LiveCDPerformance

Differences between revisions 1 and 34 (spanning 33 versions)
⇤ ← Revision 1 as of 2005-04-23 03:04:58 →
Size: 1227
Editor: CPE-60-225-13-161
Comment:
← Revision 34 as of 2005-11-03 23:35:12 → ⇥
Size: 2666
Editor: 245_220_103_66-WIFI_HOTSPOTS
Comment: comments
Deletions are marked like this. Additions are marked like this.
Line 1: Line 1:
## page was renamed from UbuntuDevel/LiveCDPerformance
Line 5: Line 6:
== Status ==

  * Created: [[Date(2005-04-23T03:04:58Z)]] by MattZimmerman[[BR]]
  * Priority: MediumPriority[[BR]]
  * People: NeedsLead, NeedsSecond[[BR]]
  * Contributors: MattZimmerman[[BR]]
  * Interested: [[BR]]
  * Status: BrainDump, BreezyGoal, UduBof, DistroSpecification[[BR]]
  * Branch: [[BR]]
  * Malone Bug: [[BR]]
  * Packages: [[BR]]
  * Depends: [[BR]]
  * UduSessions: 1, 4, 8, etc [[BR]]		  * '''Launchpad Entry''': https://launchpad.net/distros/ubuntu/+spec/live-cd-performance
 * '''Created''': [[Date(2005-04-23T03:04:58Z)]] by MattZimmerman[[BR]]
 * '''Contributors''': TollefFogHeen, MattZimmerman
 * '''Packages affected''': casper
Line 25: Line 17:
== Scope and Use Cases == The better the load time, the better the live CD experience, the greater chance an end user will want to use it and move on to installing Ubuntu or another distro.
Line 29: Line 21:
 1. Instrumentation is required in order to identify bottlenecks. d-i logs stage 1, we can wrap init scripts to provide timing information on their startup. Bootchart would also be useful.

'''MattZimmerman: needs more detail regarding bootchart. Where would it hook into the boot process and where would it store its results?'''

 2. Enable DMA on livecd - it may not work on some systems, but it's effectively required
 3. Optimise d-i modules that consume a large amount of time. Locale generation seems excessively slow, and potentially unnecessary for many language setups.

'''MattZimmerman: suggest that this focus only on the actions performed by casper, in light of the new live CD design (which doesn't use d-i)'''

 4. Readahead may be a performance win with 256MB or more, but slower otherwise. Verify with different memory configurations, and ensure that readahead is only enabled when it's a performance benefit. http://unit.aist.go.jp/itri/knoppix/readahead/index-en.html has figures for Knoppix on cloop.
 5. Make sure modules.dep is generated at the end of the livecd build and call `depmod --quick` in the default boot.

'''MattZimmerman: we already do this, or else it's unclear what you mean'''

 6. Filesystem comparison - squashfs and unionfs may give a performance benefit. http://listas.hispalinux.es/pipermail/metadistros-dev/2005-April/000580.html suggests a 50 second improvement.
 7. Background network setup - this can be left for when the user has hit the desktop (NetworkMagic)
Line 30: Line 39:

None.
Line 33: Line 44:
For instrumentation, init requires modification or bootchart, which will be a better choice. Performance issues in the first stage install will require d-i modifications. Any slow packages in second stage boot will need tweaks to improve performance.
Line 35: Line 48:
== Outstanding Issues == None.
Line 37: Line 50:
=== UDU BOF Agenda ===

 * d-i performance
 * casper performance
 * Ubuntu boot performance (FasterBoot)

=== UDU Pre-Work ===

 * Profile the live CD boot sequence to measure the time taken for each step
  * d-i startup (time-to-first-question)
  * Pre-casper d-i activity (measured per menu entry)
  * Casper d-i activity (measured per casper.d script)
  * Standard boot sequence		 ----
CategoryUdu
CategorySpec

Live CD Performance

Introduction

The boot time for the Ubuntu live CD should be comparable (or superior) to other popular live CDs.

Rationale

The better the load time, the better the live CD experience, the greater chance an end user will want to use it and move on to installing Ubuntu or another distro.

Implementation Plan

  1. Instrumentation is required in order to identify bottlenecks. d-i logs stage 1, we can wrap init scripts to provide timing information on their startup. Bootchart would also be useful.

MattZimmerman: needs more detail regarding bootchart. Where would it hook into the boot process and where would it store its results?

  1. Enable DMA on livecd - it may not work on some systems, but it's effectively required
  2. Optimise d-i modules that consume a large amount of time. Locale generation seems excessively slow, and potentially unnecessary for many language setups.

MattZimmerman: suggest that this focus only on the actions performed by casper, in light of the new live CD design (which doesn't use d-i)

  1. Readahead may be a performance win with 256MB or more, but slower otherwise. Verify with different memory configurations, and ensure that readahead is only enabled when it's a performance benefit. http://unit.aist.go.jp/itri/knoppix/readahead/index-en.html has figures for Knoppix on cloop.

  2. Make sure modules.dep is generated at the end of the livecd build and call depmod --quick in the default boot.

MattZimmerman: we already do this, or else it's unclear what you mean

  1. Filesystem comparison - squashfs and unionfs may give a performance benefit. http://listas.hispalinux.es/pipermail/metadistros-dev/2005-April/000580.html suggests a 50 second improvement.

  2. Background network setup - this can be left for when the user has hit the desktop (NetworkMagic)

Data Preservation and Migration

None.

Packages Affected

For instrumentation, init requires modification or bootchart, which will be a better choice. Performance issues in the first stage install will require d-i modifications. Any slow packages in second stage boot will need tweaks to improve performance.

User Interface Requirements

None.

CategoryUdu CategorySpec

LiveCDPerformance (last edited 2008-08-06 16:14:57 by localhost)