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 black_bg
Web: Multi-page, Single page | PDF: A4-size, Letter-size | eBook: epub black_bg

Configuring the PostgreSQL Database

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.

[return to top]

SRM or srm monitoring on a separate node

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