Re: Re[2]: Postgres is too slow?

> I was curious about this result. So I tested on my test PC and got 4.3 to 14
> times  faster results than Mamin's results.
>
 *SNIP*

I forgot to mention my test system

PC: Intel Celeron 466Mhz, 192MB RAM, UDMA33 HDD
RedHat Linux 7.0.1/J (Kernel-2.2.19, glibc-2.2)
PostgreSQL 7.1.2 (built from src. Multi-byte/locale support enabled)

postmaster options are
 -i -N 1024 -B 6000

[yohgaki@localhost test]$ ipcs -l -m

------ Shared Memory Limits --------
max number of segments = 1024
max seg size (kbytes) = 65536
max total shared memory (kbytes) = 134217728
min seg size (bytes) = 1

[yohgaki@localhost test]$ ipcs -l -s

------ Semaphore Limits --------
max number of arrays = 512
max semaphores per array = 250
max semaphores system wide = 128000
max ops per semop call = 32
semaphore max value = 32767

[yohgaki@localhost test]$ cat /proc/sys/fs/file-max
32767

[root@localhost /root]#  hdparm /dev/hda

/dev/hda:
 multcount    =  0 (off)
 I/O support  =  1 (32-bit)
 unmaskirq    =  0 (off)
 using_dma    =  1 (on)
 keepsettings =  0 (off)
 nowerr       =  0 (off)
 readonly     =  0 (off)
 readahead    =  8 (on)
 geometry     = 826/255/63, sectors = 13281408, start = 0

<Test OS uses only /dev/hdd, /dev/hda has other Linux OS>
[root@localhost /root]#  hdparm /dev/hdd

/dev/hdd:
 multcount    =  0 (off)
 I/O support  =  1 (32-bit)
 unmaskirq    =  0 (off)
 using_dma    =  1 (on)
 keepsettings =  0 (off)
 nowerr       =  0 (off)
 readonly     =  0 (off)
 readahead    =  8 (on)
 geometry     = 1650/255/63, sectors = 26520480, start = 0


Yasuo Ohgaki