From mboxrd@z Thu Jan 1 00:00:00 1970 From: Brad Hubbard Subject: Re: Query regarding storage of objects in ceph Date: Wed, 7 Sep 2016 16:18:04 +1000 Message-ID: <20160907061804.GH5914@rskikr.localdomain> References: Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Received: from mail-pf0-f175.google.com ([209.85.192.175]:32822 "EHLO mail-pf0-f175.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750856AbcIGGSW (ORCPT ); Wed, 7 Sep 2016 02:18:22 -0400 Received: by mail-pf0-f175.google.com with SMTP id g202so3191446pfb.0 for ; Tue, 06 Sep 2016 23:18:21 -0700 (PDT) Content-Disposition: inline In-Reply-To: Sender: ceph-devel-owner@vger.kernel.org List-ID: To: Elita Lobo Cc: ceph-devel On Wed, Sep 07, 2016 at 11:14:26AM +0530, Elita Lobo wrote: > Hi, > > Thanks , It was helpful. Could you please tell me how to trace local > function calls made by ceph? > I tried using gdb but it gave the following error. > > https://paste.fedoraproject.org/423219/73227055/ Those errors look to be primarily because of missing debuginfo. You can use command files in gdb or "-ex" commands on the command line to set a breakpoint, dump a backtrace, continue and detach if you want to dump stacks when known functions are hit. https://poormansprofiler.org/ is a good starting point. Adding dout statements and looking at the logs can also be helpful to understand what is going on. I'm sure others have more ideas. -- Cheers, Brad > > On Tue, Sep 6, 2016 at 10:35 AM, Brad Hubbard wrote: > > On Tue, Sep 6, 2016 at 2:31 PM, Elita Lobo wrote: > >> Hello, > >> > >> I am using Ceph in my research project and hence need to know a bit > >> about how it works internally. I would be grateful if someone would > >> answer my queries. > >> > >> When chunks of 2 objects have to be stored on an osd, are they put > >> into the same file or are these chunks stored in separate file. Is > >> there any way I could see this data using some command? And in which > >> folder of the osd are they stored in? > > > > Working your way through this may help. > > > > http://cephnotes.ksperis.com/blog/2013/08/20/ceph-osd-where-is-my-data > > > >> > >> Also, is there a way I can see the whole flow of function calls made > >> when a node repair is going on? > >> > >> Lastly, could someone please suggest some resources ( other than docs) > >> which would help me understand the internal implementation and give me > >> an idea how to debug in ceph. (Attaching gdb to ceph daemons running > >> in the background etc) > >> > >> Thanking you, > >> Yours sincerely, > >> Elita Lobo > >> -- > >> To unsubscribe from this list: send the line "unsubscribe ceph-devel" in > >> the body of a message to majordomo@vger.kernel.org > >> More majordomo info at http://vger.kernel.org/majordomo-info.html > > > > > > > > -- > > Cheers, > > Brad