List:Database Benchmarks« Previous MessageNext Message »
From:Peter Zaitsev Date:October 11 2005 11:00pm
Subject:Re: default my.cnf vs huge.cnf nearly same performance withs
ql-bench/run-all-tests
View as plain text  
On Sat, 2005-09-10 at 12:16 -0500, Matthew Lenz wrote:
> infact .. the default debian config (some of these are just explicit
> defaults but this is what debian provides):

Hi, 

Thanks for Info.  Actually results for 1 and 2 are close in most cases, 
In few cases the difference is large (ie create table) results are just
frequently very unstable.   I would do the run 3 times or so to check if
it is just accuracy or  results are really different.

Note sql-bench is test which does not perform complex operation, it also
does not use large data sizes this is why benefit of larger buffers may
be close to zero or even negative. 

Ie read_buffer_size    is set  to 2MB which means when table scan is
started 2MB read will be performed to read the buffer.   But actually if
you just needed one row  (ie LIMIT 1) smaller buffer could be more
efficient. 




> 
> [mysqld]
> user            = mysql
> pid-file        = /var/run/mysqld/mysqld.pid
> socket          = /var/run/mysqld/mysqld.sock
> port            = 3306
> basedir         = /usr
> datadir         = /var/lib/mysql
> tmpdir          = /tmp
> language        = /usr/share/mysql/english
> skip-external-locking
> old_passwords   = 1
> key_buffer              = 16M
> max_allowed_packet      = 16M
> thread_stack            = 128K
> query_cache_limit       = 1048576
> query_cache_size        = 16777216
> query_cache_type        = 1
> log-bin                 = /var/log/mysql/mysql-bin.log
> max_binlog_size         = 104857600
> skip-bdb
> 
> outperforms the huge.cnf example:
> 
> [mysqld]
> user                    = mysql
> pid-file                = /var/run/mysqld/mysqld.pid
> socket                  = /var/run/mysqld/mysqld.sock
> port                    = 3306
> basedir                 = /usr
> datadir                 = /var/lib/mysql
> tmpdir                  = /tmp
> language                = /usr/share/mysql/english
> old_passwords           = 1
> key_buffer              = 384M
> max_allowed_packet      = 16M
> table_cache             = 512
> sort_buffer_size        = 2M
> read_buffer_size        = 2M
> read_rnd_buffer_size    = 8M
> myisam_sort_buffer_size = 64M
> query_cache_size        = 32M
> thread_concurrency      = 8
> log-bin                 = /var/log/mysql/mysql-bin.log
> server-id               = 1
> skip-bdb
> skip-external-locking
> 
> in almost every regard.  What gives? :)  This is a pretty beefy config:
> 
> dual 3ghz HT xeon .. 2gig 800mhz fsb mem .. U320 SCSI RAID5.  I've
> attached a compare-results for a few machines.  the only important ones
> are 1 and 2.  1 is debians my.cnf and 2 is the slightly modified
> huge.cnf example.  What about that thread_concurrency setting in
> huge.cnf.. it doesn't seem to show up in a 'show variables' when using
> it.. is it deprecated?
> 
> -Matt
>  
>  -- MySQL Server Benchmarks Mailing List For list archives:
> http://lists.mysql.com/benchmarks To unsubscribe:
> http://lists.mysql.com/benchmarks?unsub=1
-- 
Peter Zaitsev, Senior Performance Engineer
MySQL AB, www.mysql.com

Thread
default my.cnf vs huge.cnf nearly same performance withs ql-bench/run-all-testsMatthew Lenz10 Sep
  • Re: default my.cnf vs huge.cnf nearly same performance withsql-bench/run-all-testsPeter Zaitsev12 Oct