Mail Archive Search: <+subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*Tigon3\s+5701\s+PCI\-X\s+recv\s+performance\s+problem\s*$/>

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*Tigon3\s+5701\s+PCI\-X\s+recv\s+performance\s+problem\s*$/: 88 ]

Total 88 documents matching your query.

1. Re: Tigon3 5701 PCI-X recv performance problem (score: 1): Author: John Partridge <johnip@xxxxxxx>; Date: Wed, 03 Dec 2003 16:11:22 -0600; I have not seen the change for this go into 2.6 is there something else I should be doing ? Thanks John Jeff Garzik wrote: John Partridge wrote: David S. Miller wrote: On Tue, 11 Nov 2003 14:04:50 -; /archives/netdev/2003-12/msg00086.html (10,477 bytes)
2. Re: Tigon3 5701 PCI-X recv performance problem (score: 1): Author: sson <gandalf@xxxxxxxxxxxxxx>; Date: Mon, 10 Nov 2003 19:24:38 -0600; I'm working on a patch for the tg3 driver for 2.6 Please can you look at this. I'm not too sure about the Kconfig entry as I have not done one before :- -- linux/drivers/net/tg3.c 2003-11-10 18:28:10; /archives/netdev/2003-11/msg00140.html (11,518 bytes)
3. Re: Tigon3 5701 PCI-X recv performance problem (score: 1): Author: Partridge <johnip@xxxxxxx>; Date: Mon, 10 Nov 2003 18:29:11 -0800; It belongs in arch/${ARCH}/Kconfig not drivers/net/Kconfig It's a static property of the architecture, not something the user chooses one way or the other.; /archives/netdev/2003-11/msg00142.html (10,113 bytes)
4. Re: Tigon3 5701 PCI-X recv performance problem (score: 1): Author: xxx>; Date: Tue, 11 Nov 2003 14:04:50 -0600; Is this OK ? I was not sure about the order should depends be beofre default or the other way round ? or does it matter ? I suspect it does. Thks John -- linux/drivers/net/tg3.c 2003-11-10 18:28:10.0; /archives/netdev/2003-11/msg00154.html (12,176 bytes)
5. Re: Tigon3 5701 PCI-X recv performance problem (score: 1): Author: xxx>; Date: Tue, 11 Nov 2003 12:24:03 -0800; Why are you depending upon MCKINLEY? Don't all ia64 cpus give traps for unaligned memory accesses? That is what this CONFIG option tells the whole kernel.; /archives/netdev/2003-11/msg00155.html (10,695 bytes)
6. Re: Tigon3 5701 PCI-X recv performance problem (score: 1): Author: x>; Date: Tue, 11 Nov 2003 12:25:45 -0800; Also, this help text is broken too. I repeat: "THIS IS NOT A TIGON3 5701 NETWORK ADAPTER SPECIFIC HACK" It is a config variable that all network drivers in the kernel can test to make copybreak and r; /archives/netdev/2003-11/msg00156.html (10,718 bytes)
7. Re: Tigon3 5701 PCI-X recv performance problem (score: 1): Author: xxxxxxxxxx>; Date: Tue, 11 Nov 2003 15:26:09 -0600; David S. Miller wrote: On Tue, 11 Nov 2003 14:04:50 -0600 Why are you depending upon MCKINLEY? Don't all ia64 cpus give traps for unaligned memory accesses? I have no evidence of a problem with Itani; /archives/netdev/2003-11/msg00159.html (11,477 bytes)
8. Re: Tigon3 5701 PCI-X recv performance problem (score: 1): Author: xxxxxxxx>; Date: Tue, 11 Nov 2003 15:39:49 -0600; David S. Miller wrote: Why are you depending upon MCKINLEY? Don't all ia64 cpus give traps for unaligned memory accesses? That is what this CONFIG option tells the whole kernel. OK, I made it ALL IA6; /archives/netdev/2003-11/msg00160.html (13,010 bytes)
9. Re: Tigon3 5701 PCI-X recv performance problem (score: 1): Author: Stephen Hemminger <shemminger@xxxxxxxx>; Date: Tue, 11 Nov 2003 15:09:27 -0800; This patch looks a lot better. Jeff, perhaps you'll combine this with the thing David Mosberger wanted and then merge?; /archives/netdev/2003-11/msg00170.html (11,116 bytes)
10. Re: Tigon3 5701 PCI-X recv performance problem (score: 1): Author: xxxx>; Date: Wed, 12 Nov 2003 00:53:30 +0100; Drop the "bool" line. Then it will be invisible, which is the right thing here. -Andi; /archives/netdev/2003-11/msg00179.html (10,464 bytes)
11. Re: Tigon3 5701 PCI-X recv performance problem (score: 1): Author: r@xxxxxxxx>; Date: Tue, 11 Nov 2003 19:46:38 -0600; Thanks Andi, Andi Kleen wrote: Drop the "bool" line. Then it will be invisible, which is the right thing here. -- linux/drivers/net/tg3.c 2003-11-10 18:28:10.000000000 -0600 +++ patch/drivers/net/tg3; /archives/netdev/2003-11/msg00185.html (12,357 bytes)
12. Re: Tigon3 5701 PCI-X recv performance problem (score: 1): Author: xxxxxx>; Date: Wed, 12 Nov 2003 07:19:58 +0100; Sorry to nitpick again and not catching it earlier, but are you sure it works this way? Normally the options in Kconfig are not prefixed with CONFIG_* So config UNALIGNED_EXPENSIVE would be likely c; /archives/netdev/2003-11/msg00189.html (11,053 bytes)
13. Re: Tigon3 5701 PCI-X recv performance problem (score: 1): Author: xx (Joseph Fannin); Date: Tue, 11 Nov 2003 15:57:31 -0500; David S. Miller wrote: On Tue, 11 Nov 2003 14:04:50 -0600 John Partridge <johnip@xxxxxxx> wrote: +config CONFIG_UNALIGNED_EXPENSIVE + bool "Use Aligned SKB's for Tigon3 5701 network adapters" + depen; /archives/netdev/2003-11/msg00190.html (11,592 bytes)
14. Re: Tigon3 5701 PCI-X recv performance problem (score: 1): Author: xxxx>; Date: Wed, 12 Nov 2003 02:05:35 -0500; Andi Kleen wrote: -- linux/arch/ia64/Kconfig 2003-10-25 13:44:46.000000000 -0500 +++ patch/arch/ia64/Kconfig 2003-11-11 19:45:06.000000000 -0600 @@ -468,6 +468,10 @@ agent" (/sbin/hotplug) to load mo; /archives/netdev/2003-11/msg00194.html (11,697 bytes)
15. Re: Tigon3 5701 PCI-X recv performance problem (score: 1): Author: zik <jgarzik@xxxxxxxxx>; Date: Wed, 12 Nov 2003 09:32:30 -0600; Jeff Garzik wrote: Andi Kleen wrote: Sorry to nitpick again and not catching it earlier, but are you sure it works this way? Normally the options in Kconfig are not prefixed with CONFIG_* So config U; /archives/netdev/2003-11/msg00197.html (13,180 bytes)
16. Re: Tigon3 5701 PCI-X recv performance problem (score: 1): Author: xxxxxx>; Date: Wed, 12 Nov 2003 15:43:51 +0000; this line is not needed - if you're in the ia64 Kconfig it's always set.; /archives/netdev/2003-11/msg00200.html (10,721 bytes)
17. Re: Tigon3 5701 PCI-X recv performance problem (score: 1): Author: xxx>; Date: Tue, 11 Nov 2003 16:32:00 -0500; John Partridge wrote: David S. Miller wrote: On Tue, 11 Nov 2003 14:04:50 -0600 Why are you depending upon MCKINLEY? Don't all ia64 cpus give traps for unaligned memory accesses? I have no evidence o; /archives/netdev/2003-11/msg00260.html (11,747 bytes)
18. Tigon3 5701 PCI-X recv performance problem (score: 1): Author: ert@xxxxxxxxxxx; Date: Wed, 08 Oct 2003 12:12:24 -0500; I am seeing a problem with PCI-X recv performance on the Broadcom 5701 cards. This is due to a known PCI-X errata with the DMA engine when buffers are non zero offset aligned. As well as performance; /archives/netdev/2003-10/msg00244.html (10,749 bytes)
19. Re: Tigon3 5701 PCI-X recv performance problem (score: 1): Author: johnip@xxxxxxx>; Date: Wed, 8 Oct 2003 10:10:46 -0700; Oh yeah? What are your numbers like if you just disable the ia64 kernel unaligned access printk()?; /archives/netdev/2003-10/msg00245.html (8,569 bytes)
20. Re: Tigon3 5701 PCI-X recv performance problem (score: 1): Author: vem@xxxxxxxxxx>; Date: Wed, 08 Oct 2003 12:52:57 -0500; Not too much different mig125:~ # nttcp -r -T -l262144 -w1024 -n1000 10.50.1.130 -l262144 -w1024 Bytes Real s CPU s Real-MBit/s CPU-MBit/s Calls Real-C/s CPU-C/s l318341120 10.00 9.96 254.6131 255.62; /archives/netdev/2003-10/msg00246.html (9,914 bytes)

Current List: 1 - 20
Page: [1] [2] [3] [4] [5]