Message-ID: <3A316668.FA09B6CB@computer.org>
Date: Fri, 08 Dec 2000 22:53:28 +0000
From: Garry Smith
Message-ID: <005401c061a8$a6d12be0$070210ac@horsell.ibgames.com>
From: "Alan Lenton"
I am about to start doing some performance testing on a software project that I am involved with. I would like to use my version of SuSE Linux 7.0 Professional as one of the test platforms.
How can I get Linux to provide microsecond granularity when I make calls to the system clock? In otherwords, I need a microsecond clock on Linux to get accurate performance measurements of my software?
I have seen some information about this subject on the Net, but it seems to be focused on earlier versions of the Linux kernel.
On my machine, unama -a returns : Linux eclipse 2.2.16 #1 Wed Aug 2 20:22:26 GMT 2000 i686 unknown This is a uniprocessor machine, Intel Pentium III 450
Could you explain what I must do (and how) to achieve this functionality? Or does SuSE 7.0 already support the microsecond clock as standard?
Many thanks in advance for your kind help
regards Garry
-- To unsubscribe send e-mail to suse-linux-e-unsubscribe@suse.com For additional commands send e-mail to suse-linux-e-help@suse.com Also check the FAQ at http://www.suse.com/support/faq
From: Jesse Marlin
Hi all,
I am about to start doing some performance testing on a software project that I am involved with. I would like to use my version of SuSE Linux 7.0 Professional as one of the test platforms.
How can I get Linux to provide microsecond granularity when I make calls to the system clock? In otherwords, I need a microsecond clock on Linux to get accurate performance measurements of my software?
You can use select, like so: struct timeval tv; tv.tv_sec = 0; tv.tv_usec = 1000; /* Sleep for a while */ select (0, NULL, NULL, NULL, &tv); <p> >
I have seen some information about this subject on the Net, but it seems to be focused on earlier versions of the Linux kernel.
On my machine, unama -a returns : Linux eclipse 2.2.16 #1 Wed Aug 2 20:22:26 GMT 2000 i686 unknown This is a uniprocessor machine, Intel Pentium III 450
Could you explain what I must do (and how) to achieve this functionality? Or does SuSE 7.0 already support the microsecond clock as standard?
Many thanks in advance for your kind help
regards Garry
-- To unsubscribe send e-mail to suse-linux-e-unsubscribe@suse.com For additional commands send e-mail to suse-linux-e-help@suse.com Also check the FAQ at http://www.suse.com/support/faq
Hi all,
I am about to start doing some performance testing on a software
Message-ID: <003701c0641f$6642ee00$070210ac@horsell.ibgames.com>
From: "Alan Lenton"
that I am involved with. I would like to use my version of SuSE Linux 7.0 Professional as one of the test platforms.
How can I get Linux to provide microsecond granularity when I make calls to the system clock? In otherwords, I need a microsecond clock on Linux to get accurate performance measurements of my software?
You can use select, like so:
struct timeval tv;
tv.tv_sec = 0; tv.tv_usec = 1000;
/* Sleep for a while */ select (0, NULL, NULL, NULL, &tv);
------ snip -----
From: Jesse Marlin
I think you will find that select() uses the interval timer, so therefore select() will be subject to the same granularity problems (10ms minimum time) as I mentioned in my earlier posting.
Yes, I think you are right.
Alan Lenton
----- Original Message ----- From: "Jesse Marlin"
To: "Garry Smith" Cc: Sent: Monday, December 11, 2000 3:04 PM Subject: [SLE] microsecond clock timer Hi all,
I am about to start doing some performance testing on a software
Garry Smith writes: project
that I am involved with. I would like to use my version of SuSE Linux 7.0 Professional as one of the test platforms.
How can I get Linux to provide microsecond granularity when I make calls to the system clock? In otherwords, I need a microsecond clock on Linux to get accurate performance measurements of my software?
You can use select, like so:
struct timeval tv;
tv.tv_sec = 0; tv.tv_usec = 1000;
/* Sleep for a while */ select (0, NULL, NULL, NULL, &tv);
------ snip -----
-- To unsubscribe send e-mail to suse-linux-e-unsubscribe@suse.com For additional commands send e-mail to suse-linux-e-help@suse.com Also check the FAQ at http://www.suse.com/support/faq
Message-ID: <3A36A859.5360154A@cfl.rr.com>
Date: Tue, 12 Dec 2000 17:36:09 -0500
From: Mark Hounschell
Hi all,
I am about to start doing some performance testing on a software project that I am involved with. I would like to use my version of SuSE Linux 7.0 Professional as one of the test platforms.
How can I get Linux to provide microsecond granularity when I make calls to the system clock? In otherwords, I need a microsecond clock on Linux to get accurate performance measurements of my software?
I have seen some information about this subject on the Net, but it seems to be focused on earlier versions of the Linux kernel.
On my machine, unama -a returns : Linux eclipse 2.2.16 #1 Wed Aug 2 20:22:26 GMT 2000 i686 unknown This is a uniprocessor machine, Intel Pentium III 450
Could you explain what I must do (and how) to achieve this functionality? Or does SuSE 7.0 already support the microsecond clock as standard?
Many thanks in advance for your kind help
regards Garry
Not sure if you got my first attempt at sending this. I was in a hurry to get out of work. Take a look at this. It may be a little more than you need or are looking for but we are about to begin a port of most every thing you find on this site to linux/x86 arch. The rtom brd is a pci based card that already works on NT/x86. It's really just part of a larger effort to migrate legacy gould/encore hardware/software to unix/offtheself hardware. This propriatary legacy hardware/software is used mainly in the simulation(flight) market. REAL-TIME stuff. Most of what you'll find here is for the sole purpose of emulating the instruction set and hardware of these legacy machines used in the simulation market. Oh yea, it ain't cheap. http://www.encore.com/products/software/osenhanc/980058.shtml#hw -- Mark Hounschell dmarkh@cfl.rr.com
participants (4)
-
alan@ibgames.com
-
dmarkh@cfl.rr.com
-
Garry.Smith@computer.org
-
jlm@compgen.com