Franck MIKULECZ's List: SOFTWARE PLATFORM PERFORMANCE

• How is RabbitMQ scaled and the load balance handled?
• Erlang/OTP to distribute one logical AMQP  broker across several physical nodes
• In general, it is better to create a single connection and as many channels as you need  (rather than many connections with a single channel each).
• How can I check the depth of a particular queue?
• The rabbitmqctl documentation has more information about the various options you can use with this command
• Is there a publicly available demonstration broker that I can use to experiment with  WAN AMQP connections?
• Here are the connection details:
• Does Rabbit MQ support broker to broker connections?
• 5672:tcp
• How low can latency be?
• sub-millisecond latency in transient mode under a load of  10k messages per second
• 3-5k messages per second stored to disk
• • We should be able to switch ON persistence on a per message basis for "CANCEL Quote" messages !
    I read it was possible in one of the messaging systems...
    that would accelerate the PE operation for example, as we would have non persistent for all but the CANCEL messages.
• 4000 persistent, non-transacted  one-kilobyte messages per second (Intel Pentium D,  2.8GHz, dual core, gigabit ethernet)
• How do I switch off persistence/transactionality?
• the clustering guide?
• • GPU ?
• As a result, one queue with one producer sending persistent messages   may well use up to, say, 2.5 cores, but it won't be possible to push that  wider. As you add further queues, you will be able to use more CPU cores.

• How is RabbitMQ licensed (for redistribution, etc.)?

   

   

    RabbitMQ is distributed under the open-source Mozilla Public License.
• integration with other management systems

  • Zabbix ?

• How should I interpret RabbitMQ's version numbering?

   

   

    RabbitMQ is versioned with the scheme  major.minor.patch.

  • How about ours ?

19 more annotations...

• project administrators

  • This will be interesting for our next project

• In Scala since version 2.8 it is not the case – generics are specialized for primitive types. I would rather say that what I dislike in C++ is their crappy implementation of generics based on dumb text substitution, with no proper type bounds and variance control. Feels extremely limited in comparison to what Scala generics have to offer.
• In computation, Java is the same as C++. In optimization (algorithms) Java is better than C++. Where C++ wins, is in working with memory. Its possible to make cache-aware programs in C++, while in Java it is impossible. There is no control over allocation in Java. One thing that could improve that (allocating lots of small objects in cache-aware manner, without garbage-collection overhead), would be the introduction a structs, with explicit storage in ByteBuffer-s

  • We need to find this Arpad...
• In Java RT (Jsr 1) you have far more control over memory allocation, including doing your own deallocation
• lucene

  • Text Search from Apache
• Consider Netty. In my benchmarks it was faster than Nginx, the fastest contender

  • NIO from JBoss
• any ** complex ** programs involving sockets and complex memory access patterns (i.e., complex object structures possibly requiring synchronized access) will usually be better in Java
• I use compiled (native) code for all performance critical and low level requirements, and Java for the rest. This appears to be the ideal architecture

5 more annotations...