[JBoss JIRA] (ISPN-5981) Compatibility mode: HotRod client sends request to wrong owner
by Galder Zamarreño (JIRA)
[ https://issues.jboss.org/browse/ISPN-5981?page=com.atlassian.jira.plugin.... ]
Galder Zamarreño updated ISPN-5981:
-----------------------------------
Git Pull Request: https://github.com/infinispan/infinispan/pull/3893, https://github.com/infinispan/infinispan/pull/3898 (was: https://github.com/infinispan/infinispan/pull/3893)
> Compatibility mode: HotRod client sends request to wrong owner
> --------------------------------------------------------------
>
> Key: ISPN-5981
> URL: https://issues.jboss.org/browse/ISPN-5981
> Project: Infinispan
> Issue Type: Bug
> Components: Remote Protocols
> Affects Versions: 8.0.1.Final, 8.1.0.Beta1
> Reporter: Dan Berindei
> Assignee: Galder Zamarreño
> Fix For: 8.2.0.Alpha1, 8.2.0.Final
>
> Attachments: GetAllCompatDistTest.java
>
>
> The HotRod client computes the hash on the serialized key, i.e. {{MurmurHash3.hash(obj2bytes(key))}}, but the server decides the entry location based on the unmarshalled key, i.e. {{MurmurHash3.hash(key.hashCode())}}.
> I've modified {{GetAllCompatDistTest}} (attached) to test if there are any {{ClusteredGetCommand}}s being sent for {{RemoteCache.get(key)}} operations, and it finds quite a few:
> {noformat}
> java.lang.AssertionError: expected:<100> but was:<147>
> at org.testng.AssertJUnit.fail(AssertJUnit.java:59) ~[testng-6.8.8.jar:?]
> at org.testng.AssertJUnit.failNotEquals(AssertJUnit.java:364) ~[testng-6.8.8.jar:?]
> at org.testng.AssertJUnit.assertEquals(AssertJUnit.java:80) ~[testng-6.8.8.jar:?]
> at org.testng.AssertJUnit.assertEquals(AssertJUnit.java:245) ~[testng-6.8.8.jar:?]
> at org.testng.AssertJUnit.assertEquals(AssertJUnit.java:252) ~[testng-6.8.8.jar:?]
> at org.infinispan.client.hotrod.GetAllCompatDistTest.testGetWithCompatibility(GetAllCompatDistTest.java:57) ~[test-classes/:?]
> {noformat}
--
This message was sent by Atlassian JIRA
(v6.4.11#64026)
8 years, 5 months
[JBoss JIRA] (ISPN-6027) Use bundler sender-sends-with-timer by default
by Dan Berindei (JIRA)
[ https://issues.jboss.org/browse/ISPN-6027?page=com.atlassian.jira.plugin.... ]
Dan Berindei commented on ISPN-6027:
------------------------------------
Turns out we use {{OOB | DONT_BUNDLE}}, which disables bundling on the sender side *only* when {{sender-sends-with-timer}} is selected. That would explain why {{sender-sends-with-timer}} improves the throughput, even if it's actually being worse than {{transfer-queue}} when it's in use!
> Use bundler sender-sends-with-timer by default
> ----------------------------------------------
>
> Key: ISPN-6027
> URL: https://issues.jboss.org/browse/ISPN-6027
> Project: Infinispan
> Issue Type: Task
> Components: Configuration, Core
> Affects Versions: 8.1.0.Final
> Reporter: Dan Berindei
> Assignee: Dan Berindei
> Fix For: 8.2.0.Alpha1
>
>
> Performance tests show {{sender-sends-with-timer}} is still a bit faster than {{transfer-queue}}, so we should make it the default.
--
This message was sent by Atlassian JIRA
(v6.4.11#64026)
8 years, 5 months
[JBoss JIRA] (ISPN-6027) Use bundler sender-sends-with-timer by default
by Dan Berindei (JIRA)
[ https://issues.jboss.org/browse/ISPN-6027?page=com.atlassian.jira.plugin.... ]
Dan Berindei commented on ISPN-6027:
------------------------------------
[~belaban] It was a {{radargun}} test with 4 nodes, testing via HotRod, the cache was replicated, and the get:put ratio was 2:1.
I didn't realize {{sender-sends-with-timer}} was on its way out in 4.0. TBH this was a bit of a rush decision because we've noticed a regression on the product side, but we should definitely investigate the bundlers more for JGRP-1997.
> Use bundler sender-sends-with-timer by default
> ----------------------------------------------
>
> Key: ISPN-6027
> URL: https://issues.jboss.org/browse/ISPN-6027
> Project: Infinispan
> Issue Type: Task
> Components: Configuration, Core
> Affects Versions: 8.1.0.Final
> Reporter: Dan Berindei
> Assignee: Dan Berindei
> Fix For: 8.2.0.Alpha1
>
>
> Performance tests show {{sender-sends-with-timer}} is still a bit faster than {{transfer-queue}}, so we should make it the default.
--
This message was sent by Atlassian JIRA
(v6.4.11#64026)
8 years, 5 months
[JBoss JIRA] (ISPN-5981) Compatibility mode: HotRod client sends request to wrong owner
by RH Bugzilla Integration (JIRA)
[ https://issues.jboss.org/browse/ISPN-5981?page=com.atlassian.jira.plugin.... ]
RH Bugzilla Integration commented on ISPN-5981:
-----------------------------------------------
Sebastian Łaskawiec <slaskawi(a)redhat.com> changed the Status of [bug 1285381|https://bugzilla.redhat.com/show_bug.cgi?id=1285381] from POST to MODIFIED
> Compatibility mode: HotRod client sends request to wrong owner
> --------------------------------------------------------------
>
> Key: ISPN-5981
> URL: https://issues.jboss.org/browse/ISPN-5981
> Project: Infinispan
> Issue Type: Bug
> Components: Remote Protocols
> Affects Versions: 8.0.1.Final, 8.1.0.Beta1
> Reporter: Dan Berindei
> Assignee: Galder Zamarreño
> Fix For: 8.2.0.Alpha1, 8.2.0.Final
>
> Attachments: GetAllCompatDistTest.java
>
>
> The HotRod client computes the hash on the serialized key, i.e. {{MurmurHash3.hash(obj2bytes(key))}}, but the server decides the entry location based on the unmarshalled key, i.e. {{MurmurHash3.hash(key.hashCode())}}.
> I've modified {{GetAllCompatDistTest}} (attached) to test if there are any {{ClusteredGetCommand}}s being sent for {{RemoteCache.get(key)}} operations, and it finds quite a few:
> {noformat}
> java.lang.AssertionError: expected:<100> but was:<147>
> at org.testng.AssertJUnit.fail(AssertJUnit.java:59) ~[testng-6.8.8.jar:?]
> at org.testng.AssertJUnit.failNotEquals(AssertJUnit.java:364) ~[testng-6.8.8.jar:?]
> at org.testng.AssertJUnit.assertEquals(AssertJUnit.java:80) ~[testng-6.8.8.jar:?]
> at org.testng.AssertJUnit.assertEquals(AssertJUnit.java:245) ~[testng-6.8.8.jar:?]
> at org.testng.AssertJUnit.assertEquals(AssertJUnit.java:252) ~[testng-6.8.8.jar:?]
> at org.infinispan.client.hotrod.GetAllCompatDistTest.testGetWithCompatibility(GetAllCompatDistTest.java:57) ~[test-classes/:?]
> {noformat}
--
This message was sent by Atlassian JIRA
(v6.4.11#64026)
8 years, 5 months
[JBoss JIRA] (ISPN-6027) Use bundler sender-sends-with-timer by default
by Dan Berindei (JIRA)
Dan Berindei created ISPN-6027:
----------------------------------
Summary: Use bundler sender-sends-with-timer by default
Key: ISPN-6027
URL: https://issues.jboss.org/browse/ISPN-6027
Project: Infinispan
Issue Type: Task
Components: Configuration, Core
Affects Versions: 8.1.0.Final
Reporter: Dan Berindei
Assignee: Dan Berindei
Fix For: 8.2.0.Alpha1
Performance tests show {{sender-sends-with-timer}} is still a bit faster than {{transfer-queue}}, so we should make it the default.
--
This message was sent by Atlassian JIRA
(v6.4.11#64026)
8 years, 5 months
[JBoss JIRA] (ISPN-6003) Reduce number of allocations
by RH Bugzilla Integration (JIRA)
[ https://issues.jboss.org/browse/ISPN-6003?page=com.atlassian.jira.plugin.... ]
RH Bugzilla Integration commented on ISPN-6003:
-----------------------------------------------
Vaclav Dedik <vdedik(a)redhat.com> changed the Status of [bug 1272390|https://bugzilla.redhat.com/show_bug.cgi?id=1272390] from POST to MODIFIED
> Reduce number of allocations
> ----------------------------
>
> Key: ISPN-6003
> URL: https://issues.jboss.org/browse/ISPN-6003
> Project: Infinispan
> Issue Type: Task
> Components: Core, Server
> Reporter: Dan Berindei
> Assignee: Dan Berindei
> Labels: performance
> Fix For: 8.1.0.Final
>
>
> Profiling revealed some allocations that are easy to remove:
> * The HotRod operations factory stores a list of flags in a thread-local. The thread-local can be removed, and the flags can be stored in an {{int}}.
> * JGroupsTransport copies the list of members to check if a broadcast should be sent as a unicast, and the copy is then discarded.
> * ExtendedByteBuf could use {{Array.empty}} instead of {{Array[Byte]()}}.
> * DecoratedCache could avoid calling {{Arrays.asList()}}.
--
This message was sent by Atlassian JIRA
(v6.4.11#64026)
8 years, 5 months