Re: Intel X25-M MLC SSD benchmarks - How can I be sure i am erased block aligned ?

Re: Intel X25-M MLC SSD benchmarks - How can I be sure i am erased block aligned ?

[Raz]

> ________________________________
> From: Matthew Wilcox [mailto:matthew@wil.cx]
> Sent: Thu 12/11/2008 5:44 AM
> To: Raz Ben-Yehuda
> Cc: linux-ide@vger.kernel.org; linux-scsi@vger.kernel.org
> Subject: Re: Intel X25-M MLC SSD benchmarks
>
> On Thu, Dec 11, 2008 at 12:12:37AM +0200, Raz Ben-Yehuda wrote:
>> I did not want to dive into details because it does not matter. Whether
>> noop,deadline, deadline parameters...
>> As for the controller I used 4 different controllers. Adaptec,AHCI and
>> Intel as Integrated chips on the 1025W-UR supermicro motherboard, and a
>> 4-th controller SuperMicro UIO Adaptec aac card.
>> All gave same results for most dd writes commands.
>> dd if=/dev/zero of=/dev/sda bs=1M count=1000 oflag=direct , and many
>> other variants such erase block size ( 128K ) , several erase block size
>> and so on. Kernel is 2.6.18-8.el5.
>
>>>OK, I suspect you aren't giving the drive enough work to do for it to
>>>perform at its best.  Try doing something like this:
>
>>>for i in $(seq 0 9); do \
>  >>     dd if=/dev/zero of=/dev/sda bs=1M count=1000 oflag=direct \
>  >>               seek=$(($i * 1000)) & \
>>>done
>
did that. nothing. also, I would like to note that IO flow is quite
weird.iostats reports 70GB/s in the first few seconds, and then it
degrades to 20
 MB/s and less. could it be that I am not erase-block aligment ?
how does SSD aligments interacts with a controller ?
 iostats looks like that:Device: tps Blk_read/s Blk_wrtn/s Blk_read Blk_wrt
 sda 746.46 0.00 191143.43 0 189232
 sda 546.53 0.00 139912.87 0 141312
 sda 480.00 0.00 122880.00 0 122880
 sda 469.00 0.00 120016.00 0 120016
 sda 347.00 0.00 88880.00 0 88880
 sda 403.96 0.00 103413.86 0 104448
 sda 349.00 0.00 89296.00 0 89296
 sda 424.00 0.00 108544.00 0 108544
 sda 480.00 0.00 122880.00 0 122880
 sda 184.00 0.00 47104.00 0 47104
 sda 467.00 0.00 119600.00 0 119600
 sda 408.00 0.00 104448.00 0 104448
 sda 320.00 0.00 81920.00 0 81920
 sda 357.00 0.00 91344.00 0 91344
 sda 195.00 0.00 49968.00 0 49968
 sda 280.00 0.00 71680.00 0 71680
 sda 475.25 0.00 121663.37 0 122880
 sda 85.00 0.00 21712.00 0 21712
 sda 235.00 0.00 60208.00 0 60208
 sda 216.00 0.00 55296.00 0 55296
 sda 112.00 0.00 28672.00 0 28672
 sda 245.00 0.00 62672.00 0 62672
 sda 72.00 0.00 18432.00 0 18432
 sda 75.00 0.00 19248.00 0 19248
 sda 141.00 0.00 36048.00 0 36048
 sda 11.00 0.00 2864.00 0 2864
 sda 200.00 0.00 51200.00 0 51200
 sda 88.00 0.00 22528.00 0 22528
 sda 160.00 0.00 40960.00 0 40960
 sda 118.81 0.00 30415.84 0 30720
 sda 32.00 0.00 8192.00 0 8192
 sda 128.00 0.00 32768.00 0 32768
 sda 77.00 0.00 19664.00 0 19664
 any idea ?

>> I used all on a supermicro 1025W-UR. Disks have a SAS interface, 80GB.
>> Also, I would like to note, I have 8 disks in array, while each one
>> perform READS 250 MB/s, together I degrade to 200 MB/s each. As for
>
>>>That doesn't surprise me; you're probably hitting a limitation either of
>>>the array or the cable itself.  A SAS cable can run up to 6Gbps, which
>>>will be around 600MB/s.  So three drives should be able to saturate your
>>>SAS cable.  If you're using an x4 link, that goes up to 2400MB/s which
>>>should be ample for 8 drives ... maybe you're using a 3Gbps cable which
>>>would limit each drive to 150MB/s.
I am not surprised as well. SSD is quite new for these controller. I
am using SAS cable(blue one), and no cx4 can connect to io card
controller.
anyway, I have contact supermicro for that, I want to bypass the back
panel, just to be sure.


> --
> Matthew Wilcox                          Intel Open Source Technology Centre
> "Bill, look, we understand that you're interested in selling us this
> operating system, but compare it to ours.  We can't possibly take such
> a retrograde step."
>

Re: Intel X25-M MLC SSD benchmarks - How can I be sure i am erased block aligned ?

[Matthew Wilcox]

On Thu, Dec 11, 2008 at 10:40:41PM +0200, Raz wrote:
> > ________________________________
> > From: Matthew Wilcox [mailto:matthew@wil.cx]
> > Sent: Thu 12/11/2008 5:44 AM
> > To: Raz Ben-Yehuda
> > Cc: linux-ide@vger.kernel.org; linux-scsi@vger.kernel.org
> > Subject: Re: Intel X25-M MLC SSD benchmarks
> >
> > On Thu, Dec 11, 2008 at 12:12:37AM +0200, Raz Ben-Yehuda wrote:
> >> I did not want to dive into details because it does not matter. Whether
> >> noop,deadline, deadline parameters...
> >> As for the controller I used 4 different controllers. Adaptec,AHCI and
> >> Intel as Integrated chips on the 1025W-UR supermicro motherboard, and a
> >> 4-th controller SuperMicro UIO Adaptec aac card.
> >> All gave same results for most dd writes commands.
> >> dd if=/dev/zero of=/dev/sda bs=1M count=1000 oflag=direct , and many
> >> other variants such erase block size ( 128K ) , several erase block size
> >> and so on. Kernel is 2.6.18-8.el5.
> >
> >>>OK, I suspect you aren't giving the drive enough work to do for it to
> >>>perform at its best.  Try doing something like this:
> >
> >>>for i in $(seq 0 9); do \
> >  >>     dd if=/dev/zero of=/dev/sda bs=1M count=1000 oflag=direct \
> >  >>               seek=$(($i * 1000)) & \
> >>>done
> >
> did that. nothing. also, I would like to note that IO flow is quite
> weird.iostats reports 70GB/s in the first few seconds, and then it
> degrades to 20
>  MB/s and less. could it be that I am not erase-block aligment ?

That doesn't sound likely to me.  Erase block size isn't a huge issue
with these drives.  I've been trying to replicate your problem, but I'm
not having any luck; unfortunately I only have access to an X25-E drive
(not an X25-M) and I'm seeing 175-185MB/s when it's attached to an AHCI
controller, just with a single dd (I haven't even played with the
elevator).  I'm trying to get hold of an X25-M drive, but I don't know
when I'll receive one.

> how does SSD aligments interacts with a controller ?

Controllers can generally send down large enough IOs that it isn't a
problem.  And the Intel SSDs are smart enough that you shouldn't have to
align to erase block boundaries to make them go fast.

-- 
Matthew Wilcox				Intel Open Source Technology Centre
"Bill, look, we understand that you're interested in selling us this
operating system, but compare it to ours.  We can't possibly take such
a retrograde step."

Re: Intel X25-M MLC SSD benchmarks - How can I be sure i am erased block aligned ?

[Raz]

http://www.tomshardware.com/reviews/Intel-x25-m-SSD,2012-8.html
they say that write IO fluctuates.



On 12/12/08, Matthew Wilcox <matthew@wil.cx> wrote:
> On Thu, Dec 11, 2008 at 10:40:41PM +0200, Raz wrote:
>  > > ________________________________
>  > > From: Matthew Wilcox [mailto:matthew@wil.cx]
>  > > Sent: Thu 12/11/2008 5:44 AM
>  > > To: Raz Ben-Yehuda
>  > > Cc: linux-ide@vger.kernel.org; linux-scsi@vger.kernel.org
>  > > Subject: Re: Intel X25-M MLC SSD benchmarks
>  > >
>  > > On Thu, Dec 11, 2008 at 12:12:37AM +0200, Raz Ben-Yehuda wrote:
>  > >> I did not want to dive into details because it does not matter. Whether
>  > >> noop,deadline, deadline parameters...
>  > >> As for the controller I used 4 different controllers. Adaptec,AHCI and
>  > >> Intel as Integrated chips on the 1025W-UR supermicro motherboard, and a
>  > >> 4-th controller SuperMicro UIO Adaptec aac card.
>  > >> All gave same results for most dd writes commands.
>  > >> dd if=/dev/zero of=/dev/sda bs=1M count=1000 oflag=direct , and many
>  > >> other variants such erase block size ( 128K ) , several erase block size
>  > >> and so on. Kernel is 2.6.18-8.el5.
>  > >
>  > >>>OK, I suspect you aren't giving the drive enough work to do for it to
>  > >>>perform at its best.  Try doing something like this:
>  > >
>  > >>>for i in $(seq 0 9); do \
>  > >  >>     dd if=/dev/zero of=/dev/sda bs=1M count=1000 oflag=direct \
>  > >  >>               seek=$(($i * 1000)) & \
>  > >>>done
>  > >
>  > did that. nothing. also, I would like to note that IO flow is quite
>  > weird.iostats reports 70GB/s in the first few seconds, and then it
>  > degrades to 20
>  >  MB/s and less. could it be that I am not erase-block aligment ?
>
>
> That doesn't sound likely to me.  Erase block size isn't a huge issue
>  with these drives.  I've been trying to replicate your problem, but I'm
>  not having any luck; unfortunately I only have access to an X25-E drive
>  (not an X25-M) and I'm seeing 175-185MB/s when it's attached to an AHCI
>  controller, just with a single dd (I haven't even played with the
>  elevator).  I'm trying to get hold of an X25-M drive, but I don't know
>  when I'll receive one.
>
>
>  > how does SSD aligments interacts with a controller ?
>
>
> Controllers can generally send down large enough IOs that it isn't a
>  problem.  And the Intel SSDs are smart enough that you shouldn't have to
>  align to erase block boundaries to make them go fast.
>
>
>  --
>
> Matthew Wilcox                          Intel Open Source Technology Centre
>  "Bill, look, we understand that you're interested in selling us this
>  operating system, but compare it to ours.  We can't possibly take such
>  a retrograde step."
>