Changes between Version 3 and Version 4 of Doc/env/TgccCurie
- Timestamp:
- 07/23/14 16:17:32 (10 years ago)
Legend:
- Unmodified
- Added
- Removed
- Modified
-
Doc/env/TgccCurie
v3 v4 148 148 149 149 ## SSD on standard node : how to use it for rebuild job ## 150 SSD usage could accelerate rebuild job. It's very usefull for medium and high resolution configuration like IPSLCM5A-MR. You have only to change header and RUN_DIR_PATH in rebuild.job. Take care you will run faster but cost will be multiplicated by a factor of 16 because standard node ie 16 cpus are dedicated. 150 SSD usage could accelerate rebuild job. It's very usefull for medium and high resolution configuration like IPSLCM5A-MR. You have only to change header and RUN_DIR_PATH in rebuild.job. Take care you will run faster but cost will be multiplicated by a factor of 16 because standard node ie 16 cpus are dedicated. Beware of the size of the /tmp (64GB/node) : if you have configuration with very high resolution and very high output frequency, the /tmp of standard node could be too small; in this case see below. 151 151 152 152 {{{ … … 154 154 #MSUB -x # exclusive node 155 155 RUN_DIR_PATH=/tmp/REBUILD_DIR_MR_$$ 156 }}} 157 158 ## RAM on fat node : how to use it for rebuild job ## 159 If /tmp of standard node (64GB) is too small for you, you can use fat node. You have to know the /tmp of fat node is also of 64GB. You have to use the RAM disk which is 250GB/node. You have only to change header and RUN_DIR_PATH in rebuild.job. Take care you will run faster but cost will be multiplicated by a factor of 128 because fat node ie 128 cpus are dedicated. 160 161 {{{ 162 #MSUB -q xlarge # thin nodes 163 #MSUB -x # exclusive node 164 RUN_DIR_PATH=/dev/shm/REBUILD_DIR_MR_$$ 156 165 }}} 157 166