Messages in this thread | | | Date | Mon, 28 Jun 1999 21:05:07 -0400 (EDT) | From | Chuck Lever <> | Subject | Re: Perforamnce comparison between 2.3.8 and 2.2.10 |
| |
On Mon, 28 Jun 1999, Rudolf Leitgeb wrote: > On 28-Jun-99 Andrea Arcangeli wrote: > > On Mon, 28 Jun 1999, Chuck Lever wrote: > > > >>i also believe that a multithreaded page cache for file data won't help > >>much if the file system is still serialized :) > > If the fs is single threaded, I assume that it's protected by some form > of lock, and every process that waits for I/O will sleep, i.e. not accumulate > CPU time. The parallel kernel compiles did not only take longer, they also spent > more time in the CPU. Even if the fs code was protected by a spin lock, this > would only show up in the system time, not in the user time ... > > Did I miss anything ?
the global kernel lock spins, but doesn't sleep. that explains the difference in system CPU utilization, i think.
- Chuck Lever -- corporate: <chuckl@netscape.com> personal: <chucklever@netscape.net> or <cel@monkey.org>
The Linux Scalability project: http://www.citi.umich.edu/projects/linux-scalability/
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |