linux-kernel - Question about pdflush's two ratio?

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: <4a3acf9f0803071753x19043628t2ffda8ce6e946e18@mail.gmail.com>
Date:	Sat, 8 Mar 2008 09:53:07 +0800
From:	"内核追踪" <kerneltrack@...il.com>
To:	linux-kernel <linux-kernel@...r.kernel.org>
Subject: Question about pdflush's two ratio?

Hi, buddy, In these days, I'm watching about how the pdflush kernel
thread implemented. But we I saw there are two "*_ratio", I was
puzzled about these.

My kernel version is 2.6.9 and I found get_dirty_limits() in
page-writeback.c in KERNEL_SOURCE/mm.

After read the source and annotation about the function , I got that idea about
1. *dirty_ratio* is just for work with the number in system page
cache. It means if the (dirty pages number in system)/(total number
pages) is above the
    ratio , then we start pdflush.
2. *background_ratio* is just for every process. It means if there
were a single_process write pages and (its dirty pages) / (total
number pages in system)
    is above th ratio, then we also start pdflush.

This is my interpetation. But does it correct?

 Thx.
Jiancong
--
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/