Re: [patch 1/4] network dev read_mostly

2007-03-16 Thread Stephen Hemminger
On Thu, 15 Mar 2007 09:17:22 -0400 Benjamin LaHaise [EMAIL PROTECTED] wrote: On Thu, Mar 15, 2007 at 12:25:16AM -0700, David Miller wrote: Could we obtain %rip relative addressing with the ELF relocation approach I mentioned? I think we can for some of the objects -- things like slab

Re: [patch 1/4] network dev read_mostly

2007-03-15 Thread David Miller
From: Eric Dumazet [EMAIL PROTECTED] Date: Thu, 15 Mar 2007 07:28:35 +0100 One problem with your patch is that all read_always() of pointers are going to use 3 bytes more of code, thus raising icache pressure. 48 b8 c3 08 e8 8c afmov$0x71af8ce808c3,%rax 71 00 00 instead of

Re: [patch 1/4] network dev read_mostly

2007-03-15 Thread Eric Dumazet
David Miller a écrit : From: Eric Dumazet [EMAIL PROTECTED] Date: Thu, 15 Mar 2007 07:28:35 +0100 One problem with your patch is that all read_always() of pointers are going to use 3 bytes more of code, thus raising icache pressure. 48 b8 c3 08 e8 8c afmov$0x71af8ce808c3,%rax 71 00

Re: [patch 1/4] network dev read_mostly

2007-03-15 Thread Benjamin LaHaise
On Thu, Mar 15, 2007 at 12:25:16AM -0700, David Miller wrote: Could we obtain %rip relative addressing with the ELF relocation approach I mentioned? I think we can for some of the objects -- things like slab caches are good candidates if we have the initialization done at init time, which

Re: [patch 1/4] network dev read_mostly

2007-03-15 Thread Andi Kleen
Benjamin LaHaise [EMAIL PROTECTED] writes: On Mon, Mar 12, 2007 at 02:08:18PM -0700, Stephen Hemminger wrote: For Eric, mark packet type and network device watermarks as read mostly. The following x86-64 bits might be intersting, as they allow you to completely eliminate the memory

Re: [patch 1/4] network dev read_mostly

2007-03-14 Thread Benjamin LaHaise
On Mon, Mar 12, 2007 at 02:08:18PM -0700, Stephen Hemminger wrote: For Eric, mark packet type and network device watermarks as read mostly. The following x86-64 bits might be intersting, as they allow you to completely eliminate the memory access for run time defined constants. Note that

Re: [patch 1/4] network dev read_mostly

2007-03-14 Thread David Miller
From: Benjamin LaHaise [EMAIL PROTECTED] Date: Wed, 14 Mar 2007 22:18:40 -0400 On Mon, Mar 12, 2007 at 02:08:18PM -0700, Stephen Hemminger wrote: For Eric, mark packet type and network device watermarks as read mostly. The following x86-64 bits might be intersting, as they allow you to

Re: [patch 1/4] network dev read_mostly

2007-03-14 Thread Eric Dumazet
Benjamin LaHaise a écrit : On Mon, Mar 12, 2007 at 02:08:18PM -0700, Stephen Hemminger wrote: For Eric, mark packet type and network device watermarks as read mostly. The following x86-64 bits might be intersting, as they allow you to completely eliminate the memory access for run time

[patch 1/4] network dev read_mostly

2007-03-12 Thread Stephen Hemminger
For Eric, mark packet type and network device watermarks as read mostly. Signed-off-by: Stephen Hemminger [EMAIL PROTECTED] --- net/core/dev.c | 10 +- 1 files changed, 5 insertions(+), 5 deletions(-) diff --git a/net/core/dev.c b/net/core/dev.c index 3f0c468..c82a56b 100644 ---

Re: [patch 1/4] network dev read_mostly

2007-03-12 Thread David Miller
From: Stephen Hemminger [EMAIL PROTECTED] Date: Mon, 12 Mar 2007 14:08:18 -0700 For Eric, mark packet type and network device watermarks as read mostly. Signed-off-by: Stephen Hemminger [EMAIL PROTECTED] Applied. - To unsubscribe from this list: send the line unsubscribe netdev in the body

Re: [patch 1/4] network dev read_mostly

2007-03-12 Thread Eric Dumazet
Stephen Hemminger a écrit : For Eric, mark packet type and network device watermarks as read mostly. ;) static DEFINE_SPINLOCK(ptype_lock); -static struct list_head ptype_base[16];/* 16 way hashed list */ -static struct list_head ptype_all; /* Taps */ +static struct