linux-kernel - Re: [dm-devel] [PATCH 0/5] bio-cgroup: Introduction

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

Message-Id: <20080919.210242.57356043.taka@valinux.co.jp>
Date:	Fri, 19 Sep 2008 21:02:42 +0900 (JST)
From:	Hirokazu Takahashi <taka@...inux.co.jp>
To:	dm-devel@...hat.com
Cc:	ryov@...inux.co.jp, linux-kernel@...r.kernel.org,
	containers@...ts.linux-foundation.org,
	virtualization@...ts.linux-foundation.org,
	xen-devel@...ts.xensource.com, fernando@....ntt.co.jp,
	xemul@...nvz.org, agk@...rceware.org, balbir@...ux.vnet.ibm.com
Subject: Re: [dm-devel] [PATCH 0/5] bio-cgroup: Introduction

Hi,

> Hi everyone,
> 
> Here are new releases of bio-cgroup.
> Changes from the previous version are as follows:
> 
> - Accurate dirty-page tracking
>   Support migrating pages between bio-cgroups with minimum overhead,

I'm the one implementing this code.
The implementation isn't finished yet that this this code can't handle
mmapped file pages correctly. Actually, the same problem goes with
the task I/O accounting mechanism since the two of them are using
the same hook

This happens when starting to free pages under memory pressure.
Dirty bit of a pte will be moved into PG_Dirty flag of the associated
page. This can be done in another process context, while the hook try
to charge this operation to the current process.

>   but I think such a situation is quite rare.

I implemented it though, I don't think this case often happens since
it's not normal that several processes try to write the same block
of a file.

Thanks,
Hirokazu Takahashi.

--
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/