correction...
in the info I attached the the last email, node 0 is locked up and node
1 seems to own all the resources node 0 needs:
dc1node1 - node 1
dc1node2 - node 0 (locked up)
[oraprod@dc1node1 ocfs]$ cat /proc/ocfs/version
1.0.9-PROD12
[oraprod@dc1node1 ocfs]$ cat /proc/ocfs/10/nodenum
1
Jeremy Schneider
Database/Systems Administrator
The ASU Group - IS Dept
email: jer1887@asugroup.com
>>> "Jeremy Schneider" <jer1887@asugroup.com>
02/20/2004 5:32:25 PM
>>>
having a problem with ocfs.
device /dev/sdd mounted on 2 nodes, node 0 and node 1
tried to create file /u01/oracle/prod/proddata/temp01.dbf from node 1
(ALTER TABLESPACE TEMP ADD TEMPFILE...) caused oracle server process
to
hang in a "D" state apparently trying to create the file. the file
has
not been created yet. If I type "ls" from node 2 in directory
/u01/oracle/prod it lists the contents of the directory -- however if
I
type "ls" from node 2 in directory /u01/oracle/prod/proddata it locks
up
in a "D" state. From node 1 all is well.
if i were to shutdown instance 1 of RAC and unmount the /u01 partition
on u01 all processes on node 2 would immediately resume. (this has
happened before.)
Seems like a inode or datablock locking issue and/or race condition...
it's locked up right now; i don't really know what to look for but
here's some diagnostics info - can somebody make any sense of this? i
can leave it locked up for a day or two so if anyone would like to see
output from a debugocfs command before monday i can do that... i
might
be able to leave it locked up until Monday afternoon we'll see how
long
before the DB locks up and someone yells. :)
this is a consistently recurring error at my site. we can't put RAC
into production if it's going to hang due to some race condition when
i
try to create a file. how is it that noone else has seen this
problem?
Jeremy
Lansing, MI
[root@dc1node1 root]# uname -a
Linux dc1node1.intra.asugroup.com 2.4.9-e.27enterprise #1 SMP Tue Aug
5
15:39:21 EDT 2003 i686 unknown
[root@dc1node1 root]# rpm -qa|grep ocfs
ocfs-tools-1.0.9-12
ocfs-2.4.9-e-enterprise-1.0.9-12
ocfs-support-1.0.9-12
[root@dc1node1 root]# ls /u01/oracle/prod/proddata/
abmd01.dbf bscd01.dbf dddd01.dbf hrd01.dbf itgd01.dbf
ontd01.dbf rlad01.dbf
abmx01.dbf bscx01.dbf dddx01.dbf hrid01.dbf itgx01.dbf
ontx01.dbf rlax01.dbf
ahld01.dbf cctd01.dbf domd01.dbf hrix01.dbf jad01.dbf
opid01.dbf rlmd01.dbf
ahlx01.dbf cctx01.dbf domx01.dbf hrx01.dbf jax01.dbf
opix01.dbf rlmx01.dbf
ahmd01.dbf ced01.dbf eaad01.dbf hxcd01.dbf jed01.dbf
osmd01.dbf sspd01.dbf
ahmx01.dbf cex01.dbf eaax01.dbf hxcx01.dbf jex01.dbf
osmx01.dbf sspx01.dbf
akd01.dbf clnd01.dbf eamd01.dbf hxtd01.dbf jgd01.dbf
otad01.dbf stspk01.dbf
akx01.dbf clnx01.dbf eamx01.dbf hxtx01.dbf jgx01.dbf
otax01.dbf system01.dbf
alrd01.dbf cnd01.dbf ecd01.dbf ibad01.dbf jld01.dbf
owad01.dbf system02.dbf
alrx01.dbf cntrl01.dbf ecx01.dbf ibax01.dbf jlx01.dbf
ozfd01.dbf system03.dbf
amfd01.dbf cntrl01.dbf.old ecxd01.dbf ibcd01.dbf jtfd01.dbf
ozfx01.dbf system04.dbf
amfx01.dbf cntrl02.dbf.old ecxx01.dbf ibcx01.dbf jtfx01.dbf
ozpd01.dbf system05.dbf
amsd01.dbf cntrl03.dbf.old edrd01.dbf ibed01.dbf jtmd01.dbf
ozpx01.dbf system06.dbf
amsx01.dbf cnx01.dbf edrx01.dbf ibex01.dbf jtmx01.dbf
ozsd01.dbf system07.dbf
amvd01.dbf crpd01.dbf egod01.dbf ibpd01.dbf jtsd01.dbf
ozsx01.dbf system08.dbf
amvx01.dbf crpx01.dbf egox01.dbf ibpx01.dbf jtsx01.dbf
pad01.dbf system09.dbf
apd01.dbf cscd01.dbf engd01.dbf ibud01.dbf log01a.dbf
pax01.dbf system10.dbf
applsysd01.dbf cscx01.dbf engx01.dbf ibux01.dbf log01b.dbf
pjid01.dbf system11.dbf
applsysd02.dbf csd01.dbf enid01.dbf ibyd01.dbf log02a.dbf
pjix01.dbf undo01.dbf
applsysx01.dbf csdd01.dbf enix01.dbf ibyx01.dbf log02b.dbf
pjmd01.dbf undo02.dbf
applsysx02.dbf csdx01.dbf evmd01.dbf icxd01.dbf log03a.dbf
pjmx01.dbf vead01.dbf
apx01.dbf csed01.dbf evmx01.dbf icxx01.dbf log03b.dbf
pmid01.dbf veax01.dbf
ard01.dbf csex01.dbf fad01.dbf iebd01.dbf med01.dbf
pmix01.dbf vehd01.dbf
arx01.dbf csfd01.dbf fax01.dbf iebx01.dbf mex01.dbf
pnd01.dbf vehx01.dbf
asfd01.dbf csfx01.dbf femd01.dbf iecd01.dbf mfgd01.dbf
pnx01.dbf wipd01.dbf
asfx01.dbf csid01.dbf femx01.dbf iecx01.dbf mfgx01.dbf
poad01.dbf wipx01.dbf
asgd01.dbf csix01.dbf fiid01.dbf iemd01.dbf mrpd01.dbf
poax01.dbf wmsd01.dbf
asgx01.dbf csld01.dbf fiix01.dbf iemx01.dbf mrpx01.dbf
pod01.dbf wmsx01.dbf
asld01.dbf cslx01.dbf flmd01.dbf ieod01.dbf mscd01.dbf
pomd01.dbf wpsd01.dbf
aslx01.dbf csmd01.dbf flmx01.dbf ieox01.dbf mscx01.dbf
pomx01.dbf wpsx01.dbf
asod01.dbf csmx01.dbf fptd01.dbf iesd01.dbf msdd01.dbf
pond01.dbf wshd01.dbf
asox01.dbf cspd01.dbf fptx01.dbf iesx01.dbf msdx01.dbf
ponx01.dbf wshx01.dbf
aspd01.dbf cspx01.dbf frmd01.dbf ieud01.dbf msod01.dbf
portal01.dbf wsmd01.dbf
aspx01.dbf csrd01.dbf frmx01.dbf ieux01.dbf msox01.dbf
posd01.dbf wsmx01.dbf
astd01.dbf csrx01.dbf fted01.dbf iexd01.dbf msrd01.dbf
posx01.dbf xdpd01.dbf
astx01.dbf cssd01.dbf ftex01.dbf iexx01.dbf msrx01.dbf
pox01.dbf xdpx01.dbf
axd01.dbf cssx01.dbf fvd01.dbf igcd01.dbf mwad01.dbf
prpd01.dbf xlad01.dbf
axx01.dbf csx01.dbf fvx01.dbf igcx01.dbf mwax01.dbf
prpx01.dbf xlax01.dbf
azd01.dbf ctxd01.dbf gld01.dbf igfd01.dbf oed01.dbf
psad01.dbf xnbd01.dbf
azx01.dbf cuad01.dbf glx01.dbf igfx01.dbf oex01.dbf
psax01.dbf xnbx01.dbf
bend01.dbf cuax01.dbf gmad01.dbf igid01.dbf okbd01.dbf
psbd01.dbf xncd01.dbf
benx01.dbf cued01.dbf gmax01.dbf igix01.dbf okbx01.dbf
psbx01.dbf xncx01.dbf
bicd01.dbf cuex01.dbf gmdd01.dbf igsd01.dbf okcd01.dbf
pspd01.dbf xnid01.dbf
bicx01.dbf cufd01.dbf gmdx01.dbf igsx01.dbf okcx01.dbf
pspx01.dbf xnix01.dbf
bild01.dbf cufx01.dbf gmed01.dbf igwd01.dbf oked01.dbf
pvd01.dbf xnmd01.dbf
bilx01.dbf cugd01.dbf gmex01.dbf igwx01.dbf okex01.dbf
pvx01.dbf xnmx01.dbf
bimd01.dbf cugx01.dbf gmfd01.dbf imcd01.dbf okid01.dbf
qad01.dbf xnpd01.dbf
bimx01.dbf cuid01.dbf gmfx01.dbf imcx01.dbf okix01.dbf
qax01.dbf xnpx01.dbf
bisd01.dbf cuix01.dbf gmid01.dbf imtd01.dbf okld01.dbf
qotd01.dbf xnsd01.dbf
bisx01.dbf cund01.dbf gmix01.dbf imtx01.dbf oklx01.dbf
qotx01.dbf xnsx01.dbf
bivd01.dbf cunx01.dbf gmld01.dbf invd01.dbf okod01.dbf
qpd01.dbf xtrd01.dbf
bivx01.dbf cupd01.dbf gmlx01.dbf invx01.dbf okox01.dbf
qpx01.dbf xtrx01.dbf
bixd01.dbf cupx01.dbf gmpd01.dbf ipad01.dbf okrd01.dbf
qrmd01.dbf zfad01.dbf
bixx01.dbf cusd01.dbf gmpx01.dbf ipax01.dbf okrx01.dbf
qrmx01.dbf zfax01.dbf
bned01.dbf cust01.dbf gmsd01.dbf ipdd01.dbf oksd01.dbf
rgd01.dbf zsad01.dbf
bnex01.dbf cusx01.dbf gmsx01.dbf ipdx01.dbf oksx01.dbf
rgx01.dbf zsax01.dbf
bomd01.dbf czd01.dbf grd01.dbf iscd01.dbf okxd01.dbf
rhxd01.dbf
bomx01.dbf czx01.dbf grx01.dbf iscx01.dbf okxx01.dbf
rhxx01.dbf
(this same "ls" command will not execute on node 2)
[root@dc1node1 root]# debugocfs -f /oracle/prod/ /dev/sdd
fileinfo:
Name = /oracle/prod/
curr_master = 1
file_lock = OCFS_DLM_NO_LOCK
oin_node_map = 00000000000000000000000000000000
seq_num = 0
local_ext = false
granularity = 0
filename = prod
filename_len = 4
file_size = 131072
alloc_size = 131072
attribs = OCFS_ATTRIB_DIRECTORY
prot_bits = S_IRUSR S_IWUSR S_IXUSR S_IRGRP S_IXGRP S_IROTH
S_IXOTH
uid = 510
gid = 500
create_time = Wed Jan 14 11:29:16 2004
modify_time = Wed Jan 14 11:29:16 2004
dir_node_ptr = 16179200
this_sector = 16179712
last_ext_ptr = 0
sync_flags = OCFS_SYNC_FLAG_VALID
link_cnt = 0
next_del = -1
next_free_ext = 0
extent[0].file_off = 0
extent[0].num_bytes = 0
extent[0].disk_off = 29810688
extent[1].file_off = 0
extent[1].num_bytes = 0
extent[1].disk_off = 0
extent[2].file_off = 0
extent[2].num_bytes = 0
extent[2].disk_off = 0
[root@dc1node1 root]# debugocfs -f /oracle/prod/proddata/ /dev/sdd
fileinfo:
Name = /oracle/prod/proddata/
curr_master = 1
file_lock = OCFS_DLM_ENABLE_CACHE_LOCK
oin_node_map = 00000000000000000000000000000000
seq_num = 0
local_ext = false
granularity = 0
filename = proddata
filename_len = 8
file_size = 131072
alloc_size = 131072
attribs = OCFS_ATTRIB_DIRECTORY
prot_bits = S_IRUSR S_IWUSR S_IXUSR S_IRGRP S_IXGRP S_IROTH
S_IXOTH
uid = 510
gid = 500
create_time = Wed Jan 14 11:29:16 2004
modify_time = Wed Jan 14 11:29:16 2004
dir_node_ptr = 29810688
this_sector = 29811200
last_ext_ptr = 0
sync_flags = OCFS_SYNC_FLAG_MARK_FOR_DELETION
link_cnt = 0
next_del = -1
next_free_ext = 0
extent[0].file_off = 0
extent[0].num_bytes = 0
extent[0].disk_off = 29941760
extent[1].file_off = 0
extent[1].num_bytes = 0
extent[1].disk_off = 0
extent[2].file_off = 0
extent[2].num_bytes = 0
extent[2].disk_off = 0
[root@dc1node1 root]# debugocfs -d /oracle/prod/ /dev/sdd
dirinfo:
Name = /oracle/prod/
curr_master = 0
file_lock = OCFS_DLM_NO_LOCK
oin_node_map = 00000000000000000000000000000000
seq_num = 0
alloc_file_off = 0
alloc_node = 1
free_node_ptr = INVALID_NODE_POINTER
node_disk_off = 29810688
next_node_ptr = INVALID_NODE_POINTER
indx_node_ptr = INVALID_NODE_POINTER
next_del_ent_node = INVALID_NODE_POINTER
head_del_ent_node = INVALID_NODE_POINTER
first_del = 255
num_del = 0
num_ents = 254
depth = 0
num_ent_used = 5
dir_node_flags = DIR_NODE_FLAG_ROOT
sync_flags = OCFS_SYNC_FLAG_DELETED
index_dirty = false
bad_off = 4
index = 0 2 1 3 4 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
[root@dc1node1 root]# debugocfs -d /oracle/prod/proddata/ /dev/sdd
dirinfo:
Name = /oracle/prod/proddata/
curr_master = 0
file_lock = OCFS_DLM_NO_LOCK
oin_node_map = 00000000000000000000000000000000
seq_num = 0
alloc_file_off = 131072
alloc_node = 1
free_node_ptr = INVALID_NODE_POINTER
node_disk_off = 29941760
next_node_ptr = INVALID_NODE_POINTER
indx_node_ptr = INVALID_NODE_POINTER
next_del_ent_node = INVALID_NODE_POINTER
head_del_ent_node = INVALID_NODE_POINTER
first_del = 255
num_del = 0
num_ents = 254
depth = 0
num_ent_used = 0
dir_node_flags = DIR_NODE_FLAG_ROOT
sync_flags = OCFS_SYNC_FLAG_DELETED
index_dirty = false
bad_off = 0
index = 0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
0 0 0 0 0 0 0 0 0 0 0 0 0
0
0 0
[root@dc1node1 root]# debugocfs -v 0-1 /dev/sdd
vote0:
seq_num = 1204
dir_ent = 34122240
open_handle = No
Vote0 = (0x00000000)
Vote1 = FLAG_VOTE_NODE (0x00000001)
vote1:
seq_num = 1205
dir_ent = 34343936
open_handle = No
Vote0 = FLAG_VOTE_NODE (0x00000001)
Vote1 = (0x00000000)
[root@dc1node1 root]# debugocfs -p 0-1 /dev/sdd
publish0:
time = 2508321.2554391394
vote = No
dirty = No
vote_type = (0x00000000)
vote_map = 00000000000000000000000000000000
seq_num = 1205
dir_ent = 0
hbm = 20 0
publish1:
time = 2508321.2555065604
vote = No
dirty = No
vote_type = (0x00000000)
vote_map = 00000000000000000000000000000000
seq_num = 1204
dir_ent = 0
hbm = 0 20
[root@dc1node1 root]# debugocfs -l /dev/sdd | head -30
filelisting:
File1 = /oracle/
File2 = /oracle/ctrl/
File3 = /oracle/ctrl/
File4 = /oracle/ctrl/
File5 = /oracle/ctrl/
File6 = /oracle/prod/
File7 = /oracle/prod/proddata/
File8 = /oracle/prod/ctrltest/
File9 = /oracle/prod/proddata/
File10 = /oracle/prod/ctrldata/
File11 = /oracle/prod/proddata/
File12 = /oracle/prod/proddata/zsad01.dbf
File13 = /oracle/prod/proddata/zfax01.dbf
File14 = /oracle/prod/proddata/zfad01.dbf
File15 = /oracle/prod/proddata/xtrd01.dbf
File16 = /oracle/prod/proddata/xnpx01.dbf
File17 = /oracle/prod/proddata/xnpd01.dbf
File18 = /oracle/prod/proddata/xnmx01.dbf
File19 = /oracle/prod/proddata/xnmd01.dbf
File20 = /oracle/prod/proddata/xnid01.dbf
...
File406 = /oracle/prod/proddata/axx01.dbf
File407 = /oracle/prod/proddata/astd01.dbf
File408 = /oracle/prod/proddata/aslx01.dbf
File409 = /oracle/prod/proddata/asfx01.dbf
File410 = /oracle/prod/proddata/ard01.dbf
File411 = /oracle/prod/proddata/apx01.dbf
File412 = /oracle/prod/proddata/applsysd01.dbf
File413 = /oracle/prod/proddata/amvd01.dbf
File414 = /oracle/prod/proddata/alrx01.dbf
File415 = /oracle/prod/proddata/ahmd01.dbf
File416 = /oracle/ctrl/
File417 = /backup
Jeremy Schneider
Database/Systems Administrator
The ASU Group - IS Dept
email: jer1887@asugroup.com
_______________________________________________
Ocfs-users mailing list
Ocfs-users@oss.oracle.com
http://oss.oracle.com/mailman/listinfo/ocfs-users