kudu-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From jdcry...@apache.org
Subject kudu git commit: Add a note in the YCSB post
Date Wed, 19 Jul 2017 19:46:03 GMT
Repository: kudu
Updated Branches:
  refs/heads/gh-pages 6158de4b7 -> e94e04d29


Add a note in the YCSB post

Last year we posted results in a blog post and recommended users
try some configurations related to flushing. We then changed the
defaults in the next version, but we still see instances of users
taking that post as gospel.

Change-Id: Ife414e34388cff6b139580d76d44a2c3477b9abe
Reviewed-on: http://gerrit.cloudera.org:8080/7396
Reviewed-by: Todd Lipcon <todd@apache.org>
Tested-by: Jean-Daniel Cryans <jdcryans@apache.org>


Project: http://git-wip-us.apache.org/repos/asf/kudu/repo
Commit: http://git-wip-us.apache.org/repos/asf/kudu/commit/e94e04d2
Tree: http://git-wip-us.apache.org/repos/asf/kudu/tree/e94e04d2
Diff: http://git-wip-us.apache.org/repos/asf/kudu/diff/e94e04d2

Branch: refs/heads/gh-pages
Commit: e94e04d292d9fe8edb188b0677f1799b5890412f
Parents: 6158de4
Author: Jean-Daniel Cryans <jdcryans@apache.org>
Authored: Tue Jul 11 09:49:14 2017 -0700
Committer: Jean-Daniel Cryans <jdcryans@apache.org>
Committed: Wed Jul 19 19:45:34 2017 +0000

----------------------------------------------------------------------
 _posts/2016-04-26-ycsb.md | 3 +++
 1 file changed, 3 insertions(+)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/kudu/blob/e94e04d2/_posts/2016-04-26-ycsb.md
----------------------------------------------------------------------
diff --git a/_posts/2016-04-26-ycsb.md b/_posts/2016-04-26-ycsb.md
index a6942d6..a845bb3 100644
--- a/_posts/2016-04-26-ycsb.md
+++ b/_posts/2016-04-26-ycsb.md
@@ -365,6 +365,9 @@ I anticipate that improvements to the Java client's backoff behavior will
make t
 
 Overall conclusions
 ====
+
+**07/11/17 Update: As of Kudu 0.10.0, the default configuration was changed based on the
results of the above exploration. We recommend against modifying these configuration variables
in Kudu 1.0 or later.**
+
 From these experiments, it seems clear that changing the defaults would be beneficial for
heavy write workloads, regardless of whether the writer is using batching or not. The consistency
of performance is increased as well as the overall throughput.
 
 We will likely make these changes in the next Kudu release. In the meantime, users can experiment
by adding the following flags to their tablet server configuration:


Mime
View raw message