Messages in this thread | | | Date | Tue, 27 Jul 1999 08:53:14 +0200 (CEST) | From | Rik van Riel <> | Subject | Re: (disk/cpu) 2.3.11 kernel performance problem |
| |
On Mon, 26 Jul 1999, Gerald Aigner wrote: > On Mon, 26 Jul 1999, Rik van Riel wrote: > > On Mon, 26 Jul 1999, Gerald Aigner wrote: > > > > > 1) The kernel copies data many times before it ends up in user > > > space. > > > > I'm very sorry, but you seem to be too late. This problem is > > (at least partially) fixed in the newer 2.3 kernels... > > I just tried the 2.3.11 kernel. The new kernel is slightly faster > (67 seconds instead of 69 seconds) and it uses less CPU time (37% > vs. 45%) > > However 37% is still a very high CPU utilization.
If you use 1/3rd of your memory bandwidth, then the CPU will be waiting for memory 1/3rd of the time --> 1/3rd CPU usage.
Whether it's doing anything useful besides busy waiting really doesn't matter here...
> > > 2) Using mmap doesn't help because it serializes I/O within a single > > > process (you can't read simultaneously from two disks). > > > > A single process uses a single thread of control, and yes, > > we do readahead over RAID0 sets... > > Using mmap on the linux2.3.11 kernel takes now 105 seconds, which > is still slower than doing read system calls in separate threads. > > So is there an easy way to make mmap as fast as read (in terms of > wall clock time).
Sure there is. Just port the readahead algorithm from file_read() and put it in the mmap() and swapin() code :)
Btw, we're already working on that so don't worry...
Rik -- Open Source: you deserve to be in control of your data. +-------------------------------------------------------------------+ | Le Reseau netwerksystemen BV: http://www.reseau.nl/ | | Linux Memory Management site: http://www.linux.eu.org/Linux-MM/ | | Nederlandse Linux documentatie: http://www.nl.linux.org/ | +-------------------------------------------------------------------+
- 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/
| |