Search String: Display: Description: Sort:

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*\[Question\]\s+SMP\s+for\s+Linux\s*$/: 20 ]

Total 20 documents matching your query.

1. des cbc keying (score: 1)
Author: xxxx
Date: Wed, 13 Nov 2002 07:53:04 +0100
You guys sure about this? vmstat uses stats gathered by the kernel in the structure variable kstat (of type struct kernel_stat). Here follows the func that updates this variable, it seems that time
/archives/netdev/2002-11/msg00114.html (8,543 bytes)

2. [Question] SMP for Linux (score: 1)
Author: xxxxxxxxxxxxxx>
Date: Thu, 17 Oct 2002 11:29:28 +0900
ops->ow
/archives/netdev/2002-10/msg00290.html (8,142 bytes)

3. Re: [Question] SMP for Linux (score: 1)
Author: xxxxxxxxxxx>
Date: Thu, 17 Oct 2002 12:02:43 +0200
that my
/archives/netdev/2002-10/msg00298.html (9,552 bytes)

4. Re: [Question] SMP for Linux (score: 1)
Author: ps <phillips@xxxxxxxx>
Date: Thu, 17 Oct 2002 14:00:58 +0200
n. Rega
/archives/netdev/2002-10/msg00299.html (10,298 bytes)

5. RE: [Question] SMP for Linux (score: 1)
Author: xxxxxxx>
Date: Thu, 17 Oct 2002 13:28:38 -0400
nux-kernel@xxxx
/archives/netdev/2002-10/msg00305.html (11,469 bytes)

6. RE: [Question] SMP for Linux (score: 1)
Author: xxxxxxxx>
Date: Fri, 18 Oct 2002 18:16:01 +0200
nd the necessar
/archives/netdev/2002-10/msg00326.html (8,574 bytes)

7. RE: [Question] SMP for Linux (score: 1)
Author: lists@xxxxxxx>
Date: Fri, 18 Oct 2002 19:29:58 -0400
roller: Intel 8
/archives/netdev/2002-10/msg00328.html (10,852 bytes)

8. Re: [Question] SMP for Linux (score: 1)
Author: min@xxxxxxxxxxxxxxxxxxx>
Date: Fri, 18 Oct 2002 17:20:06 -0700
to ship a 2.4.1
/archives/netdev/2002-10/msg00329.html (8,907 bytes)

9. RE: [Question] SMP for Linux (score: 1)
Author: xx>
Date: Sat, 19 Oct 2002 09:53:26 +0200
hanks, greg k-h
/archives/netdev/2002-10/msg00336.html (11,201 bytes)

10. レゼント (score: 1)
Author: hubert <ahu@xxxxxxx>
Date: Thu, 24 Oct 2002 17:00:51 -0400
rtner. 0000 is the default value for the register when the
/archives/netdev/2002-10/msg00509.html (8,408 bytes)

11. Re: [Question] SMP for Linux (score: 1)
Author: Eric Lemoine <Eric.Lemoine@xxxxxxxxxxx>
Date: Wed, 13 Nov 2002 07:53:04 +0100
You guys sure about this? vmstat uses stats gathered by the kernel in the structure variable kstat (of type struct kernel_stat). Here follows the func that updates this variable, it seems that time
/archives/netdev/2002-11/msg00332.html (8,743 bytes)

12. [Question] SMP for Linux (score: 1)
Author: Hyochang Nam <cannon@xxxxxxxxxxxxx>
Date: Thu, 17 Oct 2002 11:29:28 +0900
Many people helped me to solve the interrupt distribution problem. We tested the throughput of Layer 3 forwarding on a SMP machine which equips two Zero proessor(2Ghz). This is our results: -- SMP |
/archives/netdev/2002-10/msg00901.html (8,142 bytes)

13. Re: [Question] SMP for Linux (score: 1)
Author: bert hubert <ahu@xxxxxxx>
Date: Thu, 17 Oct 2002 12:02:43 +0200
There is something called 'irq affinity' which may be interesting for you. See here: http://www.dell.com/us/en/esg/topics/power_ps1q02-morse.htm /proc/irq/?/smp_affinity SMP is not always a win. Rega
/archives/netdev/2002-10/msg00909.html (9,670 bytes)

14. Re: [Question] SMP for Linux (score: 1)
Author: Robert Olsson <Robert.Olsson@xxxxxxxxxxx>
Date: Thu, 17 Oct 2002 14:00:58 +0200
Hello! Not always good for routing... Were you still get the problem were one interface is the output device from devices bound to different CPU's. TX-ring can hold skb's from many CPU's so a lot of
/archives/netdev/2002-10/msg00910.html (10,400 bytes)

15. RE: [Question] SMP for Linux (score: 1)
Author: "Jon Fraser" <J_Fraser@xxxxxxxxxxx>
Date: Thu, 17 Oct 2002 13:28:38 -0400
What was your cpu utilization like in the bound vs split scenarios? Does your e1000 driver have transmit interrupts enabled or disabled? I'd be really interested to see the results with two flows in
/archives/netdev/2002-10/msg00916.html (11,532 bytes)

16. RE: [Question] SMP for Linux (score: 1)
Author: Robert Olsson <Robert.Olsson@xxxxxxxxxxx>
Date: Fri, 18 Oct 2002 18:16:01 +0200
Not measured. Gonna take a look w. varient of Manfred's loadtest when possible. But measuring the CPU this way also gives affects throughput. Other softirq's are allowed to run as well now. :-) Over
/archives/netdev/2002-10/msg00937.html (8,747 bytes)

17. RE: [Question] SMP for Linux (score: 1)
Author: "Jon Fraser" <J_Fraser@xxxxxxxxxxx>
Date: Fri, 18 Oct 2002 19:29:58 -0400
I ran some tests this afternoon. The setup is: 2 x 1ghz PIII cpus w 256k cache 2 intel 82542 gig-e cards linux 2.4.20-pre11 kernel. I don't have the NAPI e1000 driver. I actually have to ship a 2.4.1
/archives/netdev/2002-10/msg00939.html (10,885 bytes)

18. Re: [Question] SMP for Linux (score: 1)
Author: Nivedita Singhvi <niv@xxxxxxxxxx>
Date: Fri, 18 Oct 2002 17:20:06 -0700
This is approximately what one should expect, correct? If you have only one task (flow), then the float case will be slower than the bound/split case (as long as the CPU isnt the bottleneck), because
/archives/netdev/2002-10/msg00940.html (8,977 bytes)

19. RE: [Question] SMP for Linux (score: 1)
Author: Robert Olsson <Robert.Olsson@xxxxxxxxxxx>
Date: Sat, 19 Oct 2002 09:53:26 +0200
NAPI stuff will do interrupt mitigation for you. You probably get a lot less RX interrupts at your loads. I did the old trick to clean TX-buffers at hard_xmit as well but don't see any particularly w
/archives/netdev/2002-10/msg00947.html (11,374 bytes)

20. RE: [Question] SMP for Linux (score: 1)
Author: "Jon Fraser" <J_Fraser@xxxxxxxxxxx>
Date: Thu, 24 Oct 2002 17:00:51 -0400
I used perfctr-2.4.0-pre2 to grab the CPU performance counters. I was interested in cache invalidates, etc. I guess I'll try using oprofile to see where in the code I'm really spending the time. Rig
/archives/netdev/2002-10/msg01120.html (8,440 bytes)


This search system is powered by Namazu