Re: [PATCH] kallsyms data size reduction / lookup speedup

[Paulo Marques <pmarques@grupopie.com>]

viro@parcelfarce.linux.theplanet.co.uk wrote:
> On Wed, Aug 25, 2004 at 08:09:33PM +0100, Paulo Marques wrote:
> 
>>Matt Mackall wrote:
>>
>>>...
>>>
>>>FYI, killing the seq_file stuff will likely prove unpopular. So you'll
>>>want to do that in a separate patch. If it doesn't affect the way
>>>you're handling compression, please repost your compression patch. I
>>>have a few comments, but otherwise I think we should move forward with it.
>>
>>I'm still not sure that the seq_file is the culprit, but doing
>>a 10000 symbol decompression in a user space application takes
>>about 340us, whereas doing a "time cat /proc/kallsyms > /dev/null"
>>gives approx. 0.2s! (this is all on a Pentium4 2.8GHz)
>>
>>*If* the seq_file is the culprit, then I don't think removing
>>it (or improving it) will be unpopular.
> 
> 
> If it really spends that much in seq_file, I bet anything that it got
> *very* dumb iterator.  Which should be fixable...

That is why I kept a big *If* in that sentence. I'm quite new to all
this, and I'm still reading a lot of source code.

If the culprit is in fact seq_file, and seq_file can be improved in a
way that works for everyone (not only kallsyms), then I also agree
that is is the way to go. But hunting this down might prove that the
problem is somewhere else. It is just too soon to draw conclusions.

-- 
Paulo Marques - www.grupopie.com