This is the mail archive of the cygwin mailing list for the Cygwin project.

Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

Re: select() too slow

On Wed, Mar 15, 2006 at 07:07:05PM +0000, Pedro Inacio wrote:
>On 2006/03/14, at 22:43, Christopher Faylor wrote:
>>On Tue, Mar 14, 2006 at 09:42:25PM +0000, Pedro Inacio wrote:
>>I don't have any 100MB files sitting around but when I tried this on a
>>14MB file, I find that cygwin is about 2X slower, not an order of
>>magnitude slower.  Taking away the pipe and using regular file  
>>makes things a little faster on cygwin.
>>So, I can't explain why you are seeing such extreme slowdowns.  I am
>>using the equivalent of a snapshot in my tests, however.  Maybe that's
>>the difference.
>I have created a 14MB file and the results were:
>On Linux: 4 seconds On Cygwin: 44 Seconds
>The test were made on 3 different platforms, and the results the same.
>Cygwin is not just 2X slower but 11X slower, each is too much.

>Another thing, what have the pipe and the file redirection to do with
>the results?  That command is given always on a Unix box which is the
>client of the echo_server.  Is just the echo_server that runs on Cygwin
>or Linux.  ;)

Ah.  When you said "run it and do the same", I thought you were saying
to run the the client/server on Cygwin, as you did with linux, not to
run the client on linux and the server on Cygwin.  I do see a slowdown
when running the client on linux however, since it's the same select()
connected to the same IP address, running the same way, it's hard to see 
how select() would be implicated.  That seems to point to winsock, if


Unsubscribe info:
Problem reports:

Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]