From owner-freebsd-fs@FreeBSD.ORG Thu Jan 13 00:58:32 2011 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id E4F57106566B for ; Thu, 13 Jan 2011 00:58:32 +0000 (UTC) (envelope-from freebsd-list@nikazam.com) Received: from mail-qw0-f54.google.com (mail-qw0-f54.google.com [209.85.216.54]) by mx1.freebsd.org (Postfix) with ESMTP id AD6EA8FC08 for ; Thu, 13 Jan 2011 00:58:32 +0000 (UTC) Received: by qwj9 with SMTP id 9so1227867qwj.13 for ; Wed, 12 Jan 2011 16:58:32 -0800 (PST) MIME-Version: 1.0 Received: by 10.224.28.140 with SMTP id m12mr1517226qac.107.1294879011576; Wed, 12 Jan 2011 16:36:51 -0800 (PST) Received: by 10.224.220.76 with HTTP; Wed, 12 Jan 2011 16:36:51 -0800 (PST) Date: Thu, 13 Jan 2011 00:36:51 +0000 Message-ID: From: Nik Azam To: freebsd-fs@freebsd.org Content-Type: text/plain; charset=ISO-8859-1 X-Content-Filtered-By: Mailman/MimeDel 2.1.5 Subject: Memory leak in ZFS? X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 13 Jan 2011 00:58:33 -0000 Hi all, For the past few weeks, I noticed that the amount of memory reported in top (sum of active, inact, wired, cache buf and free) keeps decreasing as the uptime increases. I can't pinpoint to when I first noticed this, as I have updated the system a few times just in case this has been fixed. The box has 8GB of RAM, running 8.2-PRERELEASE r216693. The ZFS pool consists of two RAIDZ1 with 5 disks each and 50GB L2 ARC. Root filesystem is on UFS on separate disk. I have samba, netatalk, istgt, mysql and apache running on the box. After booting up, top reports I have 8GB of memory as expected. After moving files around in the ZFS pool, the ARC grows to 4GB (the maximum size I set). Now the box has been up for 10 days, and the sum of memory reported in top is about 4GB (3GB wired). ARC size is about 2GB. I tried stopping all the services running, but this didn't help. When unmounting the ZFS pool (via /etc/rc.d/zfs stop), top reports that I have 8GB again. Throughout the 10 days period, there is no user activity at all to the UFS filesystem. Is there anything sinister happening here? Or is it just top is playing tricks on me? Thanks, Nik