process shared robust mutexes for tdb

[Ira Cooper]

Code review comments:

open.c:tdb_close: You did a great job insulating the rest of the code from
the locks implementation, except here.  Can you tuck it away in mutex.c
also?

Are we still upkeeping the configure build?  If so what support is needed
for configure here.

-----
Concerns: On Solaris, the locking reliable mutex locking primatives speed
scales according to the number of reliable mutexes (More strictly I believe
the number of process shared mutexes, if I remember right.  But I'd need to
go re-read that code.)  Being able to enable/disable this on a database by
database basis will be needed for Solaris, or we could actually degrade
overall performance.  (Depending on the number of hash buckets... etc.)

Thanks,

-Ira


On Sat, Jan 12, 2013 at 4:45 AM, Volker Lendecke
<Volker.Lendecke at sernet.de>wrote:

> Hi!
>
> On Sun, Jan 06, 2013 at 07:18:00PM -0500, Ira Cooper wrote:
> > Can you run the same test with 1 bucket?  Not that we'd actually want to
> > deploy that way, but, the performance of fcntl TDB shouldn't drop that
> > much... and it'd give us an estimate of how much we need the 2048 locks
> vs.
> > just using 1.
>
> Under the usual branch
>
> https://git.samba.org/?p=vl/samba.git/.git;a=shortlog;h=refs/heads/tdb
>
> Now find a patchset that survived autobuild for me. It
> contains some additional stuff, like a tdb feature flags
> field. This could for example take a flag for a dual-linked
> freelist and other future improvements.
>
> This is something that I would like to see broader testing
> and review of. Getting rid of the fcntl locks in tdb was
> something I have wanted to do for a very long time, and
> while this is not complete it is a start in that direction.
>
> With best regards,
>
> Volker Lendecke
>
> --
> SerNet GmbH, Bahnhofsallee 1b, 37081 Göttingen
> phone: +49-551-370000-0, fax: +49-551-370000-9
> AG Göttingen, HRB 2816, GF: Dr. Johannes Loxen
> http://www.sernet.de, mailto:kontakt at sernet.de
>