| From: | Bruce Momjian <bruce(at)momjian(dot)us> |
|---|---|
| To: | PostgreSQL-development <pgsql-hackers(at)postgreSQL(dot)org> |
| Subject: | Performance tests with parallel gmake |
| Date: | 2010-11-27 21:18:01 |
| Message-ID: | 201011272118.oARLI1q02199@momjian.us |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
I ran some tests on my dual-Xeon machine to see what speedup using
parallel gmake. After two builds to warm up the cache, I saw when
alternating gmake and gmake -j2:
gmake 0m57.207s
gmake -j2 0m44.305s
gmake 0m58.691s
gmake -j2 0m33.979s
As you can see, gmake -j2 is ~35% faster than gmake without -j. I will
be using -j from now on. -j3 shaves another second off.
FYI, I also use ccache for compiles.
--
Bruce Momjian <bruce(at)momjian(dot)us> http://momjian.us
EnterpriseDB http://enterprisedb.com
+ It's impossible for everything to be true. +
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Bruce Momjian | 2010-11-27 22:30:11 | Re: What do these terms mean in the SOURCE CODE? |
| Previous Message | Tom Lane | 2010-11-27 21:11:17 | Re: Small documentation enhancement for default_tablespace |