All of lore.kernel.org
 help / color / mirror / Atom feed
* Assert in OSD::build_incremental_map_msg
@ 2011-12-16 17:07 Jim Schutt
  2011-12-16 17:56 ` Sage Weil
  0 siblings, 1 reply; 5+ messages in thread
From: Jim Schutt @ 2011-12-16 17:07 UTC (permalink / raw)
  To: ceph-devel@vger.kernel.org

Hi,

I've been seeing current master branch assert in
OSD::build_incremental_map_msg during peering when starting
a new filesystem for the first time.

This behavior bisects to commit 0807e7d523:

     hobject_t: make filestore_hobject_key_t 64 bits

     So we can return 0x100000000 when max=true.

     Signed-off-by: Sage Weil <sage.weil@dreamhost.com>


Here's an example of the assert:

(gdb) bt
#0  __memcpy_ssse3_back () at ../sysdeps/x86_64/multiarch/memcpy-ssse3-back.S:1631
#1  0x00000000008f4be7 in ceph::BackTrace::print (this=0x7f2b89908270, out=...) at common/BackTrace.cc:37
#2  0x00000000008e2627 in handle_fatal_signal (signum=11) at global/signal_handler.cc:103
#3  <signal handler called>
#4  __memcpy_ssse3_back () at ../sysdeps/x86_64/multiarch/memcpy-ssse3-back.S:1475
#5  0x00000000008f4be7 in ceph::BackTrace::print (this=0x7f2b89909030, out=...) at common/BackTrace.cc:37
#6  0x00000000008e2627 in handle_fatal_signal (signum=6) at global/signal_handler.cc:103
#7  <signal handler called>
#8  0x00007f2b9500f885 in raise (sig=6) at ../nptl/sysdeps/unix/sysv/linux/raise.c:64
#9  0x00007f2b95011065 in abort () at abort.c:92
#10 0x0000003be84bea7d in __gnu_cxx::__verbose_terminate_handler() () from /usr/lib64/libstdc++.so.6
#11 0x0000003be84bcc06 in ?? () from /usr/lib64/libstdc++.so.6
#12 0x0000003be84bcc33 in std::terminate() () from /usr/lib64/libstdc++.so.6
#13 0x0000003be84bcd2e in __cxa_throw () from /usr/lib64/libstdc++.so.6
#14 0x00000000008fd19d in ceph::__ceph_assert_fail (assertion=0xac97b0 "0 == \"missing an osdmap on disk\"",
     file=0xac777f "osd/OSD.cc", line=3662, func=0xacb240 "MOSDMap* OSD::build_incremental_map_msg(epoch_t, epoch_t)")
     at common/assert.cc:70
#15 0x000000000087b558 in OSD::build_incremental_map_msg (this=0x21d8000, since=16, to=22) at osd/OSD.cc:3662
#16 0x000000000087b95c in OSD::send_incremental_map (this=0x21d8000, since=16, inst=..., lazy=false) at osd/OSD.cc:3699
#17 0x0000000000870d20 in OSD::_share_map_outgoing (this=0x21d8000, inst=...) at osd/OSD.cc:2627
#18 0x0000000000866a5a in OSD::handle_osd_ping (this=0x21d8000, m=0x2542fc0) at osd/OSD.cc:1613
#19 0x00000000008712d3 in OSD::heartbeat_dispatch (this=0x21d8000, m=0x2542fc0) at osd/OSD.cc:2652
#20 0x00000000008962bd in OSD::HeartbeatDispatcher::ms_dispatch (this=0x21d8a48, m=0x2542fc0) at osd/OSD.h:283
#21 0x000000000091e941 in Messenger::ms_deliver_dispatch (this=0x21a0500, m=0x2542fc0) at msg/Messenger.h:102
#22 0x00000000009081b0 in SimpleMessenger::dispatch_entry (this=0x21a0500) at msg/SimpleMessenger.cc:360
#23 0x00000000007a0c0e in SimpleMessenger::DispatchThread::entry (this=0x21a0998) at msg/SimpleMessenger.h:544
#24 0x0000000000969d1b in Thread::_entry_func (arg=0x21a0998) at common/Thread.cc:41
#25 0x00007f2b95d057f1 in start_thread (arg=0x7f2b8990d700) at pthread_create.c:301
#26 0x00007f2b950c270d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:115


Thanks -- Jim


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

* Re: Assert in OSD::build_incremental_map_msg
  2011-12-16 17:07 Assert in OSD::build_incremental_map_msg Jim Schutt
@ 2011-12-16 17:56 ` Sage Weil
  2011-12-16 18:26   ` Jim Schutt
  0 siblings, 1 reply; 5+ messages in thread
From: Sage Weil @ 2011-12-16 17:56 UTC (permalink / raw)
  To: Jim Schutt; +Cc: ceph-devel@vger.kernel.org

Hi Jim,

Are you able to generate an osd log leading up to this crash?

	debug osd = 20
	debug filestore = 10
	debug ms = 1

sage


On Fri, 16 Dec 2011, Jim Schutt wrote:

> Hi,
> 
> I've been seeing current master branch assert in
> OSD::build_incremental_map_msg during peering when starting
> a new filesystem for the first time.
> 
> This behavior bisects to commit 0807e7d523:
> 
>     hobject_t: make filestore_hobject_key_t 64 bits
> 
>     So we can return 0x100000000 when max=true.
> 
>     Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
> 
> 
> Here's an example of the assert:
> 
> (gdb) bt
> #0  __memcpy_ssse3_back () at
> ../sysdeps/x86_64/multiarch/memcpy-ssse3-back.S:1631
> #1  0x00000000008f4be7 in ceph::BackTrace::print (this=0x7f2b89908270,
> out=...) at common/BackTrace.cc:37
> #2  0x00000000008e2627 in handle_fatal_signal (signum=11) at
> global/signal_handler.cc:103
> #3  <signal handler called>
> #4  __memcpy_ssse3_back () at
> ../sysdeps/x86_64/multiarch/memcpy-ssse3-back.S:1475
> #5  0x00000000008f4be7 in ceph::BackTrace::print (this=0x7f2b89909030,
> out=...) at common/BackTrace.cc:37
> #6  0x00000000008e2627 in handle_fatal_signal (signum=6) at
> global/signal_handler.cc:103
> #7  <signal handler called>
> #8  0x00007f2b9500f885 in raise (sig=6) at
> ../nptl/sysdeps/unix/sysv/linux/raise.c:64
> #9  0x00007f2b95011065 in abort () at abort.c:92
> #10 0x0000003be84bea7d in __gnu_cxx::__verbose_terminate_handler() () from
> /usr/lib64/libstdc++.so.6
> #11 0x0000003be84bcc06 in ?? () from /usr/lib64/libstdc++.so.6
> #12 0x0000003be84bcc33 in std::terminate() () from /usr/lib64/libstdc++.so.6
> #13 0x0000003be84bcd2e in __cxa_throw () from /usr/lib64/libstdc++.so.6
> #14 0x00000000008fd19d in ceph::__ceph_assert_fail (assertion=0xac97b0 "0 ==
> \"missing an osdmap on disk\"",
>     file=0xac777f "osd/OSD.cc", line=3662, func=0xacb240 "MOSDMap*
> OSD::build_incremental_map_msg(epoch_t, epoch_t)")
>     at common/assert.cc:70
> #15 0x000000000087b558 in OSD::build_incremental_map_msg (this=0x21d8000,
> since=16, to=22) at osd/OSD.cc:3662
> #16 0x000000000087b95c in OSD::send_incremental_map (this=0x21d8000, since=16,
> inst=..., lazy=false) at osd/OSD.cc:3699
> #17 0x0000000000870d20 in OSD::_share_map_outgoing (this=0x21d8000, inst=...)
> at osd/OSD.cc:2627
> #18 0x0000000000866a5a in OSD::handle_osd_ping (this=0x21d8000, m=0x2542fc0)
> at osd/OSD.cc:1613
> #19 0x00000000008712d3 in OSD::heartbeat_dispatch (this=0x21d8000,
> m=0x2542fc0) at osd/OSD.cc:2652
> #20 0x00000000008962bd in OSD::HeartbeatDispatcher::ms_dispatch
> (this=0x21d8a48, m=0x2542fc0) at osd/OSD.h:283
> #21 0x000000000091e941 in Messenger::ms_deliver_dispatch (this=0x21a0500,
> m=0x2542fc0) at msg/Messenger.h:102
> #22 0x00000000009081b0 in SimpleMessenger::dispatch_entry (this=0x21a0500) at
> msg/SimpleMessenger.cc:360
> #23 0x00000000007a0c0e in SimpleMessenger::DispatchThread::entry
> (this=0x21a0998) at msg/SimpleMessenger.h:544
> #24 0x0000000000969d1b in Thread::_entry_func (arg=0x21a0998) at
> common/Thread.cc:41
> #25 0x00007f2b95d057f1 in start_thread (arg=0x7f2b8990d700) at
> pthread_create.c:301
> #26 0x00007f2b950c270d in clone () at
> ../sysdeps/unix/sysv/linux/x86_64/clone.S:115
> 
> 
> Thanks -- Jim
> 
> --
> 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
> 
> 

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

* Re: Assert in OSD::build_incremental_map_msg
  2011-12-16 17:56 ` Sage Weil
@ 2011-12-16 18:26   ` Jim Schutt
  2011-12-16 22:43     ` Samuel Just
  0 siblings, 1 reply; 5+ messages in thread
From: Jim Schutt @ 2011-12-16 18:26 UTC (permalink / raw)
  To: Sage Weil; +Cc: ceph-devel@vger.kernel.org

On 12/16/2011 10:56 AM, Sage Weil wrote:
> Hi Jim,
>
> Are you able to generate an osd log leading up to this crash?
>
> 	debug osd = 20
> 	debug filestore = 10
> 	debug ms = 1

Sent by private email.

Thanks for taking a look.

-- Jim

>
> sage
>
>
> On Fri, 16 Dec 2011, Jim Schutt wrote:
>
>> Hi,
>>
>> I've been seeing current master branch assert in
>> OSD::build_incremental_map_msg during peering when starting
>> a new filesystem for the first time.
>>
>> This behavior bisects to commit 0807e7d523:
>>
>>      hobject_t: make filestore_hobject_key_t 64 bits
>>
>>      So we can return 0x100000000 when max=true.
>>
>>      Signed-off-by: Sage Weil<sage.weil@dreamhost.com>
>>
>>
>> Here's an example of the assert:
>>
>> (gdb) bt
>> #0  __memcpy_ssse3_back () at
>> ../sysdeps/x86_64/multiarch/memcpy-ssse3-back.S:1631
>> #1  0x00000000008f4be7 in ceph::BackTrace::print (this=0x7f2b89908270,
>> out=...) at common/BackTrace.cc:37
>> #2  0x00000000008e2627 in handle_fatal_signal (signum=11) at
>> global/signal_handler.cc:103
>> #3<signal handler called>
>> #4  __memcpy_ssse3_back () at
>> ../sysdeps/x86_64/multiarch/memcpy-ssse3-back.S:1475
>> #5  0x00000000008f4be7 in ceph::BackTrace::print (this=0x7f2b89909030,
>> out=...) at common/BackTrace.cc:37
>> #6  0x00000000008e2627 in handle_fatal_signal (signum=6) at
>> global/signal_handler.cc:103
>> #7<signal handler called>
>> #8  0x00007f2b9500f885 in raise (sig=6) at
>> ../nptl/sysdeps/unix/sysv/linux/raise.c:64
>> #9  0x00007f2b95011065 in abort () at abort.c:92
>> #10 0x0000003be84bea7d in __gnu_cxx::__verbose_terminate_handler() () from
>> /usr/lib64/libstdc++.so.6
>> #11 0x0000003be84bcc06 in ?? () from /usr/lib64/libstdc++.so.6
>> #12 0x0000003be84bcc33 in std::terminate() () from /usr/lib64/libstdc++.so.6
>> #13 0x0000003be84bcd2e in __cxa_throw () from /usr/lib64/libstdc++.so.6
>> #14 0x00000000008fd19d in ceph::__ceph_assert_fail (assertion=0xac97b0 "0 ==
>> \"missing an osdmap on disk\"",
>>      file=0xac777f "osd/OSD.cc", line=3662, func=0xacb240 "MOSDMap*
>> OSD::build_incremental_map_msg(epoch_t, epoch_t)")
>>      at common/assert.cc:70
>> #15 0x000000000087b558 in OSD::build_incremental_map_msg (this=0x21d8000,
>> since=16, to=22) at osd/OSD.cc:3662
>> #16 0x000000000087b95c in OSD::send_incremental_map (this=0x21d8000, since=16,
>> inst=..., lazy=false) at osd/OSD.cc:3699
>> #17 0x0000000000870d20 in OSD::_share_map_outgoing (this=0x21d8000, inst=...)
>> at osd/OSD.cc:2627
>> #18 0x0000000000866a5a in OSD::handle_osd_ping (this=0x21d8000, m=0x2542fc0)
>> at osd/OSD.cc:1613
>> #19 0x00000000008712d3 in OSD::heartbeat_dispatch (this=0x21d8000,
>> m=0x2542fc0) at osd/OSD.cc:2652
>> #20 0x00000000008962bd in OSD::HeartbeatDispatcher::ms_dispatch
>> (this=0x21d8a48, m=0x2542fc0) at osd/OSD.h:283
>> #21 0x000000000091e941 in Messenger::ms_deliver_dispatch (this=0x21a0500,
>> m=0x2542fc0) at msg/Messenger.h:102
>> #22 0x00000000009081b0 in SimpleMessenger::dispatch_entry (this=0x21a0500) at
>> msg/SimpleMessenger.cc:360
>> #23 0x00000000007a0c0e in SimpleMessenger::DispatchThread::entry
>> (this=0x21a0998) at msg/SimpleMessenger.h:544
>> #24 0x0000000000969d1b in Thread::_entry_func (arg=0x21a0998) at
>> common/Thread.cc:41
>> #25 0x00007f2b95d057f1 in start_thread (arg=0x7f2b8990d700) at
>> pthread_create.c:301
>> #26 0x00007f2b950c270d in clone () at
>> ../sysdeps/unix/sysv/linux/x86_64/clone.S:115
>>
>>
>> Thanks -- Jim
>>
>> --
>> 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
>>
>>
>
>



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

* Re: Assert in OSD::build_incremental_map_msg
  2011-12-16 18:26   ` Jim Schutt
@ 2011-12-16 22:43     ` Samuel Just
  2011-12-16 23:13       ` Jim Schutt
  0 siblings, 1 reply; 5+ messages in thread
From: Samuel Just @ 2011-12-16 22:43 UTC (permalink / raw)
  To: Jim Schutt; +Cc: Sage Weil, ceph-devel@vger.kernel.org

bfbde5b18525406fc3b678751459e989ea5d4977 in master should fix it.
-Sam

On Fri, Dec 16, 2011 at 10:26 AM, Jim Schutt <jaschut@sandia.gov> wrote:
> On 12/16/2011 10:56 AM, Sage Weil wrote:
>>
>> Hi Jim,
>>
>> Are you able to generate an osd log leading up to this crash?
>>
>>        debug osd = 20
>>        debug filestore = 10
>>        debug ms = 1
>
>
> Sent by private email.
>
> Thanks for taking a look.
>
> -- Jim
>
>
>>
>> sage
>>
>>
>> On Fri, 16 Dec 2011, Jim Schutt wrote:
>>
>>> Hi,
>>>
>>> I've been seeing current master branch assert in
>>> OSD::build_incremental_map_msg during peering when starting
>>> a new filesystem for the first time.
>>>
>>> This behavior bisects to commit 0807e7d523:
>>>
>>>     hobject_t: make filestore_hobject_key_t 64 bits
>>>
>>>     So we can return 0x100000000 when max=true.
>>>
>>>     Signed-off-by: Sage Weil<sage.weil@dreamhost.com>
>>>
>>>
>>> Here's an example of the assert:
>>>
>>> (gdb) bt
>>> #0  __memcpy_ssse3_back () at
>>> ../sysdeps/x86_64/multiarch/memcpy-ssse3-back.S:1631
>>> #1  0x00000000008f4be7 in ceph::BackTrace::print (this=0x7f2b89908270,
>>> out=...) at common/BackTrace.cc:37
>>> #2  0x00000000008e2627 in handle_fatal_signal (signum=11) at
>>> global/signal_handler.cc:103
>>> #3<signal handler called>
>>> #4  __memcpy_ssse3_back () at
>>> ../sysdeps/x86_64/multiarch/memcpy-ssse3-back.S:1475
>>> #5  0x00000000008f4be7 in ceph::BackTrace::print (this=0x7f2b89909030,
>>> out=...) at common/BackTrace.cc:37
>>> #6  0x00000000008e2627 in handle_fatal_signal (signum=6) at
>>> global/signal_handler.cc:103
>>> #7<signal handler called>
>>> #8  0x00007f2b9500f885 in raise (sig=6) at
>>> ../nptl/sysdeps/unix/sysv/linux/raise.c:64
>>> #9  0x00007f2b95011065 in abort () at abort.c:92
>>> #10 0x0000003be84bea7d in __gnu_cxx::__verbose_terminate_handler() ()
>>> from
>>> /usr/lib64/libstdc++.so.6
>>> #11 0x0000003be84bcc06 in ?? () from /usr/lib64/libstdc++.so.6
>>> #12 0x0000003be84bcc33 in std::terminate() () from
>>> /usr/lib64/libstdc++.so.6
>>> #13 0x0000003be84bcd2e in __cxa_throw () from /usr/lib64/libstdc++.so.6
>>> #14 0x00000000008fd19d in ceph::__ceph_assert_fail (assertion=0xac97b0 "0
>>> ==
>>> \"missing an osdmap on disk\"",
>>>     file=0xac777f "osd/OSD.cc", line=3662, func=0xacb240 "MOSDMap*
>>> OSD::build_incremental_map_msg(epoch_t, epoch_t)")
>>>     at common/assert.cc:70
>>> #15 0x000000000087b558 in OSD::build_incremental_map_msg (this=0x21d8000,
>>> since=16, to=22) at osd/OSD.cc:3662
>>> #16 0x000000000087b95c in OSD::send_incremental_map (this=0x21d8000,
>>> since=16,
>>> inst=..., lazy=false) at osd/OSD.cc:3699
>>> #17 0x0000000000870d20 in OSD::_share_map_outgoing (this=0x21d8000,
>>> inst=...)
>>> at osd/OSD.cc:2627
>>> #18 0x0000000000866a5a in OSD::handle_osd_ping (this=0x21d8000,
>>> m=0x2542fc0)
>>> at osd/OSD.cc:1613
>>> #19 0x00000000008712d3 in OSD::heartbeat_dispatch (this=0x21d8000,
>>> m=0x2542fc0) at osd/OSD.cc:2652
>>> #20 0x00000000008962bd in OSD::HeartbeatDispatcher::ms_dispatch
>>> (this=0x21d8a48, m=0x2542fc0) at osd/OSD.h:283
>>> #21 0x000000000091e941 in Messenger::ms_deliver_dispatch (this=0x21a0500,
>>> m=0x2542fc0) at msg/Messenger.h:102
>>> #22 0x00000000009081b0 in SimpleMessenger::dispatch_entry
>>> (this=0x21a0500) at
>>> msg/SimpleMessenger.cc:360
>>> #23 0x00000000007a0c0e in SimpleMessenger::DispatchThread::entry
>>> (this=0x21a0998) at msg/SimpleMessenger.h:544
>>> #24 0x0000000000969d1b in Thread::_entry_func (arg=0x21a0998) at
>>> common/Thread.cc:41
>>> #25 0x00007f2b95d057f1 in start_thread (arg=0x7f2b8990d700) at
>>> pthread_create.c:301
>>> #26 0x00007f2b950c270d in clone () at
>>> ../sysdeps/unix/sysv/linux/x86_64/clone.S:115
>>>
>>>
>>> Thanks -- Jim
>>>
>>> --
>>> 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
>>>
>>>
>>
>>
>
>
> --
> 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
--
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

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

* Re: Assert in OSD::build_incremental_map_msg
  2011-12-16 22:43     ` Samuel Just
@ 2011-12-16 23:13       ` Jim Schutt
  0 siblings, 0 replies; 5+ messages in thread
From: Jim Schutt @ 2011-12-16 23:13 UTC (permalink / raw)
  To: Samuel Just; +Cc: Sage Weil, ceph-devel@vger.kernel.org

On 12/16/2011 03:43 PM, Samuel Just wrote:
> bfbde5b18525406fc3b678751459e989ea5d4977 in master should fix it.

Great, thanks for taking a look.

-- Jim

> -Sam
>
> On Fri, Dec 16, 2011 at 10:26 AM, Jim Schutt<jaschut@sandia.gov>  wrote:
>> On 12/16/2011 10:56 AM, Sage Weil wrote:
>>>
>>> Hi Jim,
>>>
>>> Are you able to generate an osd log leading up to this crash?
>>>
>>>         debug osd = 20
>>>         debug filestore = 10
>>>         debug ms = 1
>>
>>
>> Sent by private email.
>>
>> Thanks for taking a look.
>>
>> -- Jim
>>


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

end of thread, other threads:[~2011-12-16 23:14 UTC | newest]

Thread overview: 5+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2011-12-16 17:07 Assert in OSD::build_incremental_map_msg Jim Schutt
2011-12-16 17:56 ` Sage Weil
2011-12-16 18:26   ` Jim Schutt
2011-12-16 22:43     ` Samuel Just
2011-12-16 23:13       ` Jim Schutt

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.