I'm wondering which are the advantages of a LIFO stack vs a FIFO queue in the implementation of a pool with Apache Commons Pool. Wouldn't be more "secure" to default as FIFO to avoid getting timeout connections (opened at start but not used until peak hours) and probably avoid having to test on idle?
I'd appreciate any opinions. Thank you very much.
Some advantages to LIFO (the default) can be
The idle object evictor will work more effectively if turned on
Work may be concentrated on a smaller number of instances, reusing more recently used resources.
Whether or not these are benefits depends on what the pooled objects are, what the load distribution is, how important it is to keep workload concentrated on a small number of instances and how beneficial it is to reuse more recently used resources.
You are correct that using LIFO can cause some instances to sit idle in the pool for longer periods. If keeping the pool trimmed down and concentrating load are not advantages, timeouts are a problem and load distribution is such that FIFO access works to keep instances fresh, that configuration can make sense. This is why the configuration option is there.
Related
Summary:
I have a Java application that uses akka streams that's using more memory than I have specified the jvm to use. The below values are what I have set through the JAVA_OPTS.
maximum heap size (-Xmx) = 700MB
metaspace (-XX) = 250MB
stack size (-Xss) = 1025kb
Using those values and plugging them into the formula below, one would assume the application would be using around 950MB. However that is not the case and it's using over 1.5GB.
Max memory = [-Xmx] + [-XX:MetaspaceSize] + number_of_threads * [-Xss]
Question: Thoughts on how this is possible?
Application overview:
This java application uses alpakka to connect to pubsub and consumes messages. It utilizes akka stream's parallelism where it performs logic on the consumed messages and then it produces those messages to a kafka instance. See the heap dump below. Note, the heap is only 912.9MB so something is taking up 587.1MB and getting the memory usage over 1.5GB
Why is this a problem?
This application is deployed on a kubernetes cluster and the POD has a memory limit specified to 1.5GB. So when the container, where the java application is running, consumes more that 1.5GB the container is killed and restarted.
The short answer is that those do not account for all the memory consumed by the JVM.
Outside of the heap, for instance, memory is allocated for:
compressed class space (governed by the MaxMetaspaceSize)
direct byte buffers (especially if your application performs network I/O and cares about performance, it's virtually certain to make somewhat heavy use of those)
threads (each thread has a stack governed by -Xss ... note that if mixing different concurrency models, each model will tend to allocate its own threads and not necessarily provide a means to share threads)
if native code is involved (e.g. perhaps in the library Alpakka is using to interact with pubsub?), that can allocate arbitrary amounts of memory outside of the heap)
the code cache (typically 48MB)
the garbage collector's state (will vary based on the GC in use, including the presence of any tunable options)
various other things that generally aren't going to be that large
In my experience you're generally fairly safe with a heap that's at most (pod memory limit minus 1 GB), but if you're performing exceptionally large I/Os etc. you can pretty easily get OOM even then.
Your JVM may ship with support for native memory tracking which can shed light on at least some of that non-heap consumption: most of these allocations tend to happen soon after the application is fully loaded, so running with a much higher resource limit and then stopping (e.g. via SIGTERM with enough time to allow it to save results) should give you an idea of what you're dealing with.
I am using hazelcast in JVM in my application which is running 2 replicas in kubernetes. Hazelcast in both comtainers has formed a cluster and sync is working perfectly fine.
But my application has started using 20% more threads after starting to using hazelcast. On aanalyzing thread dump it is found that hazelcast is using that extra 20%
Is it okay for hazelcast to use this many number of threads or if this can be reduced, how can I go about this?
Hazelcast will self-size the number of threads it uses, based on the number of processors available to it.
(In Java, see Runtime.availableProcessors() )
How many does your container have allocated ?
You can override the threading if you are sure it's inappropriate. Look for system properties like hazelcast.*.thread.count from here. There are many options and it's not a casual task just to reduce or increase, If you tune numbers down, you risk performance being very poor.
We are suspecting that we're experciencing thread pool starvation on a server that is running a couple of ASP.NET Core APIs and a couple of .NET Core consoles.
I ran perfview one one of our servers were we are suspecting problems with thread pool starvation. However I'm having a bit of trouble analyzing the results.
I ran PerfView /threadTime collect for about 60 seconds. And this is the result I got (I chose one to look at one of our ASP.NET Core APIs):
Looking at "By Name" we can see that there is a lot of time spent in BLOCKED_TIME. If I double click then I'm taken to the following view where I can expand one of the nodes to get the following view (the overwritten part is the name of our API process):
What does that tell me? Shouldn't I be able to see what exactly is blocking? And does it look like the problem is that a lot of threads is blocking each one for a small amount of time?
Are there any other conclusions we can draw from this?
BLOCKED_TIME generally means a period when the thread wasn't doing anything at all. This could be periods of I/O, where network or other types of latency are involved or time spent waiting on locks such as in situations with semaphores. In short, this doesn't necessarily tell you anything, as there's perfectly standard and reasonable reasons for the thread to be idled. However, a goodish amount of time spent blocked can be an indication of an underlying problem. Perhaps you have too much network latency. Perhaps you're trying to do too much file system work on a slow drive. In short, it may or may not indicate a problem, and even if it does indicate a problem, it doesn't really tell you what the problem is.
In general, if you're experiencing thread starvation, the first thing you should look at is thread pool utilization. Are you using async everywhere you can? Are you doing things that are big no-nos in web apps such as using Task.Run, Task.StartNew or worse, Thread.Start? All those created threads are coming out of the same thread pool, and thus proportionally reducing your server throughput.
There's an all too common pattern of attempting to schedule long-running jobs by shuffling them to new threads. That's death to a web application. All threads in the pool are there to service requests, not long-running jobs, and as such, requests should be handled quickly and efficiently so that the thread can be returned to the pool in short order to field other requests. If you need to background work, you need to truly background it, by offloading to another process or even a different machine entirely.
Short of all that, maybe you're just getting more load than the server can handle in general. That's always a possibility. Perhaps you need to vertically scale your system resources (and the thread pool with it). Perhaps you need to horizontally scale by replicating this server with a load balancer in front. Given that you're running multiple different things on the same server, an easy way to horizontally scale is to simply divvy out these things to their own machines. That alone would probably help tremendously. However, scaling, either vertically or horizontally, should be your last resort. Make sure you're using resources efficiently first, before throwing more resources at your inefficient things.
We are noticing occasional periods of high CPU on a web server that happens to use ImageResizer. Here are the surprising results of a trace performed with NewRelic's thread profiler during such a spike:
It would appear that the cleanup routine associated with ImageResizer's DiskCache plugin is responsible for a significant percentage of the high CPU consumption associated with this application. We have autoClean on, but otherwise we're configured to use the defaults, which I understand are optimal for most typical situations:
<diskCache autoClean="true" />
Armed with this information, is there anything I can do to relieve the CPU spikes? I'm open to disabling autoClean and setting up a simple nightly cleanup routine, but my understanding is that this plugin is built to be smart about how it uses resources. Has anyone experienced this and had any luck simply changing the default configuration?
This is an ASP.NET MVC application running on Windows Server 2008 R2 with ImageResizer.Plugins.DiskCache 3.4.3.
Sampling, or why the profiling is unhelpful
New Relic's thread profiler uses a technique called sampling - it does not instrument the calls - and therefore cannot know if CPU usage is actually occurring.
Looking at the provided screenshot, we can see that the backtrace of the cleanup thread (there is only ever one) is frequently found at the WaitHandle.WaitAny and WaitHandle.WaitOne calls. These methods are low-level synchronization constructs that do not spin or consume CPU resources, but rather efficiently return CPU time back to other threads, and resume on a signal.
Correct profilers should be able to detect idle or waiting threads and eliminate them from their statistical analysis. Because New Relic's profiler failed to do that, there is no useful way to interpret the data it's giving you.
If you have more than 7,000 files in /imagecache, here is one way to improve performance
By default, in V3, DiskCache uses 32 subfolders with 400 items per folder (1000 hard limit). Due to imperfect hash distribution, this means that you may start seeing cleanup occur at as few as 7,000 images, and you will start thrashing the disk at ~12,000 active cache files.
This is explained in the DiskCache documentation - see subfolders section.
I would suggest setting subfolders="8192" if you have a larger volume of images. A higher subfolder count increases overhead slightly, but also increases scalability.
TL;DR: Is it possible that I am reactor throughput limited? How would I tell? How expensive and scalable (across threads) is the implementation of the io_service?
I have a farily massively parallel application, running on a hyperthreaded-dual-quad-core-Xeon machine with tons of RAM and a fast SSD RAID. This is developed using boost::asio.
This application accepts connections from about 1,000 other machines, reads data, decodes a simple protocol, and shuffles data into files mapped using mmap(). The application also pre-fetches "future" mmap pages using madvise(WILLNEED) so it's unlikely to be blocking on page faults, but just to be sure, I've tried spawning up to 300 threads.
This is running on Linux kernel 2.6.32-27-generic (Ubuntu Server x64 LTS 10.04). Gcc version is 4.4.3 and boost::asio version is 1.40 (both are stock Ubuntu LTS).
Running vmstat, iostat and top, I see that disk throughput (both in TPS and data volume) is on the single digits of %. Similarly, the disk queue length is always a lot smaller than the number of threads, so I don't think I'm I/O bound. Also, the RSS climbs but then stabilizes at a few gigs (as expected) and vmstat shows no paging, so I imagine I'm not memory bound. CPU is constant at 0-1% user, 6-7% system and the rest as idle. Clue! One full "core" (remember hyper-threading) is 6.25% of the CPU.
I know the system is falling behind, because the client machines block on TCP send when more than 64kB is outstanding, and report the fact; they all keep reporting this fact, and throughput to the system is much less than desired, intended, and theoretically possible.
My guess is I'm contending on a lock of some sort. I use an application-level lock to guard a look-up table that may be mutated, so I sharded this into 256 top-level locks/tables to break that dependency. However, that didn't seem to help at all.
All threads go through one, global io_service instance. Running strace on the application shows that it spends most of its time dealing with futex calls, which I imagine have to do with the evented-based implementation of the io_service reactor.
Is it possible that I am reactor throughput limited? How would I tell? How expensive and scalable (across threads) is the implementation of the io_service?
EDIT: I didn't initially find this other thread because it used a set of tags that didn't overlap mine :-/ It is quite possible my problem is excessive locking used in the implementation of the boost::asio reactor. See C++ Socket Server - Unable to saturate CPU
However, the question remains: How can I prove this? And how can I fix it?
The answer is indeed that even the latest boost::asio only calls into the epoll file descriptor from a single thread, not entering the kernel from more than one thread at a time. I can kind-of understand why, because thread safety and lifetime of objects is extremely precarious when you use multiple threads that each can get notifications for the same file descriptor. When I code this up myself (using pthreads), it works, and scales beyond a single core. Not using boost::asio at that point -- it's a shame that an otherwise well designed and portable library should have this limitation.
I believe that if you use multiple io_service object (say for each cpu core), each run by a single thread, you will not have this problem. See the http server example 2 on the boost ASIO page.
I have done various benchmarks against the server example 2 and server example 3 and have found that the implementation I mentioned works the best.
In my single-threaded application, I found out from profiling that a large portion of the processor instructions was spent on locking and unlocking by the io_service::poll(). I disabled the lock operations with the BOOST_ASIO_DISABLE_THREADS macro. It may make sense for you, too, depending on your threading situation.