Re: postgresql-performance using sysbench

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
_______________________________________________
freebsd-performance@xxxxxxxxxxx mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-performance
To unsubscribe, send any mail to "freebsd-performance-unsubscribe@xxxxxxxxxxx"

Relevant Pages

  • Re: postgresql-performance using sysbench
    ... 4G RAM machine, the disks ... How busy were your disks in your testing? ... 15-25 MB with spikes at approx. ...
    (freebsd-performance)
  • Re: postgresql-performance using sysbench
    ... I forgot to mention in my first post that I'm using ULE. ... One thing I noticed, on a 4G RAM machine, the disks are not that busy. ...
    (freebsd-performance)
  • Re: ad10: WARNING - READ_DMA UDMA ICRC error (retrying request) LBA=11441599
    ... >>that if I send hardware I want it back when you're done, ... I have two which reliably fail if you put TWO disks on them in a gmirror ... BROKEN by FreeBSD and likely to cause people trouble - including irrevocable ... the machine as the errors cause irrevocable data corruption. ...
    (freebsd-stable)
  • Re: bizar problem with a Dell latitude D600s onboard nic
    ... besides right now wether I boot it with FreeBSD, ... >you meant that after you swapped disks, ... >I had an old Compaq 5140 machine that had no problems with ACPI under ... >certified the machine to work with anything other than Windows. ...
    (freebsd-questions)
  • Re: hardware mirrors recognized as individual disks in fbsd
    ... suddenly I have 4 disks whereas in windows I had two. ... ASUS P5DR1-VM motherboard with a ULI raid chipset onboard. ... You can't write NTFS in FreeBSD anyway - or couldn't the last I knew. ... when they think they should be on slice 1 ...
    (freebsd-questions)