SGE faild to submit job, attribute is not a memory value - qsub

Question

I failed to submit a job with mem attribute. Since I am novice and after google two days, I look for help here. Any suggestion would be grateful!
Following is what had I done:
\1. Submit my script:
qsub -S /bin/bash -A assembly -pe threads 16 -l mem=2GB -cwd -N "pBcR_correct_asm" -j y -o /dev/null runCorrection.sh
Unable to run job: unknown resource "mem".
Exiting.
\2. Considering that I had replace "h" to "host", which solve my problem according to SGE unknown resource "nodes", I replace "m" to "mem”， and it didn't work.
\3. After google, I know "h" is the shortcut that was defined in "/opt/gridengine/util/resources/centry/
hostname", and can be confirmed with "qconf -sc":
qconf -sc
#name shortcut type relop requestable consumable default urgency
#----------------------------------------------------------------------------------------
arch a RESTRING == YES NO NONE 0
calendar c RESTRING == YES NO NONE 0
cpu cpu DOUBLE >= YES NO 0 0
display_win_gui dwg BOOL == YES NO 0 0
h_core h_core MEMORY <= YES NO 0 0
h_cpu h_cpu TIME <= YES NO 0:0:0 0
h_data h_data MEMORY <= YES NO 0 0
h_fsize h_fsize MEMORY <= YES NO 0 0
h_rss h_rss MEMORY <= YES NO 0 0
h_rt h_rt TIME <= YES NO 0:0:0 0
h_stack h_stack MEMORY <= YES NO 0 0
h_vmem h_vmem MEMORY <= YES NO 0 0
hostname h HOST == YES NO NONE 0
load_avg la DOUBLE >= NO NO 0 0
load_long ll DOUBLE >= NO NO 0 0
load_medium lm DOUBLE >= NO NO 0 0
load_short ls DOUBLE >= NO NO 0 0
m_core core INT <= YES NO 0 0
m_socket socket INT <= YES NO 0 0
m_topology topo RESTRING == YES NO NONE 0
m_topology_inuse utopo RESTRING == YES NO NONE 0
mem_free mf MEMORY <= YES NO 0 0
mem_total mt MEMORY <= YES NO 0 0
mem_used mu MEMORY >= YES NO 0 0
\4. I thus replaced "mt" to "mem", but it complained attribute problem. According to above output, it seemed the mem_total is almost same as "hostname" that worked previously. Then, I think jsv may be a problem after going through the SGE guide, but I can't find any scripts contain "Unable to run job: attribute......", which under the director of "/opt/gridengine/util/resources/jsv". I think I have to configure some files, but what these files, and what should I do?
qsub -S /bin/bash -A assembly -pe threads 16 -l mt=2GB -cwd -N "pBcR_correct_asm" -j y -o test.out runCorrection.sh
Unable to run job: attribute "mem_total" is not a memory value.
Exiting.

Answer 1

#Vince!
Thanks for your reply very much.
Finally I solve my problem, by using "h_vmem=2g" ("2GB" would give error), but I don't know where to find how to design the value of the complex (MEMORY).
Following information is un-necessary now.
I had read the website you gave, and configured the attribute of h_vmem and s_vmeme in complex to "consumable", but it didn't work. I guess I have to configure "complex_value" of queue which is "NONE" at the moment. However, I can't open the web http://gridscheduler.sourceforge.net/htmlman/htmlman5/sge_types.html?pathrev=V62u5_TAG that may tell me how to configure. Am I right to configure to configure queue? Do I have to configure host too?
Any suggestions would be grateful!
Fowllowing is what had I done:
\1. Change the attribute of consumable to "YES" for h_vmem and s_vmem:
qconf -sc
#name shortcut type relop requestable consumable default urgency
#----------------------------------------------------------------------------------------
arch a RESTRING == YES NO NONE 0
calendar c RESTRING == YES NO NONE 0
cpu cpu DOUBLE >= YES NO 0 0
display_win_gui dwg BOOL == YES NO 0 0
h_core h_core MEMORY <= YES NO 0 0
h_cpu h_cpu TIME <= YES NO 0:0:0 0
h_data h_data MEMORY <= YES NO 0 0
h_fsize h_fsize MEMORY <= YES NO 0 0
h_rss h_rss MEMORY <= YES NO 0 0
h_rt h_rt TIME <= YES NO 0:0:0 0
h_stack h_stack MEMORY <= YES NO 0 0
h_vmem h_vmem MEMORY <= YES YES 0 0
hostname h HOST == YES NO NONE 0
load_avg la DOUBLE >= NO NO 0 0
load_long ll DOUBLE >= NO NO 0 0
load_medium lm DOUBLE >= NO NO 0 0
load_short ls DOUBLE >= NO NO 0 0
m_core core INT <= YES NO 0 0
m_socket socket INT <= YES NO 0 0
m_topology topo RESTRING == YES NO NONE 0
m_topology_inuse utopo RESTRING == YES NO NONE 0
mem_free mf MEMORY <= YES NO 0 0
mem_total mt MEMORY <= YES NO 0 0
mem_used mu MEMORY >= YES NO 0 0
min_cpu_interval mci TIME <= NO NO 0:0:0 0
np_load_avg nla DOUBLE >= NO NO 0 0
np_load_long nll DOUBLE >= NO NO 0 0
np_load_medium nlm DOUBLE >= NO NO 0 0
np_load_short nls DOUBLE >= NO NO 0 0
num_proc p INT == YES NO 0 0
qname q RESTRING == YES NO NONE 0
rerun re BOOL == NO NO 0 0
s_core s_core MEMORY <= YES NO 0 0
s_cpu s_cpu TIME <= YES NO 0:0:0 0
s_data s_data MEMORY <= YES NO 0 0
s_fsize s_fsize MEMORY <= YES NO 0 0
s_rss s_rss MEMORY <= YES NO 0 0
s_rt s_rt TIME <= YES NO 0:0:0 0
s_stack s_stack MEMORY <= YES NO 0 0
s_vmem s_vmem MEMORY <= YES YES 0 0
seq_no seq INT == NO NO 0 0
slots s INT <= YES YES 1 1000
swap_free sf MEMORY <= YES NO 0 0
swap_rate sr MEMORY >= YES NO 0 0
swap_rsvd srsv MEMORY >= YES NO 0 0
swap_total st MEMORY <= YES NO 0 0
swap_used su MEMORY >= YES NO 0 0
tmpdir tmp RESTRING == NO NO NONE 0
virtual_free vf MEMORY <= YES NO 0 0
virtual_total vt MEMORY <= YES NO 0 0
virtual_used vu MEMORY >= YES NO 0 0
# >#< starts a comment but comments are not saved across edits --------
\2. Submit my job to the queue of smp.q, and it complained the same problem:
qsub -S /bin/bash -A assembly -q smp.q -pe newPe 16 -l h_vmem=2GB -cwd -N "pBcR_correct_asm" -j y -o runCorrection.sh
Unable to run job: attribute "h_vmem" is not a memory value.
Exiting.
\3. The information of smp.q. I think "complex_values" should be changed and "h_vmem" can keep unchanged:
qconf -sq smp.q
qname smp.q
hostlist #smp.q
seq_no 0
load_thresholds np_load_avg=1.75
suspend_thresholds NONE
nsuspend 1
suspend_interval 00:05:00
priority 0
min_cpu_interval 00:05:00
processors UNDEFINED
qtype BATCH INTERACTIVE
ckpt_list NONE
pe_list make newPe
rerun FALSE
slots 160
tmpdir /tmp
shell /bin/csh
prolog NONE
epilog NONE
shell_start_mode posix_compliant
starter_method NONE
suspend_method NONE
resume_method NONE
terminate_method NONE
notify 00:00:60
owner_list NONE
user_lists NONE
xuser_lists NONE
subordinate_list NONE
complex_values NONE
projects NONE
xprojects NONE
calendar NONE
initial_state default
s_rt INFINITY
h_rt INFINITY
s_cpu INFINITY
h_cpu INFINITY
s_fsize INFINITY
h_fsize INFINITY
s_data INFINITY
h_data INFINITY
s_stack INFINITY
h_stack INFINITY
s_core INFINITY
h_core INFINITY
s_rss INFINITY
h_rss INFINITY
s_vmem INFINITY
h_vmem INFINITY
\4. The information of hosts in #smp.q:
qconf -sconf smp03.local
#smp03.local:
mailer /bin/mail
xterm /usr/bin/X11/xterm
execd_spool_dir /opt/gridengine/default/spool
\5. The global information. Have I add h_vmem and s_vmem here?
qconf -sconf
#global:
execd_spool_dir /opt/gridengine/default/spool
mailer /bin/mail
xterm /usr/bin/X11/xterm
load_sensor none
prolog none
epilog none
shell_start_mode posix_compliant
login_shells sh,ksh,csh,tcsh
min_uid 0
min_gid 0
user_lists none
xuser_lists none
projects none
xprojects none
enforce_project false
enforce_user auto
load_report_time 00:00:40
max_unheard 00:05:00
reschedule_unknown 00:00:00
loglevel log_warning
administrator_mail none
set_token_cmd none
pag_cmd none
token_extend_time none
shepherd_cmd none
qmaster_params none
execd_params ENABLE_ADDGRP_KILL=TRUE H_MEMORYLOCKED=infinity
reporting_params accounting=true reporting=true \
flush_time=00:00:15 joblog=true sharelog=00:00:00
finished_jobs 100
gid_range 20000-20100
qlogin_command builtin
qlogin_daemon builtin
rlogin_command builtin
rlogin_daemon builtin
rsh_command builtin
rsh_daemon builtin
max_aj_instances 2000
max_aj_tasks 75000
max_u_jobs 0
max_jobs 0
max_advance_reservations 0
auto_user_oticket 0
auto_user_fshare 0
auto_user_default_project none
auto_user_delete_time 86400
delegated_file_staging false
reprioritize 0
jsv_url none
jsv_allowed_mod ac,h,i,e,o,j,M,N,p,w

Answer 2

What you likely want is h_vmem. At least that is the attribute I always use to specify the memory I want request for a job.
See:
http://gridscheduler.sourceforge.net/htmlman/htmlman5/queue_conf.html?pathrev=V62u5_TAG
Specifically,
The resource limit parameters s_vmem and h_vmem are imple-
mented by Sun Grid Engine as a job limit. They impose a
limit on the amount of combined virtual memory consumed by
all the processes in the job. If h_vmem is exceeded by a job
running in the queue, it is aborted via a SIGKILL signal
(see kill(1)). If s_vmem is exceeded, the job is sent a
SIGXCPU signal which can be caught by the job. If you wish
to allow a job to be "warned" so it can exit gracefully
before it is killed then you should set the s_vmem limit to
a lower value than h_vmem. For parallel processes, the
limit is applied per slot which means that the limit is mul-
tiplied by the number of slots being used by the job before
being applied.
Also, you may need to set this as consumable using qconf.