Bug #40815 Data/undo files are when initialized written 32k at a time

• Submitted: 18 Nov 2008 11:20
• Modified: 19 Nov 2008 10:49
• Reporter: Jonas Oreland
• Status: Closed
• Category: Server: Cluster
• Severity: S3 (Non-critical)
• OS: Any
• Assigned to: Jonas Oreland

[18 Nov 2008 11:20] Jonas Oreland

Description:
When creating a datafile or a undofile
(or soon redo-file), the file is written 32k at a time.

This can give poor io-throughput

How to repeat:
create data/undo file(s)

Suggested fix:
improve write size

[18 Nov 2008 11:21] Bugs System

A patch for this bug has been committed. After review, it may
be pushed to the relevant source trees for release in the next
version. You can access the patch from:

  http://lists.mysql.com/commits/59046

2750 Jonas Oreland	2008-11-18
      ndb - bug#40815 - increase init-write-size to 512k

[18 Nov 2008 11:22] Jonas Oreland

this patch increases to 512k

[18 Nov 2008 11:31] Bugs System

Pushed into 5.1.29-ndb-6.4.0  (revid:[e-mail]-20081118102128-d2pqz3oz0b9rad96)
(version source revid:[e-mail]-20081118102803-7wuzv99dlrvsbv46) (pib:5)

[18 Nov 2008 11:33] Bugs System

Pushed into 5.1.29-ndb-6.3.19  (revid:[e-mail]-20081118102128-d2pqz3oz0b9rad96)
(version source revid:[e-mail]-20081118102128-d2pqz3oz0b9rad96) (pib:5)

[18 Nov 2008 18:17] Jon Stephens

Documented bugfix in the NDB-6.3.19 changelog as follows:

        Redo logs, undo logs, and data files were created in 32K increments. 
        Now these files are created in 512K increments, resulting in shorter
        creation times.

[18 Nov 2008 20:55] Jonas Oreland

redo are not affected
(yet... but might be if I push the SparseInitFragmentLogfiles)

[19 Nov 2008 10:49] Jon Stephens

Amended changelog entry per comment from Jonas. Closed.