Changes between Version 6 and Version 7 of Public/User_Guide/Filesystems

Timestamp:

Oct 22, 2019, 1:04:19 PM (5 years ago)

Author:

Jochen Kreutz

Comment:

minor updates to reflect latest HW changes (e.g. KNMs have been removed)

Public/User_Guide/Filesystems

@@ -22 +22 @@
 || /p/project || /p/project/cdeep/$USER || SDV, DEEP-EST || GPFS exported via NFS || Global || || || || Project directory;[[BR]]GPFS main storage file system;[[BR]]not suitable for performance relevant applications or benchmarking || ||
 || /work || /work/cdeep || DEEP-EST* || BeeGFS || Global || BeeGFS 7.1.2 || || || Work file system || *Also available in the SDV but only through 1 Gig network connection ||
-|| /sdv-work || /sdv-work/cdeep/$USER || SDV (deeper-sdv nodes via EXTOLL, KNL and KNM via GbE only), DEEP-EST (1 GbE only) || BeeGFS || Global || BeeGFS 7.1.2 || Type: RAID0,[[BR]]Chunksize: 512K,[[BR]]Number of storage targets: desired: 4 || 1831.85 MiB/s write, 1308.62 MiB/s read[[BR]]15202 ops/s create, 5111 ops/s remove* || Work file system || *Test results and parameters used stored in JUBE:[[BR]][[BR]]`user@deep $ cd /usr/local/deep-er/sdv-benchmarks/synthetic/ior`[[BR]]`user@deep $ jube2 result benchmarks`[[BR]][[BR]]`user@deep $ cd /usr/local/deep-er/sdv-benchmarks/synthetic/mdtest`[[BR]]`user@deep $ jube2 result benchmarks` ||
+|| /sdv-work || /sdv-work/cdeep/$USER || SDV (deeper-sdv nodes via EXTOLL, KNL and ml-gpu via GbE only), DEEP-EST (1 GbE only) || BeeGFS || Global || BeeGFS 7.1.2 || Type: RAID0,[[BR]]Chunksize: 512K,[[BR]]Number of storage targets: desired: 4 || 1831.85 MiB/s write, 1308.62 MiB/s read[[BR]]15202 ops/s create, 5111 ops/s remove* || Work file system || *Test results and parameters used stored in JUBE:[[BR]][[BR]]`user@deep $ cd /usr/local/deep-er/sdv-benchmarks/synthetic/ior`[[BR]]`user@deep $ jube2 result benchmarks`[[BR]][[BR]]`user@deep $ cd /usr/local/deep-er/sdv-benchmarks/synthetic/mdtest`[[BR]]`user@deep $ jube2 result benchmarks` ||
 || /nvme || /nvme/tmp || SDV || NVMe device || Local || BeeGFS 7.1.2 || Block size: 4K || 1145 MiB/s write,  3108 MiB/s read[[BR]]139148 ops/s create,  62587 ops/s remove* || 1 NVMe device available at each SDV compute node || *Test results and parameters used stored in JUBE:[[BR]][[BR]]`user@deep $ cd /usr/local/deep-er/sdv-benchmarks/synthetic/ior`[[BR]]`user@deep $ jube2 result benchmarks`[[BR]][[BR]]`user@deep $ cd /usr/local/deep-er/sdv-benchmarks/synthetic/mdtest`[[BR]]`user@deep $ jube2 result benchmarks` ||
 || /mnt/beeond || /mnt/beeond || SDV || BeeGFS On Demand running on the NVMe || Local || BeeGFS 7.1.2 || Block size: 512K || 1130 MiB/s write, 2447 MiB/s read[[BR]]12511 ops/s create, 18424 ops/s remove* || 1 BeeOND instance running on each NVMe device || *Test results and parameters used stored in JUBE:[[BR]][[BR]]`user@deep $ cd /usr/local/deep-er/sdv-benchmarks/synthetic/ior`[[BR]]`user@deep $ jube2 result benchmarks`[[BR]][[BR]]`user@deep $ cd /usr/local/deep-er/sdv-benchmarks/synthetic/mdtest`[[BR]]`user@deep $ jube2 result benchmarks` ||
@@ -79 +79 @@
 
 == Notes ==
- * The /work file system which is available in the DEEP-EST prototype, is as well reachable from the nodes in the SDV (including KNLs and KNMs) but through a slower connection of 1 Gig. The file system is therefore not suitable for benchmarking or I/O task intensive jobs from those nodes
+ * The /work file system which is available in the DEEP-EST prototype, is as well reachable from the nodes in the SDV (including KNLs and ml-gpu nodes) but through a slower connection of 1 Gig. The file system is therefore not suitable for benchmarking or I/O task intensive jobs from those nodes
 
  * Performance tests (IOR and mdtest) reports are available in the BSCW under DEEP-ER -> Work Packages (WPs) -> WP4 -> T4.5 - Performance measurement and evaluation of I/O software -> Jülich DEEP Cluster -> Benchmarking reports: https://bscw.zam.kfa-juelich.de/bscw/bscw.cgi/1382059
 
- * Test results and parameters used stored in JUBE:
+ * Test results and parameters used are stored in JUBE:
 
 {{{