Re: os io unit , db block size relation

FM <fabrizio.magni_at_mycontinent.com> wrote in message news:<414B39D4.6080806_at_mycontinent.com>...
> >
> > A slightly off-topic question. What if the filesystem block size is
> > not 4k while PAGE_SIZE is 4096? (I had this question before for
> > Solaris http://groups.google.com/groups?selm=b3cb12d6.0203181445.f3d2b36%40posting.google.com)
> >
>
> Not so "off-topic".
> The file system block size is normally limited by "page size". So you
> cannot have bigger blocks than your system pagesize but you can have
> them smaller.
> It will risult in better space allocation but worst performance due to
> the overhead for the increasing i/o calls.

Quite reasonable. Now the question is, if the filesystem was created with a block size different than memory page size (let's not talk about why), iostat wsec/s divided by wrqm/s should be roughly equal to page size or filesystem block size?  

> I'm not sure but if my mind is not falling apart solaris and hp-ux
> should have a default of 8k. Aix and linux 4k.

8k is default for Solaris UFS (actually the only choice for sun4u, but default for sun4m and sun4d). I don't remember HPUX. AIX is 4k. But on Redhat Linux, mkfs.ext2 and mkfs.ext3 man pages for -b option don't seem to say 4k *is* the default. I don't recall seeing a Linux ext2 filesystem created with block size other than 4k, though.

Yong Huang Received on Sat Sep 18 2004 - 22:38:56 CDT