Rechercher dans le manuel MySQL

22.5.10.20 The ndbinfo diskpagebuffer Table

Table des matières

The diskpagebuffer table provides statistics about disk page buffer usage by NDB Cluster Disk Data tables.

The following table provides information about the columns in the diskpagebuffer table. For each column, the table shows the name, data type, and a brief description. Additional information can be found in the notes following the table.

Table 22.394 Columns of the diskpagebuffer table

Column Name Type Description
node_id integer The data node ID
block_instance integer Block instance
pages_written integer Number of pages written to disk.
pages_written_lcp integer Number of pages written by local checkpoints.
pages_read integer Number of pages read from disk
log_waits integer Number of page writes waiting for log to be written to disk
page_requests_direct_return integer Number of requests for pages that were available in buffer
page_requests_wait_queue integer Number of requests that had to wait for pages to become available in buffer
page_requests_wait_io integer 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 determine whether DiskPageBufferMemory is 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 DiskPageBufferMemory to the total number of reads using a query such as this one, which obtains this ratio as a percentage:

  1. SELECT
  2.   node_id,
  3.   100 * page_requests_direct_return /
  4.     (page_requests_direct_return + page_requests_wait_io)
  5.       AS hit_ratio
  6. 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):

  1. +---------+-----------+
  2. | node_id | hit_ratio |
  3. +---------+-----------+
  4. |       5 |   97.6744 |
  5. |       6 |   97.6879 |
  6. |       7 |   98.1776 |
  7. |       8 |   98.1343 |
  8. +---------+-----------+
  9. 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 setting for DiskPageBufferMemory needs to be increased in the config.ini file.

Note

A change in DiskPageBufferMemory requires a rolling restart of all of the cluster's data nodes before it takes effect.

block_instance refers to an instance of a kernel block. Together with the block name, this number can be used to look up a given instance in the threadblocks table. Using this information, you can obtain information about disk page buffer metrics relating to individual threads; an example query using LIMIT 1 to limit the output to a single thread is shown here:

  1. mysql> SELECT
  2.      >   node_id, thr_no, block_name, thread_name, pages_written,
  3.      >   pages_written_lcp, pages_read, log_waits,
  4.      >   page_requests_direct_return, page_requests_wait_queue,
  5.      >   page_requests_wait_io
  6.      > FROM ndbinfo.diskpagebuffer
  7.      >   INNER JOIN ndbinfo.threadblocks USING (node_id, block_instance)
  8.      >   INNER JOIN ndbinfo.threads USING (node_id, thr_no)
  9.      > WHERE block_name = 'PGMAN' LIMIT 1\G
  10. *************************** 1. row ***************************
  11.                     node_id: 1
  12.                      thr_no: 1
  13.                  block_name: PGMAN
  14.                 thread_name: rep
  15.               pages_written: 0
  16.           pages_written_lcp: 0
  17.                  pages_read: 1
  18.                   log_waits: 0
  19. page_requests_direct_return: 4
  20.    page_requests_wait_queue: 0
  21.       page_requests_wait_io: 1
  22. 1 row in set (0.01 sec)

Rechercher dans le manuel MySQL

Traduction non disponible

Le manuel MySQL n'est pas encore traduit en français sur l'infobrol. Seule la version anglaise est disponible pour l'instant.

Document créé le 26/06/2006, dernière modification le 26/10/2018
Source du document imprimé : https://www.gaudry.be/mysql-rf-mysql-cluster-ndbinfo-diskpagebuffer.html

L'infobrol est un site personnel dont le contenu n'engage que moi. Le texte est mis à disposition sous licence CreativeCommons(BY-NC-SA). Plus d'info sur les conditions d'utilisation et sur l'auteur.

Références

  1. Consulter le document html Langue du document :en Manuel MySQL : https://dev.mysql.com/

Ces références et liens indiquent des documents consultés lors de la rédaction de cette page, ou qui peuvent apporter un complément d'information, mais les auteurs de ces sources ne peuvent être tenus responsables du contenu de cette page.
L'auteur de ce site est seul responsable de la manière dont sont présentés ici les différents concepts, et des libertés qui sont prises avec les ouvrages de référence. N'oubliez pas que vous devez croiser les informations de sources multiples afin de diminuer les risques d'erreurs.

Table des matières Haut