Mail Archive Search: <+subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*_High_\s+CPU\s+usage\s+while\s+routing\s+$mostly$\s+small\s+UDP\s+packets\s*$/>

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*_High_\s+CPU\s+usage\s+while\s+routing\s+$mostly$\s+small\s+UDP\s+packets\s*$/: 62 ]

Total 62 documents matching your query.

1. Transmission limit) (score: 1): Author: Karsten Desler <kdesler@xxxxxxxxxx>; Date: Mon, 6 Dec 2004 21:53:05 +0100; all packets at GIGE wire speed this will make development and testing much easier... A first router test with our setup below. Opteron 1.6 GHz SMP kernel. usin; /archives/netdev/2004-12/msg00120.html (13,651 bytes)
2. ) small UDP packets (score: 1): Author: "David S. Miller" <davem@xxxxxxxxxxxxx>; Date: Mon, 6 Dec 2004 13:48:49 -0800; ith two active e1000 interfaces, that mostly deals with small (<200b) udp packets. I'm using Linux 2.6.10-rc3 (32bit), but I tried 64bit with early 2.6.9-rc ve; /archives/netdev/2004-12/msg00121.html (9,182 bytes)
3. Transmission limit) (score: 1): Author: Karsten Desler <kdesler@xxxxxxxxxx>; Date: Mon, 6 Dec 2004 23:41:07 +0100; ut clone_skb with various versions of the driver. This matches the data I see in my tests here with and without clone_skb. I've included a lot of pps numbers b; /archives/netdev/2004-12/msg00123.html (10,552 bytes)
4. e7501-based system? (score: 1): Author: Con Kolivas <kernel@xxxxxxxxxxx>; Date: Tue, 07 Dec 2004 10:56:58 +1100; .11. it was not correctly fetching the config information from the card, and was displaying zeroed data instead. i've included a patch at the end of this email; /archives/netdev/2004-12/msg00125.html (10,245 bytes)
5. _enable and irq ack (score: 1): Author: Karsten Desler <kdesler@xxxxxxxxxx>; Date: Tue, 7 Dec 2004 01:18:15 +0100; _for_quiescence() needs to disable the NAPI processing but it has no reason to lock any part of the driver which would try to do the same at a later time. Let'; /archives/netdev/2004-12/msg00127.html (10,525 bytes)
6. TU for large frames (score: 1): Author: Karsten Desler <kdesler@xxxxxxxxxx>; Date: Tue, 7 Dec 2004 01:20:12 +0100; u range it claims. Experimenting with the Tx threshold and/or the PCI burst size does not seem to improve the behavior. Signed-off-by: Francois Romieu <romieu@; /archives/netdev/2004-12/msg00131.html (10,644 bytes)
7. 90: network driver. (score: 1): Author: jamal <hadi@xxxxxxxxxx>; Date: 06 Dec 2004 21:46:35 -0500; It doesnt sound like good behavior neither legit. Does this happen to only raw sockets? Herbert asked for a sample small program that reproduces it. I dont th; /archives/netdev/2004-12/msg00138.html (11,939 bytes)
8. ) small UDP packets (score: 1): Author: Karsten Desler <kdesler@xxxxxxxxxx>; Date: Tue, 7 Dec 2004 03:54:56 +0100; e having other issues in the box. You should be able to do much higher packet rates even with iptables compiled in. Some numbers at: http://www.suug.ch/sucon/0; /archives/netdev/2004-12/msg00139.html (11,309 bytes)
9. ) small UDP packets (score: 1): Author: jamal <hadi@xxxxxxxxxx>; Date: 06 Dec 2004 22:18:54 -0500; Thanks, I'll look into it. But what could be the reason? I'm really out of ideas. The only thing I can think off is the 66/64 PCI bus and the disadvantageous p; /archives/netdev/2004-12/msg00140.html (11,259 bytes)
10. Transmission limit) (score: 1): Author: Karsten Desler <kdesler@xxxxxxxxxx>; Date: Tue, 7 Dec 2004 04:24:38 +0100; eers, jamal; /archives/netdev/2004-12/msg00142.html (11,750 bytes)
11. ) small UDP packets (score: 1): Author: jamal <hadi@xxxxxxxxxx>; Date: 06 Dec 2004 22:30:41 -0500; roller: Intel Corp. 82545EM Gigabit Ethernet Controller (Fiber) (rev 01) 0000:01:03.0 Ethernet controller: Intel Corp. 82546GB Gigabit Ethernet Controller (rev; /archives/netdev/2004-12/msg00143.html (11,861 bytes)
12. ) small UDP packets (score: 1): Author: Karsten Desler <kdesler@xxxxxxxxxx>; Date: Tue, 7 Dec 2004 05:02:35 +0100; 46GB Gigabit Ethernet Controller (rev; /archives/netdev/2004-12/msg00144.html (11,896 bytes)
13. a velocity in 2.6.9 (score: 1): Author: Karsten Desler <kdesler@xxxxxxxxxx>; Date: Tue, 7 Dec 2004 11:21:32 +0100; lenar@xxxxxxxxx> : [...] the machine just locked up after ifconfig up. With 2.6.9, it doesn't lock up, but it doesn't work either (data seems to go to black ho; /archives/netdev/2004-12/msg00149.html (13,071 bytes)
14. ) small UDP packets (score: 1): Author: P@xxxxxxxxxxxxxx; Date: Tue, 07 Dec 2004 10:47:52 +0000; t so sure anymore. Is there any other way to find out? version: 5.5.4-k2-NAPI version: 5.5.4-k2-NAPI CPU0 CPU1 169: 5 115554253 IO-APIC-level eth0 177: 7899834; /archives/netdev/2004-12/msg00150.html (12,633 bytes)
15. ) small UDP packets (score: 1): Author: Karsten Desler <kdesler@xxxxxxxxxx>; Date: Tue, 7 Dec 2004 12:21:39 +0100; wrote: It's spending nearly half of it's time in iptables. Try to consolidate your rules if possible. This is the part of netfilter that really doesn't scale w; /archives/netdev/2004-12/msg00151.html (12,656 bytes)
16. ked fine with 2.6.9 (score: 1): Author: jamal <hadi@xxxxxxxxxx>; Date: 07 Dec 2004 07:34:05 -0500; h as it is, I didn't want to take any; /archives/netdev/2004-12/msg00153.html (12,676 bytes)
17. ) small UDP packets (score: 1): Author: Robert Olsson <Robert.Olsson@xxxxxxxxxxx>; Date: Tue, 7 Dec 2004 13:38:56 +0100; e a dual opteron 244. You are supposed to be kicking ass with that machine - not 200Kpps+ you are getting with all that CPU overload. Something is wrong with y; /archives/netdev/2004-12/msg00154.html (11,814 bytes)
18. ) small UDP packets (score: 1): Author: Karsten Desler <kdesler@xxxxxxxxxx>; Date: Tue, 7 Dec 2004 13:50:01 +0100; not to say almost impossible to extrapolate idle cpu into any network system capacity. I guess this is what you are trying to do? Rather load and overload the; /archives/netdev/2004-12/msg00155.html (12,012 bytes)
19. ress family problem (score: 1): Author: jamal <hadi@xxxxxxxxxx>; Date: 07 Dec 2004 08:04:33 -0500; ues the flushing after a response from the kernel. It happens to be flushing IPV4 addresses. Thats why your filter in ip is the answer. BTW, did the gnet_stats; /archives/netdev/2004-12/msg00158.html (12,010 bytes)
20. ) small UDP packets (score: 1): Author: Karsten Desler <kdesler@xxxxxxxxxx>; Date: Tue, 7 Dec 2004 14:11:25 +0100; forward - rather just packet capturing? Are you using a tcpdump patched with mmaped packet socket? The 230-240Kpps you are reporting as a capture dont seem as; /archives/netdev/2004-12/msg00159.html (12,131 bytes)

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