> > And we have no guarantie that all buffers passed to the PIO properly
> > aligned. I.e. it is not a question of activate file flag only
> >
>
> This becomes interesting - I was sure they are. I suppose that in case
> of correct alignment windows may start DMA using allocated buffer
> directly. Without correct alignment performance degradation is possible
> - OS has to copy data to/from correctly aligned buffer, and use it for
> physical IO. Taking into account, that we have never seen errors with
> bad alignment code, this is what probably happening.

Last time i was looking at it (more than year ago) i remember it in PIO_header
But now it called with properly aligned buffer (assuming MIN_PAGE_SIZE >
sector size or 1024 > 512). But this assumption can become wrong in some [near]
future ;) And i'm not sure we have not more such places in code

Regards,
Vlad

PS BTW, is somebody looked on prefetch code (ifdef'ed by SUPERSERVER_V2) ?
If yes - how good it is ? Is it make sence to enable and debug it or it is all wrong
and implementation must be another (if will be) ?