From mboxrd@z Thu Jan 1 00:00:00 1970 From: Xiaopong Tran Subject: Re: placement group sizing Date: Sat, 27 Apr 2013 12:45:11 +0800 Message-ID: <517B57D7.8080306@gmail.com> References: <02E999F2-8374-4D47-88DC-D8DC30547068@saaby.com> <517A718E.2000203@42on.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Return-path: Received: from mail-da0-f46.google.com ([209.85.210.46]:60331 "EHLO mail-da0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752797Ab3D0EpH (ORCPT ); Sat, 27 Apr 2013 00:45:07 -0400 Received: by mail-da0-f46.google.com with SMTP id x4so1654585daj.33 for ; Fri, 26 Apr 2013 21:45:06 -0700 (PDT) In-Reply-To: Sender: ceph-devel-owner@vger.kernel.org List-ID: To: Anders Saaby Cc: Wido den Hollander , "ceph-devel@vger.kernel.org" On 04/27/2013 01:07 AM, Anders Saaby wrote: > >> How many OSDs per machine do you have and how much memory do you have per machine? > > 12 OSD's per machine. A bit over 1GB memory per OSD. (16GB per machine) > Try more. If you have a large-ish cluster, with many OSDs, and if you have large PGs, when one or more OSDs go down (for different reasons, a crash, a disk failure, etc), Ceph will start to remap and rebalance, memory usage per OSD can easily balloon to GBs per OSD. When this happens, and if you don't have enough memory, the OSD processes might get OOM-killed, and you'll get into a vicious cycle. >> The more PGs you have, the more peering PGs you will have when an OSD boots again, so that could be heavy for the CPU in the machines. > > Right. >