Date: Sat, 24 Feb 2007 16:56:31 -0800 (PST)
Message-Id: <20070224.165631.78711967.davem@davemloft.net>
To: wli@holomorphy.com
Cc: npiggin@suse.de, linux-kernel@vger.kernel.org
Subject: Re: [rfc][patch] dynamic resizing dentry hash using RCU
From: David Miller <davem@davemloft.net>
In-Reply-To: <20070224225631.GA9222@holomorphy.com>
References: <20070224042444.GU21484@holomorphy.com>
	<20070224050937.GA16601@wotan.suse.de>
	<20070224225631.GA9222@holomorphy.com>
Mime-Version: 1.0
Content-Type: Text/Plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 881
Lines: 21

From: William Lee Irwin III <wli@holomorphy.com>
Date: Sat, 24 Feb 2007 14:56:31 -0800

> just do it on a per-directory basis so you don't intermix children
> of different parents in some boot-time -allocated global trainwreck
> and you're home free.  Benchmarking is probably needed to gauge
> which performs best.

The original dentry implementation in the kernel did things
per-directory and it sucked.

The problem you run into is that you end up with recursive algorithms
all over the place, which chew up and overflow the kernel stack.

So it would be a regression to go to a per-directory type
lookup data structure for dentries.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/