Re: 10X decrease in performance with Ignite 2.0.0

2017-05-12 Thread Denis Magda
Chris, These are some links for reference: 1. BinaryObject and BinaryObjectBuilder interfaces usage: https://apacheignite.readme.io/docs/binary-marshaller#section-binaryobject-cache-api

How to deploy ignite service evenly across the cluster ?

2017-05-12 Thread dany74q
Hi everyone, We use ignite's (1.7.4) service grid to deploy hundreds of (different) services in our cluster. There's a behavior we've noticed, once deploying that many services, that they tend do deploy unevenly in the cluster, that means that we can get to a point where a great number of

Re: 10X decrease in performance with Ignite 2.0.0

2017-05-12 Thread Sergi Vladykin
According to our benchmarks Ignite 2.0 is not slower for get operation. I think we need some minimal reproducer that shows the performance degradation before making any conclusions. Sergi 2017-05-12 1:10 GMT+03:00 Yakov Zhdanov : > Cross-posting to devlist. > > --Yakov >

Re: 10X decrease in performance with Ignite 2.0.0

2017-05-12 Thread Yakov Zhdanov
Absolutely agree here. I think if we can add getAll() benchmark and run it with batch sizes of 5 and 10. Thanks! -- Yakov Zhdanov, Director R *GridGain Systems* www.gridgain.com 2017-05-12 10:48 GMT+03:00 Sergi Vladykin : > According to our benchmarks Ignite 2.0 is not

Re: Ignite 2.0 C++ Segfault

2017-05-12 Thread Igor Sapego
Hi, Thanks for the report - I'll investigate the issue and let you know. We do not use std::shared_ptr as we want to let C++03 applications use Ignite too. Best Regards, Igor On Fri, May 12, 2017 at 11:56 AM, tolga wrote: > There seems to be some kind of race situation:

Kindly tell me where to find these jar files.

2017-05-12 Thread blasteralfred
Hi all, I am using *kafka - 0.10.2.0*, *ignite - 1.6.0*. Kafka is installed in my linux box (confluent) and ignite in my windows, both are connected and up. I would like to insert to ignite cache from Kafka topic, so that I have followed `## Streaming Data to Ignite via Kafka Connect` described

Re: 10X decrease in performance with Ignite 2.0.0

2017-05-12 Thread Yakov Zhdanov
I think it will also be useful to switch to offheap tiered (cacheConfig.setMemoryMode()) in 1.9 and compare results again. --Yakov 2017-05-12 11:30 GMT+03:00 Alexey Goncharuk : > Hi Chris, > > One of the most significant changes made in 2.0 was moving to an off-heap

Re: 10X decrease in performance with Ignite 2.0.0

2017-05-12 Thread Alexey Goncharuk
Hi Chris, One of the most significant changes made in 2.0 was moving to an off-heap storage by default. This means that each time you do a get(), your value gets deserialized, which might be an overhead (though, I would be a bit surprised if this causes the 10x drop). Can you try setting

Re: Ignite 2.0 C++ Segfault

2017-05-12 Thread tolga
There seems to be some kind of race situation: 0x01381206 in std::less::operator() (this=0x1a4e4b0, __x=, __y=@0x7fff80846e04: 2066246303) at /usr/include/c++/6.3.1/bits/stl_function.h:386 #4 0x015040cd in ignite::impl::binary::BinaryTypeManager::GetHandler (this=0x1a560d0,

what does CurrentCpuLoad in ClusterLocalNodeMetricsMXBeanImpl means?

2017-05-12 Thread bluehu
what does CurrentCpuLoad in ClusterLocalNodeMetricsMXBeanImpl means? "the TOTAL system cpuload" or "cpuload the node consume"? -- View this message in context: http://apache-ignite-users.70518.x6.nabble.com/what-does-CurrentCpuLoad-in-ClusterLocalNodeMetricsMXBeanImpl-means-tp12658.html Sent

Re: Kindly tell me where to find these jar files.

2017-05-12 Thread Humphrey
I've done the same thing, but just with Ignite 1.9.1 and all on one Linux machine, but that wouldn't matter. I used maven repository to get the jar files for me. I can share my dependencies of pom.xml with you. The jars are only needed on the machine where you start Ignite. Change the

Ignite 2.0 C++ Segfault

2017-05-12 Thread Tolga HOŞGÖR
The following segfault happens in multi-threaded ignite c++ application: C [test+0xf8116a] std::less::operator()(int const&, int const&) const+0x14 C [test+0x1106305] std::_Rb_tree, std::_Select1st >, std::less, std::allocator >

Re: Kindly tell me where to find these jar files.

2017-05-12 Thread blasteralfred
Hi Humphrey, Thanks for your reply.I am trying to use *Kafka Connect* for pushing to Kafka, and from there, to Ignite, and that's why I have asked for jar files. Its okay, that I can try the Stream also. I have no idea on how to use streams, and the examples I have found were, not in a beginner

Re: 10X decrease in performance with Ignite 2.0.0

2017-05-12 Thread Chris Berry
Yakov, The entire reason we use the Compute Grid is because the data employed to do the compute is large (~0.25MB) and we compute 200 at once (spread across the grid -- so ~20 per Node w/ 10 Nodes). So I do not doubt that moving the data from off-heap-memory could be large. Is there a way to try

Re: Kindly tell me where to find these jar files.

2017-05-12 Thread Humphrey Lopez
I'm not able to help you out today but Monday I can send you some code. I used the ignite Kafka streamer to get the messages from Kafka. So ignite is pulling from Kafka rather than Kafka pushing to ignite. Humphrey > On 12 May 2017, at 10:15, blasteralfred wrote: >

Re: Ignite Authentication using .Net C# client.

2017-05-12 Thread Pavel Tupitsyn
Hi, this can be done by implementing security in Java and setting it up via Spring config xml and IgniteConfiguration.SpringConfigUrl in .NET. There is no direct support yet. On Fri, May 12, 2017 at 5:16 PM, virs wrote: > Hi, > > I am trying to implement authentication

Re: Network errors while running scan queries

2017-05-12 Thread Nikolai Tikhonov
Hello, It looks like you server was unavailable in some period. It might be different reasons, but probably it gc pause on server node. Could you enable gc logs and share it? -- View this message in context:

Re: HDP, Hive + Ignite

2017-05-12 Thread Ivan Veselovsky
Alena, as I understand, the message "19988 Killed "$JAVA"" means that the Ignite node process was killed by the operating system. Can you please see the kernel log -- what does it say near the node crash time? -- View this message in context:

Re: 10X decrease in performance with Ignite 2.0.0

2017-05-12 Thread Chris Berry
Hi, I hope this helps. This is the flow. It is very simple. Although, the code in the ComputeJob (executor.compute(request, algType, correlationId);) is relatively application complex. I hope this code makes sense. I had to take the actual code and expunge all of the actual Domain bits from

Re: Concurrent job execution and FifoQueueCollisionSpi.parallelJobsNumber=1

2017-05-12 Thread ryan
I used the previously provided example and duplicated the issue in the Ignite 2.0 release on Windows 10 I also created an issue: IGNITE-5183 On 4/12/2017 2:15 PM, Ryan Ripken wrote: I tried the below example with Ignite 1.9 and I continue

Understanding the mechanics of peer class loading

2017-05-12 Thread Ilya
Hi all! The question was originally asked (but not answered) on SO: http://stackoverflow.com/questions/43803402/how-does-peer-classloading-work-in-apache-ignite In short, we have "Failed to deploy user message" exceptions under high load in our project. Here is an overview of our architecture:

Ignite Authentication using .Net C# client.

2017-05-12 Thread virs
Hi, I am trying to implement authentication from .Net/C# client but could not find any straight forward way to do that. Though Java api provides method like setSecurityCredentialsProvider for ignite configuration. It seems its not there for .Net API. It will be really helpfull if someone can

Alerting and Eventing in Ignite

2017-05-12 Thread Swetad90
Hi, I went through the docs on Apache Ignite Alerting & Eventing - https://apacheignite.readme.io/docs/events https://apacheignite-tools.readme.io/v1.9/docs/alerts-configuration Here is my usecase - 1. Start up 5 server nodes to form 1 cluster group 2. Include events on default events(ie NODE

Re: 10X decrease in performance with Ignite 2.0.0

2017-05-12 Thread Dmitriy Setrakyan
Chris, After looking at your code, the only slow down that may have occurred between 1.9 and 2.0 is the actual cache "get(...)" operation. As you may already know, Ignite 2.0 has moved data off-heap completely, so we do not cache data in the deserialized form any more, by default. However, you

Re: 10X decrease in performance with Ignite 2.0.0

2017-05-12 Thread Chris Berry
Thank you. I will try on Monday (-ish) Yes, the objects are large. (average ~0.25MB) Could you please tell me the magic config I will need to try both these options? If not, I will do my homework. Thank you again, -- Chris -- View this message in context:

Apache Ignite weekly update

2017-05-12 Thread Dieds
Hi Igniters, We have 4 new blog posts (starting from May 5) of interest to you this past week. https://ignite.apache.org/blogs.html And if you're in Miami next week, I'm sure you'll be attending ApacheCon North America -- if so please checkout Denis Magda's talks on May 18 there: * Apache