diskpagebuffer table provides statistics
about disk page buffer usage by NDB Cluster Disk Data tables.
diskpagebuffer table contains the
The data node ID
Number of pages written to disk.
Number of pages written by local checkpoints.
Number of pages read from disk
Number of page writes waiting for log to be written to disk
Number of requests for pages that were available in buffer
Number of requests that had to wait for pages to become available in buffer
Number of requests that had to be read from pages on disk (pages were unavailable in buffer)
You can use this table with NDB Cluster Disk Data tables to
sufficiently large to allow data to be read from the buffer
rather from disk; minimizing disk seeks can help improve
performance of such tables.
You can determine the proportion of reads from
the total number of reads using a query such as this one, which
obtains this ratio as a percentage:
SELECT node_id, 100 * page_requests_direct_return / (page_requests_direct_return + page_requests_wait_io) AS hit_ratio FROM ndbinfo.diskpagebuffer;
The result from this query should be similar to what is shown here, with one row for each data node in the cluster (in this example, the cluster has 4 data nodes):
+---------+-----------+ | node_id | hit_ratio | +---------+-----------+ | 5 | 97.6744 | | 6 | 97.6879 | | 7 | 98.1776 | | 8 | 98.1343 | +---------+-----------+ 4 rows in set (0.00 sec)
hit_ratio values approaching 100% indicate
that only a very small number of reads are being made from disk
rather than from the buffer, which means that Disk Data read
performance is approaching an optimum level. If any of these
values are less than 95%, this is a strong indicator that the
needs to be increased in the
A change in
requires a rolling restart of all of the cluster's data
nodes before it takes effect.
block_instance column provides the NDB
kernel block instance number. You can use this to obtain
information about specific threads from the