Re: [PATCH] Coverity issue 740457

> * the string created by tempnam() apparently needs to be xfree()'d when
> done.

doh! Ok.

> * please add a comment in the #else condition noting the tempnam() is
> officially obsolete from POSIX-2008.1.
> (in a few more years we should drop the #else code entirely.)

Done.
we may want to shuffle this to compat/ somewhere.

> * please also add a note that tmpfile() is not an option since we desire the
> /tmp file to stick around after process exit for administrators use.

Do we? There's an unlink(filename) call at the end of that function

> As a followup change we need to consider that this whole process leaves a
> /tmp file sitting around from every crash, which could over time build up.
> I'm in two minds about how desirable this behaviour is.

Generally /tmp is either a ramdisk or there are system tools to clean
accumulated cruft up. I wouldn't worry about this.

> + we could check for the files on startup and do something when Squid is
> re-started after a crash.
> + administrator can manually find the file even if the mail attempt failed
> (known to happen).
>
> - the files build up over time and could be a big waste of disk space.

See above.

-- 
    /kinkie