linux-kernel - SCHED_RR and kernel thread

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: <f24b07420904052201o45c9e814q597f766749a60005@mail.gmail.com>
Date:	Mon, 6 Apr 2009 10:31:28 +0530
From:	Bhavesh Parekh <bhaveshparekh1@...il.com>
To:	linux-kernel@...r.kernel.org
Subject: SCHED_RR and kernel thread

Hi All,
We have a mulit-threaded application which run on linux kernel 2.6.23.
This application uses the real time thread, using the SCHED_RR policy.
We can't use the SCHED_NORMAL as the heuristic use to compute the
Dynamic priority is not suitted for our application.

As the application is CPU bound if we use the SCHED_RR in the
application then it will stale the system after some time. So we
decided to switch the Kernel thread to the SCHED_RR too.( higher
priority then application).

Now the important question here is that this kernel thread are not
design to work in SCHED_RR policy. What I mean is that  a particular
kernel thread(eg:ksoftirqd)  might take more time to finish it work if
the policy of the thread is change.

Further it is also possible that a particular thread wake-up(eg:
pdflush) and take around 20-50 ms to execution time. So I need to know
is there any test-case to test the time taken by a  particular thread
to finish it work.

-Thanks
Bhavesh
--
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/