linux-kernel - Re: [RFC v2] timers: Don't wake ktimersoftd on every tick

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Fri, 3 Feb 2017 12:27:01 -0600
From:   Haris Okanovic <haris.okanovic@...com>
To:     Sebastian Andrzej Siewior <bigeasy@...utronix.de>
CC:     <linux-rt-users@...r.kernel.org>, <linux-kernel@...r.kernel.org>,
        <tglx@...utronix.de>, <julia.cartwright@...com>,
        <gratian.crisan@...com>
Subject: Re: [RFC v2] timers: Don't wake ktimersoftd on every tick



On 02/03/2017 10:51 AM, Sebastian Andrzej Siewior wrote:
> On 2016-12-13 15:44:05 [-0600], Haris Okanovic wrote:
>> Changed the way timers are collected per Julia and Thomas'
>> recommendation: Expired timers are now collected in interrupt context
>> and fired in ktimersoftd to avoid double-walk of `pending_map`.
> …
>> Thanks,
>> Haris
>
> I've been staring at it for a while now and now I applied it locally and
> look how it goes.
> I would need that patch signed as per
> 	https://kernel.org/doc/html/latest/process/submitting-patches.html#sign-your-work-the-developer-s-certificate-of-origin
> if you want it applied.

Sent a proper PATCH email with sign-off.

Built and booted with both CONFIG_HZ_PERIODIC=y and CONFIG_NO_HZ_IDLE=y 
configurations (100 HZ). Ran short cyclictest to verify numbers.

>> ---
>>  kernel/time/timer.c | 97 ++++++++++++++++++++++++++++++++++++-----------------
>>  1 file changed, 67 insertions(+), 30 deletions(-)
>
> Sebastian
>