From mboxrd@z Thu Jan 1 00:00:00 1970 From: =?iso-8859-2?Q?=A3ukasz_Chrustek?= Subject: Re: problem with removing osd Date: Thu, 29 Dec 2016 23:02:11 +0100 Message-ID: <10710520745.20161229230211@tlen.pl> References: <16310616780.20161229160718@tlen.pl> <109878557.20161229212030@tlen.pl> <1498014063.20161229214621@tlen.pl> <1039341611.20161229215518@tlen.pl> Reply-To: =?iso-8859-2?Q?=A3ukasz_Chrustek?= Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-2 Content-Transfer-Encoding: 8BIT Return-path: Received: from mx-out.tlen.pl ([193.222.135.142]:30246 "EHLO mx-out.tlen.pl" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751112AbcL2XCP (ORCPT ); Thu, 29 Dec 2016 18:02:15 -0500 In-Reply-To: Sender: ceph-devel-owner@vger.kernel.org List-ID: To: Sage Weil Cc: ceph-devel@vger.kernel.org Hi, Thank You very much for analize and the file ! I had similar :) but wasn't sure if it wan't distroy something in cluster. > The encoded tree bucket -11 had bad values. I don't really trust the tree > bucket code in crush... it's not well tested (and is a poor balance > computation and efficiency anyway). We should probably try to remove tree > entirely. > I've attached a fixed map that you can inject with > ceph osd setcrushmap -i Now it works, and also ceph osd crush dump -f json-pretty runs OK. > Bucket -11 is now empty; not sure what was supposed to be in it. this server will be reinstalled, there where three osds. > I suggest switching all of your tree buckets over to straw2 as soon as > possible. Note that this will result in some rebalancing. You could do > it one bucket a time if that's concerning. OK, changing alg to straw2 will rebalance ale PGs on all nodes ? -- Regards, Luk