Mail Archive Search: <+subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*\[PATCH\s+2\.6\]\:\s+Make\s+packet\s+scheduler\s+clock\s+source\s+configurable\s*$/>

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*\[PATCH\s+2\.6\]\:\s+Make\s+packet\s+scheduler\s+clock\s+source\s+configurable\s*$/: 42 ]

Total 42 documents matching your query.

1. [PATCH 2.6]: Make packet scheduler clock source configurable (score: 1): Author: xxxxxxx>; Date: Tue, 13 Jul 2004 04:21:52 +0200; Hi Dave, this patch replaces PSCHED_CLOCK_SOURCE by three new config options and fixes HTB compilation with CONFIG_NET_SCH_CLK_GETTIMEOFDAY. Patch compiles with all three options. If you like it I wi; /archives/netdev/2004-07/msg00352.html (8,993 bytes)
2. Re: [PATCH 2.6]: Make packet scheduler clock source configurable (score: 1): Author: mal <hadi@xxxxxxxxxx>; Date: Mon, 12 Jul 2004 20:35:16 -0700 (PDT); I have a patch (to the original) which replaces the arch dependant CPU stuff with the arch neutral sched_clock() which although slightly slower works on a x86_64 and ia64 as well.; /archives/netdev/2004-07/msg00358.html (9,727 bytes)
3. Re: [PATCH 2.6]: Make packet scheduler clock source configurable (score: 1): Author: xxxx>; Date: Mon, 12 Jul 2004 20:50:37 -0700; I also want to add sparc64 %tick register support here too. This is an area with a lot of potential cleanup. We should made an asm/pkt_sched.h to abstract out the clock source implementation instead; /archives/netdev/2004-07/msg00360.html (9,735 bytes)
4. Re: [PATCH 2.6]: Make packet scheduler clock source configurable (score: 1): Author: xxxx>; Date: Tue, 13 Jul 2004 09:16:06 -0700; Here is the patch I have been testing against 2.6.8-rc1 to use sched_clock. diff -Nru a/include/net/pkt_sched.h b/include/net/pkt_sched.h -- a/include/net/pkt_sched.h 2004-07-12 11:06:52 -07:00 +++ b; /archives/netdev/2004-07/msg00365.html (15,226 bytes)
5. Re: [PATCH 2.6]: Make packet scheduler clock source configurable (score: 1): Author: Stephen Hemminger <shemminger@xxxxxxxx>; Date: Wed, 14 Jul 2004 03:02:37 +0200; David S. Miller wrote: I also want to add sparc64 %tick register support here too. This is an area with a lot of potential cleanup. We should made an asm/pkt_sched.h to abstract out the clock source; /archives/netdev/2004-07/msg00370.html (11,000 bytes)
6. Re: [PATCH 2.6]: Make packet scheduler clock source configurable (score: 1): Author: r@xxxxxxxx>; Date: Wed, 14 Jul 2004 05:46:19 +0200; Patrick McHardy wrote: David S. Miller wrote: I also want to add sparc64 %tick register support here too. This is an area with a lot of potential cleanup. We should made an asm/pkt_sched.h to abstrac; /archives/netdev/2004-07/msg00372.html (15,506 bytes)
7. Re: [PATCH 2.6]: Make packet scheduler clock source configurable (score: 1): Author: xxxx>; Date: Wed, 21 Jul 2004 14:31:10 -0700; This looks great. As you mention some platforms return zero, for example sparc32, for get_cycles(). I suggest we just expand the dependency list for NET_SCH_CLK_TSC to include SPARC64 PPC64 and perha; /archives/netdev/2004-07/msg00500.html (10,983 bytes)
8. Re: [PATCH 2.6]: Make packet scheduler clock source configurable (score: 1): Author: xxxxxxx>; Date: Fri, 23 Jul 2004 01:36:22 +0200; David S. Miller wrote: This looks great. As you mention some platforms return zero, for example sparc32, for get_cycles(). I suggest we just expand the dependency list for NET_SCH_CLK_TSC to include; /archives/netdev/2004-07/msg00521.html (11,830 bytes)
9. Re: [PATCH 2.6]: Make packet scheduler clock source configurable (score: 1): Author: ideaki / 吉藤英明 <yoshfuji@xxxxxxxxxxxxxx>; Date: Thu, 22 Jul 2004 17:17:52 -0700; I see. I know for a fact that sparc64 meets this criterion, and I'm pretty sure ppc64 does too. We could bug check this in psched calibration, in fact I think we should.; /archives/netdev/2004-07/msg00526.html (11,365 bytes)
10. Re: [PATCH 2.6]: Make packet scheduler clock source configurable (score: 1): Author: m@xxxxxxxxxx>; Date: Fri, 23 Jul 2004 02:52:32 +0200; David S. Miller wrote: It needs to increment at slightly above 1Mhz, otherwise delay will be zero after this division and everything will fall apart: delay /= rdelay. I see. I know for a fact that sp; /archives/netdev/2004-07/msg00529.html (12,515 bytes)
11. Re: [PATCH 2.6]: Make packet scheduler clock source configurable (score: 1): Author: avem@xxxxxxxxxx>; Date: Fri, 23 Jul 2004 03:00:52 +0200; Patrick McHardy wrote: David S. Miller wrote: We could bug check this in psched calibration, in fact I think we should. Done by this patch. I used BUG_ON instead of just printing a warning because us; /archives/netdev/2004-07/msg00530.html (12,268 bytes)
12. Re: [PATCH 2.6]: Make packet scheduler clock source configurable (score: 1): Author: <davem@xxxxxxxxxx>; Date: Thu, 22 Jul 2004 18:03:17 -0700; Ok.; /archives/netdev/2004-07/msg00531.html (12,070 bytes)
13. Re: [PATCH 2.6]: Make packet scheduler clock source configurable (score: 1): Author: uji@xxxxxxxxxxxxxx>; Date: Fri, 23 Jul 2004 19:14:48 +0200; Patrick McHardy wrote: I'm pretty sure x86, x86_64, alpha, sparc64, ppc64 and ia64 can be used. I'm not sure if the frequency of all ppcs is high enough, so I won't add support for them. This is the; /archives/netdev/2004-07/msg00540.html (22,655 bytes)
14. Re: [PATCH 2.6]: Make packet scheduler clock source configurable (score: 1): Author: ebian@xxxxxxxxxxxxxx>; Date: Fri, 23 Jul 2004 10:53:24 -0700; Looks great, glad to see this cleaned up.; /archives/netdev/2004-07/msg00541.html (12,135 bytes)
15. Re: [PATCH 2.6]: Make packet scheduler clock source configurable (score: 1): Author: Salim <hadi@xxxxxxxx>; Date: Fri, 23 Jul 2004 13:54:59 -0700; We can't use this stuff on Alpha, it's cycle counter overflows after just 10 minutes. It works very strangely, something like only the lower 32-bits are guarenteed to be continually incrementing. I'm; /archives/netdev/2004-07/msg00547.html (12,012 bytes)
16. Re: [PATCH 2.6]: Make packet scheduler clock source configurable (score: 1): Author: r" <davem@xxxxxxxxxx>; Date: Fri, 23 Jul 2004 13:57:44 -0700; Sure, give it a shot. If it gets too ugly I may not take it though, so be warned :-); /archives/netdev/2004-07/msg00548.html (10,536 bytes)
17. Re: [PATCH 2.6]: Make packet scheduler clock source configurable (score: 1): Author: ler" <davem@xxxxxxxxxx>; Date: Sat, 24 Jul 2004 01:18:50 +0200; David S. Miller wrote: We can't use this stuff on Alpha, it's cycle counter overflows after just 10 minutes. It works very strangely, something like only the lower 32-bits are guarenteed to be contin; /archives/netdev/2004-07/msg00552.html (12,461 bytes)
18. Re: [PATCH 2.6]: Make packet scheduler clock source configurable (score: 1): Author: Miller" <davem@xxxxxxxxxx>; Date: Sat, 24 Jul 2004 01:21:10 +0200; David S. Miller wrote: On Fri, 23 Jul 2004 19:14:48 +0200 Patrick McHardy <kaber@xxxxxxxxx> wrote: Dave, do you want me to provide patches for 2.4 as well ? Sure, give it a shot. If it gets too ugly; /archives/netdev/2004-07/msg00553.html (11,281 bytes)
19. Re: [PATCH 2.6]: Make packet scheduler clock source configurable (score: 1): Author: xxxxxxx>; Date: Sat, 24 Jul 2004 23:27:05 -0700; Let me know if you get feedback or not. For now I'm pushing to Linus with Alpha removed from the list.; /archives/netdev/2004-07/msg00577.html (11,432 bytes)
20. Re: [PATCH 2.6]: Make packet scheduler clock source configurable (score: 1): Author: erbert@xxxxxxxxxxxxxxxxxxx>; Date: Sun, 25 Jul 2004 23:56:51 +0200; David S. Miller wrote: Let me know if you get feedback or not. For now I'm pushing to Linus with Alpha removed from the list. According to Richard Henderson it should work fine. The fastest Alpha cyc; /archives/netdev/2004-07/msg00585.html (11,660 bytes)

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