kafka-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From guozh...@apache.org
Subject kafka-site git commit: Update JVM version and tuning settings
Date Tue, 01 Dec 2015 19:21:20 GMT
Repository: kafka-site
Updated Branches:
  refs/heads/asf-site 53fa90aa4 -> 70833375c


Update JVM version and tuning settings

Changes copied from 0.9.0 branch of the kafka repo.


Project: http://git-wip-us.apache.org/repos/asf/kafka-site/repo
Commit: http://git-wip-us.apache.org/repos/asf/kafka-site/commit/70833375
Tree: http://git-wip-us.apache.org/repos/asf/kafka-site/tree/70833375
Diff: http://git-wip-us.apache.org/repos/asf/kafka-site/diff/70833375

Branch: refs/heads/asf-site
Commit: 70833375c410fc8e03973ea2dca78301a3b4165c
Parents: 53fa90a
Author: Ismael Juma <ismael@juma.me.uk>
Authored: Tue Dec 1 11:03:34 2015 +0000
Committer: Ismael Juma <ismael@juma.me.uk>
Committed: Tue Dec 1 11:03:34 2015 +0000

----------------------------------------------------------------------
 090/ops.html | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/kafka-site/blob/70833375/090/ops.html
----------------------------------------------------------------------
diff --git a/090/ops.html b/090/ops.html
index 2624527..04d4e7a 100644
--- a/090/ops.html
+++ b/090/ops.html
@@ -390,19 +390,23 @@ producer.purgatory.purge.interval.requests=100
 Our client configuration varies a fair amount between different use cases.
 
 <h3><a id="java" href="#java">Java Version</a></h3>
-We're currently running JDK 1.7 u51, and we've switched over to the G1 collector. If you
do this (and we highly recommend it), make sure you're on u51. We tried out u21 in testing,
but we had a number of problems with the GC implementation in that version.
 
-Our tuning looks like this:
+From a security perspective, we recommend you use the latest released version of JDK 1.8
as older freely available versions have disclosed security vulnerabilities.
+
+LinkedIn is currently running JDK 1.8 u5 (looking to upgrade to a newer version) with the
G1 collector. If you decide to use the G1 collector (the current default) and you are still
on JDK 1.7, make sure you are on u51 or newer. LinkedIn tried out u21 in testing, but they
had a number of problems with the GC implementation in that version.
+
+LinkedIn's tuning looks like this:
 <pre>
--Xms4g -Xmx4g -XX:PermSize=48m -XX:MaxPermSize=48m -XX:+UseG1GC
--XX:MaxGCPauseMillis=20 -XX:InitiatingHeapOccupancyPercent=35
+-Xmx6g -Xms6g -XX:MetaspaceSize=96m -XX:+UseG1GC
+-XX:MaxGCPauseMillis=20 -XX:InitiatingHeapOccupancyPercent=35 -XX:G1HeapRegionSize=16M
+-XX:MinMetaspaceFreeRatio=50 -XX:MaxMetaspaceFreeRatio=80
 </pre>
 
 For reference, here are the stats on one of LinkedIn's busiest clusters (at peak):
-        - 15 brokers
-        - 15.5k partitions (replication factor 2)
-        - 400k messages/sec in
-        - 70 MB/sec inbound, 400 MB/sec+ outbound
+        - 60 brokers
+        - 50k partitions (replication factor 2)
+        - 800k messages/sec in
+        - 300 MB/sec inbound, 1 GB/sec+ outbound
 
 The tuning looks fairly aggressive, but all of the brokers in that cluster have a 90% GC
pause time of about 21ms, and they're doing less than 1 young GC per second.
 


Mime
View raw message