You are viewing a plain text version of this content. The canonical link for it is here.
Posted to notifications@couchdb.apache.org by jaydoane <gi...@git.apache.org> on 2016/09/11 05:10:17 UTC
[GitHub] couchdb-couch issue #185: 3061 adaptive header search
Github user jaydoane commented on the issue:
https://github.com/apache/couchdb-couch/pull/185
I have simplified the pread/2 based header search, and hopefully addressed most of the issues raised against the previous implementations. For a simple speed comparison using the same file as before, the new algorithm was measured to be about 13x faster than the current algorithm. When 4 such files are searched in parallel, it's only about 7x faster. Nevertheless, it uses many fewer disk reads, imposes less load and even seems to use less memory, as shown in the graphs below. It also seems like the file:advise/4
This first image shows first a single search using the default algorithm starting around 19:27 and ending around 19:35, followed by a single search using the pread/2 algorithm from around 19:43 to 19:45
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---