mmap vs. read/write performance/overhead revisited

[Wolfgang Draxinger]

Hi!

So how is it _today_ with the current 4.x kernels when it comes to mmap 
vs read(2)/write(2)?

Either it's my Google-foo lacking or the most recent comment on the 
topic really dates back 15 years, but this is the only substancial 
background information relevant for Linux I did find:

http://marc.info/?l=linux-kernel&m=95496636207616&w=2

... that was 15 years ago, the beaver was not even conceived, not to 
speak going into detox, or even its predecessor. So I'm wondering, how 
relevant are the deliberations of back then today?

I've got a very practical application for which this deliberation is 
relevant, but I don't want to spam the list with a technical lecture on 
ultra high speed OCT imaging.


Cheers,

Wolfgang
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/