On Wed, 04 Oct 2006 09:56:57 +0200, Ingo Molnar said: > > * [email protected] <[email protected]> wrote: > > > Even though I have CONFIG_HZ=1000, this ends up generating a synthetic > > count that works out to 100 per second. gkrellm and vmstat are happy > > with that state of affairs, but I'm not sure why it came out to > > 100/sec rather than 1000/sec. > > that's how it worked for quite some time: all userspace APIs are > HZ-independent and depend on USER_HZ (which is 100 even if HZ is 1000). Nevermind - I missed where fs/proc/proc_misc.c applied jiffies_64_to_clock_t() to the number before handing it to userspace. So the numbers *were* being kept in terms of HZ (as my reading of the code indicated), they just didn't manage to escape to userspace that way....
Attachment:
pgpmjFLQRjUyX.pgp
Description: PGP signature
- References:
- [patch 00/21] high resolution timers / dynamic ticks - V2
- From: Thomas Gleixner <[email protected]>
- Re: [patch 00/21] high resolution timers / dynamic ticks - V2
- From: [email protected]
- Re: [patch 00/21] high resolution timers / dynamic ticks - V2
- From: Thomas Gleixner <[email protected]>
- Re: [patch 00/21] high resolution timers / dynamic ticks - V2
- From: [email protected]
- [patch] dynticks core: Fix idle time accounting
- From: Thomas Gleixner <[email protected]>
- Re: [patch] dynticks core: Fix idle time accounting
- From: [email protected]
- Re: [patch] dynticks core: Fix idle time accounting
- From: Thomas Gleixner <[email protected]>
- Re: [patch] dynticks core: Fix idle time accounting
- From: [email protected]
- Re: [patch] dynticks core: Fix idle time accounting
- From: Thomas Gleixner <[email protected]>
- Re: [patch] dynticks core: Fix idle time accounting
- From: [email protected]
- Re: [patch] dynticks core: Fix idle time accounting
- From: Ingo Molnar <[email protected]>
- [patch 00/21] high resolution timers / dynamic ticks - V2
- Prev by Date: [PATCH] SCSI st: fix error handling in module init, sysfs
- Next by Date: PCI/IDE generic IDE driver + bus master DMA logic errors
- Previous by thread: Re: [patch] dynticks core: Fix idle time accounting
- Next by thread: Re: [patch 00/21] high resolution timers / dynamic ticks - V2
- Index(es):