Does Zabbix's "InnoDB Buffer Pool Efficiency" Calculation Formula Seem Backwards?

[[email protected]]

Zabbix's formula for calculating buffer pool efficiency is...

last(//mysql.innodb_buffer_pool_reads) /
( last(//mysql.innodb_buffer_pool_read_requests) +
( last(//mysql.innodb_buffer_pool_read_requests) = 0 ) ) * 100 *
( last(//mysql.innodb_buffer_pool_read_requests) > 0 )

That yields extremely low numbers. On a database that is showing 650K read requests per second, of which only 15 reads go to disk, Zabbix says that is 0.009% efficiency, but it seems to me that the opposite is true. The pool is being 99.998% efficient. What am I missing?

[Yafimm]

The formula for calculating buffer pool efficiency in Zabbix is:

last(//mysql.innodb_buffer_pool_reads) / ( last(//mysql.innodb_buffer_pool_read_requests) + ( last(//mysql.innodb_buffer_pool_read_requests) = 0 ) ) * 100 * ( last(//mysql.innodb_buffer_pool_read_requests) > 0 )
This formula calculates the ratio of reads from the buffer pool to read requests, and then multiplies it by 100 to express it as a percentage.

It looks like you are experiencing an issue where the calculated efficiency is much lower than expected, despite a large number of read requests being served from the buffer pool.

There are a few possible reasons for this:

1. The formula may be incorrect: It is possible that the formula itself is incorrect, or that it is not being applied correctly in Zabbix. Make sure that the formula is being applied correctly, and check for any errors or issues in the formula itself.
2. The data being collected may be incorrect: Make sure that the data being collected for the buffer pool reads, read requests, and other related metrics is accurate and up to date. If the data is incorrect, the calculated efficiency will also be incorrect.
3. The buffer pool may not be sized appropriately: If the buffer pool is not large enough to accommodate all of the read requests, it will result in a higher number of reads from disk, which will lower the calculated efficiency. Make sure that the buffer pool is sized appropriately for your workload.

I hope this helps! Let me know if you have any questions.

[imghch]

Innodb_buffer_pool_reads: The number of logical reads that InnoDB could not satisfy from the buffer pool, and had to read directly from disk. So, it is a bad guy, the lower the better.