Downport of InnoDB/ICP from mysql 5.6 increased Innodb_buffer_pool_read_requests

Bug #929838 reported by Sergey Petrunia
8
This bug affects 1 person
Affects Status Importance Assigned to Milestone
MariaDB
In Progress
High
Sergey Petrunia

Bug Description

After downport of InnoDB/ICP from mysql 5.6 (revno: 2955, revision-id: <email address hidden>) the number of Innodb_buffer_pool_read_requests made by the sample query has increased.

Fixed made by
revno: 3406 revision-id: <email address hidden>
revno: 3407 revision-id: <email address hidden>

address the problem for the most part, but certain difference remains.

Changed in maria:
milestone: none → 5.3
Revision history for this message
Sergey Petrunia (sergefp) wrote :

Ways to repeat:

1. Make the dataset:
./sysbench --test=./tests/db/oltp.lua --oltp-table-size=10000000 \
--db-driver=mysql --mysql-user=root --mysql-socket=/tmp/mysqld.sock \
--mysql-table-engine=innodb prepare

2. Prepare two trees,
1. "Before" tree: 5.3 branched at -r2954
2. "After" tree: 5.3, branched at -r2955, with 3406

Run the attached script and watch the difference in output:

"Before" tree produces (showing only lines with 'OUT'):

incr OUT
13 OUT
incr OUT
12 OUT
incr OUT
12 OUT
incr OUT
12 OUT
incr OUT
12 OUT

"After" tree produces (showing only lines with 'OUT'):
incr OUT
14 OUT
incr OUT
13 OUT
incr OUT
13 OUT
incr OUT
13 OUT
incr OUT
13 OUT

Revision history for this message
Sergey Petrunia (sergefp) wrote :

The script.
- it is intended to be run from sql/ directory of a tree
- modify to point to your my.cnf file, which should specify a datadir with pre-loaded sysbench data as specified in earlier comments.

Changed in maria:
assignee: nobody → Igor Babaev (igorb-seattle)
Revision history for this message
Sergey Petrunia (sergefp) wrote :

If you have trouble compiling the tree because of "warnings being treated as errors", here is a patch that shuts that off.

Revision history for this message
Sergey Petrunia (sergefp) wrote :

The dataset is at:

work.askmonty.org:/tmp/sysbench-data-10m.sql.bz2

Revision history for this message
Igor Babaev (igorb-seattle) wrote :

We have a performance degradation for sysbench that was explained in Olav's Sandstaa patch for mysql-5.6. (see rev 3639.1.70 of lp:mysql-server/trunk )
Olav dis not suggest any more or less general solution. He just prohibited using ICP for innodb primary clustered keys.

Changed in maria:
importance: Undecided → High
status: New → Confirmed
status: Confirmed → In Progress
Changed in maria:
assignee: Igor Babaev (igorb-seattle) → Sergey Petrunia (sergefp)
To post a comment you must log in.
This report contains Public information  
Everyone can see this information.

Other bug subscribers