 5.5, it can be installed in SAS disks.
4.When I press F2 to setup bios for C240 M3S, I can't find the item for the raid of Cisco UCSC RAID SAS 2008M-8i Mezzanine
5. C240 M3S can't boot from the Cisco UCSC RAID SAS 2008M-8i Mezzanine
6. BIOS have been reloaded for many times, it can't work.
Anybody have any idea for this problem? Thank you!

Sorry,
I can't find the item of local storage.
I never setup the boot order ( default bios can find raid card, I don't know that raid can't be found at this time )
Would you please offer any references, thank you
By the way, I check the install guide for c240 m3
If the RAID controller does not appear in the system boot order even with the option ROMs for those
slots are enabled, the RAID controller option ROM might not have sufficient memory space to
execute. In that case, disable other option ROMs that are not needed for the system configuration to
free up some memory space for the RAID controller option ROM.
this means I want to turn off all option ROMs to get more memory ? However, I turn off all option ROMs, I still can't find the raid.
Thank you very much!!

UCS C220 M3S with PCI mezzanine card raid SAS 2008M-8i :((

Hello
May be someone has already spend a little time with this configuration. the main stuff is my ucsc doesn't think he has disk to boot one even if with CIMC I see the opposite.
I configure with server conf utility ucs-cxx-scu-3.1.3b.iso with raid1 and as I have 2 UCS C220M3S I do also with Raid0 on another one. the trick is when I install ESXI 5.1 (VMware-VMvisor-Installer-5.1.0-799733.x86_64.iso) during install the setup od VMware detect the disk and install on it but after reboot always same storie no disk !!!
I don't see where to do something ??? So If someone encountered this problem, my be has already find the trick
The bios is C220M3.1.4b.0 and I have also a PCI Broadcom 5709 1Gbps 4 port NIC on slot 2 on both UCSC
here is the config 2xXeon CPU E5-2650 @2.00Ghz with 64 GB of Ram.
Any idea is welcome
Cheers
CX
and for the one configure with raid1

UCS C220 M3S with PCI mezzanine card raid SAS 2008M-8i
file attach UCSC220M3S right setup.pdf give illustrated answer
Point was VM distribution but bios which does not see SAS PCI Mezzanine Ctrl
Thanks to PDI help

LSI SAS 1064 Linux kernel build on x4600

Has anyone built a newer Linux kernel on a x4600 that uses the LSI SAS 1064 controller?
I don't seem to be able to get it to mount the partition after it reads the ramdisk.
Thanks in advance.
Message was edited by:
AragonX

I performed all these steps from the FAQ (skipped # mount /dev/sdx boot/ (your /boot partition) as I have no dedicated boot partition)
# mkdir /mnt/arch
# mount /dev/sdx /mnt/arch (your root partition)
# cd /mnt/arch
# mount -t proc proc proc/
# mount -t sysfs sys sys/
# mount -o bind /dev dev/
# chroot . /bin/bash
# pacman -Syu
# pacman -S udev
# pacman -S mkinitcpio
# mkinitcpio -p linux
does not fix the problem but brings up other errors when executing
# pacman -S udev
# pacman -S mkinitcpio
warning: could not get filesystem information for /bootmnt: No such file or directory
warning: could not get filesystem information for /cowspace: No such file or directory
warning: could not get filesystem information for /sfs/root-image: No such file or directory
warning: could not get filesystem information for /sfs/lib-modules: No such file or directory
warning: could not get filesystem information for /sfs/usr-shares: No such file or directory
warning: could not get filesystem information for /repo/core/x86_64: No such file or directory
warning: could not get filesystem information for /repo/core/any: No such file or directory
warning: could not get filesystem information for /bootmnt: No such file or directory
warning: could not get filesystem information for /dev/pts: No such file or directory
warning: could not get filesystem information for /dev/shm: No such file or directory

XServe RAID RAID5 performance?

Hello,
I would like to know how the XServe RAID performs in RAID5.
We are using multiple FC and SCSI RAID-subsystems at work and we need a bigger one by the end of the year.
TIA
Best
Nicolas

The Xserve RAID is specifically tuned for RAID 5 performance -- RAID 5 is about 99% as fast as RAID 0. Unless you were hosting a database on the RAID, and doing lots of small I/Os, there is no reason to use any other RAID scheme on Xserve RAID
There's a performance page here:
http://www.apple.com/xserve/raid/performance.html
With some info... not very detailed. If you can get ahold of an eval unit (Apple's direct sales force has a program for this), you can run Iozone benchmarks on one, and see how it might fit your usage pattern.

Assistance Making Arch RAID Driver from Source - LSI MegaRAID 9240-4i

Hey all-
I've been on Arch for about 6 months now and love it. However, I just built out a new workstation and need some assistance trying to get my RAID card up and running. Obviously, Arch Linux isn't going to be officially supported by any manufacturer, so I went with a card that fit the price and feature set I wanted and decided I'll do battle later. Later is now and I'm a little stuck. Here's what I have and know:
First, I went to http://www.lsi.com/storage_home/product … index.html and looked at the different drivers they had source code for. I decided that the Slackware driver is probably the best place to start since rpms and debs are more distro-specific and since between the other two Slackware is more current than Scientific. I have downloaded and extracted the source for the Slack driver and am in that directory with a dkms.conf, Makefile, megaraid_sas.c, megaraid_sas.h, and Module.supported in it, along with two folders worth of patches and the like.
My understanding is that since this driver isn't going to be available in the Arch Build System, I should follow the guide at http://wiki.archlinux.org/index.php/Creating_Packages to make a PKGBUILD. However, to be fair, I haven't coded since my C++ in college and it's been a while. Specifically, I am lost at the "Download and test the installation" heading. How am I to test the installation? I'm on an Arch box right now and the whole point of this was to get something I could successfully install on Arch.
Ouside of being lost there, I assume that when this all finishes, I will have some module package either megaraid_sas.o or megaraid_sas.ko that I can drop into my install and set to load via rc.conf.
If anyone has any light they can shed on this subject, please reply. If you need more info from me, please say so, so I can provide it. I tried to at least give a solid overview in my initial post.
-Ryan
Last edited by commonmanthemes (2010-09-27 20:14:40)

for future reference : the linux kernel supports many raid controllers (adaptec, areca, lsi meagraid sata etc ) check kernel source for details.
I recommend you add a non-raid drive to the megaraid system, and install arch on that drive.
Edit : Dieter says exactly what i wanted to say
Dieter@be wrote:Afaik the megaraid will write metadata on that disk. So you loose some flexibility, say when your controller breaks. I have my arch install on a disk which is connected to my motherboard directly. (without raid etc)
Next you should create your own pkgbuild .
This Aur pkgbuild for a highpoint sata raid controller (made by me sometime ago) should help you with writing your own : http://aur.archlinux.org/packages.php?ID=12865
once you have built the package, use pacman -U to install it.
modprobe the megaraid_sas module .
check dmesg and/or /dev to see if your raid drives are now detected.
if they are, you can start mounting/accessing/testing the functionality of your raid drives.
Note : it is possible to install archlinux on drives that require an external kernel module, but that makes the process a lot more complicated.
Last edited by Lone_Wolf (2010-10-05 12:39:30)

HP 360p G8 + LSI SAS 6160 + HP SW P2000 G3 compatible?

Hello
Anybody knows, are HP ProLiant DL380p G8 (733739-421) with HP 221HBA (729552-B21) and HP StorageWorks P2000 G3 (AW593B) compatible with LSI SAS 6160 ?
Thanks,

K9A Platinum Low Raid 0 Performance?

hi i just build this pc a few days ago and i did some tests on my raid using HD Tach (and on a website called pcpitstop.com)
both of these seem to be reporting my hard drives are doing no more than 80MB/s ... even though i have setup RAID 0 for 3 drives on the utility with the motherboard,
a friend of mine (who uses 4 drives in raid 0 of EXACTLY the same type of hard drive) gets more than 320MB/s on his drives ....
i fail to see how 3 of my drives = 80 MB/s, whilst 4 of his = 320MB/s
I installed the driver and took off the jumper at the back of the drive (to make them SATA II)
I checked the RAID config utility and all the settings seem to be perfect, however the drives seem to be failing to deliver the transfer speed i am looking for ...
My IDE drive is comparable to this setup, which kind of defies the point of me paying so much money for a RAID setup that's giving me the performance of only one of my drives
Windows recognises one drive, and says RAID 0 so i guess the RAID is working it's just not performing properly
Any help or suggestions would be greatly appreciated,
thanks

Quote from: Hans on 14-June-07, 03:56:02
Hi!
Please read Moan Guide first.
In general: RAID-0 performance is often exaggerated, although your speed seems to be too low. RAID-0 speeds depend on many things: the way the RAID has been set up (block/chunk size, driver, disks, controller, etc). Furthermore, different bench tools will show you different speeds, so don't depend too much on what a tool tells you.
*Edit: don't confuse burst speed with average read/write speeds! The burst speed can exceed the read/write speeds by a factor more than 2!
Some tips you may want to try:
- enable/disable NCQ (Device Manager -> SCSI/RAID-devices);
- try a different block size;
- try a different/newer driver or try the driver that came with the board;
- use the manufacturer's disk tool to have all disks checked for any errors. You may need to connect them as if they are IDE's to make them being recognized properly.
Then this: As far as I'm aware, Windows will not show RAID-0, unless you set up the RAID through Windows disk manager (system tools). If you did setup through Windows disk manager, please setup RAID again using the RAID bios on you board.
hey thanks for the reply, i'll try and give you some more info on what's going on;
firstly some more computer specs:
CPU: AMD Athlon 64 bit dual core 5000+
Graphics: ATI x1950XT-X Crossfire Edition (Single card at the moment)
Mobo: K9A Platinum (havent updated bios yet)
PSU: OCZ GameXStream 700W
RAM: Corsair 2GB DDR2 XMS2 Dominator DHX PC2-6400C4 TwinX (2x1GB)
HDD: 3xSeagate Barracuda 7200.10 320GB ST3320620AS SATA-II 16MB Cache - (Took the jumpers off the back to make them SATA II)
The motherboard uses the ATI XPRESS 3200 chipset, which supports up to 4x SATA II Drives, this is what i have used to connect the hard drives to. The Motherboard also offers a RAID utility for 0,1, and 0+1 RAID - i have used raid 0 with block size 128KB (it offered 64 or 128), FastInit was ON, and the other 2 settings i couldnt change, i activated all drives to the array and setup (in the BIOS) for the SATA's to be seen as a RAID configuration.
The latest drivers i used was catalyst 7.5 available from ATI website, the drivers on the CD dont work because i use Vista 64, and the CD says it doesnt support my OS, so i downloaded them.
In response to windows seeing the RAID .... i meant it see's one normal hard drive but the disk comes up as a RAID SCSI device in Propeties -> Hardware, that is the name the RAID utility (straight after POST) gives to the array i think, and so windows recognises it as one.

LSI SAS Raid Speed

I m courrious about how hight the transferspeed is going with the onboard controller.
I need 400 mb/s - this meight be realistic with 3 - 4 SAS HD in Raid 0 - but is the LSI controller able to provide this amount of data. How is the controller connected to the motherboard? PCI-e (x2) ?
Any experience with SATA and SAS Raid?
Thank you for sharing your experience.
Michael
Solved!
Go to Solution.

martindishwater wrote:
are there any differences in performance between using LSI controller ports or the intel controller ports or reasons to chose one instead of the other?
overall the LSI controller seems faster, even with SATA drives. since there are five total HDD bays on the D10, you can use the five LSI ports (bottom row with blue connectors) for HDDs and the intel ports (upper row with black connectors) for optical drives.
(edit: typo)
Message Edited by erik on 08-27-2008 04:23 PM
ThinkStation C20
ThinkPad X1C · X220 · X60T · s30 · 600

X4200 Lsi SAS Controller and...RAID??

Hi all,
I've got an X4200 with a 4x73 GB SAS drives.
Accessing to LSI Logic configuration I've discovered something I really didn't like.
With 2 disks on a X4100 server I created a RAID-1 and that's ok but with these 4 disks on X4200 the only things I could choose was:
1. a stripe of the 4 disks and that's absolutely to avoid :-/
2. a mirror (R1) of the first couple of disks and the 3rd and 4th disks left alone...
I thought that I was able to create at least a stripe of two disks and then to couple in R-1 with another stripe of the remaining ones...nothing to do
I can understand that I can let the os to manage some R-5 but unfortunately I was installing an ESX server 3 that has no driver for dynamic disks...
Suggestions?

Hi all,
I've got an X4200 with a 4x73 GB SAS drives.
Accessing to LSI Logic configuration I've discovered something I really didn't like.
With 2 disks on a X4100 server I created a RAID-1 and that's ok but with these 4 disks on X4200 the only things I could choose was:
1. a stripe of the 4 disks and that's absolutely to avoid :-/
2. a mirror (R1) of the first couple of disks and the 3rd and 4th disks left alone...
I thought that I was able to create at least a stripe of two disks and then to couple in R-1 with another stripe of the remaining ones...nothing to do
I can understand that I can let the os to manage some R-5 but unfortunately I was installing an ESX server 3 that has no driver for dynamic disks...
Suggestions?

RAID-1 performance with Sun v40z

We are using Sun v40z machines with built in LSI RAID controller (RAID level 1). I was wondering about the performance of RAID on these machines. Our application does a lot of I/O (mainly random and sequential reads). Since we are using a RAID-1 system with two disks, I expect the performance to be good, but it is not, and it seems that all read requests are served from one disk. We are running RedHat Linux 4.
For investigating, I used dd to read a large file and write it to /dev/null. During this operation, iostat showed around 400-500 transactions per second with 100K blocks read per second. When I instead run two parallel dd command to read from two different files, number of transactions per second drop dramatically to 100-120, with just 30-40K blocks read per second. This is very bad given that we have two disks mirrored using RAID-1 and both should be readable in parallel.
I have conducted the same experiment on a different machine (Linux desktop, non-Sun, without-RAID), and I was able to read 75-80K blocks per second with two parallel read processes.
I am using:
time dd of=/dev/null count=5000000 bs=16k if=file1.txt
time dd of=/dev/null count=5000000 bs=16k if=file2.txt
I haven't configured much with the RAID controller, it is as it came with the machine. Infact, I was not able to find any documentation or support about the RAID hardware on these machines from Sun's v40z site. If you know of location of documentation, please point me to it.
Any help about how to improve the performance will be appreciated.
thanks in advace,
Nilesh

Most controllers will simply round-robin between the two disks, so you shoudl not expect any performance improvements between a single disk and RAID1. SVM has a "geometric" read option which theoretically can help large sequential reads, but it defaults to round robin, and my guess is that most embedded controllers do as well.
Most likely read performance falls off as you try two file copies because you are trying to copy the same file. The two processes are trying to read the same disk sectors, so one of them is going to have to wait for the disk to spin around to the same sector the other process just read. There are lots of other reasons why this could happen. You should see the same effect with a single disk.

Software Raid 5 - Performance

Hi all,
we have a problem with a software RAID 5. Its read performance is acceptable (61 MB/s via UFS filesystem) while its write performance is very very bad. 3 MB/s through UFS filesystem is not acceptable for a machine with 6 1.35 GHz CPUs and 7 very fast (10K) fiberchannel disks.
Raid 1 write performance is okay (42 MB/s) as well as the performance of individual disks (read: 74 MB/s).
The RAID 5 includes 5 disks (140 GB each, 10K) and was built using the standard commands from the man page and online help.
The hardware: SunFire 890, 6 CPUs (1.35 GHz US IV), 24 GB Memory, 7 disks (140 GB, 10K each). The machine runs SunOS 5.10.
The question is: What are the options to speed up write performance of RAID 5?
A much cheaper Athlon 64 based Linux system with slower SATA disks is much faster in reading (180 MB/s) and writing (around 50 MB/s) on a similar software raid 5.
While searching the net I found some benchmarks that indicate that "normally" write and read on solaris software raid 5 should be nearly the same.
Are there any ideas what to do?
Greetinga and thanks in advance,
Jan

Hi,
thanks for your answer. But... I don't think this is the problem here. It is clear that these facts slow down the write process compared to the native write performance of the underlying disks, but the slowdown is IMO one order of magnitude too high.
As already mentioned... an Athlon Linux system with 4 disks has also a slowdown in write performance (compared to reading) but write performance is still 25%...30% of read performance. For this sun machine it is 5% of read performance. If the problem would be caused by contention and queuing it should apply there also, right?
Or, to use the measurements: The Athlon with linux has around 50 MB/s write and 180 MB/s read which makes sense for a fileserver with Gigabit ethernet. The sun has 61 MB/s read which is acceptable for such a server while the writing speed of 3 MB/s is even too slow for a single 100 MBit/s client.
Some benchmarks that I found on the net does not show such a big performance gap between read and write on Solaris software RAID 5 so I still guess there is a fundamental problem in our installation.
What about others... has anyone numbers from experiments such as writing 1 GB with dd to an empty partition and measure the time for that? The same for reading... after reboot or remount in order to empty the fs cache.
Greetings,
Jan

RAID 5 performance

I have 4 320gb disks. I have put them in RAID 5(Intel ICH10). I have used RAID 0 and RAID 1 before. This is the first time I am using RAID 5. Read performance is excellent, but write is very slow at 15MB/sec. Is it normal for RAID 5?Single disk write for my disks is around 70MB/sec.

Those write speeds are normal for a RAID5 array using an even number of disks. To get excellent write speeds on software RAID5 controllers like the ICH8R-ICH10R, you need an odd number of disks. The only options are a 3 or 5 disk RAID5 array since there are only a maximum of 6 ports.
See this thread to get an idea of what I'm talking about. The thread is about the nForce onboard SATA RAID, but the concepts also apply to ICHR chipsets as well:
http://forums.storagereview.net/index.php?showtopic=25786
To summarize the thread, when dealing with RAID0 or RAID5, to get optimal performance you need to use aligned partitions, ideally created at offsets of 1024KB x (number of usable drives in array). The overall best stripe size to use for the best read, write performance for all filesizes is 32KB. The best cluster size to use when formatting the partition with NTFS is 32KB when storing a variety of filesizes on the array. If you are only dealing with very large files on the array (256MB+), you can get the best performance by using a 128KB stripe size for the RAID array and a 64KB cluster size for the NTFS partition. I store a variety of files on my RAID array, so I use the 32KB stripe/32KB cluster option.
The next thing you need to do is create an aligned first partition on the array. If you use Windows Vista or later to create a partition it will create an aligned first partition by default. If you are using Windows XP, then you need to use a utility called diskpar.exe (not diskpart.exe since the XP version does not have partition alignment capability, but Windows Server 2003's diskpart.exe, and Vista and later's diskpart.exe do). You can gain slightly more performance by manually aligning the partition yourself using diskpar/diskpart. If you have a 5 disk RAID5 array, you would align the first partition on the array to 4096KB, or 1024KB for every non-parity (i.e. usable) drive in the array. For a 3 disk RAID5 array, you would align on 2048KB.
Yes, you can get awesome RAID5 write speeds on an Intel onboard RAID controller using the information above. My 5 disk RAID5 array with Samsung F1 500GB drives has a maximum read speed of 350MB/s and write speeds of nearly 300MB/s. They trail off linearly as you get further into the array just as any mechanical HDD's performance does when looking at HDtach/HDTune benchmarks. You're never going to get read and write speeds that match a RAID0 array with the same number of drives, but with proper stripe/cluster/alignment you can get close. For comparison, the same 5 drives in RAID0 have a max read speed of 450MB/s and write speeds over 400MB/s. On ICHR chipsets, RAID0 arrays are not severely hampered by non-aligned partitions, but alignment does help quite a bit. For RAID5, partition alignment is essential for good write performance.
Diskpart.exe usage (done on a clean drive/array with no partitions):
1) Open a command prompt window and type diskpart then hit Enter.
2.) Type: list disk then hit enter. Look for the disk number that corresponds to your RAID array
3.) Type: select disk 1 (if disk 1 is your RAID array)
4.) Type: create partition primary align 4096 (if you have a 5 disk RAID5 array, use 2048 if you have a 3 disk array)
That's it. Format the drive making sure to select the correct cluster size (at least 32KB). If you created a first partition that didn't fill the drive, any subsequent partitions you create on the drive will be aligned because the first one is aligned.

3 drive sata Raid 5 and 1 drive sas?

I cant see if it possible to have a single sas drive on the same Raid card as Raid 5 3 drive sata. Anyone help?

http://www.apple.com/macpro/technology/storage.html
http://docs.info.apple.com/article.html?artnum=306231

RAID-5 performance of LSI SAS 2008m-8i in C240 M3?

Similar Messages

Maybe you are looking for