Hello,
i started the "mds10" metadata server and afterwards i  did:
ps auwwx|grep pvfs2-serverroot     19931 44.7  1.3 163592 27192 pts/0    Sl+  
17:05   0:08 /usr/sbin/pvfs2-server /etc/pvfs2-fs.conf -d -a xxx.xxxuser  19971 
 0.0  0.0  60244   704 pts/1    R+   17:05   0:00 grep pvfs2-server
So, the pvfs2-server process is running.
With the error i receive , does it mean that the client is not interacting with 
the server?I don't know if any firewall is running. Can i see that with ps -A?
Thanks, in advance
From: [email protected]
To: [email protected]
CC: [email protected]
Subject: RE: [Pvfs2-users] Problem with pvfs2 - Warning: msgpair failed to      
tcp://xxx.xxx:3334, will retry: Connection refused
Date: Fri, 16 Dec 2011 08:52:25 -0500



Any time you get a message that looks something like this:Warning: msgpair 
failed to tcp://client1:3334, will retry: Connection refusedit means the server 
indicated in the message does not have a pvfs2-server process that is 
responding or that a firewall is in the way. Since your servers and client have 
successfully communicated in the past a firewall should not be the issue. 
Carefully check the machine indicated in the messages to make sure the 
pvfs2-server process is running. -- Elaine From: 
[email protected] 
[mailto:[email protected]] On Behalf Of g_p g_p
Sent: Thursday, December 15, 2011 5:20 PM
To: [email protected]
Cc: pvfs2
Subject: RE: [Pvfs2-users] Problem with pvfs2 - Warning: msgpair failed to 
tcp://xxx.xxx:3334, will retry: Connection refused 
Hello and thanks for replying, the "mds10" metadata server seems to have a 
problem because when i tried to create a directory i received the output cannot 
create [/mnt/pvfs2/file279]Warning: non PVFS2 error code (19):PVFS_sys_lookup: 
No such device The /tmp/pvfs2-server.log file of "mds10" is empty with 0 lines. 
The pvfs2tab file in the client node is located under /etc/ folder . I've 
noticed that the pvfs2tab in all the metadata servers is not located under 
/etc/. In "mds10" i copied the pvfs2tab file of the client node in the "mds10" 
folder /etc/. And i executed the command:(In my testing, only one metadata 
server "mds10" is up and only one client is up which is a datanode too) sudo 
/usr/bin/pvfs2-ping -m  /mnt/pvfs2/ (1) Parsing tab file... (2) Initializing 
system interface... (3) Initializing each file system found in tab file: 
/etc/pvfs2tab...    PVFS2 servers: tcp://client1:3334   Storage name: pvfs2-fs  
 Local mount point: /mnt/pvfs2[E 23:04:17.372012] Warning: msgpair failed to 
tcp://client1:3334, will retry: Connection refused[E 23:04:19.380893] Warning: 
msgpair failed to tcp://client1:3334, will retry: Connection refused[E 
23:04:21.384946] Warning: msgpair failed to tcp://client1:3334, will retry: 
Connection refused[E 23:04:27.402221] *** msgpairarray_completion_fn: msgpair 
to server [UNKNOWN] failed: Connection refused[E 23:04:27.402235] *** Out of 
retries.   /mnt/pvfs2: FAILURE! Failure: could not initialze at least one of 
the target file systems. (4) Searching for /mnt/pvfs2/ in pvfstab...    PVFS2 
servers: tcp://client1:3334   Storage name: pvfs2-fs   Local mount point: 
/mnt/pvfs2    meta servers:   tcp://xxx:3334    data servers:   
tcp://client1:3334 (5) Verifying that all servers are responding...     meta 
servers:[E 23:04:27.404148] Warning: msgpair failed to tcp://xxx:3334, will 
retry: Connection refused[E 23:04:27.404172] *** msgpairarray_completion_fn: 
msgpair to server tcp://xxx:3334 failed: Connection refused[E 23:04:27.404185] 
*** No retries requested.   tcp://xxx:3334 FAILURE: PVFS_mgmt_noop failed for 
server: tcp://xxxx:3334Failure: could not communicate with one of the servers.  
(6) Verifying that fsid 1436697865 is acceptable to all servers...[E 
23:04:27.405572] Warning: msgpair failed to tcp://xxx:3334, will retry: 
Connection refused[E 23:04:29.412193] Warning: msgpair failed to 
tcp://xxxx:3334, will retry: Connection refused[E 23:04:37.432431] *** 
msgpairarray_completion_fn: msgpair to server tcp://xxx:3334 failed: Connection 
refused[E 23:04:37.432445] *** Out of retries.PVFS_mgmt_setparam_all: Detailed 
per-server errors are available (error class: 0)Failure: not all servers 
accepted fsid 1436697865        Per-server errors:        Server: 
tcp://xxxx:3334: Connection refused        Server: tcp://client1:3334: 
Connection refused (7) Verifying that root handle is owned by one server...    
Root handle: 1048576[E 23:04:37.433816] Warning: msgpair failed to 
tcp://xxx:3334, will retry: Connection refused[E 23:04:39.436437] Warning: 
msgpair failed to tcp://xxx:3334, will retry: Connection refused[E 
23:04:47.455823] *** msgpairarray_completion_fn: msgpair to server 
tcp://xxx:3334 failed: Connection refused[E 23:04:47.455837] *** Out of 
retries.Failure: check root handle failedPVFS_mgmt_setparam_all: Detailed 
per-server errors are available (error class: 0)         Exactly one server 
must own the root handle.        In this setup, no servers own the root handle. 
Per-server 
errors:-------------------------------------------------------------------------------
 The PVFS2 filesystem at /mnt/pvfs2/ appears to have problems. Well the 
metadata server "mds10" seems to have problems.Can these problems be 
solved?Cause i need this metadata server for my work. Thanks, in advance  Date: 
Thu, 15 Dec 2011 08:53:44 -0500
Subject: Re: [Pvfs2-users] Problem with pvfs2 - Warning: msgpair failed to 
tcp://xxx.xxx:3334, will retry: Connection refused
From: [email protected]
To: [email protected]
CC: [email protected]

For pvfs2-ping to work it needs access to a pvfs2tab file. You can see in the 
error message the various places the utility looks for that file. I would 
recommend placing the pvfs2tab file in the same location as you did on your 
client node. One other possibility is to place a pvfs2tab file in the current 
directory your shell is in when running the pvfs2-ping command. It looks like, 
what you are calling "Client node", is also running a pvfs2-server process. 
That is okay, I just wanted to make sure that is what you intended. It appears 
that the pvfs2-server process is not running for some reason on the host mds10. 
On mds10 look at the file /tmp/pvfs2-server.log. It should provide a reason why 
the server failed to start on that host. If you changed the default LogFile 
parameter in the configuration file you should look at the file in that 
location. Michael 2011/12/15 g_p g_p <[email protected]>Hello,  i'm actually 
testing the pvfs2 with one client which is a datanode too and one metadata 
server.I restarted the server again and it didn't output that warning "Warning: 
msgpair failed to tcp://xxx.xxx:3334, will retry: Connection refused". In 
Client node i executed the command: sudo /usr/sbin/pvfs2-server 
/etc/pvfs2-fs.conf -a client1[S 12/15 13:35] PVFS2 Server on node client1 
version 2.8.1 starting... In metadata server "mds10" i executed the command ps 
auwwx|grep pvfs2user   3119  0.0  0.0  60244   704 pts/0    S+   14:17   0:00 
grep pvfs2 So, a pvfs2-server is not running.and i started the server. After 
starting the mds and the client i could create a directory and i could list all 
the files. But when i executed the following command on metadata server 
"mds10": sudo /usr/bin/pvfs2-ping -m  /mnt/pvfs2/ (1) Parsing tab file...[E 
15:04:38.583196] Error: could not find any pvfs2 tabfile entries.[E 
15:04:38.583287] Error: tried the following tabfiles:[E 15:04:38.583300]        
(null)[E 15:04:38.583312]        /etc/fstab[E 15:04:38.583322]        
/etc/pvfs2tab[E 15:04:38.583344]        pvfs2tab[E 15:04:38.583354]        
/etc/mtabWarning: non PVFS2 error code (1):PVFS_util_parse_pvfstab: Operation 
not permittedFailure: could not parse pvfstab. Because i can execute 
pvfs2-mkdir and pvfs-ls without any problem,but when i execute the command 
"pvfs2-ping" i receive the errors. Can i fix these warnings? Thanks, in advance 
    Date: Thu, 15 Dec 2011 06:51:35 -0500
Subject: Re: [Pvfs2-users] Problem with pvfs2 - Warning: msgpair failed to 
tcp://xxx.xxx:3334, will retry: Connection refused
From: [email protected]
To: [email protected]
CC: [email protected]

It looks like the pvfs2-server process is no longer running. Confirm that a 
pvfs2-server process is running on each of the servers. If it is not running, 
restart it. Michael 2011/12/15 g_p g_p <[email protected]>Hello, i started 
the client in pvfs2 and in one of the metadata servers. When i execute the 
command from the client  sudo /usr/bin/pvfs2-ls -l /mnt/pvfs2/ Warning: msgpair 
failed to tcp://xxx.x:3334, will retry: Connection refused Warning: msgpair 
failed to  tcp://xxx.xxx.xxx:3334, will retry: Connection refused[E 
10:57:24.005042] Warning: msgpair failed to  tcp://xxx.xxx.xxx:3334, will 
retry: Connection refused[E 10:57:26.012154] Warning: msgpair failed to  
tcp://xxx.xxx.xxx:3334, will retry: Connection refused[E 10:57:26.012199] *** 
msgpairarray_completion_fn: msgpair to server [UNKNOWN] failed: Connection 
refused[E 10:57:26.012214] *** Out of retries.Error: could not initialize any 
file systems from /etc/pvfs2tab Where is the problem located?Can this be 
solved?Because i was working on pvfs2 and it's urgent for me because i can't 
work at all now Thanks, in advance
_______________________________________________
Pvfs2-users mailing list
[email protected]
http://www.beowulf-underground.org/mailman/listinfo/pvfs2-users                 
                          
_______________________________________________
Pvfs2-users mailing list
[email protected]
http://www.beowulf-underground.org/mailman/listinfo/pvfs2-users

Reply via email to