On Thu, Dec 11, 2008 at 10:40:41PM +0200, Raz wrote: > > ________________________________ > > From: Matthew Wilcox [mailto:matthew@xxxxxx] > > Sent: Thu 12/11/2008 5:44 AM > > To: Raz Ben-Yehuda > > Cc: linux-ide@xxxxxxxxxxxxxxx; linux-scsi@xxxxxxxxxxxxxxx > > 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." -- To unsubscribe from this list: send the line "unsubscribe linux-scsi" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
