Mail Archives: cygwin/2013/02/27/12:20:50
Greetings, Adam Dinwoodie!
>> I was need to pipe some bytes through application and watch it's reaction.
>> But with /dev/urandom the stream speed is only about 40Mb/sec. Using
>> /dev/zero, however, makes it 3 orders of magnitude faster (~35Gb/s), but for
>> technical reasons, using monotonous sequence is highly undesirable. Is there
>> any more performant source of non-monotonous byte sequences available to
>> Cygwin? I would be pretty happy even with sequential bytes, I think. Only two
>> reservations are good performance (something around 100 Mb/sec or more would
>> suffice) and a degree of randomness.
> You want a source of data that's non-monotonous but faster than /dev/urandom.
> I don't see how this is a Cygwin issue at all, and thus I don't think it
> belongs on this list.
I'm not very familiar with this kind of things in general, and as I'm writing
scripts for Cygwin right now, I though there may be some Cygwin specifics in
place.
> Nonetheless, I suspect the easiest solution is to write a short C program to
> produce your output, along the lines of (untested):
> #include <stdio.h>
> int main () {
> unsigned char c;
> for (c = 0;; c++)
> putchar(c);
> }
6Mb/sec, but thanks for a try.
> Alternatively, pre-cache some output and use that:
> head --bytes=1G >/var/cache/randomdata
> ./myapp <(while :;do cat /var/cache/randomdata; done)
Seems, like that would be the most reasonable way of doing things.
And since this is, apparently, not specific to Cygwin, I consider the question
answered.
--
WBR,
Andrey Repin (anrdaemon AT freemail DOT ru) 27.02.2013, <20:42>
Sorry for my terrible english...
--
Problem reports: http://cygwin.com/problems.html
FAQ: http://cygwin.com/faq/
Documentation: http://cygwin.com/docs.html
Unsubscribe info: http://cygwin.com/ml/#unsubscribe-simple
- Raw text -