<montywi> I have now checked up latest 5.3
<montywi> 5.2 has: Innodb_buffer_pool_read_requests | 5545982
<montywi> 5.3 has: Innodb_buffer_pool_read_requests | 5739153
<montywi> when running a lot of between queries
<montywi> sp things are better, but not perfect...

I've checked on the provided query: the increment is still 14 (vs 13 on mariadb-5.2)

In MySQL 5.5 increment is 12

In MySQL 5.6 (revision-id: andrei.elkin@oracle.com-20120131161820-rz3uf7oqgzq6wmh2), the increment is 12, too.

In MariaDB 5.3 before ICP fixes backport (revno: 3273, revision-id: psergey@askmonty.org-20111107123902-xzbzx5y5sdeq4ojh) :
counter increment is 12

increment is 13 on r3274 (right after backport with MRR fixes) with patches from r3406 , r3407 (recent fixes by Igor)

Reported https://bugs.launchpad.net/maria/+bug/929838 (Igor's part of the work)

Checking counters increments for all revisions that made changes to xtradb.
5.3-r3388 14 13 13 13 13
5.3-r3377 14 13 13 13 13
5.3-r3344 14 13 13 13 13
5.3-r3340 14 13 13 13 13 <<
5.3-r3288 13 12 12 12 12
5.3-r3279 13 12 12 12 12

Checking counter increments in all revisions that made changes to xtradb within the 5.3-r3340 revision (which is a merge):

5.3-r3327.1.2 14 13 13 13 13
5.3-r2732.46.24 13 12 12 12 12 Igor's patches didn't apply
5.3-r2732.46.19 13 12 12 12 12 Igor's patches didn't apply
5.3-r2732.48.1 13 12 12 12 12 Igor's patches didn't apply
5.3-r2643.143.51

5.3-r2643.143.49 13 12 12 12 12 Igor's patches didn't apply
5.3-r2643.149.1 13 12 12 12 12 Igor's patches didn't apply

We get higher increments after 5.3-r3327.1.2. That revision is a merge from 5.2. 5.2 has small counter increments (13 12 12 12 12) . After the merge we get (14 13 13 13)

I installed sysbench on my computer and found the patch in mysql-5.6 after which the sysbench performance came back to normal (to the same as in mysql-5.5). (Here Sergey's script helped me a lot. Sergey, thank you.)

Note that even in the release mysql-5.6.4 they had the same performance as the latest mariadb-5.3. In my runs both showed 14 incr with Sergey'sscript while mysql-5.5 and mariadb-5.2 reached 13 incr.(In all my experiments I had always either 14 incr or 13 incr. There were no deviation from these numbers.)

So for both mariadb and mysql I observed only 1 extra request returned by Sergey's script: mariadb-5.3.4 vs mariadb-5.2/5.3.2 (14:13), mysql-5.6.4-mysql-5.5(14:13).

Here's the comment for the patch by Olav Sandstaa from mysql-server/trunk rev 3639.1.70 where he explains why we have aperformance degradation for sysbench.
<<
Revision id: olav.sandstaa@oracle.com-20111201141210-e3b0gucoy6oz2asq
Committer: Olav Sandstaa <olav.sandstaa@oracle.com>
Timestamp: Thu 2011-12-01 15:12:10 +0100

Fix for Bug#13430436 PERFORMANCE DEGRADATION IN SYSBENCH ON INNODB DUETO ICP

When running sysbench on InnoDB there is a performance degradation due to index condition pushdown (ICP). Several of the queries in sysbench have a WHERE condition that the optimizer uses for executing these queries as range scans. The upper and lower limit of the range scan will ensure that the WHERE condition is fulfilled. Still, the WHERE condition is part of the queries' condition and if ICP is enabled the condition will be pushed down to InnoDB as an index condition.

Due to the range scan's upper and lower limits ensure that the WHERE condition is fulfilled, the pushed index condition will not filter out any records. As a result the use of ICP for these queries results in a
performance overhead for sysbench. This overhead comes from using resources for determining the part of the condition that can be pushed down to InnoDB and overhead in InnoDB for executing the pushed index condition.
...
/>>

The patch was not pushed into mysql-5.6.4 that was out as late as on Dec 19 2011. My understanding is that they did not consider this fix as
a critical one. I think we equally could not to care too much about this degradation when releasing mariadb-5.3.4 RC.

Of course, the problem should be fixed for mariadb-5.3.5 GA.

I would suggest a pretty simple fix. You can read about it in my post "On the Innodb_buffer_pool_read_requests problem (part 2)" sent out to dev@sakmonty.org on Feb 10.

or> montywi, spetrunia : when it became clear that the bug is a pure ICP problem, not the problem InnoDB support for ICP that I back-ported from mysql-5.6,
<igor> should I be still reponsible for this bug?
<montywi> preferably spetrunia and you should solve it (but better to have spetrunia drive this as it's his code)
<igor> montywi: then I will reassign the bug to him.
<montywi> ok

> So for both mariadb and mysql I observed only 1 extra request returned by Sergey's script: mariadb-5.3.4 vs mariadb-5.2/5.3.2 (14:13), mysql-5.6.4-mysql-5.5(14:13).

Did I understand you correctly that: you consider counter increments up to 14 not to be a problem?

Olav's patch applied and pushed.