Re: [Pvfs2-users] pvfs2 stability

Andrea Carotti Mon, 22 May 2006 09:18:03 -0700

Dear Mr Murali,
I'm using the 1.4.0 version.

everything seems to work: pvfs2-fs-dump, pvfs2-ping, pvfs2-ls...and also thetypical commands like mkdir and cp works well on all the nodes and on theserver.

One strange thing is also happening at the login:
[EMAIL PROTECTED]:~]su
Password:
open: No such file or directory
apparent state: unit 27 named -e
lately writing direct unformatted external IO
Segnale di annullamento
open: No such file or directory
apparent state: unit 27 named -f
lately writing direct unformatted external IO
Segnale di annullamento
open: No such file or directory
apparent state: unit 27 named -f
lately writing direct unformatted external IO
Segnale di annullamento
open: No such file or directory
apparent state: unit 27 named -f
lately writing direct unformatted external IO
Segnale di annullamento
open: No such file or directory
apparent state: unit 27 named -f
lately writing direct unformatted external IO
Segnale di annullamento
open: No such file or directory
apparent state: unit 27 named -e
lately writing direct unformatted external IO
Segnale di annullamento


thanks a lot
Andrea

----- Original Message -----From: "Murali Vilayannur" <[EMAIL PROTECTED]>

To: "Andrea Carotti" <[EMAIL PROTECTED]>
Cc: <[email protected]>
Sent: Monday, May 22, 2006 6:07 PM
Subject: Re: [Pvfs2-users] pvfs2 stability

Hi Andrea,
Hmm..Nothing looks out of the ordinary from the config files..
Since you mentioned that the VFS interface does not work, could you
confirm if the pvfs system interface based tools work or not?
(i.e. pvfs2-fs-dump, pvfs2-ping, pvfs2-ls etc under src/apps/admin)
It would be good to narrow down which component(s) is/are causing all
these failures...Any other information from the logs (or running all the
components with extra verbose logging) could also help narrow down what
the issue might be.. BTW, are you using pvfs2 1.4.0 or CVS head?
Thanks,
Murali

cat /home/Application/pvfs/conf/pvfs2-fs.conf
<Defaults>
        UnexpectedRequests 50
        LogFile /tmp/pvfs2-server.log
        EventLogging none
        LogStamp usec
        BMIModules bmi_tcp
        FlowModules flowproto_multiqueue
        PerfUpdateInterval 1000
        ServerJobBMITimeoutSecs 30
        ServerJobFlowTimeoutSecs 30
        ClientJobBMITimeoutSecs 300
        ClientJobFlowTimeoutSecs 300
        ClientRetryLimit 5
        ClientRetryDelayMilliSecs 2000
</Defaults>

<Aliases>
        Alias dom1 tcp://dom1:3334
        Alias dom2 tcp://dom2:3334
        Alias dom3 tcp://dom3:3334
        Alias dom4 tcp://dom4:3334
        Alias om1 tcp://om1:3334
        Alias om2 tcp://om2:3334
        Alias om3 tcp://om3:3334
        Alias om4 tcp://om4:3334
        Alias om5 tcp://om5:3334
</Aliases>

<Filesystem>
        Name pvfs2-fs
        ID 1869706856
        RootHandle 1048576
        <MetaHandleRanges>
                Range om1 4-429496732
        </MetaHandleRanges>
        <DataHandleRanges>
                Range dom1 429496733-858993461
                Range dom2 858993462-1288490190
                Range dom3 1288490191-1717986919
                Range dom4 1717986920-2147483648
                Range om1 2147483649-2576980377
                Range om2 2576980378-3006477106
                Range om3 3006477107-3435973835
                Range om4 3435973836-3865470564
                Range om5 3865470565-4294967293
        </DataHandleRanges>
        <StorageHints>
                TroveSyncMeta yes
                TroveSyncData no
                AttrCacheKeywords datafile_handles,metafile_dist
                AttrCacheKeywords dir_ent, symlink_target
                AttrCacheSize 4093
                AttrCacheMaxNumElems 32768
        </StorageHints>
</Filesystem>

Om1 is the server/client hostname
cat /home/Application/pvfs/conf/pvfs2-server.conf-om1
StorageSpace /pvfs2-storage-space
HostID "tcp://om1:3334"

Om2 is a client hostname
cat /home/Application/pvfs/conf/pvfs2-server.conf-om2
StorageSpace /pvfs2-storage-space
HostID "tcp://om2:3334"


Let me know if you need more informations.
Thanks
Andrea

----- Original Message -----
From: "Murali Vilayannur" <[EMAIL PROTECTED]>
To: "Andrea Carotti" <[EMAIL PROTECTED]>
Cc: <[email protected]>
Sent: Monday, May 22, 2006 5:45 PM
Subject: Re: [Pvfs2-users] pvfs2 stability


> Hi Andrea,
> It does look a bit strange to see these messages and yet have the FS
> working..
> Could you post your fs.conf and server.conf files?
> thanks,
> Murali
>
> On Mon, 22 May 2006, Andrea Carotti wrote:
>
>> Hi all,

>> I'm new to this list and to the pvfs2 program. I'm using it on our>> home

>> made

>> cluster (9 nodes) running an openMosix kernel 2.4.22-3 and Fedora>> Core2.

>> I've installed it with one node running as meta server ,  PVFS2 server
>> and
>> data servers and all the others like data servers.
>> I've also compiled and installed the module.
>> This is my actual configuration:
>> 1)on all nodes I've an entry in /etc/fstab like this:
>> tcp://om1:3334/pvfs2-fs /mnt/pvfs2 pvfs2 default,noauto 0 0
>> 2)i've added at the rc.local these lines:
>> insmod /lib/modules/2.4.22-oM3src/kernel/fs/pvfs2/pvfs2.o
>> /home/Application/pvfs/sbin/pvfs2-client -p
>> /home/Application/pvfs/sbin/pvfs2-client-core
>> mount -t pvfs2 tcp://om1:3334/pvfs2-fs /mnt/pvfs2
>> 3) I've enbled the default service for the startup on all the nodes
>> /etc/init.d/pvfs2-server
>>
>> I'm encountering some problems with its usage:

>> if I start the server (/etc/init.d/pvfs2-server start) everything>> seems

>> ok
>> but on the server the /tmp/pvfs2-client.log appears with this errors:
>>
>> [E 16:57:50.651742] msgpair failed, will retry:: Broken pipe
>> [E 16:57:52.691656] msgpair failed, will retry:: Connection refused
>> [E 16:57:54.731666] msgpair failed, will retry:: Connection refused
>> [E 16:57:56.771657] msgpair failed, will retry:: Connection refused
>> [E 16:57:58.811658] msgpair failed, will retry:: Connection refused
>> [E 16:58:00.851658] msgpair failed, will retry:: Connection refused
>> [E 16:58:00.851731] *** msgpairarray_completion_fn: msgpair to server
>> tcp://om1:3334 failed: Connection refused
>> [E 16:58:00.851750] *** Out of retries.

>> [E 16:58:00.851769] getattr_object_getattr_failure : Connection>> refused

>>

>> However it seems to work: i can write on the /mnt/pvfs2 , make dirs,>> and

>> so
>> on with the normal commands cp,mkdir and so on .
>>

>> But during the day something go wrong infact the next day I never can>> see

>> the /mnt/pvfs2 without restarting the server and looking on the
>> /var/log/messages
>> i see:
>> May 18 23:21:20 om1 kernel: pvfs2: pvfs2_statfs -- wait timed out and
>> retries exhausted. aborting attempt.
>> May 18 23:27:20 om1 kernel: pvfs2: pvfs2_statfs -- wait timed out and
>> retries exhausted. aborting attempt.

>> May 19 01:06:07 om1 kernel: pvfs2: pvfs2_inode_getattr -- wait timed>> out

>> and
>> retries exhausted. aborting attempt.
>> May 19 04:08:26 om1 kernel: pvfs2: pvfs2_statfs -- wait timed out and
>> retries exhausted. aborting attempt.

>> May 19 04:15:40 om1 kernel: pvfs2: pvfs2_inode_getattr -- wait timed>> out

>> and
>> retries exhausted. aborting attempt.
>> May 19 23:20:48 om1 kernel: pvfs2: pvfs2_statfs -- wait timed out and
>> retries exhausted. aborting attempt.
>> May 19 23:26:48 om1 kernel: pvfs2: pvfs2_statfs -- wait timed out and
>> retries exhausted. aborting attempt.

>> May 20 01:06:04 om1 kernel: pvfs2: pvfs2_inode_getattr -- wait timed>> out

>> and
>> retries exhausted. aborting attempt.
>> May 20 04:08:25 om1 kernel: pvfs2: pvfs2_statfs -- wait timed out and
>> retries exhausted. aborting attempt.

>> May 20 04:15:34 om1 kernel: pvfs2: pvfs2_inode_getattr -- wait timed>> out

>> and
>> retries exhausted. aborting attempt.
>> May 20 23:21:09 om1 kernel: pvfs2: pvfs2_statfs -- wait timed out and
>> retries exhausted. aborting attempt.
>> May 20 23:27:09 om1 kernel: pvfs2: pvfs2_statfs -- wait timed out and
>> retries exhausted. aborting attempt.

>> May 21 01:06:05 om1 kernel: pvfs2: pvfs2_inode_getattr -- wait timed>> out

>> and
>> retries exhausted. aborting attempt.
>> May 21 04:08:31 om1 kernel: pvfs2: pvfs2_statfs -- wait timed out and
>> retries exhausted. aborting attempt.

>> May 21 04:15:41 om1 kernel: pvfs2: pvfs2_inode_getattr -- wait timed>> out

>> and
>> retries exhausted. aborting attempt.
>> May 21 23:24:05 om1 kernel: pvfs2: pvfs2_statfs -- wait timed out and
>> retries exhausted. aborting attempt.

>> May 22 01:06:03 om1 kernel: pvfs2: pvfs2_inode_getattr -- wait timed>> out

>> and
>> retries exhausted. aborting attempt.
>> May 22 04:08:33 om1 kernel: pvfs2: pvfs2_statfs -- wait timed out and
>> retries exhausted. aborting attempt.

>> May 22 04:15:41 om1 kernel: pvfs2: pvfs2_inode_getattr -- wait timed>> out

>> and
>> retries exhausted. aborting attempt.
>>
>> Same errors at the same time.
>> Sorry for the long message...Hope for someone help
>> Thanks
>> Andrea
>>
>>
>>
>> _______________________________________________
>> 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


_______________________________________________
Pvfs2-users mailing list
[email protected]
http://www.beowulf-underground.org/mailman/listinfo/pvfs2-users

Re: [Pvfs2-users] pvfs2 stability

Reply via email to