incubator-couchdb-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Adam Kocoloski (JIRA)" <>
Subject [jira] Updated: (COUCHDB-738) more efficient DB compaction (fewer seeks)
Date Tue, 04 May 2010 05:22:56 GMT


Adam Kocoloski updated COUCHDB-738:

    Attachment: 738-efficient-compaction-v2.patch

Here's a new patch which applies cleanly to trunk@940505 and has one important change.  In
couch_view_updater:load_doc() we call couch_doc:to_doc_info() if we have a #full_doc_info{}
record before calling couch_db:open_doc_int().  The reason for this is to skip the rather
expensive call to get the entire revision path for the winning revision which shows up in
the open_doc_int clause handling #full_doc_info{} records.  With this change I get the following
timings on a 100 edits/doc DB:

Elapsed time: 5.98 (s)
Elapsed time: 5.85 (s)
Elapsed time: 4.87 (s)

Elapsed time: 0.86 (s)
Elapsed time: 1.05 (s)
Elapsed time: 0.75 (s)

Those are essentially identical to the timings I got earlier for trunk.

> more efficient DB compaction (fewer seeks)
> ------------------------------------------
>                 Key: COUCHDB-738
>                 URL:
>             Project: CouchDB
>          Issue Type: Improvement
>          Components: Database Core
>    Affects Versions: 0.9.2, 0.10.1, 0.11
>            Reporter: Adam Kocoloski
>            Assignee: Adam Kocoloski
>             Fix For: 1.1
>         Attachments: 738-efficient-compaction-v1.patch, 738-efficient-compaction-v2.patch
> CouchDB's database compaction algorithm walks the by_seq btree, then does a lookup in
the by_id btree for every document in the database.  It does this because the #full_doc_info{}
record with the full revision tree is only stored in the by_id tree.  I'm proposing instead
to store duplicate copies of #full_doc_info{} in both trees, and to have the compactor use
the by_seq tree exclusively.  The net effect is significantly fewer calls to pread(), and
an compaction IO pattern where reads tend to be clustered close to each other in the file.
> If the by_id tree is fully cached, or if the id tree nodes are located near the seq tree
nodes, the performance improvement is small but noticeable (~10% in some simple tests).  On
the other hand, in the worst-case scenario of randomly-generated docids and a database much
larger than main memory the improvement is huge.  Joe Williams did some simple benchmarks
with a 50k document, 600 MB database on a 256MB VPS.  The compaction time for that DB dropped
from 15m to 2m20s, so more than 6x faster.
> Storing the #full_doc_info{} in the seq tree also allows for some similar optimizations
in the replicator.
> This patch might have downsides when documents have a large number of edits.  These include
an increase in the size of the database and slower view indexing.  I expect both to be small
> The patch can be applied directly to trunk@934272.  Existing DBs are still readable,
new updates will be written in the new format, and databases can be fully upgraded by compacting.

This message is automatically generated by JIRA.
You can reply to this email to add a comment to the issue online.

View raw message