Messages in this thread | | | Date | Thu, 15 Jul 1999 19:28:44 +0200 | From | Thierry Danis <> | Subject | Re: 2.2.10-ac10 : bad NFS performance |
| |
On Thu, Jul 15, 1999 at 10:12:08AM -0700, Ken VanDine wrote: > I am running 2.2.10-ac10 as a NFS Server and 2 others as clients. Is there > away this could be changed to help peak performance? Or would that be a bad > idea???? > > TIA, > --Ken > > Benjamin LaHaise wrote: > > > On Thu, 15 Jul 1999, Thierry Danis wrote: > > > > > That is, 2.2.10-ac10 performs really slowly as server and client > > > compared to 2.2.10-ac4 (both are running RH 6.0/knfsd 1.4.1). > > > > > > Any comment/explanation ? > > > > 2.2.10-ac10 has SLAB_POSIONING enabled, which fills freed memory with a > > pattern to help detect misuse of freed memory. In short: it's expected. > > > > -ben > > > > -
I defined :
#define SLAB_MGMT_CHECKS 0 #define SLAB_DEBUG_SUPPORT 0
in mm/slab.c and performance is almost equal to -ac4. Now, I have to put them back to 1 to benefit of debug if an OOPS occurs.
-- Thierry Danis Poste : 53 53 danis@spmo.sagem.fr
- 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/
| |