release notes
| Book:
1.9.5,
1.9.12 (opt, FHS),
2.6 (FHS),
2.7 (FHS),
2.8 (FHS),
2.9 (FHS),
2.10 (FHS),
2.11 (FHS),
| Wiki
| Q&A
We highly recommend to make sure that PostgreSQL database files are stored on a separate disk that is not used for anything else (not even PostgreSQL logging). BNL Atlas Tier 1 observed a great improvement in srm-database communication performance after they deployed PostgreSQL on a separate dedicated machine.
If SRM or srm monitoring is going to be installed on a
separate node, you need to add an entry in the file
/var/lib/pgsql/data/pg_hba.conf for this
node as well:
host all all <monitoring node> trust host all all <srm node> trust
The file postgresql.conf should contain the following:
#to enable network connection on the default port
max_connections = 100
port = 5432
...
shared_buffers = 114688
...
work_mem = 10240
...
#to enable autovacuuming
stats_row_level = on
autovacuum = on
autovacuum_vacuum_threshold = 500 # min # of tuple updates before
# vacuum
autovacuum_analyze_threshold = 250 # min # of tuple updates before
# analyze
autovacuum_vacuum_scale_factor = 0.2 # fraction of rel size before
# vacuum
autovacuum_analyze_scale_factor = 0.1 # fraction of rel size before
#
# setting vacuum_cost_delay might be useful to avoid
# autovacuum penalize general performance
# it is not set in US-CMS T1 at Fermilab
#
# In IN2P3 add_missing_from = on
# In Fermilab it is commented out
# - Free Space Map -
max_fsm_pages = 500000
# - Planner Cost Constants -
effective_cache_size = 16384 # typically 8KB each