Mail Archive Search: <+subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*NAPI\s+vs\.\s+interrupts\s*$/>

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*NAPI\s+vs\.\s+interrupts\s*$/: 8 ]

Total 8 documents matching your query.

1. NAPI vs. interrupts (score: 1): Author: ulj@xxxxxxxxxx>; Date: Sat, 11 Jan 2003 17:08:26 -0500; I am seeing some tg3 reports occasionally that show a fair number of interrupts-per-second, even though tg3 is 100% NAPI. It seems to me that as machines get faster, and amount of memory increase [xl; /archives/netdev/2003-01/msg00091.html (9,453 bytes)
2. Re: NAPI vs. interrupts (score: 1): Author: rzik@xxxxxxxxx>; Date: Sat, 11 Jan 2003 22:41:32 -0500 (EST); sample data? This is very interesting - I havent come across such a CPU myself. I am just about to unleash a P4 machine (> 2Ghz) so i may see this. I think you may have added one more transaction on; /archives/netdev/2003-01/msg00093.html (13,134 bytes)
3. NAPI vs. interrupts (score: 1): Author: xxxxxxxxxxxxxx>; Date: Mon, 13 Jan 2003 16:57:12 +0100; True. Another "worst case" :-) NAPI subsequent iterations of dev->poll at softirq whereas a non-NAPI driver **always** does IRQ ack irqs process events So for this we pay the "insurance fee" of ackin; /archives/netdev/2003-01/msg00095.html (11,834 bytes)
4. RE: NAPI vs. interrupts (score: 1): Author: sri@xxxxxxxxxx>; Date: Wed, 15 Jan 2003 00:06:26 -0800; e1000+NAPI is this path. I've tried something similar to this while playing around with e1000 recently. Using ITR (InterruptThrottleRate), dial in a max intr/sec rate of say 4000 intr/sec, and then; /archives/netdev/2003-01/msg00125.html (8,629 bytes)
5. NAPI vs. interrupts (score: 1): Author: Jeff Garzik <jgarzik@xxxxxxxxx>; Date: Sat, 11 Jan 2003 17:08:26 -0500; I am seeing some tg3 reports occasionally that show a fair number of interrupts-per-second, even though tg3 is 100% NAPI. It seems to me that as machines get faster, and amount of memory increase [xl; /archives/netdev/2003-01/msg00287.html (9,453 bytes)
6. Re: NAPI vs. interrupts (score: 1): Author: jamal <hadi@xxxxxxxxxx>; Date: Sat, 11 Jan 2003 22:41:32 -0500 (EST); sample data? This is very interesting - I havent come across such a CPU myself. I am just about to unleash a P4 machine (> 2Ghz) so i may see this. I think you may have added one more transaction on; /archives/netdev/2003-01/msg00289.html (13,194 bytes)
7. NAPI vs. interrupts (score: 1): Author: Robert Olsson <Robert.Olsson@xxxxxxxxxxx>; Date: Mon, 13 Jan 2003 16:57:12 +0100; True. Another "worst case" :-) NAPI subsequent iterations of dev->poll at softirq whereas a non-NAPI driver **always** does IRQ ack irqs process events So for this we pay the "insurance fee" of ackin; /archives/netdev/2003-01/msg00291.html (11,894 bytes)
8. RE: NAPI vs. interrupts (score: 1): Author: "Feldman, Scott" <scott.feldman@xxxxxxxxx>; Date: Wed, 15 Jan 2003 00:06:26 -0800; e1000+NAPI is this path. I've tried something similar to this while playing around with e1000 recently. Using ITR (InterruptThrottleRate), dial in a max intr/sec rate of say 4000 intr/sec, and then; /archives/netdev/2003-01/msg00321.html (8,629 bytes)

Current List: 1 - 8
Page: [1]