Slashdot Mirror
What Sustained Disk Transfer Rates Do You Get?
Mr. Jackson asks: "What kind of disk transfer rates (MB/s) do people get in the real world when moving around large (100s MB) files? Either every machine in our building is mis-configured, or our notions about what we were getting are way off. I've tested half a dozen machines, mostly Win2k, some Linux, by just copying a large file and timing it with a watch. 8 MB/s seems to be about average for inter-disk copies. RAID 1 (stripped) got as high as 12 MB/s after fiddling with cache settings. RAID 5 was as low as 2 MB/s. We all thought the numbers should have been around 30 MB/s."
I've benchmarked our various disk subsystems heavily.
Once you get exhaust the on-disk cache and the filesystem cache, the raw disk access speeds are visible. Here's what I've found for Seagate ATA-IV 80MB drives:
Sustained Sequential read: 40MB/sec
Sustained Sequential write: 17MB/sec
That was benchmarked on a 2Gz dual Xeon system under linux with nothing else running, and IDE tuned optimally. So, real life results are going to be worse.
It would not surprise me to see most consumer level systems with sustained speeds on a single disk under 10MB/sec. Most systems that use IDE drives don't have the DMA/ATA mode settings tuned aggressively.
Most systems with RAIDs have crappy implementations. Get a hardware RAID controller with its own processor and a large-bandwidth backend bus (ie, SCSI-160 or higher) and with lots of onboard battery-backed memory so you can safely turn on write caching.
Massive databases or file size large :
... they are the same speed.
On my fairly new Dell Latitude C800 (30G OEM IDE drive, PIII/1GHz laptop) I have seen that sequential database reads with a little data crunching runs around 16 megabytes per second.
Change that to read/write access (roughly 50/50) and it drops to 1.5MB/s read, 1.5MB/s write (total, 3MB/s).
On my desktop, two IBM 9.1G u160 SCSI drives in a RAID 0 array using a American Megatrend MegaRAID card (428) and 32M of RAM for read/write cache the sequential read access only peaks around 10MB/s, but in read/write access it is something like 3MB/s read, 3MB/s write for 6MB/s combined.
The SCSI drives were rated u160, but my card was only a 20 (68pin U/W, hell I forget what the 428 is rated for but I think 20) but even in a RAID 0 array it wasn't going to go any faster than 10MB/s peak sustained read.
If the file sizes were less than 16M, the writeback cache on the SCSI RAID array skewed the benchmarks bigtime, access times were almost as fast as ramdrive. Goes REAL FAST.
On a regular IDE drive, I would be insanely happy with anything better than 20MB/s unless you were doing some serious transaction based computing.
If you have to get a stopwatch out to decide if one is faster than the other
Glonoinha the MebiByte Slayer
http://www.seagate.com/cda/products/discsales/ente rprise/tech/0,1084,337,00.html
There is no such thing as true sustained data rate, it will always peak at the outer side of the platter. Using Hdtach 2.61 the maximum is around 65, which slowly decreases to the low 40's on the inside. My maxtor 80GB (98196H8) drive gets 30MB/sec on the outer side of the platter, I might have highballed that number on the inside it goes to about 19MB/sec.
Keep in mind that as platter density increases, and speed stays constant, transfer rate goes up. So a 5400rpm 80GB drive with 4 20GB platters will be slower than a 5400rpm drive with 1 80GB platter.
"I don't know that atheists should be considered citizens, nor should they be considered patriots." George HW Bush
/sbin/hdparm -d1 -c3 /dev/hd[abcdefgh] is generally safe for most IDE chipsets and could very easily double or triple your transfer rate.
I get about 35MB/s copying between my IDE IBM 60G drives
Are you kidding me? That's why we have ATA/133 coming out, because IDE drives are getting that fast, oh wait, that must be 133Mbits/sec (*sarcasm*) (yes people have told me this)
Try turning on DMA, you absolutely _need_ DMA turned on for modern drives, PIO Mode 4 maxes out at 16MB/sec with 100% cpu utilization, PIO Mode 5 isn't official and will most likely break your hardware. After you turn on DMA you can set your interface speed at 16/33/66/100/133MBYTES/sec.
I hate to repeat myself but here are the Specs for ST318452LW, Cheetah x15
Internal Transfer Rate (min) 548 Mbits/sec
Internal Transfer Rate (max) 706 Mbits/sec
Formatted Int Transfer Rate (min) 51.8 MBytes/sec
Formatted Int Transfer Rate (max) 68.1 MBytes/sec
External (I/O) Transfer Rate (max) 160 MBytes/sec
Avg Formatted Transfer Rate 61 MBytes/sec
"I don't know that atheists should be considered citizens, nor should they be considered patriots." George HW Bush
Most distros use very conservative settings for the IDE interfaces which will work with just about any old drives, but do not take advantage of more modern hardware. hdparm allows you to activate those advanced features.
There is a nice write-up about using hdparm here: http://www.oreillynet.com/pub/a/linux/2000/06/29/h dparm.html
Of course, all this only applies to Linux boxes.
Hey, who else could go for some flapjacks right now?
As you've found out it does matter which RAID scheme you use. RAID 0+1 will outperform RAID 5 substantially.
Think spindles. Because each disk has only one spindle, the disk head can only be over one given track at any instant. If you want the heads to nearer to your where your data is stored you want to have more heads. With RAID 1 your read or write request can be handled by more than one disk spindle. That gives you the best performance.
To get more spindles, use as many disks as practical. I've had some long conversations with my co-workers that now that disks are really cheap it doesn't matter that RAID 1 "wastes" half the disks. It does matter that disk I/O is a bottleneck and more disks will help ease that bottleneck..
References:
Ever dream you could fly? Get up from the Flight Sim. I Fly
There's 8 bits in each byte.
Topher
On RAID technologies, speaking in general terms assuming vendors do a good job of implementing it, here's a summary:
RAID 0: Pure striping, maximum performance, no redundancy. Cost is the same as concatenating disks to get the space you need.
RAID 1: Pure Mirroring, full redundancy - reads can be as fast as a stripe of the same width as the number of mirrors (2-way stripe, 2-way mirror, same read speed, etc) if they do round-robin reading. Writes happen in parallel, and can be slower unless you've got the headroom and the disk spindle is the only write bottleneck. Cost is double a simple concat or stripe.
RAID 2-4: Sometimes used for very special purposes, but generally ignored by all because one of the other raid levels does the same thing better. I've seen RAID-3 recently, there are occasionally valid uses for like 0.01% of people out there.
RAID 5: You get some data redundancy to survive a single disk failure, but you don't pay the double disk cost of full mirroring. It's an N+1 type of configuration. Speed is generally the slowest compared to everything else.
Now on top of those very basic things, there are other factors. Because RAID-5 is cheapest disk-wise, and (IMHO) because it has the highest number of the well-standardized RAID levels, RAID-5 is very popular. To make up for RAID-5's abysmal performance, people use hardware RAID-5 accelerators with cache and whatnot. The problem there is that the controller can add significant cost (in some cases enough to have paid for a full mirror in plainly controlled disks), and that the RAID controller itself can become a single point of failure.
At my office (where a lot of bad decisions get made every day and I have to eat it) they built a Veritas cluster of Sun machines around a SAN. The idea was that no node was a single point of failure because of clustering (with veritas allowing all nodes to reach the SAN storage). However, the SAN storage was a big fat RAID-5 array with redundant controllers/disks/yadda/yadda. Of course, as much as the vendor tries to bury it in the fine print, the RAID-5 hardware is a single point of failure. Sure enough, our very reputable vendor's "redundant" hardware raid-5 controller did fully fail one, knocking our data offline for hours.
For the same cost as the expensive raid-5 array and the disks in it, we could have bought two independant JBOD arrays (just a bunch of disks, no raid controller), placed them on the redundant SAN, with the redundant clustered machines doing software mirroring to the disks, and been truly free from single points of failure (assuming we do all the details right - that the mirrors are always across seperate arrays, and that the arrays are on seperate power, etc)..
I've spent a lot of time on these problems, and it is my strong belief that the optimal solution for almost all normal situations where you want high availability is to do software mirror/stripe (1+0). Be careful that there is a difference between 1+0 and 0+1 when the 0 part's stripe is more than two disks wide... Consider two JBOD arrays of 5x 36G disks each...
In 0+1, you first stripe each array into a 180G stripe, then mirror the two together. When your first disk fails, nothing so mcuh as hiccups. However, of your remaining 9 disks, if any of the 5 disks in the array opposite the one with the first disk fails, you will lose data. Thus there's a 5/9 chance that the second disk failure causes data loss.
In 1+0, you first mirror each disk from the first array with its partnet in the second array. You then take your 5 36G mirrors and stripe them together for your 180G. Again, first failure, no hiccups. If a second disk fails, in order to cause data loss it must be the partner of the first failed disk - any of the other disks can fail and you still lose nothing. So the chances of data loss on a second disk failure are now 1/9 instead of 5/9.
11*43+456^2