Re: Slowdown with randomize_va_space in 2.6.12.2

2005-07-31 Thread Arjan van de Ven
> > It has the virtue of simplicity. Arjan, were you planning on anything > fancier? short term: no. (eg 2.6.13). Long term I wanted to turn this into a bitmask so that you can control the randomisations individual (eg keep the stack one disable the library one only) - To unsubscribe from this

Re: Slowdown with randomize_va_space in 2.6.12.2

2005-07-30 Thread Arjan van de Ven
> It has the virtue of simplicity. Arjan, were you planning on anything > fancier? not for 2.6.13; this was the plan for later I was going to turn it into a bitmask for the individual randomisations signature.asc Description: This is a digitally signed message part

Re: Slowdown with randomize_va_space in 2.6.12.2

2005-07-29 Thread Andrew Morton
Eric Lammerts <[EMAIL PROTECTED]> wrote: > > > On Thu, 7 Jul 2005, Arjan van de Ven wrote: > > On Wed, 2005-07-06 at 18:12 -0700, Andrew Morton wrote: > > > Dave Jones <[EMAIL PROTECTED]> wrote: > > > > On Transmeta CPUs that probably triggers a retranslation of > > > > x86->native bytecode, if it

Re: Slowdown with randomize_va_space in 2.6.12.2

2005-07-29 Thread Eric Lammerts
On Thu, 7 Jul 2005, Arjan van de Ven wrote: > On Wed, 2005-07-06 at 18:12 -0700, Andrew Morton wrote: > > Dave Jones <[EMAIL PROTECTED]> wrote: > > > On Transmeta CPUs that probably triggers a retranslation of > > > x86->native bytecode, if it thinks it hasn't seen code at that > > > address befor

Re: Slowdown with randomize_va_space in 2.6.12.2

2005-07-06 Thread Arjan van de Ven
On Wed, 2005-07-06 at 23:41 -0700, Andrew Morton wrote: > Arjan van de Ven <[EMAIL PROTECTED]> wrote: > > > > > > On Transmeta CPUs that probably triggers a retranslation of > > > > x86->native bytecode, if it thinks it hasn't seen code at that > > > > address before. > > > > > > > > > > ouc

Re: Slowdown with randomize_va_space in 2.6.12.2

2005-07-06 Thread Andrew Morton
Arjan van de Ven <[EMAIL PROTECTED]> wrote: > > > > On Transmeta CPUs that probably triggers a retranslation of > > > x86->native bytecode, if it thinks it hasn't seen code at that > > > address before. > > > > > > > ouch. What do we do? Default to off? Default to off on xmeta? > > off

Re: Slowdown with randomize_va_space in 2.6.12.2

2005-07-06 Thread Arjan van de Ven
On Wed, 2005-07-06 at 18:12 -0700, Andrew Morton wrote: > Dave Jones <[EMAIL PROTECTED]> wrote: > > > > On Wed, Jul 06, 2005 at 12:57:19PM -0700, David S. Miller wrote: > > > From: Paulo Marques <[EMAIL PROTECTED]> > > > Date: Wed, 06 Jul 2005 15:23:56 +0100 > > > > > > > What is weird is that

Re: Slowdown with randomize_va_space in 2.6.12.2

2005-07-06 Thread
Quoting "David S. Miller" <[EMAIL PROTECTED]>: > From: Andrew Morton <[EMAIL PROTECTED]> > Date: Wed, 6 Jul 2005 18:12:20 -0700 > > > ouch. What do we do? Default to off? Default to off on xmeta? > > Good question. Whatever security is gained by the va randomization > stuff is definitely no

Re: Slowdown with randomize_va_space in 2.6.12.2

2005-07-06 Thread David S. Miller
From: Andrew Morton <[EMAIL PROTECTED]> Date: Wed, 6 Jul 2005 18:12:20 -0700 > ouch. What do we do? Default to off? Default to off on xmeta? Good question. Whatever security is gained by the va randomization stuff is definitely not worth a 0.23 --> 3.0 second performance regression. - To uns

Re: Slowdown with randomize_va_space in 2.6.12.2

2005-07-06 Thread Andrew Morton
Dave Jones <[EMAIL PROTECTED]> wrote: > > On Wed, Jul 06, 2005 at 12:57:19PM -0700, David S. Miller wrote: > > From: Paulo Marques <[EMAIL PROTECTED]> > > Date: Wed, 06 Jul 2005 15:23:56 +0100 > > > > > What is weird is that most of the extra time is being accounted as > > > user-space time,

Re: Slowdown with randomize_va_space in 2.6.12.2

2005-07-06 Thread David S. Miller
From: Dave Jones <[EMAIL PROTECTED]> Subject: Re: Slowdown with randomize_va_space in 2.6.12.2 Date: Wed, 6 Jul 2005 16:53:15 -0400 > On Wed, Jul 06, 2005 at 12:57:19PM -0700, David S. Miller wrote: > > It might be attributable to more cpu cache misses in userspace since &

Re: Slowdown with randomize_va_space in 2.6.12.2

2005-07-06 Thread Arjan van de Ven
On Wed, 2005-07-06 at 12:57 -0700, David S. Miller wrote: > From: Paulo Marques <[EMAIL PROTECTED]> > Date: Wed, 06 Jul 2005 15:23:56 +0100 > > > What is weird is that most of the extra time is being accounted as > > user-space time, but the user-space application is exactly the same in > > both

Re: Slowdown with randomize_va_space in 2.6.12.2

2005-07-06 Thread Dave Jones
On Wed, Jul 06, 2005 at 12:57:19PM -0700, David S. Miller wrote: > From: Paulo Marques <[EMAIL PROTECTED]> > Date: Wed, 06 Jul 2005 15:23:56 +0100 > > > What is weird is that most of the extra time is being accounted as > > user-space time, but the user-space application is exactly the same

Re: Slowdown with randomize_va_space in 2.6.12.2

2005-07-06 Thread David S. Miller
From: Paulo Marques <[EMAIL PROTECTED]> Date: Wed, 06 Jul 2005 15:23:56 +0100 > What is weird is that most of the extra time is being accounted as > user-space time, but the user-space application is exactly the same in > both runs, only the "randomize_va_space" parameter changed. It might be a