linux-kernel - When should I not use CLONE

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]

Date:	Fri, 19 Dec 2014 01:01:45 +0000 (GMT)
From:	Steven Stewart-Gallus <sstewartgallus00@...angara.bc.ca>
To:	linux-kernel@...r.kernel.org
Subject: When should I not use CLONE_IO?

Hello,

Currently GLibc does not use CLONE_IO and does not expose a way to use CLONE_IO
(for threads which are where it'd be most useful I assume). The documentation is
unclear though and leaves me in the dark about a lot. For example, I don't see
why GLibc shouldn't use CLONE_IO with every thread by default. Also, it seems to
me that if threads share I/O contexts they should also have to share I/O
schedulers right? Does this mean that if threads share I/O contexts with
CLONE_IO that sched_setscheduler either severs the I/O context sharing or sets
the same scheduler for both of them? Even if the threads sharing the same I/O
context must use the same scheduler can they have different priorities?

Thank you,
Steven Stewart-Gallus
--
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/