Looking for hdparm benchmark results from SCSI drives

Looking for hdparm benchmark results from SCSI drives

Post by David Huggi » Thu, 11 Dec 1997 04:00:00



Particularly (though not necessarily) from Symbios 53c8xx adapters on
older PCI motherboards...  As I posted earlier, my system is a bit slow
and I'm trying to pinpoint the weak link (after unsuccessfully fiddling
with every driver option imaginable)

All you have to do is run "hdparm -T -t /dev/sda" as root and e-mail me
the results... (maybe with a little bit of info on your configuration)

Or, alternately, if there is a WWW site somewhere with this sort of
thing on it and you can direct me that way (Most of them only have data
from nice new P-200s and the like!)

Thanks

Dave

 
 
 

1. invitation to a simple benchmark: hdparm results under Linux

Hello!

I'd like to ask people to send results of a simple HD benchmarks in
reply to this message or to give me a pointer to a web page where those
results are collected.  

I'd want to compare my results to those of other systems to see if mine
is any good... I'd also be interested in any other ways to improve the
performance of my HD since this seems to be the bottleneck in my system
(under VMWARE at least ;-)).

This is what I get:

----------------------------------------

/dev/hdc:
 Timing buffered disk reads:  64 MB in  3.37 seconds =18.99 MB/sec


/dev/hdc:
 Timing buffer-cache reads:   128 MB in  1.38 seconds =92.75 MB/sec


/dev/hdc:
 multcount    = 16 (on)
 I/O support  =  1
(32-bit)                                                    
using_dma    =  1 (on)
 keepsettings =  0 (off)
 nowerr       =  0 (off)
 readonly     =  0 (off)
 readahead    =  1 (on)
 geometry     = 1123/255/63, sectors = 18041184, start = 0


/dev/hdc:

 Model=QUANTUM FIREBALLP KA9.1, FwRev=A42.0400, SerialNo=369908833289
 Config={ HardSect NotMFM HdSw>15uSec Fixed DTR>10Mbs }
 RawCHS=17898/16/63, TrkSize=32256, SectSize=21298, ECCbytes=4
 BuffType=3(DualPortCache), BuffSize=371kB, MaxMultSect=16, MultSect=off
 DblWordIO=no, maxPIO=2(fast), DMA=yes, maxDMA=2(fast)
 CHS=1123/255/63 LBA Native, LBAsects=18041184
 tDMA={min:120,rec:120}, DMA modes: mword0 mword1 mword2
 IORDY=on/off, tPIO={min:120,w/IORDY:120}, PIO modes: mode3 mode4
 UDMA modes: mode0 mode1 *mode2 mode3 mode4
 Drive Supports : ATA/ATAPI-4 T13 1153D revision 15 : ATA-1 ATA-2 ATA-3
ATA-4


Linux pc77 2.2.10 #3 SMP Mon Aug 9 21:33:53 EDT 1999 i686 unknown  


 11:11am  up 51 min,  1 user,  load average: 0.12, 0.03, 0.01  
----------------------------------------

...on my Abit BP6, 2*366 (OC'ed to 450) w/128 megs of RAM. Linux distrib
is Mandrake.

Thank you,

--
Ricky Ng-Adam                                    
Montreal (Quebec), Canada              [Powered by Linux!]

2. Solaris 2.3 AnswerBook and DNS

3. Wanted: hdparm results for seagate drives

4. XF86Config and a pile of hair

5. Acard 7720UW SCSI-IDE converter (benchmark results enclosed)

6. Usefulness of MUs / cachefs patch (was: Re: Maintenance Updates for 2.5.1 x86)

7. how do you hdparm IDE drives on a RAID controler when Linux thinks its SCSI

8. Rec. P4 board for Linux?

9. hdparm says "Hmm.. suspicious results"

10. What average result for '' hdparm -t "" with ATA66 HD ??

11. Hdparm suspicious results ?!

12. Wanted: Your hdparm results

13. ASUS P4PE spurious hdparm -tT results...UPDATE