From owner-freebsd-stable@freebsd.org Wed Jul 15 16:44:11 2015 Return-Path: Delivered-To: freebsd-stable@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id F09FC9A2029 for ; Wed, 15 Jul 2015 16:44:11 +0000 (UTC) (envelope-from emz@norma.perm.ru) Received: from elf.hq.norma.perm.ru (unknown [IPv6:2a00:7540:1::5]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client CN "mail.norma.perm.ru", Issuer "Vivat-Trade UNIX Root CA" (not verified)) by mx1.freebsd.org (Postfix) with ESMTPS id 30B0118EB for ; Wed, 15 Jul 2015 16:44:09 +0000 (UTC) (envelope-from emz@norma.perm.ru) Received: from [192.168.248.34] ([192.168.248.34]) by elf.hq.norma.perm.ru (8.14.9/8.14.9) with ESMTP id t6FGi0e8014593 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES128-SHA bits=128 verify=NO) for ; Wed, 15 Jul 2015 21:44:01 +0500 (YEKT) (envelope-from emz@norma.perm.ru) Message-ID: <55A68DCB.2060501@norma.perm.ru> Date: Wed, 15 Jul 2015 21:43:55 +0500 From: "Eugene M. Zheganin" User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:31.0) Gecko/20100101 Thunderbird/31.7.0 MIME-Version: 1.0 To: FreeBSD Stable Mailing List Subject: zfs dataset and hanging getdirentries() on it Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.4.3 (elf.hq.norma.perm.ru [192.168.3.10]); Wed, 15 Jul 2015 21:44:01 +0500 (YEKT) X-Spam-Status: No hits=-102.3 bayes=0.0000 testhits ALL_TRUSTED=-1, AWL=0.643, BAYES_00=-1.9, USER_IN_WHITELIST=-100 autolearn=ham autolearn_force=no version=3.4.0 X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on elf.hq.norma.perm.ru X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.20 Precedence: list List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 15 Jul 2015 16:44:12 -0000 Hi. I have a funny zfs dataset on a recent stable, which listing takes several minutes. In the same time - it runs last available pool version with all available feature flags enabled (however, problem manifested itself on a one year old stable) - it's an old /tmp directory - it used to hold 2.5 millions of files (operational error from nagios) - now it's empty - zpool status shows no errors - scrub found no errors - ktrace shows it's getdirentries() that is waiting for something - ps shows zio->io_(trimmed)wchan state Does someone take a look into this, in case this is some kind of rare bug (and I suppose it is) ? If not, I will just delete it - I've already recreated /tmp and renamed old one. Eugene.