We just pushed to sysbench support for workload against multiple tables ( traditionally it used only single table).
It is available from launchpad source tree lp:sysbench .
This is set of LUA scripts for sysbench 0.5 ( it supports scripting), and it works following way:
- you should use --test=tests/db/oltp.lua to runtest
i.e. prepare ./sysbench --test=tests/db/oltp.lua --oltp-tables-count=25 prepare
run: ./sysbench --test=tests/db/oltp.lua --oltp-tables-count=25 --num-threads=5 run
As continuation of my CPU benchmarks it is interesting to see what is scalability limitation in 5.6.2, and I am going to check that using PERFORMANCE SCHEMA, but before that let's estimate what is potential overhead of using PERFORMANCE SCHEMA. So I am going to run the same benchmarks (sysbench read-only and read-write) as in previous post with different performance schema options and compare results.
I am going to use Cisco C250
with next settings:
PERFORMANCE SCHEMA disabled (NO PS)
Having two big boxes in our lab, one based Cisco ) and second on AMD Opteron ( C250 Dell ), I decided to run some simple sysbench benchmark to compare how both R815 perform and what kind of scalability we can expect.(
It is hard to make apples to apples comparison, but I think it is still interesting.
Cisco UCS C250 has total 12 cores / 24 threads of Intel Nehalem X5670, and Dell PowerEdge R815 has 48 cores of AMD Opteron 6168.
It is well known fact that InnoDB standard page size is 16K or 16384 bytes. Sometime ago we added feature to Percona Server to change that to 4K or 8K ( innodb_page_size ). That maybe useful for SSD that operates with 4K blocks and you can get really much better throughput with 4K ( however we need to run benchmarks yet to see real effect from it).
The bigger limitation is that this setting is for whole database instance and you need to mysqldump your data, re-create database and load data.
After MySQL 5.5 moved to CMake, and cygwin compilation is not supported anymore, it took some efforts for us to come up with native Windows builds, but they are there already. We consider them "alpha" quality, as there some know limitations,
but you should be able to make backup and restore from it. If you are interested in Windows backup I encourage …
There were recent discussion about DROP TABLE performance in,
It may not sound that serious, but if your workload often uses DROP TABLE and you have big buffer pool it may be significant issue. And this is getting especially …
…helper script README-Solaris for building on. ( Vadim Tkachenko)
Changes were made to the post-install messages ( Ignacio Nin)
Bug # 631667 - The mysql binary is now built with readline support so that command line browsing is possible. ( Ignacio Nin)
Bug # 727704 - When …
Added option --extra-lsndir to innobackupex . When specified for the backup phase, the option is passed to xtrabackup , and lsn information is stored with the file in the specified directory. This is needed so that lsn information is preserved during stream backup. ( Vadim Tkachenko)
Added option --incremental-lsn to innobackupex . If specified, this option …
I mentioned problems with previous post .flushing in a
Before getting to ideas on a solution, let's define some terms and take a look into theory.
The two most important parameters for InnoDB performance are innodb_buffer_pool_size and innodb_log_file_size .
InnoDB works with data in memory, and all changes to data are performed in memory. In order to survive a crash or system failure, InnoDB is logging changes into InnoDB transaction logs. The size of …
You may have seen in the last couple of weekly news posts that Baron mentioned we are working on a new adaptive flushing algorithm in InnoDB. In fact, we already have three such algorithms in Percona Server (reflex, estimate, keep_average). Why do we need one more? Okay, first let me start by showing the current problems, and then we will go to solutions.
The basic problem is that, unfortunately, none of the existing flushing implementations (including both MySQL native adaptive flushing …