All of lore.kernel.org
 help / color / mirror / Atom feed
* fuse problem
@ 2011-05-19 11:12 huang jun
  2011-05-19 14:32 ` Brian Chrisman
  0 siblings, 1 reply; 11+ messages in thread
From: huang jun @ 2011-05-19 11:12 UTC (permalink / raw)
  To: ceph-devel

hi, all
i just encountered a problem about cfuse:
i mount cfsue successfully on /mnt by using
   "cfuse -m 192.168.0.170:6789 /mnt"
but when i enter /mnt directory, it shows that:
   [root@localhost mnt]# ll
   ls: .: Transport endpoint is not connected
my cfuse client is on centos5, it kernel version is 2.6.18
and OSD cluster is on debian5, 2.6.35
i don't know whether it related to SimpleMessenger,so anyone can give
me some prompts?

thanks!

^ permalink raw reply	[flat|nested] 11+ messages in thread

* Re: fuse problem
  2011-05-19 11:12 fuse problem huang jun
@ 2011-05-19 14:32 ` Brian Chrisman
  2011-05-19 23:52   ` huang jun
  0 siblings, 1 reply; 11+ messages in thread
From: Brian Chrisman @ 2011-05-19 14:32 UTC (permalink / raw)
  To: huang jun; +Cc: ceph-devel

On Thu, May 19, 2011 at 4:12 AM, huang jun <hjwsm1989@gmail.com> wrote:
> hi, all
> i just encountered a problem about cfuse:
> i mount cfsue successfully on /mnt by using
>   "cfuse -m 192.168.0.170:6789 /mnt"
> but when i enter /mnt directory, it shows that:
>   [root@localhost mnt]# ll
>   ls: .: Transport endpoint is not connected

This is a FUSE failure message that generally occurs when your
userspace process (in this case cfuse) has exited (closed its
connection to the FUSE kernel driver).
does 'ceph -s' show that your ceph cluster is up and healthy?
You may want to turn on client debugging to see why cfuse is exiting:
http://ceph.newdream.net/wiki/Debugging


> my cfuse client is on centos5, it kernel version is 2.6.18
> and OSD cluster is on debian5, 2.6.35
> i don't know whether it related to SimpleMessenger,so anyone can give
> me some prompts?
>
> thanks!
> --
> 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] 11+ messages in thread

* Re: fuse problem
  2011-05-19 14:32 ` Brian Chrisman
@ 2011-05-19 23:52   ` huang jun
  2011-05-20  0:47     ` Colin Patrick McCabe
  0 siblings, 1 reply; 11+ messages in thread
From: huang jun @ 2011-05-19 23:52 UTC (permalink / raw)
  To: Brian Chrisman; +Cc: ceph-devel

hi,brian
my 'ceph -s' shows everything is ok
and if i do it  on the other machine, i did not find this error.
i trun on the debug on ceph.conf like :
   [client]
       debug ms = 1
       debug client = 10
but i can't find where does this info goes to ?  not in /var/log/ceph/
so where should i look for this debug output?

thanks!

2011/5/19 Brian Chrisman <brchrisman@gmail.com>:
> On Thu, May 19, 2011 at 4:12 AM, huang jun <hjwsm1989@gmail.com> wrote:
>> hi, all
>> i just encountered a problem about cfuse:
>> i mount cfsue successfully on /mnt by using
>>   "cfuse -m 192.168.0.170:6789 /mnt"
>> but when i enter /mnt directory, it shows that:
>>   [root@localhost mnt]# ll
>>   ls: .: Transport endpoint is not connected
>
> This is a FUSE failure message that generally occurs when your
> userspace process (in this case cfuse) has exited (closed its
> connection to the FUSE kernel driver).
> does 'ceph -s' show that your ceph cluster is up and healthy?
> You may want to turn on client debugging to see why cfuse is exiting:
> http://ceph.newdream.net/wiki/Debugging
>
>
>> my cfuse client is on centos5, it kernel version is 2.6.18
>> and OSD cluster is on debian5, 2.6.35
>> i don't know whether it related to SimpleMessenger,so anyone can give
>> me some prompts?
>>
>> thanks!
>> --
>> 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] 11+ messages in thread

* Re: fuse problem
  2011-05-19 23:52   ` huang jun
@ 2011-05-20  0:47     ` Colin Patrick McCabe
  2011-05-20  1:01       ` huang jun
  0 siblings, 1 reply; 11+ messages in thread
From: Colin Patrick McCabe @ 2011-05-20  0:47 UTC (permalink / raw)
  To: huang jun; +Cc: Brian Chrisman, ceph-devel

Hi Huang,

cfuse is a client, so it will use whatever the logging settings are for clients.
you can set this by adding something like this to the [client] section
of your configuration file:

log_file = /my_log_file

You can also use this command-line switch to override the configuration:
--log-file=/my/log/file

cheers,
Colin


On Thu, May 19, 2011 at 4:52 PM, huang jun <hjwsm1989@gmail.com> wrote:
> hi,brian
> my 'ceph -s' shows everything is ok
> and if i do it  on the other machine, i did not find this error.
> i trun on the debug on ceph.conf like :
>   [client]
>       debug ms = 1
>       debug client = 10
> but i can't find where does this info goes to ?  not in /var/log/ceph/
> so where should i look for this debug output?
>
> thanks!
>
> 2011/5/19 Brian Chrisman <brchrisman@gmail.com>:
>> On Thu, May 19, 2011 at 4:12 AM, huang jun <hjwsm1989@gmail.com> wrote:
>>> hi, all
>>> i just encountered a problem about cfuse:
>>> i mount cfsue successfully on /mnt by using
>>>   "cfuse -m 192.168.0.170:6789 /mnt"
>>> but when i enter /mnt directory, it shows that:
>>>   [root@localhost mnt]# ll
>>>   ls: .: Transport endpoint is not connected
>>
>> This is a FUSE failure message that generally occurs when your
>> userspace process (in this case cfuse) has exited (closed its
>> connection to the FUSE kernel driver).
>> does 'ceph -s' show that your ceph cluster is up and healthy?
>> You may want to turn on client debugging to see why cfuse is exiting:
>> http://ceph.newdream.net/wiki/Debugging
>>
>>
>>> my cfuse client is on centos5, it kernel version is 2.6.18
>>> and OSD cluster is on debian5, 2.6.35
>>> i don't know whether it related to SimpleMessenger,so anyone can give
>>> me some prompts?
>>>
>>> thanks!
>>> --
>>> 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] 11+ messages in thread

* Re: fuse problem
  2011-05-20  0:47     ` Colin Patrick McCabe
@ 2011-05-20  1:01       ` huang jun
  2011-05-20  2:04         ` Colin Patrick McCabe
  0 siblings, 1 reply; 11+ messages in thread
From: huang jun @ 2011-05-20  1:01 UTC (permalink / raw)
  To: Colin Patrick McCabe; +Cc: ceph-devel

hi,colin
i try it as you said, but i can not see anything
 [client]
     log_file = /home/client_logfile
     debug ms = 1
     debug client = 10
     client cache size = 1024*1024*100
is there anything wrong with this setting?

thanks!
2011/5/20 Colin Patrick McCabe <colin.mccabe@dreamhost.com>:
> Hi Huang,
>
> cfuse is a client, so it will use whatever the logging settings are for clients.
> you can set this by adding something like this to the [client] section
> of your configuration file:
>
> log_file = /my_log_file
>
> You can also use this command-line switch to override the configuration:
> --log-file=/my/log/file
>
> cheers,
> Colin
>
>
> On Thu, May 19, 2011 at 4:52 PM, huang jun <hjwsm1989@gmail.com> wrote:
>> hi,brian
>> my 'ceph -s' shows everything is ok
>> and if i do it  on the other machine, i did not find this error.
>> i trun on the debug on ceph.conf like :
>>   [client]
>>       debug ms = 1
>>       debug client = 10
>> but i can't find where does this info goes to ?  not in /var/log/ceph/
>> so where should i look for this debug output?
>>
>> thanks!
>>
>> 2011/5/19 Brian Chrisman <brchrisman@gmail.com>:
>>> On Thu, May 19, 2011 at 4:12 AM, huang jun <hjwsm1989@gmail.com> wrote:
>>>> hi, all
>>>> i just encountered a problem about cfuse:
>>>> i mount cfsue successfully on /mnt by using
>>>>   "cfuse -m 192.168.0.170:6789 /mnt"
>>>> but when i enter /mnt directory, it shows that:
>>>>   [root@localhost mnt]# ll
>>>>   ls: .: Transport endpoint is not connected
>>>
>>> This is a FUSE failure message that generally occurs when your
>>> userspace process (in this case cfuse) has exited (closed its
>>> connection to the FUSE kernel driver).
>>> does 'ceph -s' show that your ceph cluster is up and healthy?
>>> You may want to turn on client debugging to see why cfuse is exiting:
>>> http://ceph.newdream.net/wiki/Debugging
>>>
>>>
>>>> my cfuse client is on centos5, it kernel version is 2.6.18
>>>> and OSD cluster is on debian5, 2.6.35
>>>> i don't know whether it related to SimpleMessenger,so anyone can give
>>>> me some prompts?
>>>>
>>>> thanks!
>>>> --
>>>> 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] 11+ messages in thread

* Re: fuse problem
  2011-05-20  1:01       ` huang jun
@ 2011-05-20  2:04         ` Colin Patrick McCabe
  2011-05-20  2:31           ` huang jun
  0 siblings, 1 reply; 11+ messages in thread
From: Colin Patrick McCabe @ 2011-05-20  2:04 UTC (permalink / raw)
  To: huang jun; +Cc: ceph-devel

Usually you don't have the ability to create directories or files in
/home unless you're root. Perhaps you should create
/home/client_logfile and give it the right permissions?

If that doesn't work, make sure you are editing the configuration that
you are actually using. You can force cfuse to use the configuration
you want with -c.

regards,
Colin


On Thu, May 19, 2011 at 6:01 PM, huang jun <hjwsm1989@gmail.com> wrote:
> hi,colin
> i try it as you said, but i can not see anything
>  [client]
>     log_file = /home/client_logfile
>     debug ms = 1
>     debug client = 10
>     client cache size = 1024*1024*100
> is there anything wrong with this setting?
>
> thanks!
> 2011/5/20 Colin Patrick McCabe <colin.mccabe@dreamhost.com>:
>> Hi Huang,
>>
>> cfuse is a client, so it will use whatever the logging settings are for clients.
>> you can set this by adding something like this to the [client] section
>> of your configuration file:
>>
>> log_file = /my_log_file
>>
>> You can also use this command-line switch to override the configuration:
>> --log-file=/my/log/file
>>
>> cheers,
>> Colin
>>
>>
>> On Thu, May 19, 2011 at 4:52 PM, huang jun <hjwsm1989@gmail.com> wrote:
>>> hi,brian
>>> my 'ceph -s' shows everything is ok
>>> and if i do it  on the other machine, i did not find this error.
>>> i trun on the debug on ceph.conf like :
>>>   [client]
>>>       debug ms = 1
>>>       debug client = 10
>>> but i can't find where does this info goes to ?  not in /var/log/ceph/
>>> so where should i look for this debug output?
>>>
>>> thanks!
>>>
>>> 2011/5/19 Brian Chrisman <brchrisman@gmail.com>:
>>>> On Thu, May 19, 2011 at 4:12 AM, huang jun <hjwsm1989@gmail.com> wrote:
>>>>> hi, all
>>>>> i just encountered a problem about cfuse:
>>>>> i mount cfsue successfully on /mnt by using
>>>>>   "cfuse -m 192.168.0.170:6789 /mnt"
>>>>> but when i enter /mnt directory, it shows that:
>>>>>   [root@localhost mnt]# ll
>>>>>   ls: .: Transport endpoint is not connected
>>>>
>>>> This is a FUSE failure message that generally occurs when your
>>>> userspace process (in this case cfuse) has exited (closed its
>>>> connection to the FUSE kernel driver).
>>>> does 'ceph -s' show that your ceph cluster is up and healthy?
>>>> You may want to turn on client debugging to see why cfuse is exiting:
>>>> http://ceph.newdream.net/wiki/Debugging
>>>>
>>>>
>>>>> my cfuse client is on centos5, it kernel version is 2.6.18
>>>>> and OSD cluster is on debian5, 2.6.35
>>>>> i don't know whether it related to SimpleMessenger,so anyone can give
>>>>> me some prompts?
>>>>>
>>>>> thanks!
>>>>> --
>>>>> 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] 11+ messages in thread

* Re: fuse problem
  2011-05-20  2:04         ` Colin Patrick McCabe
@ 2011-05-20  2:31           ` huang jun
  2011-05-20  3:13             ` huang jun
  2011-05-20 17:25             ` Colin Patrick McCabe
  0 siblings, 2 replies; 11+ messages in thread
From: huang jun @ 2011-05-20  2:31 UTC (permalink / raw)
  To: Colin Patrick McCabe; +Cc: ceph-devel

unfortunately, i tried all what you have told me, but no one
works.there still nothing
in /home/client_logfile:
     huangjun:/mnt# ll /home/client_logfile
     -rwxrwxrwx 1 root root 1 2011-05-19 20:57 /home/client_logfile
but i think this is not so seriously, i have a problem confused me a lot.
i list what i have done
1) [root@localhost /]# cfuse  -o nonempty -m 192.168.0.11:6789 /mnt/
      ARNING: bsdocfs inode numbers are 64 bits wide, and FUSE on
32-bit kernels does
         not cope well with that situation.  Expect to crash shortly.

     cfuse[3771]: starting bsdocfs client
     2011-05-20 10:27:06.655823 b7fe16d0 thread 3086879632 start
     2011-05-20 10:27:06.656084 b7fe16d0 thread 3076389776 start
     2011-05-20 10:27:06.656229 b7fe16d0 thread 3065899920 start
     2011-05-20 10:27:06.656345 b7fe16d0 thread 3055410064 start
     2011-05-20 10:27:06.656508 b7fe16d0 thread 3044920208 start
     2011-05-20 10:27:06.656982 b7fe16d0 thread 3034430352 start
     2011-05-20 10:27:06.661384 b4ddbb90 thread 3033377680 start
     2011-05-20 10:27:06.663117 b7fe16d0 thread 3032325008 start
     2011-05-20 10:27:06.667000 b4bd9b90 thread 3031272336 start
     2011-05-20 10:27:06.870996 b4ad8b90 reader got ack seq 1 >= 1 on
0xa1a4d38      client_session(request_open) v1
     2011-05-20 10:27:07.285882 b4ad8b90 reader got ack seq 3 >= 2 on
0xa1a55c8 client_session(request_renewcaps seq 1) v1
     2011-05-20 10:27:07.286002 b4ad8b90 reader got ack seq 3 >= 3 on
0xa1a56f8  client_request(client5467:1 getattr pAsLsXsFs #1) v1
     cfuse[3771]: starting fuse
2) [root@localhost /]# df -TH
Filesystem    Type     Size   Used  Avail Use% Mounted on
/dev/mapper/VolGroup00-LogVol00
              ext3     305G   4.2G   285G   2% /
/dev/sda1     ext3     104M    19M    80M  20% /boot
tmpfs        tmpfs     2.1G      0   2.1G   0% /dev/shm
fuse          fuse      12T    38G    11T   1% /mnt
3) [root@localhost mnt]# cd /mnt &&  mkdir ss
mkdir: cannot create directory `ss': Transport endpoint is not connected

4) i ckeck the mon of osd clustrt state
   T02-MON11:~# ceph  -s
2011-05-20 10:18:16.120627    pg v3447: 3960 pgs: 3960 active+clean;
35200 MB data, 33363 MB used, 10212 GB / 10246 GB avail
2011-05-20 10:18:16.126746   mds e21: 1/1/1 up {0=up:active}
2011-05-20 10:18:16.126772   osd e469: 14 osds: 14 up, 14 in
2011-05-20 10:18:16.126897   mon e1: 1 mons at {0=192.168.0.11:6789/0}

so where can i find the wrong point? i just can't do any operation in /mnt
thank you very much!

2011/5/20 Colin Patrick McCabe <colin.mccabe@dreamhost.com>:
> Usually you don't have the ability to create directories or files in
> /home unless you're root. Perhaps you should create
> /home/client_logfile and give it the right permissions?
>
> If that doesn't work, make sure you are editing the configuration that
> you are actually using. You can force cfuse to use the configuration
> you want with -c.
>
> regards,
> Colin
>
>
> On Thu, May 19, 2011 at 6:01 PM, huang jun <hjwsm1989@gmail.com> wrote:
>> hi,colin
>> i try it as you said, but i can not see anything
>>  [client]
>>     log_file = /home/client_logfile
>>     debug ms = 1
>>     debug client = 10
>>     client cache size = 1024*1024*100
>> is there anything wrong with this setting?
>>
>> thanks!
>> 2011/5/20 Colin Patrick McCabe <colin.mccabe@dreamhost.com>:
>>> Hi Huang,
>>>
>>> cfuse is a client, so it will use whatever the logging settings are for clients.
>>> you can set this by adding something like this to the [client] section
>>> of your configuration file:
>>>
>>> log_file = /my_log_file
>>>
>>> You can also use this command-line switch to override the configuration:
>>> --log-file=/my/log/file
>>>
>>> cheers,
>>> Colin
>>>
>>>
>>> On Thu, May 19, 2011 at 4:52 PM, huang jun <hjwsm1989@gmail.com> wrote:
>>>> hi,brian
>>>> my 'ceph -s' shows everything is ok
>>>> and if i do it  on the other machine, i did not find this error.
>>>> i trun on the debug on ceph.conf like :
>>>>   [client]
>>>>       debug ms = 1
>>>>       debug client = 10
>>>> but i can't find where does this info goes to ?  not in /var/log/ceph/
>>>> so where should i look for this debug output?
>>>>
>>>> thanks!
>>>>
>>>> 2011/5/19 Brian Chrisman <brchrisman@gmail.com>:
>>>>> On Thu, May 19, 2011 at 4:12 AM, huang jun <hjwsm1989@gmail.com> wrote:
>>>>>> hi, all
>>>>>> i just encountered a problem about cfuse:
>>>>>> i mount cfsue successfully on /mnt by using
>>>>>>   "cfuse -m 192.168.0.170:6789 /mnt"
>>>>>> but when i enter /mnt directory, it shows that:
>>>>>>   [root@localhost mnt]# ll
>>>>>>   ls: .: Transport endpoint is not connected
>>>>>
>>>>> This is a FUSE failure message that generally occurs when your
>>>>> userspace process (in this case cfuse) has exited (closed its
>>>>> connection to the FUSE kernel driver).
>>>>> does 'ceph -s' show that your ceph cluster is up and healthy?
>>>>> You may want to turn on client debugging to see why cfuse is exiting:
>>>>> http://ceph.newdream.net/wiki/Debugging
>>>>>
>>>>>
>>>>>> my cfuse client is on centos5, it kernel version is 2.6.18
>>>>>> and OSD cluster is on debian5, 2.6.35
>>>>>> i don't know whether it related to SimpleMessenger,so anyone can give
>>>>>> me some prompts?
>>>>>>
>>>>>> thanks!
>>>>>> --
>>>>>> 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] 11+ messages in thread

* Re: fuse problem
  2011-05-20  2:31           ` huang jun
@ 2011-05-20  3:13             ` huang jun
  2011-05-20 17:25             ` Colin Patrick McCabe
  1 sibling, 0 replies; 11+ messages in thread
From: huang jun @ 2011-05-20  3:13 UTC (permalink / raw)
  To: Colin Patrick McCabe; +Cc: ceph-devel, brchrisman

thanks,all
i find the problem, as Brian Chrisman said,the cfuse process exited,so
i need to find why it exits.
the output of debug below:
2011-05-20 11:09:06.531980 b7ff56d0 thread 3086961552 start
2011-05-20 11:09:06.532043 b7ff56d0 thread 3076471696 start
2011-05-20 11:09:06.532061 b7ff56d0 thread 3065981840 start
2011-05-20 11:09:06.532081 b7ff56d0 thread 3055491984 start
2011-05-20 11:09:06.532100 b7ff56d0 thread 3045002128 start
2011-05-20 11:09:06.532319 b7ff56d0 thread 3034512272 start
2011-05-20 11:09:06.533669 b4defb90 thread 3033459600 start
2011-05-20 11:09:06.535570 b7ff56d0 thread 3032406928 start
2011-05-20 11:09:06.536743 b4bedb90 thread 3031354256 start
2011-05-20 11:09:06.541680 b4aecb90 reader got ack seq 1 >= 1 on
0x8276cf0 client_session(request_
open) v1
2011-05-20 11:09:06.542535 b4aecb90 reader got ack seq 2 >= 2 on
0x8277918 client_session(request_
renewcaps seq 1) v1
2011-05-20 11:09:06.543546 b4aecb90 reader got ack seq 3 >= 3 on
0x8277a48 client_request(client41
03:1 getattr pAsLsXsFs #1) v1
2011-05-20 11:09:07.536841 b4aecb90 reader got ack seq 4 >= 4 on
0x8276cf0 client_session(request_
renewcaps seq 2) v1
2011-05-20 11:09:20.722233 b4aecb90 reader got ack seq 5 >= 5 on
0x8279c08 client_request(client41
03:2 readdir #1) v1
client/Client.cc: In function 'Inode* Client::_ll_get_inode(vinodeno_t)':
client/Client.cc:5497: FAILED assert(inode_map.count(vino))
 1: /usr/bin/cfuse [0x80badbf]
 2: (Client::ll_getattr(vinodeno_t, stat*, int, int)+0xce) [0x80e2b1e]
 3: /usr/bin/cfuse [0x80b8867]
 4: /lib/libfuse.so.2 [0xfcb402]
 5: /lib/libfuse.so.2 [0xfcbead]
 6: (fuse_session_process()+0x26) [0xfcd9a6]
 7: (fuse_session_loop()+0x95) [0xfc9925]
 8: (ceph_fuse_ll_main(Client*, int, char const**, int)+0x175) [0x80b6eb5]
 9: (main()+0x2d4) [0x8095f24]
 10: (__libc_start_main()+0xdc) [0x68ce9c]
 11: (__gxx_personality_v0()+0x3e9) [0x8095b21]
 NOTE: a copy of the executable, or `objdump -rdS <executable>` is
needed to interpret this.
*** Caught signal (Aborted) ***
in thread b7ff56d0

 1: /usr/bin/cfuse [0x81e28a7]
 2: [0x5cb420]
 3: [0x5cb410]
 4: (gsignal()+0x50) [0x69fdf0]
 5: (abort()+0x101) [0x6a1701]
 6: (__gnu_cxx::__verbose_terminate_handler()+0x150) [0x929b50]
 7: /usr/lib/libstdc++.so.6 [0x927555]
 8: /usr/lib/libstdc++.so.6 [0x927592]
 9: /usr/lib/libstdc++.so.6 [0x9276ca]
 a: (ceph::__ceph_assert_fail(char const*, char const*, int, char
const*)+0x264) [0x81ce944]
 b: /usr/bin/cfuse [0x80badbf]
 c: (Client::ll_getattr(vinodeno_t, stat*, int, int)+0xce) [0x80e2b1e]
 d: /usr/bin/cfuse [0x80b8867]
 e: /lib/libfuse.so.2 [0xfcb402]
 f: /lib/libfuse.so.2 [0xfcbead]
 10: (fuse_session_process()+0x26) [0xfcd9a6]
 11: (fuse_session_loop()+0x95) [0xfc9925]
 12: (ceph_fuse_ll_main(Client*, int, char const**, int)+0x175) [0x80b6eb5]
 13: (main()+0x2d4) [0x8095f24]
 14: (__libc_start_main()+0xdc) [0x68ce9c]
 15: (__gxx_personality_v0()+0x3e9) [0x8095b21]
(END)

does can be fixed? i'm use cfuse client on centos 5.5
thanks!

2011/5/20 huang jun <hjwsm1989@gmail.com>:
> unfortunately, i tried all what you have told me, but no one
> works.there still nothing
> in /home/client_logfile:
>     huangjun:/mnt# ll /home/client_logfile
>     -rwxrwxrwx 1 root root 1 2011-05-19 20:57 /home/client_logfile
> but i think this is not so seriously, i have a problem confused me a lot.
> i list what i have done
> 1) [root@localhost /]# cfuse  -o nonempty -m 192.168.0.11:6789 /mnt/
>      ARNING: bsdocfs inode numbers are 64 bits wide, and FUSE on
> 32-bit kernels does
>         not cope well with that situation.  Expect to crash shortly.
>
>     cfuse[3771]: starting bsdocfs client
>     2011-05-20 10:27:06.655823 b7fe16d0 thread 3086879632 start
>     2011-05-20 10:27:06.656084 b7fe16d0 thread 3076389776 start
>     2011-05-20 10:27:06.656229 b7fe16d0 thread 3065899920 start
>     2011-05-20 10:27:06.656345 b7fe16d0 thread 3055410064 start
>     2011-05-20 10:27:06.656508 b7fe16d0 thread 3044920208 start
>     2011-05-20 10:27:06.656982 b7fe16d0 thread 3034430352 start
>     2011-05-20 10:27:06.661384 b4ddbb90 thread 3033377680 start
>     2011-05-20 10:27:06.663117 b7fe16d0 thread 3032325008 start
>     2011-05-20 10:27:06.667000 b4bd9b90 thread 3031272336 start
>     2011-05-20 10:27:06.870996 b4ad8b90 reader got ack seq 1 >= 1 on
> 0xa1a4d38      client_session(request_open) v1
>     2011-05-20 10:27:07.285882 b4ad8b90 reader got ack seq 3 >= 2 on
> 0xa1a55c8 client_session(request_renewcaps seq 1) v1
>     2011-05-20 10:27:07.286002 b4ad8b90 reader got ack seq 3 >= 3 on
> 0xa1a56f8  client_request(client5467:1 getattr pAsLsXsFs #1) v1
>     cfuse[3771]: starting fuse
> 2) [root@localhost /]# df -TH
> Filesystem    Type     Size   Used  Avail Use% Mounted on
> /dev/mapper/VolGroup00-LogVol00
>              ext3     305G   4.2G   285G   2% /
> /dev/sda1     ext3     104M    19M    80M  20% /boot
> tmpfs        tmpfs     2.1G      0   2.1G   0% /dev/shm
> fuse          fuse      12T    38G    11T   1% /mnt
> 3) [root@localhost mnt]# cd /mnt &&  mkdir ss
> mkdir: cannot create directory `ss': Transport endpoint is not connected
>
> 4) i ckeck the mon of osd clustrt state
>   T02-MON11:~# ceph  -s
> 2011-05-20 10:18:16.120627    pg v3447: 3960 pgs: 3960 active+clean;
> 35200 MB data, 33363 MB used, 10212 GB / 10246 GB avail
> 2011-05-20 10:18:16.126746   mds e21: 1/1/1 up {0=up:active}
> 2011-05-20 10:18:16.126772   osd e469: 14 osds: 14 up, 14 in
> 2011-05-20 10:18:16.126897   mon e1: 1 mons at {0=192.168.0.11:6789/0}
>
> so where can i find the wrong point? i just can't do any operation in /mnt
> thank you very much!
>
> 2011/5/20 Colin Patrick McCabe <colin.mccabe@dreamhost.com>:
>> Usually you don't have the ability to create directories or files in
>> /home unless you're root. Perhaps you should create
>> /home/client_logfile and give it the right permissions?
>>
>> If that doesn't work, make sure you are editing the configuration that
>> you are actually using. You can force cfuse to use the configuration
>> you want with -c.
>>
>> regards,
>> Colin
>>
>>
>> On Thu, May 19, 2011 at 6:01 PM, huang jun <hjwsm1989@gmail.com> wrote:
>>> hi,colin
>>> i try it as you said, but i can not see anything
>>>  [client]
>>>     log_file = /home/client_logfile
>>>     debug ms = 1
>>>     debug client = 10
>>>     client cache size = 1024*1024*100
>>> is there anything wrong with this setting?
>>>
>>> thanks!
>>> 2011/5/20 Colin Patrick McCabe <colin.mccabe@dreamhost.com>:
>>>> Hi Huang,
>>>>
>>>> cfuse is a client, so it will use whatever the logging settings are for clients.
>>>> you can set this by adding something like this to the [client] section
>>>> of your configuration file:
>>>>
>>>> log_file = /my_log_file
>>>>
>>>> You can also use this command-line switch to override the configuration:
>>>> --log-file=/my/log/file
>>>>
>>>> cheers,
>>>> Colin
>>>>
>>>>
>>>> On Thu, May 19, 2011 at 4:52 PM, huang jun <hjwsm1989@gmail.com> wrote:
>>>>> hi,brian
>>>>> my 'ceph -s' shows everything is ok
>>>>> and if i do it  on the other machine, i did not find this error.
>>>>> i trun on the debug on ceph.conf like :
>>>>>   [client]
>>>>>       debug ms = 1
>>>>>       debug client = 10
>>>>> but i can't find where does this info goes to ?  not in /var/log/ceph/
>>>>> so where should i look for this debug output?
>>>>>
>>>>> thanks!
>>>>>
>>>>> 2011/5/19 Brian Chrisman <brchrisman@gmail.com>:
>>>>>> On Thu, May 19, 2011 at 4:12 AM, huang jun <hjwsm1989@gmail.com> wrote:
>>>>>>> hi, all
>>>>>>> i just encountered a problem about cfuse:
>>>>>>> i mount cfsue successfully on /mnt by using
>>>>>>>   "cfuse -m 192.168.0.170:6789 /mnt"
>>>>>>> but when i enter /mnt directory, it shows that:
>>>>>>>   [root@localhost mnt]# ll
>>>>>>>   ls: .: Transport endpoint is not connected
>>>>>>
>>>>>> This is a FUSE failure message that generally occurs when your
>>>>>> userspace process (in this case cfuse) has exited (closed its
>>>>>> connection to the FUSE kernel driver).
>>>>>> does 'ceph -s' show that your ceph cluster is up and healthy?
>>>>>> You may want to turn on client debugging to see why cfuse is exiting:
>>>>>> http://ceph.newdream.net/wiki/Debugging
>>>>>>
>>>>>>
>>>>>>> my cfuse client is on centos5, it kernel version is 2.6.18
>>>>>>> and OSD cluster is on debian5, 2.6.35
>>>>>>> i don't know whether it related to SimpleMessenger,so anyone can give
>>>>>>> me some prompts?
>>>>>>>
>>>>>>> thanks!
>>>>>>> --
>>>>>>> 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] 11+ messages in thread

* Re: fuse problem
  2011-05-20  2:31           ` huang jun
  2011-05-20  3:13             ` huang jun
@ 2011-05-20 17:25             ` Colin Patrick McCabe
  2011-05-23 23:53               ` huang jun
  1 sibling, 1 reply; 11+ messages in thread
From: Colin Patrick McCabe @ 2011-05-20 17:25 UTC (permalink / raw)
  To: huang jun; +Cc: ceph-devel

On Thu, May 19, 2011 at 7:31 PM, huang jun <hjwsm1989@gmail.com> wrote:
> unfortunately, i tried all what you have told me, but no one
> works.there still nothing
> in /home/client_logfile:
>     huangjun:/mnt# ll /home/client_logfile
>     -rwxrwxrwx 1 root root 1 2011-05-19 20:57 /home/client_logfile
> but i think this is not so seriously, i have a problem confused me a lot.
> i list what i have done
> 1) [root@localhost /]# cfuse  -o nonempty -m 192.168.0.11:6789 /mnt/
>      ARNING: bsdocfs inode numbers are 64 bits wide, and FUSE on
> 32-bit kernels does
>         not cope well with that situation.  Expect to crash shortly.

Perhaps it has something to do with this message:

WARNING: Ceph inode numbers are 64 bits wide, and FUSE on 32-bit kernels does
not cope well with that situation.  Expect to crash shortly.

cheers,
Colin


>
>     cfuse[3771]: starting bsdocfs client
>     2011-05-20 10:27:06.655823 b7fe16d0 thread 3086879632 start
>     2011-05-20 10:27:06.656084 b7fe16d0 thread 3076389776 start
>     2011-05-20 10:27:06.656229 b7fe16d0 thread 3065899920 start
>     2011-05-20 10:27:06.656345 b7fe16d0 thread 3055410064 start
>     2011-05-20 10:27:06.656508 b7fe16d0 thread 3044920208 start
>     2011-05-20 10:27:06.656982 b7fe16d0 thread 3034430352 start
>     2011-05-20 10:27:06.661384 b4ddbb90 thread 3033377680 start
>     2011-05-20 10:27:06.663117 b7fe16d0 thread 3032325008 start
>     2011-05-20 10:27:06.667000 b4bd9b90 thread 3031272336 start
>     2011-05-20 10:27:06.870996 b4ad8b90 reader got ack seq 1 >= 1 on
> 0xa1a4d38      client_session(request_open) v1
>     2011-05-20 10:27:07.285882 b4ad8b90 reader got ack seq 3 >= 2 on
> 0xa1a55c8 client_session(request_renewcaps seq 1) v1
>     2011-05-20 10:27:07.286002 b4ad8b90 reader got ack seq 3 >= 3 on
> 0xa1a56f8  client_request(client5467:1 getattr pAsLsXsFs #1) v1
>     cfuse[3771]: starting fuse
> 2) [root@localhost /]# df -TH
> Filesystem    Type     Size   Used  Avail Use% Mounted on
> /dev/mapper/VolGroup00-LogVol00
>              ext3     305G   4.2G   285G   2% /
> /dev/sda1     ext3     104M    19M    80M  20% /boot
> tmpfs        tmpfs     2.1G      0   2.1G   0% /dev/shm
> fuse          fuse      12T    38G    11T   1% /mnt
> 3) [root@localhost mnt]# cd /mnt &&  mkdir ss
> mkdir: cannot create directory `ss': Transport endpoint is not connected
>
> 4) i ckeck the mon of osd clustrt state
>   T02-MON11:~# ceph  -s
> 2011-05-20 10:18:16.120627    pg v3447: 3960 pgs: 3960 active+clean;
> 35200 MB data, 33363 MB used, 10212 GB / 10246 GB avail
> 2011-05-20 10:18:16.126746   mds e21: 1/1/1 up {0=up:active}
> 2011-05-20 10:18:16.126772   osd e469: 14 osds: 14 up, 14 in
> 2011-05-20 10:18:16.126897   mon e1: 1 mons at {0=192.168.0.11:6789/0}
>
> so where can i find the wrong point? i just can't do any operation in /mnt
> thank you very much!
>
> 2011/5/20 Colin Patrick McCabe <colin.mccabe@dreamhost.com>:
>> Usually you don't have the ability to create directories or files in
>> /home unless you're root. Perhaps you should create
>> /home/client_logfile and give it the right permissions?
>>
>> If that doesn't work, make sure you are editing the configuration that
>> you are actually using. You can force cfuse to use the configuration
>> you want with -c.
>>
>> regards,
>> Colin
>>
>>
>> On Thu, May 19, 2011 at 6:01 PM, huang jun <hjwsm1989@gmail.com> wrote:
>>> hi,colin
>>> i try it as you said, but i can not see anything
>>>  [client]
>>>     log_file = /home/client_logfile
>>>     debug ms = 1
>>>     debug client = 10
>>>     client cache size = 1024*1024*100
>>> is there anything wrong with this setting?
>>>
>>> thanks!
>>> 2011/5/20 Colin Patrick McCabe <colin.mccabe@dreamhost.com>:
>>>> Hi Huang,
>>>>
>>>> cfuse is a client, so it will use whatever the logging settings are for clients.
>>>> you can set this by adding something like this to the [client] section
>>>> of your configuration file:
>>>>
>>>> log_file = /my_log_file
>>>>
>>>> You can also use this command-line switch to override the configuration:
>>>> --log-file=/my/log/file
>>>>
>>>> cheers,
>>>> Colin
>>>>
>>>>
>>>> On Thu, May 19, 2011 at 4:52 PM, huang jun <hjwsm1989@gmail.com> wrote:
>>>>> hi,brian
>>>>> my 'ceph -s' shows everything is ok
>>>>> and if i do it  on the other machine, i did not find this error.
>>>>> i trun on the debug on ceph.conf like :
>>>>>   [client]
>>>>>       debug ms = 1
>>>>>       debug client = 10
>>>>> but i can't find where does this info goes to ?  not in /var/log/ceph/
>>>>> so where should i look for this debug output?
>>>>>
>>>>> thanks!
>>>>>
>>>>> 2011/5/19 Brian Chrisman <brchrisman@gmail.com>:
>>>>>> On Thu, May 19, 2011 at 4:12 AM, huang jun <hjwsm1989@gmail.com> wrote:
>>>>>>> hi, all
>>>>>>> i just encountered a problem about cfuse:
>>>>>>> i mount cfsue successfully on /mnt by using
>>>>>>>   "cfuse -m 192.168.0.170:6789 /mnt"
>>>>>>> but when i enter /mnt directory, it shows that:
>>>>>>>   [root@localhost mnt]# ll
>>>>>>>   ls: .: Transport endpoint is not connected
>>>>>>
>>>>>> This is a FUSE failure message that generally occurs when your
>>>>>> userspace process (in this case cfuse) has exited (closed its
>>>>>> connection to the FUSE kernel driver).
>>>>>> does 'ceph -s' show that your ceph cluster is up and healthy?
>>>>>> You may want to turn on client debugging to see why cfuse is exiting:
>>>>>> http://ceph.newdream.net/wiki/Debugging
>>>>>>
>>>>>>
>>>>>>> my cfuse client is on centos5, it kernel version is 2.6.18
>>>>>>> and OSD cluster is on debian5, 2.6.35
>>>>>>> i don't know whether it related to SimpleMessenger,so anyone can give
>>>>>>> me some prompts?
>>>>>>>
>>>>>>> thanks!
>>>>>>> --
>>>>>>> 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] 11+ messages in thread

* Re: fuse problem
  2011-05-20 17:25             ` Colin Patrick McCabe
@ 2011-05-23 23:53               ` huang jun
  2011-05-24 21:11                 ` Colin Patrick McCabe
  0 siblings, 1 reply; 11+ messages in thread
From: huang jun @ 2011-05-23 23:53 UTC (permalink / raw)
  To: Colin Patrick McCabe; +Cc: ceph-devel

thanks,colin
    do you think that now we can not use 32bit cfuse client to mount
on 64 OSD cluster?
but i mount cfuse on the machine that also running cosd,cmds,cmon
process,it also
failed to operate.
    just like :
    WARNING: ceph inode numbers are 64 bits wide, and FUSE on 32-bit
kernels does
         not cope well with that situation.  Expect to crash shortly.
   i want to note that the cfuse client and OSD cluster  on  same
machine, so why this WARING turn up?

2011/5/21 Colin Patrick McCabe <colin.mccabe@dreamhost.com>:
> On Thu, May 19, 2011 at 7:31 PM, huang jun <hjwsm1989@gmail.com> wrote:
>> unfortunately, i tried all what you have told me, but no one
>> works.there still nothing
>> in /home/client_logfile:
>>     huangjun:/mnt# ll /home/client_logfile
>>     -rwxrwxrwx 1 root root 1 2011-05-19 20:57 /home/client_logfile
>> but i think this is not so seriously, i have a problem confused me a lot.
>> i list what i have done
>> 1) [root@localhost /]# cfuse  -o nonempty -m 192.168.0.11:6789 /mnt/
>>      ARNING: bsdocfs inode numbers are 64 bits wide, and FUSE on
>> 32-bit kernels does
>>         not cope well with that situation.  Expect to crash shortly.
>
> Perhaps it has something to do with this message:
>
> WARNING: Ceph inode numbers are 64 bits wide, and FUSE on 32-bit kernels does
> not cope well with that situation.  Expect to crash shortly.
>
> cheers,
> Colin
>
>
>>
>>     cfuse[3771]: starting bsdocfs client
>>     2011-05-20 10:27:06.655823 b7fe16d0 thread 3086879632 start
>>     2011-05-20 10:27:06.656084 b7fe16d0 thread 3076389776 start
>>     2011-05-20 10:27:06.656229 b7fe16d0 thread 3065899920 start
>>     2011-05-20 10:27:06.656345 b7fe16d0 thread 3055410064 start
>>     2011-05-20 10:27:06.656508 b7fe16d0 thread 3044920208 start
>>     2011-05-20 10:27:06.656982 b7fe16d0 thread 3034430352 start
>>     2011-05-20 10:27:06.661384 b4ddbb90 thread 3033377680 start
>>     2011-05-20 10:27:06.663117 b7fe16d0 thread 3032325008 start
>>     2011-05-20 10:27:06.667000 b4bd9b90 thread 3031272336 start
>>     2011-05-20 10:27:06.870996 b4ad8b90 reader got ack seq 1 >= 1 on
>> 0xa1a4d38      client_session(request_open) v1
>>     2011-05-20 10:27:07.285882 b4ad8b90 reader got ack seq 3 >= 2 on
>> 0xa1a55c8 client_session(request_renewcaps seq 1) v1
>>     2011-05-20 10:27:07.286002 b4ad8b90 reader got ack seq 3 >= 3 on
>> 0xa1a56f8  client_request(client5467:1 getattr pAsLsXsFs #1) v1
>>     cfuse[3771]: starting fuse
>> 2) [root@localhost /]# df -TH
>> Filesystem    Type     Size   Used  Avail Use% Mounted on
>> /dev/mapper/VolGroup00-LogVol00
>>              ext3     305G   4.2G   285G   2% /
>> /dev/sda1     ext3     104M    19M    80M  20% /boot
>> tmpfs        tmpfs     2.1G      0   2.1G   0% /dev/shm
>> fuse          fuse      12T    38G    11T   1% /mnt
>> 3) [root@localhost mnt]# cd /mnt &&  mkdir ss
>> mkdir: cannot create directory `ss': Transport endpoint is not connected
>>
>> 4) i ckeck the mon of osd clustrt state
>>   T02-MON11:~# ceph  -s
>> 2011-05-20 10:18:16.120627    pg v3447: 3960 pgs: 3960 active+clean;
>> 35200 MB data, 33363 MB used, 10212 GB / 10246 GB avail
>> 2011-05-20 10:18:16.126746   mds e21: 1/1/1 up {0=up:active}
>> 2011-05-20 10:18:16.126772   osd e469: 14 osds: 14 up, 14 in
>> 2011-05-20 10:18:16.126897   mon e1: 1 mons at {0=192.168.0.11:6789/0}
>>
>> so where can i find the wrong point? i just can't do any operation in /mnt
>> thank you very much!
>>
>> 2011/5/20 Colin Patrick McCabe <colin.mccabe@dreamhost.com>:
>>> Usually you don't have the ability to create directories or files in
>>> /home unless you're root. Perhaps you should create
>>> /home/client_logfile and give it the right permissions?
>>>
>>> If that doesn't work, make sure you are editing the configuration that
>>> you are actually using. You can force cfuse to use the configuration
>>> you want with -c.
>>>
>>> regards,
>>> Colin
>>>
>>>
>>> On Thu, May 19, 2011 at 6:01 PM, huang jun <hjwsm1989@gmail.com> wrote:
>>>> hi,colin
>>>> i try it as you said, but i can not see anything
>>>>  [client]
>>>>     log_file = /home/client_logfile
>>>>     debug ms = 1
>>>>     debug client = 10
>>>>     client cache size = 1024*1024*100
>>>> is there anything wrong with this setting?
>>>>
>>>> thanks!
>>>> 2011/5/20 Colin Patrick McCabe <colin.mccabe@dreamhost.com>:
>>>>> Hi Huang,
>>>>>
>>>>> cfuse is a client, so it will use whatever the logging settings are for clients.
>>>>> you can set this by adding something like this to the [client] section
>>>>> of your configuration file:
>>>>>
>>>>> log_file = /my_log_file
>>>>>
>>>>> You can also use this command-line switch to override the configuration:
>>>>> --log-file=/my/log/file
>>>>>
>>>>> cheers,
>>>>> Colin
>>>>>
>>>>>
>>>>> On Thu, May 19, 2011 at 4:52 PM, huang jun <hjwsm1989@gmail.com> wrote:
>>>>>> hi,brian
>>>>>> my 'ceph -s' shows everything is ok
>>>>>> and if i do it  on the other machine, i did not find this error.
>>>>>> i trun on the debug on ceph.conf like :
>>>>>>   [client]
>>>>>>       debug ms = 1
>>>>>>       debug client = 10
>>>>>> but i can't find where does this info goes to ?  not in /var/log/ceph/
>>>>>> so where should i look for this debug output?
>>>>>>
>>>>>> thanks!
>>>>>>
>>>>>> 2011/5/19 Brian Chrisman <brchrisman@gmail.com>:
>>>>>>> On Thu, May 19, 2011 at 4:12 AM, huang jun <hjwsm1989@gmail.com> wrote:
>>>>>>>> hi, all
>>>>>>>> i just encountered a problem about cfuse:
>>>>>>>> i mount cfsue successfully on /mnt by using
>>>>>>>>   "cfuse -m 192.168.0.170:6789 /mnt"
>>>>>>>> but when i enter /mnt directory, it shows that:
>>>>>>>>   [root@localhost mnt]# ll
>>>>>>>>   ls: .: Transport endpoint is not connected
>>>>>>>
>>>>>>> This is a FUSE failure message that generally occurs when your
>>>>>>> userspace process (in this case cfuse) has exited (closed its
>>>>>>> connection to the FUSE kernel driver).
>>>>>>> does 'ceph -s' show that your ceph cluster is up and healthy?
>>>>>>> You may want to turn on client debugging to see why cfuse is exiting:
>>>>>>> http://ceph.newdream.net/wiki/Debugging
>>>>>>>
>>>>>>>
>>>>>>>> my cfuse client is on centos5, it kernel version is 2.6.18
>>>>>>>> and OSD cluster is on debian5, 2.6.35
>>>>>>>> i don't know whether it related to SimpleMessenger,so anyone can give
>>>>>>>> me some prompts?
>>>>>>>>
>>>>>>>> thanks!
>>>>>>>> --
>>>>>>>> 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] 11+ messages in thread

* Re: fuse problem
  2011-05-23 23:53               ` huang jun
@ 2011-05-24 21:11                 ` Colin Patrick McCabe
  0 siblings, 0 replies; 11+ messages in thread
From: Colin Patrick McCabe @ 2011-05-24 21:11 UTC (permalink / raw)
  To: huang jun; +Cc: ceph-devel

On Mon, May 23, 2011 at 4:53 PM, huang jun <hjwsm1989@gmail.com> wrote:
> thanks,colin
>    do you think that now we can not use 32bit cfuse client to mount
> on 64 OSD cluster?
> but i mount cfuse on the machine that also running cosd,cmds,cmon
> process,it also
> failed to operate.
>    just like :
>    WARNING: ceph inode numbers are 64 bits wide, and FUSE on 32-bit
> kernels does
>         not cope well with that situation.  Expect to crash shortly.
>   i want to note that the cfuse client and OSD cluster  on  same
> machine, so why this WARING turn up?

Hi Huang,

We do not support using cfuse on 32-bit machines. You can use the
kernel client or use libceph to access Ceph from a 32-bit machine.

There is a hack to get cfuse working on 32-bit machines, but it's
probably more trouble than it's worth. In case you are interested,
details are here:
http://ceph.newdream.net/wiki/Cfuse_on_32-bit_kernels

cheers,
Colin



>
> 2011/5/21 Colin Patrick McCabe <colin.mccabe@dreamhost.com>:
>> On Thu, May 19, 2011 at 7:31 PM, huang jun <hjwsm1989@gmail.com> wrote:
>>> unfortunately, i tried all what you have told me, but no one
>>> works.there still nothing
>>> in /home/client_logfile:
>>>     huangjun:/mnt# ll /home/client_logfile
>>>     -rwxrwxrwx 1 root root 1 2011-05-19 20:57 /home/client_logfile
>>> but i think this is not so seriously, i have a problem confused me a lot.
>>> i list what i have done
>>> 1) [root@localhost /]# cfuse  -o nonempty -m 192.168.0.11:6789 /mnt/
>>>      ARNING: bsdocfs inode numbers are 64 bits wide, and FUSE on
>>> 32-bit kernels does
>>>         not cope well with that situation.  Expect to crash shortly.
>>
>> Perhaps it has something to do with this message:
>>
>> WARNING: Ceph inode numbers are 64 bits wide, and FUSE on 32-bit kernels does
>> not cope well with that situation.  Expect to crash shortly.
>>
>> cheers,
>> Colin
>>
>>
>>>
>>>     cfuse[3771]: starting bsdocfs client
>>>     2011-05-20 10:27:06.655823 b7fe16d0 thread 3086879632 start
>>>     2011-05-20 10:27:06.656084 b7fe16d0 thread 3076389776 start
>>>     2011-05-20 10:27:06.656229 b7fe16d0 thread 3065899920 start
>>>     2011-05-20 10:27:06.656345 b7fe16d0 thread 3055410064 start
>>>     2011-05-20 10:27:06.656508 b7fe16d0 thread 3044920208 start
>>>     2011-05-20 10:27:06.656982 b7fe16d0 thread 3034430352 start
>>>     2011-05-20 10:27:06.661384 b4ddbb90 thread 3033377680 start
>>>     2011-05-20 10:27:06.663117 b7fe16d0 thread 3032325008 start
>>>     2011-05-20 10:27:06.667000 b4bd9b90 thread 3031272336 start
>>>     2011-05-20 10:27:06.870996 b4ad8b90 reader got ack seq 1 >= 1 on
>>> 0xa1a4d38      client_session(request_open) v1
>>>     2011-05-20 10:27:07.285882 b4ad8b90 reader got ack seq 3 >= 2 on
>>> 0xa1a55c8 client_session(request_renewcaps seq 1) v1
>>>     2011-05-20 10:27:07.286002 b4ad8b90 reader got ack seq 3 >= 3 on
>>> 0xa1a56f8  client_request(client5467:1 getattr pAsLsXsFs #1) v1
>>>     cfuse[3771]: starting fuse
>>> 2) [root@localhost /]# df -TH
>>> Filesystem    Type     Size   Used  Avail Use% Mounted on
>>> /dev/mapper/VolGroup00-LogVol00
>>>              ext3     305G   4.2G   285G   2% /
>>> /dev/sda1     ext3     104M    19M    80M  20% /boot
>>> tmpfs        tmpfs     2.1G      0   2.1G   0% /dev/shm
>>> fuse          fuse      12T    38G    11T   1% /mnt
>>> 3) [root@localhost mnt]# cd /mnt &&  mkdir ss
>>> mkdir: cannot create directory `ss': Transport endpoint is not connected
>>>
>>> 4) i ckeck the mon of osd clustrt state
>>>   T02-MON11:~# ceph  -s
>>> 2011-05-20 10:18:16.120627    pg v3447: 3960 pgs: 3960 active+clean;
>>> 35200 MB data, 33363 MB used, 10212 GB / 10246 GB avail
>>> 2011-05-20 10:18:16.126746   mds e21: 1/1/1 up {0=up:active}
>>> 2011-05-20 10:18:16.126772   osd e469: 14 osds: 14 up, 14 in
>>> 2011-05-20 10:18:16.126897   mon e1: 1 mons at {0=192.168.0.11:6789/0}
>>>
>>> so where can i find the wrong point? i just can't do any operation in /mnt
>>> thank you very much!
>>>
>>> 2011/5/20 Colin Patrick McCabe <colin.mccabe@dreamhost.com>:
>>>> Usually you don't have the ability to create directories or files in
>>>> /home unless you're root. Perhaps you should create
>>>> /home/client_logfile and give it the right permissions?
>>>>
>>>> If that doesn't work, make sure you are editing the configuration that
>>>> you are actually using. You can force cfuse to use the configuration
>>>> you want with -c.
>>>>
>>>> regards,
>>>> Colin
>>>>
>>>>
>>>> On Thu, May 19, 2011 at 6:01 PM, huang jun <hjwsm1989@gmail.com> wrote:
>>>>> hi,colin
>>>>> i try it as you said, but i can not see anything
>>>>>  [client]
>>>>>     log_file = /home/client_logfile
>>>>>     debug ms = 1
>>>>>     debug client = 10
>>>>>     client cache size = 1024*1024*100
>>>>> is there anything wrong with this setting?
>>>>>
>>>>> thanks!
>>>>> 2011/5/20 Colin Patrick McCabe <colin.mccabe@dreamhost.com>:
>>>>>> Hi Huang,
>>>>>>
>>>>>> cfuse is a client, so it will use whatever the logging settings are for clients.
>>>>>> you can set this by adding something like this to the [client] section
>>>>>> of your configuration file:
>>>>>>
>>>>>> log_file = /my_log_file
>>>>>>
>>>>>> You can also use this command-line switch to override the configuration:
>>>>>> --log-file=/my/log/file
>>>>>>
>>>>>> cheers,
>>>>>> Colin
>>>>>>
>>>>>>
>>>>>> On Thu, May 19, 2011 at 4:52 PM, huang jun <hjwsm1989@gmail.com> wrote:
>>>>>>> hi,brian
>>>>>>> my 'ceph -s' shows everything is ok
>>>>>>> and if i do it  on the other machine, i did not find this error.
>>>>>>> i trun on the debug on ceph.conf like :
>>>>>>>   [client]
>>>>>>>       debug ms = 1
>>>>>>>       debug client = 10
>>>>>>> but i can't find where does this info goes to ?  not in /var/log/ceph/
>>>>>>> so where should i look for this debug output?
>>>>>>>
>>>>>>> thanks!
>>>>>>>
>>>>>>> 2011/5/19 Brian Chrisman <brchrisman@gmail.com>:
>>>>>>>> On Thu, May 19, 2011 at 4:12 AM, huang jun <hjwsm1989@gmail.com> wrote:
>>>>>>>>> hi, all
>>>>>>>>> i just encountered a problem about cfuse:
>>>>>>>>> i mount cfsue successfully on /mnt by using
>>>>>>>>>   "cfuse -m 192.168.0.170:6789 /mnt"
>>>>>>>>> but when i enter /mnt directory, it shows that:
>>>>>>>>>   [root@localhost mnt]# ll
>>>>>>>>>   ls: .: Transport endpoint is not connected
>>>>>>>>
>>>>>>>> This is a FUSE failure message that generally occurs when your
>>>>>>>> userspace process (in this case cfuse) has exited (closed its
>>>>>>>> connection to the FUSE kernel driver).
>>>>>>>> does 'ceph -s' show that your ceph cluster is up and healthy?
>>>>>>>> You may want to turn on client debugging to see why cfuse is exiting:
>>>>>>>> http://ceph.newdream.net/wiki/Debugging
>>>>>>>>
>>>>>>>>
>>>>>>>>> my cfuse client is on centos5, it kernel version is 2.6.18
>>>>>>>>> and OSD cluster is on debian5, 2.6.35
>>>>>>>>> i don't know whether it related to SimpleMessenger,so anyone can give
>>>>>>>>> me some prompts?
>>>>>>>>>
>>>>>>>>> thanks!
>>>>>>>>> --
>>>>>>>>> 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] 11+ messages in thread

end of thread, other threads:[~2011-05-24 21:11 UTC | newest]

Thread overview: 11+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2011-05-19 11:12 fuse problem huang jun
2011-05-19 14:32 ` Brian Chrisman
2011-05-19 23:52   ` huang jun
2011-05-20  0:47     ` Colin Patrick McCabe
2011-05-20  1:01       ` huang jun
2011-05-20  2:04         ` Colin Patrick McCabe
2011-05-20  2:31           ` huang jun
2011-05-20  3:13             ` huang jun
2011-05-20 17:25             ` Colin Patrick McCabe
2011-05-23 23:53               ` huang jun
2011-05-24 21:11                 ` Colin Patrick McCabe

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.