SCIENTIFIC-LINUX-USERS Archives

October 2012

SCIENTIFIC-LINUX-USERS@LISTSERV.FNAL.GOV

Options: Use Monospaced Font
Show Text Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Subject:
From:
Akemi Yagi <[log in to unmask]>
Reply To:
Akemi Yagi <[log in to unmask]>
Date:
Wed, 3 Oct 2012 13:16:14 -0700
Content-Type:
text/plain
Parts/Attachments:
text/plain (27 lines)
On Wed, Oct 3, 2012 at 3:02 AM, jdow <[log in to unmask]> wrote:
> On 2012/10/03 01:33, g wrote:

>> as stated in orig post, it was used as a _factor_to_adjust_ the
>> 'tick rate'. no speed up or slow down as 'adj-time' does.

> I have the impression that Linux tends to be tickless and adjusts
> itself to perceived needs to a large degree. But I've not followed
> that very much of late.

RHEL (therefore SL) kernels became tickless as of 6.0.

If the OP meant, by 'tick rate', "kernel timer interrupt frequency",
then it is defined in the kernel config.

In the case of SL 6.3 kernels,

$ grep _HZ /boot/config-`uname -r`
CONFIG_NO_HZ=y
# CONFIG_HZ_100 is not set
# CONFIG_HZ_250 is not set
# CONFIG_HZ_300 is not set
CONFIG_HZ_1000=y
CONFIG_HZ=1000

Akemi

ATOM RSS1 RSS2