[Top] [All Lists]

Re: [PATCH 0/5] Per superblock shrinkers V2

To: Dave Chinner <david@xxxxxxxxxxxxx>
Subject: Re: [PATCH 0/5] Per superblock shrinkers V2
From: Nick Piggin <npiggin@xxxxxxx>
Date: Thu, 27 May 2010 02:44:37 +1000
Cc: linux-kernel@xxxxxxxxxxxxxxx, linux-fsdevel@xxxxxxxxxxxxxxx, linux-mm@xxxxxxxxx, xfs@xxxxxxxxxxx
In-reply-to: <1274777588-21494-1-git-send-email-david@xxxxxxxxxxxxx>
References: <1274777588-21494-1-git-send-email-david@xxxxxxxxxxxxx>
User-agent: Mutt/1.5.20 (2009-06-14)
On Tue, May 25, 2010 at 06:53:03PM +1000, Dave Chinner wrote:
> This series reworks the filesystem shrinkers. We currently have a
> set of issues with the current filesystem shrinkers:
>         1. There is an dependency between dentry and inode cache
>            shrinking that is only implicitly defined by the order of
>            shrinker registration.
>         2. The shrinkers need to walk the superblock list and pin
>            the superblock to avoid unmount races with the sb going
>            away.
>         3. The dentry cache uses per-superblock LRUs and proportions
>            reclaim between all the superblocks which means we are
>            doing breadth based reclaim. This means we touch every
>            superblock for every shrinker call, and may only reclaim
>            a single dentry at a time from a given superblock.
>         4. The inode cache has a global LRU, so it has different
>            reclaim patterns to the dentry cache, despite the fact
>            that the dentry cache is generally the only thing that
>            pins inodes in memory.
>         5. Filesystems need to register their own shrinkers for
>            caches and can't co-ordinate them with the dentry and
>            inode cache shrinkers.

Seems like a fairly good approach overall. Thanks.

<Prev in Thread] Current Thread [Next in Thread>