Dear Expert:
Is [log in to unmask] still in use?
Cheers,Gang
On 01/18/2013 03:33 PM, qing wrote:
> Dear Expert:
>
> After checking the log I found that two disks (localdisk3 and
> localdisk4) on valtical00 were not taken into account when xrootd
> starts up:
>
> Config using configuration file /opt/vdt-xrootd/xrootd/etc/xrootd.cfg
> =====> all.adminpath /opt/vdt-xrootd/xrootd/var/admin
> =====> xrd.port 1094
> Config maximum number of connections restricted to 1024
> Copr. 2007 Stanford University/SLAC cmsd.
> ++++++ [log in to unmask] <mailto:[log in to unmask]> phase
> 1 initialization started.
> =====> all.export /localdisk/xrootd
> =====> all.export /localdisk/proofbox r/o
> =====> all.adminpath /opt/vdt-xrootd/xrootd/var/admin
> =====> all.manager valtical.cern.ch:1213
> =====> all.role server
> =====> oss.cache public /localdisk/xrootd/*
> =====> oss.cache public /localdisk2/xrootd
> =====> oss.cache public /localdisk5/xrootd
> =====> oss.cache public /localdisk6/xrootd
> The following paths are available to the redirector:
> r /localdisk/proofbox
> w /localdisk/xrootd
>
> ------ [log in to unmask] <mailto:[log in to unmask]> phase
> 1 server initialization completed.
> ++++++ [log in to unmask] <mailto:[log in to unmask]> phase
> 2 server initialization started.
> 130118 15:26:12 001 Meter: Duplicate filesystem
> /localdisk/xrootd/proof skipped for free space.
> 130118 15:26:12 001 Meter: Duplicate filesystem
> /localdisk/xrootd/productions skipped for free space.
> 130118 15:26:12 001 Meter: Duplicate filesystem
> /localdisk/xrootd/users skipped for free space.
> 130118 15:26:12 001 Meter: Duplicate filesystem /localdisk/xrootd/test
> skipped for free space.
> 130118 15:26:12 001 Meter: Found 4 filesystem(s); 7TB total (0% util);
> 1TB free (1TB max)
>
>
> But actually localdisk3 and localdisk4 are configured in the
> configuration file /opt/vdt-xrootd/xrootd/etc/xrootd.cfg:
>
> all.role server
> xrootd.chksum max 3 adler32 ${xrootdlocation}/bin/xrdadler32
> cms.perf int 2m pgm ${xrootdlocation}/etc/XrdOlbMonPerf 120
> set osscachepath = /localdisk/xrootd
> oss.cache public $(osscachepath)/* xa
> oss.cache public /localdisk2/xrootd xa
> oss.cache public /localdisk4/xrootd xa
> oss.cache public /localdisk3/xrootd xa
> oss.cache public /localdisk5/xrootd xa
> oss.cache public /localdisk6/xrootd xa
> oss.usage log ${xrootdlocation}/var/admin
>
> any idea ?
>
> Cheers,Gang
>
> On 01/18/2013 12:35 PM, qing wrote:
>> Dear Expert:
>>
>> Today when I try to upload some files, the following error appeared:
>>
>> root://valtical.cern.ch//localdisk/xrootd/test1.root
>>
>> Last server error 3011 ('No servers are available to write the file,
>> however, on one file server there are still ~ 5TB free space.
>>
>> valtical.cern.ch is the xrdr, while valtical00 is one of the disk
>> servers which has a lot of free space, the other disk servers are all
>> full at this time.
>>
>> Here is the xrootd configuration file on valtical00:
>> ------------------------------------------------------------------------------------------------------------------------
>>
>>
>> xrootd.fslib ${xrootdlocation}/lib/libXrdOfs.so
>>
>> if $(xrdr)
>> all.role manager
>>
>> # CNSD_XRDR_BEGIN
>> # broadcast mv, rm, rmdir and trunc operations to all data
>> servers, and
>> # redirect the client to CNS (the second xrootd instance on
>> redirector)
>> # to do the operation on shadow file/dir.
>> ofs.forward 3way $(xrdr):2094 mv rm rmdir trunc
>> # CNSD_XRDR_END
>> else
>>
>> all.role server
>> xrootd.chksum max 3 adler32 ${xrootdlocation}/bin/xrdadler32
>> cms.perf int 2m pgm ${xrootdlocation}/etc/XrdOlbMonPerf 120
>> set osscachepath = /localdisk/xrootd
>> oss.cache public $(osscachepath)/* xa
>> oss.cache public /localdisk2/xrootd xa
>> oss.cache public /localdisk3/xrootd xa
>> oss.cache public /localdisk4/xrootd xa
>> oss.cache public /localdisk5/xrootd xa
>> oss.cache public /localdisk6/xrootd xa
>> oss.usage log ${xrootdlocation}/var/admin
>>
>> # CNSD_BEGIN
>> ofs.notify create closew mkdir |
>> ${xrootdlocation}/bin/XrdCnsd -d -l
>> ${xrootdlocation}/var/logs/cnsd.log root://$(xrdr):2094
>> ofs.notifymsg create $TID create $FMODE $LFN?$CGI
>> ofs.notifymsg closew $TID closew $LFN $FSIZE
>> # CNSD_END
>> --------------------------------------------------------------------------------------------------------------------------------------
>>
>>
>> As you see, on valtical00 we still have 3 disks empty
>> [valtical00] /afs/cern.ch/user/q/qing > df -h | grep localdisk
>> /dev/sdb1 1.8T 1.7T 0 100% /localdisk
>> /dev/sdc1 1.8T 1.7T 0 100% /localdisk2
>> /dev/sdd1 1.8T 192G 1.6T 11% /localdisk3
>> /dev/sde1 1.8T 43G 1.7T 3% /localdisk4
>> /dev/sdg1 1.8T 1.7T 0 100% /localdisk5
>> /dev/sdh1 1.8T 196M 1.7T 1% /localdisk6
>>
>> Any idea what can be done to use these 3 disks?
>>
>> Cheers,Gang
>>
>>
>>
>>
>
########################################################################
Use REPLY-ALL to reply to list
To unsubscribe from the XROOTD-L list, click the following link:
https://listserv.slac.stanford.edu/cgi-bin/wa?SUBED1=XROOTD-L&A=1
