Re: [HACKERS] MIT benchmarks pgsql multicore (up to 48)performance
От
Robert Haas
Тема
Re: [HACKERS] MIT benchmarks pgsql multicore (up to 48)performance
Дата
Msg-id
AANLkTikKaNhHHimcO1XPdwvTCa-HYH4UJAGwgHjTKaQM@mail.gmail.com
Ответ на
Re: [HACKERS] MIT benchmarks pgsql multicore (up to
48)performance (Kevin Grittner)
Список
Дерево обсуждения
MIT benchmarks pgsql multicore (up to 48)performance Hakan Kocaman <hkocam@googlemail.com>
Re: [HACKERS] MIT benchmarks pgsql multicore (up to 48)performance Dan Ports <drkp@csail.mit.edu>
Re: [HACKERS] MIT benchmarks pgsql multicore (up to 48)performance Josh Berkus <josh@agliodbs.com>
Re: [HACKERS] MIT benchmarks pgsql multicore (up to 48)performance Ivan Voras <ivoras@freebsd.org>
Re: [HACKERS] MIT benchmarks pgsql multicore (up to 48)performance Tom Lane <tgl@sss.pgh.pa.us>
Re: [HACKERS] MIT benchmarks pgsql multicore (up to 48)performance Ivan Voras <ivoras@freebsd.org>
Re: [HACKERS] MIT benchmarks pgsql multicore (up to 48)performance Robert Haas <robertmhaas@gmail.com>
Re: [HACKERS] MIT benchmarks pgsql multicore (up to
48)performance Stephen Frost <sfrost@snowman.net>
Re: [HACKERS] MIT benchmarks pgsql multicore (up to 48)performance Robert Haas <robertmhaas@gmail.com>
Re: [HACKERS] MIT benchmarks pgsql multicore (up to
48)performance Stephen Frost <sfrost@snowman.net>
Re: [HACKERS] MIT benchmarks pgsql multicore (up to 48)performance Robert Haas <robertmhaas@gmail.com>
Re: [HACKERS] MIT benchmarks pgsql multicore (up to
48)performance "Kevin Grittner" <Kevin.Grittner@wicourts.gov>
Re: [HACKERS] MIT benchmarks pgsql multicore (up to
48)performance Stephen Frost <sfrost@snowman.net>
Re: [HACKERS] MIT benchmarks pgsql multicore (up to
48)performance "Kevin Grittner" <Kevin.Grittner@wicourts.gov>
Re: [HACKERS] MIT benchmarks pgsql multicore (up to 48)performance Robert Haas <robertmhaas@gmail.com>
Re: [HACKERS] MIT benchmarks pgsql multicore (up to 48)performance Ivan Voras <ivoras@freebsd.org>
Re: [HACKERS] MIT benchmarks pgsql multicore (up to 48)performance Jon Nelson <jnelson+pgsql@jamponi.net>
Re: MIT benchmarks pgsql multicore (up to 48)performance Scott Marlowe <scott.marlowe@gmail.com>
On Thu, Oct 7, 2010 at 1:21 PM, Kevin Grittner wrote: > Robert Haas wrote: > >> perhaps it would be possible by, say, increasing the number of >> lock partitions by 8x. It would be nice to segregate these issues >> though, because using pread/pwrite is probably a lot less work >> than rewriting our lock manager. > > You mean easier than changing this 4 to a 7?: > > #define LOG2_NUM_LOCK_PARTITIONS 4 > > Or am I missing something? Right. They did something more complicated (and, I think, better) than that, but that change by itself might be enough to ameliorate the lock contention enough to see the lsek() issue. -- Robert Haas EnterpriseDB: http://www.enterprisedb.com The Enterprise Postgres Company
В списке pgsql-performance по дате отправления
