From owner-freebsd-current@FreeBSD.ORG Wed Jul 17 17:19:04 2013 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by hub.freebsd.org (Postfix) with ESMTP id 4B102611; Wed, 17 Jul 2013 17:19:04 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: from mail-we0-x22b.google.com (mail-we0-x22b.google.com [IPv6:2a00:1450:400c:c03::22b]) by mx1.freebsd.org (Postfix) with ESMTP id 8B044E95; Wed, 17 Jul 2013 17:19:03 +0000 (UTC) Received: by mail-we0-f171.google.com with SMTP id m46so2072009wev.30 for ; Wed, 17 Jul 2013 10:19:02 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type; bh=QcE8DTskG1MeoodPIsqtquSYJMiHeaUmzK/gBYHIom4=; b=wzgeE/Vid9VR66auA1B1uq7BT9BHFsG7BA9L4fliwv/IYB0Mu8zwKA+/O2ro23N3+D pwnChAlscZsi1r9U8eOK/OmHTTMS1/Vk6+hIcq/xpi9u1Shir4WHr3WZEELIynmTdCtS nFjUQxSG1UmrfVP00z/pO46xzj12xxkl728HBzgVuVNNBOh2jCjvlssk28f4zzgGvDCN 7vbWdyGRn3Q80e8RKlyqWfDjSHDKAl7Kztaj04DmzwD7U/3d5chRNu8v7cDPwu0SyRmM EIhKrI7xkocOYh1nCTmRbiokJwIaqkuausv/xKwFr7HSUcwLeZiQtF/O/mtzozyBD+Je gkKA== MIME-Version: 1.0 X-Received: by 10.194.63.229 with SMTP id j5mr5541008wjs.79.1374081542505; Wed, 17 Jul 2013 10:19:02 -0700 (PDT) Sender: adrian.chadd@gmail.com Received: by 10.217.94.132 with HTTP; Wed, 17 Jul 2013 10:19:02 -0700 (PDT) In-Reply-To: <51E67F54.9080800@FreeBSD.org> References: <51DCFEDA.1090901@FreeBSD.org> <51E59FD9.4020103@FreeBSD.org> <51E67F54.9080800@FreeBSD.org> Date: Wed, 17 Jul 2013 10:19:02 -0700 X-Google-Sender-Auth: ptSTsrEDyA2Cg2Pxbh0saE1rqCw Message-ID: Subject: Re: Deadlock in nullfs/zfs somewhere From: Adrian Chadd To: Andriy Gapon Content-Type: text/plain; charset=ISO-8859-1 Cc: freebsd-fs@freebsd.org, freebsd-current X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 17 Jul 2013 17:19:04 -0000 On 17 July 2013 04:26, Andriy Gapon wrote: > on 16/07/2013 22:40 Adrian Chadd said the following: >> :( So it's a deadlock. Ok, so what's next? > > A creative process... Wonderful. :) > One possibility is to add getnewvnode_reserve() calls before the ZFS transaction > beginnings in the places where a new vnode/znode may have to be allocated within > a transaction. > This looks like a quick and cheap solution but it makes the code somewhat messier. > > Another possibility is to change something in VFS machinery, so that VOP_RECLAIM > getting blocked for one filesystem does not prevent vnode allocation for other > filesystems. > > I could think of other possible solutions via infrastructural changes in VFS or > ZFS... Well, what do others think? This seems like a showstopper for systems with lots and lots of ZFS filesystems doing lots and lots of activity. -adrian