Task #3528
Story #3526: Material required for Reverse Site Visit
Collate total storage space available at all member nodes
100%
Description
We need to report on the total storage available at the production nodes.
For each production node (MN and CN) determine the total space available and the total free space currently available in GB.
This will likely involve contacting node operators to get these numbers.
History
#1 Updated by Ben Leinfelder over 11 years ago
There are a couple things to consider here (using KNB as an example):
1. Size of the files on disk (/var/metacat/*)
Used:
sudo du -ch /var/metacat/ | grep total
173G total
Available:
sudo df -h /var/metacat
Filesystem Size Used Avail Use% Mounted on
/dev/mapper/mn--ucsb--3--var-var
15T 325G 14T 3% /var
2. Size of the Postgres databaseSELECT pg_size_pretty(pg_database_size('knb'));¶
59 GB
The available space will therefore be less than the free disk space since there is overhead of the Postgres DB. Tracking a 1 GB data file and a 1 KB data file takes the same space in the Postgres table. For the KNB this is currently 34% of the disk usage. I suppose we could knock off a third of the available space to get a more realistic estimate, but given that we do not know how large (or small) the data files will be on any given node this is a very crud estimate.
#2 Updated by Ben Leinfelder over 11 years ago
I have reports from all but ORNL.
#3 Updated by Ben Leinfelder over 11 years ago
- File d1_node_storage.xlsx added
- File d1_node_storage.xlsx added
#4 Updated by Ben Leinfelder over 11 years ago
- File deleted (
d1_node_storage.xlsx)
#5 Updated by Ben Leinfelder over 11 years ago
- File d1_node_storage.xlsx added
- File d1_node_storage.xlsx added
All nodes are now reported in the attached spreadsheet
#6 Updated by Ben Leinfelder over 11 years ago
- Status changed from New to Closed
- translation missing: en.field_remaining_hours set to 0.0
