Differences

This shows you the differences between two versions of the page.

--- doku:scratch [2014/06/18 08:58] – [Global parallel file system] ir
+++ doku:scratch [2015/03/23 09:31] (current) – dieter
@@ Line 1: / Line 1: @@
-====== Global parallel file system ======
+===== Scratch Directories on VSC_2 =====
-**F**raun**h**ofer **G**lobal **F**ile **S**ystem (FhGFS)
-\\or\\
-BeeGFS/FhGFS - The Fraunhofer Parallel Cluster File System
-===== Scratch Directories =====
 In addition to $HOME, which is fine to use for standard jobs with rather few small files (<1000 files, overall size <1G), there are a number of specialized scratch directories.
-The [[http://www.fhgfs.com/cms/documentation|Fraunhofer parallel cluster file system (FhGFS)]] is used in $GLOBAL and $SCRATCH.
+The [[http://www.fhgfs.com/cms/documentation|Fraunhofer parallel cluster file system (FhGFS)/BeeGFS]] is used in $GLOBAL and $SCRATCH.
 === Global Personal Scratch Directories $GLOBAL ===
@@ Line 20: / Line 16: @@
 The Fraunhofer parallel file system is shared by all users and by all nodes.
 Single jobs producing heavy load (>>1000 requests per second) have been observed to reduce responsiveness for all jobs and all users.
+Lifetime of data is limited, see table below.
 === Per-node Scratch Directories $SCRATCH ===
@@ Line 70: / Line 68: @@
 |                      || $GLOBAL                        || $SCRATCH               || $TMPDIR                 || $JOBLOCAL (experimental) ||
 | Recommended file size || large                         || large                  || small                   || small ||
-| Lifetime             || until file system failure      || job                    || job                     || job ||
+| Lifetime             || files older than 180 days deleted if $GLOBAL space is running low     || job                    || job                     || job ||
 | Size                 || x00 TB (for all users)         || x00 TB (for all users) || a few GB (within memory) || about 5 GB (hard limit: 32GB) ||
-| Scaling              || troubles with very many small file accesses (from more than 100 nodes) || troubles with very many small file accesses (from more than 100 nodes) || no problem (local) || no problem (local) ||
+| Scaling              || does not fit very large number of small file IO || does not fit very large number of small file IO  || no problem (local) || no problem (local) ||
 | Visibility           || global                         || node (see above)      || node                    || job ||
-| Recommended usage     || large files, available after job life || large files    || small files, or many seek-operations within a file || many small files (>1000), or many seek-operations within a file ||
+| Recommended usage     || large files, available temporarily after job life || large files    || small files, or many seek-operations within a file || many small files (>1000), or many seek-operations within a file ||