Re: another pre-release ?

Are we still using O_NDELAY?

I have a memory of fixing this ages ago. O_NDELAY is not standardized,
and behaves sligthly differently on different OS:es, where quite many
return 0 in various non-EOF conditions..

Ah.. SunOS & Solaris is excluded from the use of O_NONBLOCK. Do you
remember why (this is inherited all the way from Harvest cached.. see
comm.c revision 1.1, way before my time)

/Henrik

Duane Wessels wrote:
>
> On Wed, 24 Jan 2001, Adrian Chadd wrote:
>
> >
> > Hi,
> >
> > Should we roll another pre-stable release for 2.4 ?
> > Are there still any outstanding issues with the
> > 2.4 code?
>
> I found two problems recently.
>
> 1) Solaris-8 (at least) needs to use O_NONBLOCK instead of
> O_NDELAY. kernel pipes that use O_NDELAY return 0 instead
> of -1 when the read would block.
>
> 2) a large, bogus Age: value causes an assertion in refresh.c
Received on Fri Feb 09 2001 - 13:11:35 MST