Date: Fri, 25 Jun 1999 19:40:29 +0200 (MET DST) From: Thomas Schuerger <schuerge@wjpserver.CS.Uni-SB.DE> To: Sheldon Hearn <sheldonh@uunet.co.za> Cc: freebsd-bugs@freebsd.org Subject: Re: kern/12381: Bad scheduling in FreeBSD Message-ID: <199906251740.TAA01611@wjpserver.cs.uni-sb.de> In-Reply-To: <21531.930331519@axl.noc.iafrica.com> from Sheldon Hearn at "Jun 25, 1999 07:25:19 pm"
next in thread | previous in thread | raw e-mail | index | archive | help
> > Updating the ports with 2 rc5des (notice: 2 processors) processes > > in the background (niced to +20): > > John Polstra, the author of CVSup, would be the first to tell you that > CVSup is a CPU hog itself. This isn't the right test to be using. So what? Do you have an explaination why cvsup should take 3.5 times as long? What kind of test should I do to demonstrate the problem? One my system cvsup uses about 6% of CPU time on an unloaded system, so it really isn't a CPU hog. > > I have exported a directory via NFS and NFS accesses are VERY MUCH > > slower from a remote machine, > > Again, NFS is something that _does_ require CPU. Use a real test like > FTP on a large file when the network is not loaded. > > It's not that I'm not interested, it's just that my experience of > FreeBSD differs radically from what you're suggesting. It would be good > if you could produce a test that > > a) Demonstrates a serious problem that affects real-world > scenarios, and > > b) Is measureable using appropriate tests. The tests I did may not be the best ones to choose, but they ARE real-life scenarios. And I DID an FTP test, demonstrating that network transfer speed drops by about 25%. I would be glad if you had some suggestions about what tests I could do. Ciao, Thomas. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-bugs" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199906251740.TAA01611>