memory fragmentation issues in 1.2?

Paul T pault12345 at yahoo.com
Thu Dec 7 17:00:57 UTC 2006


So now I somehow defend non-portable software? 
Oh, the twisted paths of the internet mailing lists.

All I'm saying is that the only defence for slabs in
memcached that I see on the internet is a hypotetical
'empirical' email that is couple years old and is
describing effect that could be caused by
misconfigured swappiness parameter.

Slabs come with a price - they make valgdrind useless,
they were causing wasting up to 50% of RAM (dunno if
Facebook  fixed that, I suppose they did, but there
was no benchmark to see how much RAM is still getting
wasted in those 'regions') ... and it turns out that
memory is still leaking ...

Once upon a time instead of arguing for years about
(many) moments like slabs I just bit the bullet and
rewrote the whole thing without the slabs, without
timers, without proprietory semi-binary protocol,
without fancy (but logically questionable) 'automata'
protocol implementation, without 'custom hash' e t.c.
e t.c. 

Not only I did that, but I also opened the source of
that rewrite.

I think what I did is open source. 

And I (still) don't see why would univca be less
portable than memcached. 

Univca is *more* portable already - univca is using
HTTP for a protocol hence it works with all the tools
out there, that support HTTP protocol - memcached is
using proprietory protocol that suffers from
big/little endian problems.

I am out of this thread now, because arguing about
abstract hypotetical or political issues surrouding
memcahed - without a line of source code - is out of
my interest, I would rather be coding. 

Not that I think that arguing about abstract,
hypotetical or political issues is bad - it is just I
personally have no time for it.

Have fun.

Rgds.Paul.

--- Rev Lebaredian <iflassman at gmail.com> wrote:

> On 12/7/06, Paul T <pault12345 at yahoo.com> wrote:
> >
> >
> >
> > > Can you say this with certainty for all
> > > implementations of malloc out there?
> >
> > Nope. I can not.
> >
> > That is what open source is for. To test the stuff
> on
> > different hardware / software combinations, openly
> > share the observations e t.c. That is what open
> source
> > used to be when I was young ;-) When there was no
> > money in it, you know ;-)
> >
> > Rgds.Paul.
> 
> 
> 
> That's interesting.  I was under the impression that
> open source was always
> about freedom to do with the software as you please.
>  Different people have
> different needs and uses for open source projects. 
> It's perfectly
> reasonable and desirable to try to implement one's
> software project for that
> matter to minimize variance in critical behavior
> across multiple platforms.
> Not doing this limits the portability of an open
> source software project, in
> turn makes it far less useful.
> 
> Rev
> 


__________________________________________________
Do You Yahoo!?
Tired of spam?  Yahoo! Mail has the best spam protection around 
http://mail.yahoo.com 


More information about the memcached mailing list