Messages in this thread | | | From | Benno Senoner <> | Subject | Re: 2.4.0test5-pre4-lowlat latencies benchmarked, 2.2.16+Ingo's LL patch = strange behaviour | Date | Wed, 26 Jul 2000 02:13:58 +0200 |
| |
On Wed, 26 Jul 2000, Mark Hahn wrote: > > Unfortunately during disk writes it performs still quite bad , about 50msec > > during disk writes. > > you still mean misconfigured (PIO) disk writes, right?
for all my tests (past/present/future) assume EIDE DMA=on , unmask irq=on 32bit access=on
I do not care about untuned , non-DMAed IDE disks, because these are not the typical machines of the power desktop multimedia machine.
The user who wants low latencies is willing to buy non-flawed hardware. Bloating the kernel to deliver good latencies on old, slow polled devices etc is simply silly.
Benno.
- 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/
| |