aic7xxx / AHA2940 worries... anyone?

[Edward Welbon]

On Mon, 11 Aug 1997, Doug Ledford wrote:

One thing I did not make clear was that the crashes occur more frequently
when the file sizes are larger and also occur more frequently when the CPU
speed increases.  At a 2GB file size, a single pass of Bonnie often wont
complete.  This evening I have been running Bonnie in the background on
2GB files with Symbios 875 based controllers so I don't think it is my
drives excepting that the 875 will not queue deeper than 12 commands.. 
 
> driver firmware, it may just be that under the kind of load 9 drives can 
> create on a controller, we are losing commands and getting hosed.

I have three controllers with three drives per controller.  The mdadd is
set up such that in sequential accesses the each next card is accessed.  I
did this thining that it would distribute the load accross the controllers
a little better.  There are cases were it is faster.  The mdadd is: 

/sbin/mdadd /dev/md0 /dev/sdb2 /dev/sde2 /dev/sdh2 \
                     /dev/sdc2 /dev/sdf2 /dev/sdi2 \
                     /dev/sdd2 /dev/sdg2 /dev/sdj2
/sbin/mdrun -p0 -c64k /dev/md0

disks sdb, sdc and sdd are on scsi2. 
disks sde, sdf and sdg are on scsi3.
disks sdh, sdi and sdj are on scsi4.

So in a sequential access the code hops from controller to controller.  It
makes a measureable difference when I read from cylinders near the outer
edge.  I don't have a direct comparison to a case with the interleaving at
my fingertips, but check out the block read and block write rates in the
attachment.  Not too shabby IMHO. 

Ed Welbon; welbon at bga.com;


-------------- next part --------------
THe order of the columns matches those of Bonnie.  May 8 driver, 2.1.42
kernel, 16 command queueing, SCB enabled, 248 clock PCI latency time.
Cylinders at the outer edge.  System memory was 32MB (the size of
the test file is significantly larger than the amount of ram buffer).
This is a somewhat pathological, special case measurement.  However, those
outermost cylinders make dandy page spaces.  I have not tried this test
with any other than the 2940UW adapters.  The maximums and minimums are
striken from the averages.  There were 32 passes total.

AVERAGE      30.0    192.0 10934.0    97.7 42669.9    75.7 13148.7    54.6 13185.3    96.7 38327.9    84.5   200.5     3.2
MAXIMUMS     30.0    192.0 10958.0    98.3 46258.0    84.9 13377.0    57.5 13443.0    99.3 39033.0    88.6   208.8     3.8
MINIMUMS     30.0    192.0 10897.0    97.4 39819.0    69.2 12526.0    42.7 12927.0    81.8 36530.0    40.7   190.0     2.5
SIGMA        30.0      0.0    18.3     0.2  1322.4     3.4   154.5     2.9    46.9     5.3   390.0     2.4     5.0     0.3
SPREADS      30.0      0.0     3.3     5.2     4.9     4.6     5.5     5.0    11.0     3.3     6.4    20.3     3.7     4.8
COV          30.0     0.0%    0.2%    0.2%    3.1%    4.5%    1.2%    5.4%    0.4%    5.4%    1.0%    2.8%    2.5%    8.5%