Messages in this thread | | | Date | Wed, 18 Nov 1998 12:27:28 -0500 (EST) | From | Rafael Reilova <> | Subject | Re: elevator algorithm bug in ll_rw_blk.c |
| |
On Mon, 16 Nov 1998, Gerard Roudier wrote:
> On Mon, 16 Nov 1998, Stephen C. Tweedie wrote:
> > On Sun, 15 Nov 1998 20:38:05 +0100 (MET), Gerard Roudier > > <groudier@club-internet.fr> said: > > > > > My understanding of Linux architecture is that IO blocks coalescing only > > > occurs in ll_rw_blk.c. > > > > Yes, except for scsi which does its Own Thing, of course. > > When I imagine a system with a large memory space, for example 1 GB, > running several hundreds of processes (thousands?) performing writes, all > of them sharing the only 64 requests (NR_REQUEST) in 2.1.128 kernel, I > cannot believe that coalescence will work that well. > Did I miss something important?
I agree mostly. A very simple "fix" to this situation would be to make the queue longer as you hint. Even make it a tunable kernel parameter under /proc. If you have 1 GB of memory you can spare a few bytes for a larger queue. Although against this, we can argue that such a large system *should* already have an intelligent disk controller (RAID?) that has sufficiently large buffers to do these optimizations. Just my 2 centavos...
Cheers,
Rafael
- 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/
| |