For a general description of RCF facilities go here
RHIC General Use
rssh.rhic.bnl.gov - ssh-only gateway (round-robins between different machines).
NOTE: Once you are on a gateway, you can ssh to the machine name without
specifying the net:
E.g. to get to rcas4002, just type
> ssh rcas4002 [ENTER]
Interactive machines:
As of mid-2010, all machines run Condor but two are also usable for
interactive work. On these nodes, Condor jobs run at lower priority.
Used to login, edit files, run programs etc. rcrs4027,
4028
Large Data Transfers Use:
rftpexp.rcf.bnl.gov - scp/kftp/ssh-ftp
gateway. Linux
Analysis Machines:
Accessible by interactive direct login or by using the LSF batch queue system. from
an interactive machine. Available for use by phobos collaborators.
The following is all old, not sure what, if any, is still valid.
LSF and Condor only (No interactive login unless specified above)
LSF queues for MC (Monte Carlo) and analysis. Non-general Phobos use queues are specified.
LSF queue(s) |
Condor CPU_speed |
machines(dual CPU) |
speed |
#machines |
purpose |
phslow | 1 | rcrs4001-4029 |
450 MHz |
29 |
CS, analysis, MC |
phcas |
1 2 |
rcrs4030-4074, rcrs4075-4138 |
800 MHz, 1 GHz |
88 |
analysis, repass, MC |
phcasfast |
3 | rcrs4139-4165 |
1.4 GHz |
48 |
analysis, repass, MC |
phcrs |
4 5 |
rcrs4166-4264 rcrs4265-4301 |
2.4 GHz 3.1 GHz |
99 37 |
new data production, analysis, MC |
(none) | 5 | rcrs4302-4339 | 3.1 GHz | 38 | new data production, analysis, MC |
Specific queue details
(User job limit, time limit (in CPU-hours, not actual hours), and job priority)
Queue Notes:
For summer 2004, production repasses will be done on phcrs, so jobs running on those
queues may be superceded by production.
For how to setup to use LSF queues, see (updated October 13, 2003!) the LSF in Phobos web page
For more information on LSF queues availability and use (somewhat old document) see here.
Central Reconstruction Server (CRS):
Accessible in batch through
Tom Throwe's Reconstruction
Control Software scripts. Is being replaced by Condor-based CRS system with similar
interface.
PHOBOS-specific
instructions should eventually appear here.
Use of this resource should be
coordinated through Marguerite.
CRS Queues:
CRS Queue No.= 6
Use
= Runs all phobos reconstruction/Pass0 jobs +MC when necessary. (By permission only, takes
priority over phcrs LSF jobs).
Machine IP's = rcrs4265->rcrs4339
Machine Specs = 75 dual Pentium-IIIs (3060 MHz). Running RedHat Linux 8
CRS Queue No.= 5
Use
= Runs all phobos reconstruction/Pass0 jobs +MC when necessary. (By permission only, takes
priority over phcrs LSF jobs).
Machine IP's = rcrs4166->rcrs4264
Machine Specs = 99 dual Pentium-IIIs (2400 MHz). Running RedHat Linux 8
CRS Queue No.= 4
Use
= Runs MC jobs & repass jobs primarily. Overflow on production. Will take priority
over phcasfast LSF jobs.
Machine IP's = rcrs4139->rcrs4165
Machine Specs = 48 dual Pentium-IIIs (1400 MHz). Running RedHat Linux 8
CRS Queue No. = 3
Use
= Runs MC jobs & repass jobs primarily. Not normally production. Will take priority
over phcas LSF jobs.
Machine IP's = rcrs4075-rcrs4138
Machine Specs = 64 dual Pentium-IIIs (1000 MHz). Running RedHat Linux 8
CRS Queues = 2
Use
= Runs MC jobs primarily, repass/production jobs only if necessary. Will take priority
over phcas LSF jobs
Machine IP's = rcrs4030->rcrs4074
Machine Specs = 45 dual Pentium-IIIs (800 MHz). Running RedHat Linux 8
CRS Queue No.= 1
Use
= Runs Checksum jobs for data taking & MC jobs. (By permission only, priority over
phslow LSF jobs)
Machine IP's = rcrs4001->rcrs4029
Machine Specs = 29 dual Pentium-IIIs (450 MHz). Running RedHat Linux 8
Click here
for current CRS usage.
For more information on CRS queues availability and use goto here.
Official RCF list of CAS machines & CRS machines
NFS/Centralized Disk Servers
rmine401 (phobmds)- You should not login here. This node has access to HPSS and also the big disks are served/mounted from this machine (/phobos/u,/phobos/data/common, $SCR,$SCR2,/data02. i.e. home/user directories,phobos common file directories, $DV_OUT).
rmine402 - You should not login here. This node has access to HPSS and also the big disks are nfs served from this machine (/phobos/data2000 (1TB),/phobos/data2001 (1TB), /phobos/userdata(0.66TB),/phobos/mc(0.78 TB)).
Tape Servers/Data Movers
rmdsXX: these nodes are non-interactive but move the data in HPSS.
Distributed Disk:
Each rcas and rcrs machine has locally mounted disks on it, which are available through CatWeb for storage and access of data on the distributed disk system. Currently it has ~88 TB total space.
Email Server
rcf.rhic.bnl.gov- email server, can not directly login to, has a separate password from the rest of the facility. For details go here.
Print Queue Server+Solaris machine+quota information
rcf2.rhic.bnl.gov - Sees NFS mounted disks, has print queues, do not
use as a gateway, but good for Netscape etc. Operating system Solaris. May have some
software individual rcas nodes don't. Can find out quota with vxquota -v username
on rcf2 (not on rcas machines).
Note: To login to interactive nodes from rcf2 need to connect to the linux gateway. This
is done by ssh rssh.rhic.bnl.gov
This page is randomly maintained by Burt Holzman
Last Edited: Wednesday, September 15, 2010 15:42