[uClinux-dev] Most stable 2.4.x kernel for ARM

Andrei Martynov andrei.martynov at web.de
Tue Feb 24 04:10:17 EST 2009


Thursday, February 19, 2009, 8:57:46 PM, Jamie Lokier wrote:

> 2.4.37 is a bit better because it has some USB storage bug fixes and
> things like that.

I've just found an old thread about different memory allocator
behavior in 2.4.17 and 2.4.24 that results in memory fragmentation
during system boot. How is it in 2.4.37?

Mail list archives are not available at the moment so I had to attach
the original mail.

-- 
Best regards,
 Andrei                            mailto:andrei.martynov at web.de

================================================================================
From davidm at snapgear.com  Thu Oct 21 20:08:10 2004
From: davidm at snapgear.com (David McCullough)
Date: Thu Oct 21 20:08:16 2004
Subject: [uClinux-dev] Insmod memory issue
In-Reply-To: <9F77D654ED40B74CA79E5A60B97A087B023705D2 at sd-exchange.sdesigns.com>
References: <9F77D654ED40B74CA79E5A60B97A087B023705D2 at sd-exchange.sdesigns.com>
Message-ID: <20041022000810.GB6118 at beast>


Jivin Fabrice Gautier lays it down ...
> Precisions:
> 
> Is was using uClinux-2.4.24-uc0 and busybox 1.0-rc2.
> 
> I noted that if I used uClinux-2.4.17-uc0, I dont get the same issue.
> 
> With 2.4.17 after insmod I only see one big chunk of the size of
> text+data+bss.
> 
> I also noticed that 2.4.17 non power of 2 allocator, allocate the small
> stuff at the end of the memory and the big chunks at the beggining. 2.4.24
> seems to be doing the other way around.

Yes,  this was changed to try and address some of the speed issues with
the non-power of 2 allocator.  The search for blocks at the beginning is
faster,  and you normally need to find single pages (for IO) faster than
larger blocks (for apps).

> Is there anything that changed between 2.4.17 and 2.4.24 that could sched
> some light on this ?

Only the above change above that I know of,

Cheers,
Davidm





More information about the uClinux-dev mailing list