![(please configure the [header_logo] section in trac.ini)](/trac/issm/chrome/common/trac_banner.png)
Changes between Version 2 and Version 3 of andes
- Timestamp:
- 05/01/24 16:15:07 (12 months ago)
Legend:
- Unmodified
- Added
- Removed
- Modified
-
andes
v2 v3 23 23 == Password-less ssh == 24 24 25 Discovery**officially** suggests using `GSSAPI` for passwordless access, see [[https://services.dartmouth.edu/TDClient/1806/Portal/KB/ArticleDet?ID=89203|here]].25 Andes **officially** suggests using `GSSAPI` for passwordless access, see [[https://services.dartmouth.edu/TDClient/1806/Portal/KB/ArticleDet?ID=89203|here]]. 26 26 27 27 On your local machine, you will need to enter: … … 29 29 kinit -f -l 7d username@KIEWIT.DARTMOUTH.EDU 30 30 }}} 31 with your NetID at `username` and the password for NetID to request a ticket for 7 days (or any time period you need), then you can use {{{ssh discovery}}} without entering a password.31 with your NetID at `username` and the password for NetID to request a ticket for 7 days (or any time period you need), then you can use {{{ssh andes}}} without entering a password. 32 32 33 33 == Environment == 34 34 35 On Discovery, add the following lines to `~/.bashrc`:35 On Andes, add the following lines to `~/.bashrc`: 36 36 {{{ 37 37 #!sh … … 88 88 srun --nodes=1 --ntasks-per-node=16 --pty /bin/bash 89 89 }}} 90 == Installing ISSM with CoDiPack (AD) on Discovery==90 == Installing ISSM with CoDiPack (AD) on Andes == 91 91 92 92 You will need to install the following additional packages: … … 123 123 }}} 124 124 125 == discovery_settings.m ==126 127 You have to add a file in `$ISSM_DIR/src/m` entitled ` discovery_settings.m` with your personal settings on your local ism install:125 == andes_settings.m == 126 127 You have to add a file in `$ISSM_DIR/src/m` entitled `andes_settings.m` with your personal settings on your local ism install: 128 128 129 129 {{{ … … 134 134 }}} 135 135 136 use your NetID for the `login` and enter your code path and execution path. These settings will be picked up automatically by matlab when you do `md.cluster= discovery()`137 138 The file sytem on Discoveryis called DartFS (or DarFS-hpc). Your home directory on DartFS is only 50GB, it would be better to use the lab folder which has 1TB:136 use your NetID for the `login` and enter your code path and execution path. These settings will be picked up automatically by matlab when you do `md.cluster= andes()` 137 138 The file sytem on Andes is called DartFS (or DarFS-hpc). Your home directory on DartFS is only 50GB, it would be better to use the lab folder which has 1TB: 139 139 {{{ 140 140 #!sh … … 149 149 {{{ 150 150 #!m 151 md.cluster = discovery('numnodes',1,'cpuspernode',8);151 md.cluster = andes('numnodes',1,'cpuspernode',8); 152 152 }}} 153 153 … … 156 156 157 157 Each node has it's own time limit for jobs that are being run from the queue, but they tend to be 10 or 30 days. 158 You can find the time limit of each node by entering on Discovery:158 You can find the time limit of each node by entering on Andes: 159 159 {{{ 160 160 #!sh 161 161 sinfo 162 162 }}} 163 If you are running something interactively on Discovery, there may be a credential limit for the DartFS system of 10 hours.163 If you are running something interactively on Andes, there may be a credential limit for the DartFS system of 10 hours. 164 164 Read more here: [[https://services.dartmouth.edu/TDClient/1806/Portal/KB/ArticleDet?ID=76691]] 165 165 166 Now if you want to check the status of your job and the node you are using, type in the bash with the Discoverysession:166 Now if you want to check the status of your job and the node you are using, type in the bash with the Andes session: 167 167 {{{ 168 168 #!sh … … 193 193 If you want to use more than one node (not recommended), the current (temporary) solution is to:\\ 194 194 1) start the job\\ 195 2) go to Discovery and see which nodes discoveryis using (see `squeue` usage below)\\195 2) go to Andes and see which nodes andes is using (see `squeue` usage below)\\ 196 196 3) cancel the job (see `scancel` usage below)\\ 197 197 4) find the .queue script for your run and manually edit the start of the mpirun command to look like:
