linux and high volume web sites

I have a high volume web site under linux : kernel is 2.2.17 hardware is 5 bi-PIII 700Mhz / 512Mb, eepro100 all server are diskless (nfs on an netapp filer) except for tmp and swap dispatch is done by the Resonate product web server is apache+php (something like 400 processes), database backend

tcp_v4_hash bug ?

t !) maybe someone can help me find what's go wrong, I can do some testing, but as I don't understand what means the error message... PS: kernel is a 2.2.17 with dhighen NFS patch running on HPnetserver LPr (NRC scsi module, eepro100 module, SMP box booted with maxcups=1 becau

qestion about tcp_v4_hash

scaling support off net.ipv4.tcp_window_scaling = 0 from my config solve the problem ! note : it's a 2*PII 750 Lpr HP netserver with a 2.2.17 kernel. Thanks Valery -- Valery BRASSEUR| Phone # +33 320 60 7982 Atos Branche Multimedia| Fax # +33 320 60 7649 Uni

Re: qestion about tcp_v4_hash

Andi Kleen wrote: > > On Mon, Oct 09, 2000 at 09:47:43AM +0200, valery brasseur wrote: > > I have a Oops in the kernel which say's "tcp_v4_hash: bug, socket state > > is 1" > > can someone explain me what's wrong ? > > Hard to say when you do

Re: qestion about tcp_v4_hash

Andi Kleen wrote: > > On Mon, Oct 09, 2000 at 02:51:28PM +0200, valery brasseur wrote: > > Andi Kleen wrote: > > > > > > On Mon, Oct 09, 2000 at 09:47:43AM +0200, valery brasseur wrote: > > > > I have a Oops in the kernel which say's "tcp_

reboot problem in 2.6.x kernels, where 2.4.x kernels work well

reboot combinations (apm=on|off acpi=on|off reboot=b|w) i tried so far. So, it looks like problem is rather specific to kernels 2.6.x only. No idea why though. P.S. Thank you for Cc answers to me. -- Valery A.Khamenya - To unsubscribe from this list: send the line "unsubscribe linux-kernel&qu

reboot problem with VIA EPIA-MS motherboard

ferent kernel boot options lead to different reboot implementations. One of tracked by me implementations ends up in mach-default/mach_reboot.h, inlined function "mach_reboot". The second udelay(50) in the loop is the last call, after which nothing happens anymore. 6. Any other details/lo

[PATCH] staging: android: ion: remove unnecessary intermediate variable 'objs'

It is not necesssary to use 'objs' as an intermediate variable for assignment operation. Signed-off-by: Valery Ivanov --- drivers/staging/android/ion/ion.c | 7 ++- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/staging/android/ion/ion.c b/drivers/stagi