On Fri, Dec 23, 2011 at 2:54 PM, Heikki Linnakangas <heikki.linnakan...@enterprisedb.com> wrote: > Sorry. Last minute changes, didn't retest properly.. Here's another attempt.
I tried this one out on Nate Boley's system. Looks pretty good. m = master, x = with xloginsert-scale-2 patch. shared_buffers = 8GB, maintenance_work_mem = 1GB, synchronous_commit = off, checkpoint_segments = 300, checkpoint_timeout = 15min, checkpoint_completion_target = 0.9, wal_writer_delay = 20ms. pgbench, scale factor 100, median of five five-minute runs. Permanent tables: m01 tps = 631.875547 (including connections establishing) x01 tps = 611.443724 (including connections establishing) m08 tps = 4573.701237 (including connections establishing) x08 tps = 4576.242333 (including connections establishing) m16 tps = 7697.783265 (including connections establishing) x16 tps = 7837.028713 (including connections establishing) m24 tps = 11613.690878 (including connections establishing) x24 tps = 12924.027954 (including connections establishing) m32 tps = 10684.931858 (including connections establishing) x32 tps = 14168.419730 (including connections establishing) m80 tps = 10259.628774 (including connections establishing) x80 tps = 13864.651340 (including connections establishing) And, on unlogged tables: m01 tps = 681.805851 (including connections establishing) x01 tps = 665.120212 (including connections establishing) m08 tps = 4753.823067 (including connections establishing) x08 tps = 4638.690397 (including connections establishing) m16 tps = 8150.519673 (including connections establishing) x16 tps = 8082.504658 (including connections establishing) m24 tps = 14069.077657 (including connections establishing) x24 tps = 13934.955205 (including connections establishing) m32 tps = 18736.317650 (including connections establishing) x32 tps = 18888.585420 (including connections establishing) m80 tps = 17709.683344 (including connections establishing) x80 tps = 18330.488958 (including connections establishing) Unfortunately, it does look like there is some raw loss of performance when WALInsertLock is NOT badly contended; hence the drop-off at a single client on permanent tables, and up through 24 clients on unlogged tables. -- Robert Haas EnterpriseDB: http://www.enterprisedb.com The Enterprise PostgreSQL Company -- Sent via pgsql-hackers mailing list (pgsql-hackers@postgresql.org) To make changes to your subscription: http://www.postgresql.org/mailpref/pgsql-hackers
