I looked online for a while and besides the source code on github, there are only tutorials on how to use torque.
Can someone give and overview of how it actually work? what are the algorithms?
I'm asking this because i'm trying to understand what is the scaling complexity, how it compares with spark/hadoop in terms of startup time of for jobs. I think these question will clarify with a basic understanding of how things work. For example, is it similar to linux's CFS?
In Torque a scheduler is decoupled from the queue, job and process management. That means that one can run different schedulers.
The two no cost schedulers provided with Torque are
The basic scheduler pbs_sched that implements a fifo with constraints.
MAUI that implements several scheduling policies, such as fairshare, backfill based on wallclock limits, and a tunable FIFO policy.
Also read on MOAB, a commercially available scheduler for torque.
Related
In the past I worked with what I believe were "microservices". We had a service discovery and the applications communicated with each other through REST sync calls, which I believe is called request / response.
Now we are working on an application that is simply broken down into multiple small applications which work together through publish / subscribe using Kafka, there's no direct communication between them nor a service discovery, per say.
Is it safe to say that these are "Microservices" too or what should I call them?
As one commenter pointed out- An answer will always be opinionated (and stackoverflow is generally not the best place for opinion based questions), but I am not afraid to give mine in an attempt to help.
My view goes along the lines of what Martin Fowler and others have taught us in last decade, as well as the insight from the pioneering work of Werner Vogels at Amazon. Their definitions are that microservices are not a well defined single standard, but an architectural style that can encompass a range of different approaches in distributed computing. What they have in common are the goals of providing scalability in many different dimensions, but mostly system complexity, organizational productivity, throughput and resilience - All while being affordable. To achieve that the designs should be centered around:
Service boundaries cut according to business goals (a type of Domain Driven Design).
Sizing / Scope of services to be limited (the famous two-pizza team size idea).
Clear separation in terms of organizational responsibilities and maintenance. This includes independent teams and release-/ maintenance cycles for each service.
Embrace of automation on all layers (how cloud virtualization, devops, CICD, infrastructure as code, etc. became popular tools).
Design focus on failure-resilient operation, e.g. avoid cascading failures, defined failure states, fallbacks, etc.
A consequence of those goals is also the embrace of distributed system architectures and design for horizontal scalability (statelessness, separation of compute and storage, etc.).
So if you feel your designs are along those lines then in my opinion you would have applied the microservices architectural style successfully.
If you want to learn more about this school of thought I recommend this read.
I have a small Akka application that passes many messages between its actors and each actor does some calculations on the data it receives. What I want is to profile this application in order to see which parts of the code take up most time and so on.
I tried VisualVM but I cannot really understand what's going on. I added a picture of the profiler output.
My questions are
What for example is this first line and why does it take up so much time? (scala.concurrent.forkjoin.ForkJoinPool.scan())
Can Akka applications because of their asynchronous behaviour be profiled well at all?
Can I see for instance how long one specific actor(-type) works for one specific message(-type) it receives?
Are there other best-practices for profiling Akka applications?
There are packages not profiled by default and it is their time that is accounted in the profile of scala.concurrent.forkjoin.ForkJoinPool.scan(). If all the hidden packages are allowed to be sampled, the true CPU time consumers will be revealed. For example, the following before/after illustrative profiles uncover that threads are put to sleep most of the time by sun.misc.Unsafe.park waiting to be unparked.
Akka applications can be profiled quite well with proper instrumentation and call tracing. Google's prominent Dapper, a Large-Scale Distributed Systems Tracing Infrastructure paper contains detailed explanation of the technique. Twitter created Zipkin based on that. It is open sourced and has an extension for distributed tracing of Akka. Follow its wiki for a good explanation of how to set up a system that allows to
trace call hierarchies inside an actor system;
debug request processing pipelines (you can log to traces, annotate them with custom key-value pairs);
see dependencies between derived requests and their contribution to resulting response time;
find and analyse slowest requests in your system.
There is also a new kid on the block, Kamon. It is a reactive-friendly toolkit for monitoring applications that run on top of the JVM, which is specially enthusiastic to applications built with the Typesafe Reactive Platform. That definitely means yes for Akka and the integration comes in the form of the kamon-akka and kamon-akka-remote modules that bring bytecode instrumentation to gather metrics and perform automatic trace context propagation on your behalf. Explore the documentation starting from Akka Integration Overview to understand what it can and how to achieve that.
Just a couple of days ago TypeSafe announced that TypeSafe console now is free. I don't know what can be better for profiling Scala/Akka applications. Of cause you can try JProfiler for JVM languages, I've used it with Java projects, but it's not free and for Java.
I was thinking about profiling/metrics in code since I also use Akka/Scala a lot for building production applications, but I also eager to hear alternative ways to make sure that application is healthy.
Metrics (like Dropwizard)
Very good tool for collecting metrics in the code, with good documentation and embedded support for Graphite, Ganglia, Logback, etc.
It has verbose tools for collecting in-app statistics like gauges, counter histograms, timings - information to figure out what is the current state of your app, how many actors were created, etc, if they are alive, what the current state is of majority of actors, etc.
Agree, it's a bit different from profiling but helps a lot to find roots of the problem, especially if integrated with some char building tool.
Profilers like (VisualVM, XRebel)
Since I'm a big fun of doing monitoring, it still answers a slightly different question - what are current insights of my application right now?
But there is quite another matter may disturb us - what of my code is slow (or sloppy)?
For that reason, we have VisualVM and another answers to this question - how to profile Akka actors with VisualVM.
Also, I'd suggest trying XRebel profiler that just adds a bit more firepower to process of figuring out what code makes app slower. It's also paid but on my project it saved a lot of time dealing with sloppy code.
New Relic
I'd suggest it for some playground projects since you can get some monitoring/profiling solutions for free, but on more serious projects I'd go for things I highlighted above.
So I hope, that my overview was helpful.
At a couple of places there is state that akka is somehow "real-time". E.g.:
http://doc.akka.io/docs/akka/2.0/intro/what-is-akka.html
Unfortunately I was not able to find a deeper explanation in which way akka is "real-time". So this is the question:
In which way is akka real-time?
I assume akka is not really a real-time computing system in the sense of the following definition, isn't it?: https://en.wikipedia.org/wiki/Real-time_computing
No language built on the JVM can be real-time in the sense that it's guaranteed to react within a certain amount of time unless it is using a JVM that supports real-time extensions (and takes advantage of them). It just isn't technically possible--and Akka is no exception.
However, Akka does provide support for running things quickly and with pretty good timing compared to what is possible. And in the docs, the other definitions of real-time (meaning online, while-running, with-good-average-latency, fast-enough-for-you-not-to-notice-the-delay, etc.) may be used on occasion.
Since akka is a message driven system, the use of real-time relates to one of the definition of the wikipedia article you mention in the domain of data transfer, media processing and enterprise systems, the term is used to mean 'without perceivable delay'.
"real time" here equates to "going with the flow": events/messages are efficiently processed/consumed as they are produced (in opposition to "batch processing").
Akka can be a foundation for a soft real-time system, but not for a hard one, because of the limitations of the JVM. If you scroll a bit down in the Wikipedia article, you will find the section "Criteria for real-time computing", and there is a nice explanation about the different "real-timeness" criteria.
systems that are subject to a "real-time constraint"— e.g. operational
deadlines from event to system response.
en.wikipedia.org/wiki/Real-time_computing
The akka guys might be reffering to features like futures that allow you to add a time constraint on expectations from a computation.
Also the clustering model of akka may be used to mean an online system which is real-time(Abstracted so as to look like its running locally).
My take is that the Akka platform can support a form of real-time constraint by delivering responsive applications through the use of (I'm quoting here):
Asynchronous, non-blocking and highly performant event-driven programming model
Fault tolerance through supervisor hierarchies with “let-it-crash” semantics
Definition of time-out policies in the response delivery
As already said, all these features combined provides a platform with a form of response time guarantee, especially compared to mainstream applications and tools available nowadays on the JVM.
It's still arguable to claim that Akka could be strictly defined as a real-time computing system, as per wikipedia's definition.
For such claims to be proven, you would better refer to the Akka team itself.
I am building an enhancement to the Spark framework (http://www.spark-project.org/). Spark is a project out of UC Berkeley that does MapReduce quickly in RAM. Spark is built in Scala.
The enhancement I'm building allows some data to be shared between the mappers while they are computing. This can be useful, for example, if each of the mappers is looking for an optimal solution, and they all want to share the current best solution (to prune out bad solutions early). The solution may be slightly out of date as it propagates, but this should still speed up the solution. In general, this is called the branch-and-bound approach.
We can share monotonically increasing numbers, but also we can share arrays, and dictionaries.
We are also looking at machine learning applications where the mappers describe local natural gradient information, and then a new best current optimal solution is shared among all nodes.
What are some other good real-world applications of this kind of enhancement? What kinds of real, useful applications might benefit from a Map Reduce computation with just a little bit of information-sharing between mappers. What applications use MapReduce or Hadoop right now but are just a little too slow because of the independence restriction of the Map phase?
The benefit can be to either speed up the map phase, or improve the solution.
The enhancement I'm building allows some data to be shared between the mappers while they are computing.
Apache Giraph is based on Google Pregel which is based on BSP and is used for graph processing. In BSP, there is data sharing between the processes in the communication phase.
Giraph depends on Hadoop for implementation. In general there is no communication between the mappers in MapReduce, but in Giraph the mappers communicate with each other during the communication phase of BSP.
You might be also interested in Apache Hama which implements BSP and can be used for more than graph processing.
There might be some reason why mappers don't communicate in the MR. Have you considered these factors in your enhancement?
What are some other good real-world applications of this kind of enhancement?
Graph processing is one thing I can think of, similar to Giraph. Checkout the different use cases for BSP, some might be applicable for this kind of enhancement. I am also very interested what other have to say on this.
I'm taking an introductory course (3 months) about real time systems design, but any implementation.
I would like to build something that let me understand better what I'll learn in theory, but since I have never done any real time system I can't estimate how long will take any project. It would be a concept proof project, or something like that, given my available time and knowledge.
Please, could you give me some idea? Thank you in advance.
I programm in TSQL, Delphi and C#, but I'll not have any problem in learning another language.
Suggest you consider exploring the Real-Time Specification for Java (RTSJ). While it is not a traditional environment for constructing real-time software, it is an up-and-coming technology with a lot of interest. Even better, you can witness some of the ongoing debate about what matters and what doesn't in real-time systems.
Sun's JavaRTS is freely available for download, and has some interesting demonstrations available to show deterministic behavior, and show off their RT garbage collector.
In terms of a specific project, I suggest you start simple: 1) Build a work-generator that you can tune to consume a given amount of CPU time; 2) Put this into a framework that can produce a distribution of work-generator tasks (as threads, or as chunks of work executed in a thread) and a mechanism for logging the work produced; 3) Produce charts of the execution time, sojourn time, deadline, slack/overrun of these tasks versus their priority; 4) demonstrate that tasks running in the context of real-time threads (vice timesharing) behave differently.
Bonus points if you can measure the overhead in the scheduler by determining at what supplied load (total CPU time produced by your work generator tasks divided by wall-clock time) your tasks begin missing deadlines.
Try to think of real-time tasks that are time-critical, for instance video-playing, which fails if tasks are not finished (e.g. calculating the next frame) in time.
You can also think of some industrial solutions, but they are probably more difficult to study in your local environment.
You should definitely consider building your system using a hardware development board equipped with a small processor (ARM, PIC, AVR, any one will do). This really helped remove my fear of the low-level when I started developing. You'll have to use C or C++ though.
You will then have two alternatives : either go bare-metal, or use a real-time OS.
Going bare-metal, you can learn :
How to initalize your processor from scratch and most importantly how to use interrupts, which are the fastest way you have to respond to an externel event
How to implement lightweight threads with fast context switching, something every real-time OS implements
In order to ease this a bit, look for a dev kit which comes with lots of documentation and source code. I used Embedded Artists ARM boards and they give you a lot of material.
Going with the RT OS :
You'll fast-track your project, and will be able to learn how to fine-tune a RT OS
You may try your hand at an open-source OS, such as Linux or the BSDs, and learn a lot from the source code
Either choice is good, you will get a really cool hands-on project to show off and hopefully better understand your course material. Good luck!
As most realtime systems are still implemented in C or C++ it may be good to brush up your knowledge of these programming languages. Many realtime systems are also embedded systems, so you might want to play around with a cheap open source one like BeagleBoard (http://beagleboard.org/). This will also give you a chance to learn about cross compiling etc.