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] [thread-next>] [day] [month] [year] [list]
Message-ID: <Pine.LNX.4.64.0701191014250.15317@schroedinger.engr.sgi.com>
Date:	Fri, 19 Jan 2007 10:21:33 -0800 (PST)
From:	Christoph Lameter <clameter@....com>
To:	Aubrey Li <aubreylee@...il.com>
cc:	linux-kernel@...r.kernel.org, linux-mm@...ck.org,
	Linus Torvalds <torvalds@...l.org>,
	Andrew Morton <akpm@...l.org>,
	Nick Piggin <nickpiggin@...oo.com.au>,
	"linux-os (Dick Johnson)" <linux-os@...logic.com>,
	Robin Getz <rgetz@...ckfin.uclinux.org>
Subject: Re: [RPC][PATCH 2.6.20-rc5] limit total vfs page cache

On Thu, 18 Jan 2007, Aubrey Li wrote:

> +int sysctl_pagecache_ratio = 10;
> +

Pagecache ratio is the ratio of memory to be left over? Would it not be 
better to twist this around and to be able to specify how much of the
memory of a node may be used by the pagecache?

Why limit the size of the pagecache? Some kind of rationale would be 
useful. Maybe it was there in earlier incarnations of the patch that I did 
not see? It should be kept with it.

zone_reclaim already dynamically limits the size of the pagecache.

> +	if (alloc_flags & ALLOC_PAGECACHE)
> +		min = min + (sysctl_pagecache_ratio * z->present_pages) / 100;

The calculation of the multiplication / division is usually not done in 
the hot allocation path. See f.e. how min_unmapped_pages is handled in 
mm/page_alloc.c
-
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/

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ