postgresql-performance using sysbench

[Mark Kirkwood]

Mike Tancsa wrote:
> At 03:46 PM 1/28/2008, Claus Guttesen wrote:
>
>> I had (allready) saved the thread in my mail-account so I could look
>> it up before I started testing. :-) So I compiled postgresql with the
>> option WITH_THREADSAFE=true and used sysbench with --pgsql-host="" .
>> As pointed out by Ivan my test also involved r/w whereas the thread
>> you (probably) mention at
>> http://groups.google.com/group/mailing.freebsd.stable/browse_thread/thread/e224cd4f76e9ec2d 
>>
>> is a read-only test.
>>
>> I forgot to mention in my first post that I'm using ULE. The p800
>> controller has a (factory set) 25/75 read/write cache ratio.
>
>
> I am still going through my own testing.  One thing I noticed, on a 4G 
> RAM machine (still waiting for the RAM to test with 8G), the disks are 
> not that busy.  It seems to be the CPU that is the bottleneck on 
> FreeBSD.  I tried the test with 900,000 rows instead.
>
>  procs      memory      page                    disks     faults      cpu
>  r b w     avm    fre   flt  re  pi  po    fr  sr ad5 da0   in   sy   
> cs us sy id
> 38 1 0  271024 3439656  6329   0   0   0     4   0   0 1703 1709 
> 120725 41505 44 18 37
>  0 38 0  271024 3438860  9590   0   0   0     8   0   0 1932 1938 
> 183844 47958 70 28  3
>  6 33 0  271024 3438120  7814   0   0   0     0   0   0 1823 1827 
> 169969 44914 62 25 13
> 39 0 0  271024 3437960  1530   0   0   0     0   0   0 994  998 36521 
> 14927 13  8 79
> 38 1 0  271024 3437244  7374   0   0   0     0   0   0 2724 2731 
> 173493 51821 71 20  9
>  0 39 0  271024 3436620  4773   0   0   0     8   0   0 2727 2734 
> 125699 39962 47 20 33
> 37 1 0  271024 3435836  6884   0   0   0     8   0   0 2796 2804 
> 177453 58430 70 26  4
>
> I am also using ULE, pgsql with WITH_THREADSAFE=true and not using TCP 
> to connect.  How busy were your disks in your testing ?

Something else it may be worth noting - currently Linux 2.6 kernels are 
measurably faster at reading cached file pages compared to Freebsd (6 or 
7) - by a factor of about 1.5 to 2 times (see thread titled "cached file 
read performance"), and in this sort of oltp benchmark, you may be 
running into this effect frequently enough to be impacting your results.

regards

Mark