The xrootd data server disk space is obtained twice a day and written to a nfs log directory. From these values a simple table with the last usage values is created:
The data are also loaded to an Oracle database and are accessible through a web application (currently in test stage):
The disk space usage values are stored in Oracle. A key-value together with the date is recorded. The following key names are used:
Key | Description |
---|---|
xrootd_freeGB_<server> | free disk space in GB for <server>, e.g.: xrootd_freeGB_wain021 |
xrootd_diskGB_<server> | disk size in GB for <server> |
xrootd_usedGB_<server> | used disk space in GB for <server>, (xrootd_diskGB_server> - xrootd_freeGB_<server>) |
xrootd_all_freeGB | free disk space in GB summed over all xrootd data servers. |
xrootd_all_xrdfreeGB | free space that XRootD sees. A XRootD server is full once its space drops below a minimum (~2% of total space). |
xrootd_all_diskGB | disk size in GB summed over all xrootd data servers. |
xrootd_all_usedGB | used disk space in GB summed over all xrootd data servers, (xrootd_all_diskGB - xrootd_all_freeGB) |
The cronjob, running in crontab on each xrootd data server, is
/opt/xrootd/admin/mon_diskspace.sh
It collects the total and free diskspcae as well as the inode usage for ufs file systems (zfs has no inode restrictions).
The disk usage is stored in files:
/nfs/farm/g/glast/u15/xrootd/diskspace/df_server_YYYYMM
where server is the server name and YYYYMM is the year and month the values were collected. For example
/nfs/farm/g/glast/u15/xrootd/diskspace/df_wain020_200806
Each line in these files shows the disk usage for a particular date. The format is:
DF <date> <server> <totalSpace> <freeSpace> <%Used> [<inodesFree> <%inodesFree>]
The format of date is YYYYMMDDTHHMMSS, e.g. 20080712T123258. The totalSpace and freeSpace are in GB. The inode info is only shown for serves that use the ufs file system (all sulkies) but not for the servers that employ zfs.
In order to calculate the free disk and total disk space of the xrootd cluster the values, taken around the same time , for all data servers have to be summed.