linux-kernel - new sched options

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>] [day] [month] [year] [list]

Message-ID: <CAF-VNaq0P+UaUgEGGDy2+CHaSXCQa7cHVGimrxOTxWXT20rOog@mail.gmail.com>
Date:	Tue, 6 Nov 2012 21:45:35 +0100
From:	Lars Segerlund <lars.segerlund@...il.com>
To:	linux-kernel@...r.kernel.org
Subject: new sched options

 Hi,

 The options schedule for power and schedule for powersave are in my
opinion quite stupid.

 The real use cases are packing on scheduler domains, symetric
multithreading, asymetric packing and over commit on threads or cores
?

 So where are the options like sched_mc, sched_smt and asymetric
packing ? The patch for controlling overcommit on sched mc was very
usefull.

 it's very interesting to use some of these options on the fly, both
for embedded and for datacenter usage.

 For embedded it's interesting to free up a core for RT or to keep the
system in it's  thermal range, or to keep the power consumption low,
but you need parameters for some use cases to play with.

 For the datacenter it's vital to be able to consolidate and control
the load and thermal.

 I don't mind the performance or powersave option, but I miss a sysfs
entry to specify stuff like packing, overcommit and such

 I feel like it's an attempt to simplify something which is both
really hard and has many nuances, no one size fit's all.

 / just my two cents .... Lars Segerlund.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/