All of lore.kernel.org
 help / color / mirror / Atom feed
* Query regarding storage of objects in ceph
@ 2016-09-06  4:31 Elita Lobo
  2016-09-06  5:05 ` Brad Hubbard
  0 siblings, 1 reply; 5+ messages in thread
From: Elita Lobo @ 2016-09-06  4:31 UTC (permalink / raw)
  To: ceph-devel

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?

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

^ permalink raw reply	[flat|nested] 5+ messages in thread

* Re: Query regarding storage of objects in ceph
  2016-09-06  4:31 Query regarding storage of objects in ceph Elita Lobo
@ 2016-09-06  5:05 ` Brad Hubbard
  2016-09-07  5:44   ` Elita Lobo
  0 siblings, 1 reply; 5+ messages in thread
From: Brad Hubbard @ 2016-09-06  5:05 UTC (permalink / raw)
  To: Elita Lobo; +Cc: ceph-devel

On Tue, Sep 6, 2016 at 2:31 PM, Elita Lobo <loboelita@gmail.com> 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

^ permalink raw reply	[flat|nested] 5+ messages in thread

* Re: Query regarding storage of objects in ceph
  2016-09-06  5:05 ` Brad Hubbard
@ 2016-09-07  5:44   ` Elita Lobo
  2016-09-07  6:18     ` Brad Hubbard
  0 siblings, 1 reply; 5+ messages in thread
From: Elita Lobo @ 2016-09-07  5:44 UTC (permalink / raw)
  To: Brad Hubbard; +Cc: ceph-devel

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/

On Tue, Sep 6, 2016 at 10:35 AM, Brad Hubbard <bhubbard@redhat.com> wrote:
> On Tue, Sep 6, 2016 at 2:31 PM, Elita Lobo <loboelita@gmail.com> 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

^ permalink raw reply	[flat|nested] 5+ messages in thread

* Re: Query regarding storage of objects in ceph
  2016-09-07  5:44   ` Elita Lobo
@ 2016-09-07  6:18     ` Brad Hubbard
       [not found]       ` <CAA8xDw0mVqDLHuKHZU+x3uFnQf5WJ9NsXTJa_zMbRnvB=SB9Hw@mail.gmail.com>
  0 siblings, 1 reply; 5+ messages in thread
From: Brad Hubbard @ 2016-09-07  6:18 UTC (permalink / raw)
  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 <bhubbard@redhat.com> wrote:
> > On Tue, Sep 6, 2016 at 2:31 PM, Elita Lobo <loboelita@gmail.com> 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

^ permalink raw reply	[flat|nested] 5+ messages in thread

* Re: Query regarding storage of objects in ceph
       [not found]       ` <CAA8xDw0mVqDLHuKHZU+x3uFnQf5WJ9NsXTJa_zMbRnvB=SB9Hw@mail.gmail.com>
@ 2016-09-11 16:13         ` Elita Lobo
  0 siblings, 0 replies; 5+ messages in thread
From: Elita Lobo @ 2016-09-11 16:13 UTC (permalink / raw)
  To: Brad Hubbard; +Cc: ceph-devel

Hi,

Thanks, Will look into it.


Regards,
Elita Lobo

On Sun, Sep 11, 2016 at 9:41 PM, Elita Lobo <loboelita@gmail.com> wrote:
> Hi,
>
> Thanks, Will look into it.
>
>
> Regards,
> Elita Lobo
>
> On Wed, Sep 7, 2016 at 11:48 AM, Brad Hubbard <bhubbard@redhat.com> wrote:
>>
>> 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 <bhubbard@redhat.com>
>> > wrote:
>> > > On Tue, Sep 6, 2016 at 2:31 PM, Elita Lobo <loboelita@gmail.com>
>> > > 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
>
>

^ permalink raw reply	[flat|nested] 5+ messages in thread

end of thread, other threads:[~2016-09-11 16:13 UTC | newest]

Thread overview: 5+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2016-09-06  4:31 Query regarding storage of objects in ceph Elita Lobo
2016-09-06  5:05 ` Brad Hubbard
2016-09-07  5:44   ` Elita Lobo
2016-09-07  6:18     ` Brad Hubbard
     [not found]       ` <CAA8xDw0mVqDLHuKHZU+x3uFnQf5WJ9NsXTJa_zMbRnvB=SB9Hw@mail.gmail.com>
2016-09-11 16:13         ` Elita Lobo

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.