> More or less... you don't describe your environment, from the host config I > guess it's SKAS however... Do you set TMPDIR to a tmpfs or ramfs mount > point? Without those tricks, any test is pointless. I use SKAS. But I don't set TMPDIR. Do they speed ip UML? I probably need extra host memory for it, right?
> Creating a process inside UML takes a lot longer of the host... try to > rewrite the scripts in perl or C, or any scripting language, and you'll see > that the difference reduce a lot. > > The problem is that starting the "touch" process is a lot slower than > creating the file itself! Try this: > > $ > a Tremendously faster. (host: 0.086 s; guest: 0,34s) > to create that file, and times will probably improve (I'm not sure, since > probably the shell forks anyway to execute a command, so we loose > anyway)... On the other side, you'd get a 18x difference even if you ran a > loop with of 100.000 /bin/echo... or maybe in that case the difference > would be even bigger. With echo the numbers are host: 0.25s, guest: 3.5s. They are still a lot better than touch on both systems. Maybe because touch tries to read the file first. > In many real workloads, however, things are a lot better... pure userspace > computation, without page faults, sees no difference inside UML vs. inside > the host, and a kernel compilation gives only something littler than 2x as > slowdown ratio... (I don't have even a order of figures about this, there > was something in the list)... We run the site http://www.musipedia.org/ on an UML-guest. Last saturday it became the Kim Komando Cool Site of the Day (http://www.komando.com/koolsites.asp). This caused so much traffic that the site was nearly unusable. The site uses typo3, php and mysql. I started to search where the performance is lost. Top on host (kernel 2.4) showed lot's of idle time, but the load went high (2-3 on host and above 10 on the guest). I assumed that some processes are waiting for IO. My first suspect was mysql. But mysql was only serving 3 SQL queries per second. Usually mysql needs only few ms for each of these queries. Besides mysql only a few log files were written on the guest. I couldn't find any reason for the high load. We moved mysql to the host and limited apache to 12 parallel requests. Now the site feels a little bit better, but the traffic is less alreaady now. > You should check for the guest too, but I have no reason to think the guest > is swapping. No the guest doesn't have any swap at all. Thanks for your help Christian ------------------------------------------------------- This SF.Net email is sponsored by: IntelliVIEW -- Interactive Reporting Tool for open source databases. Create drag-&-drop reports. Save time by over 75%! Publish reports on the web. Export to DOC, XLS, RTF, etc. Download a FREE copy at http://www.intelliview.com/go/osdn_nl _______________________________________________ User-mode-linux-user mailing list User-mode-linux-user@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/user-mode-linux-user
