<-
Apache > HTTP Server > Documentation > Version 2.4 > Modules

Apache MPM event

Available Languages:  en  |  fr 

Description:A variant of the worker MPM with the goal of consuming threads only for connections with active processing
Status:MPM
Module Identifier:mpm_event_module
Source File:event.c

Summary

The event Multi-Processing Module (MPM) is designed to allow more requests to be served simultaneously by passing off some processing work to supporting threads, freeing up the main threads to work on new requests. It is based on the worker MPM, which implements a hybrid multi-process multi-threaded server. Run-time configuration directives are identical to those provided by worker.

To use the event MPM, add --with-mpm=event to the configure script's arguments when building the httpd.

Topics

Directives

See also

top

How it Works

This MPM tries to fix the 'keep alive problem' in HTTP. After a client completes the first request, the client can keep the connection open, and send further requests using the same socket. This can save significant overhead in creating TCP connections. However, Apache HTTP Server traditionally keeps an entire child process/thread waiting for data from the client, which brings its own disadvantages. To solve this problem, this MPM uses a dedicated thread to handle both the Listening sockets, all sockets that are in a Keep Alive state, and sockets where the handler and protocol filters have done their work and the only remaining thing to do is send the data to the client. The status page of mod_status shows how many connections are in the mentioned states.

top

Graceful process termination and Scoreboard usage

This mpm showed some scalability bottlenecks in the past leading to the following error: "scoreboard is full, not at MaxRequestWorkers". MaxRequestWorkers limits the number of simultaneous requests that will be served at any given time and also the number of allowed processes (MaxRequestWorkers / ThreadsPerChild), meanwhile the Scoreboard is a representation of all the running processes and the status of their worker threads. If the scoreboard is full (so all the threads have a state that is not idle) but the number of active requests served is not MaxRequestWorkers, it means that some of them are blocking new requests that could be served but that are queued instead (up to the limit imposed by ListenBacklog). Most of the times the threads are stuck in the Graceful state, namely they are waiting to finish their work with a TCP connection to safely terminate and free up a scoreboard slot (for example handling long running requests, slow clients or connections with keep-alive enabled). Two scenarios are very common:

  • During a graceful restart. The parent process signals all its children to complete their work and terminate, while it reloads the config and forks new processes. If the old children keep running for a while before stopping, the scoreboard will be partially occupied until their slots are freed.
  • When the server load goes down in a way that causes httpd to stop some processes (for example due to MaxSpareThreads). This is particularly problematic because when the load increases again, httpd will try to start new processes. If the pattern repeats, the number of processes can rise quite a bit, ending up in a mixture of old processes trying to stop and new ones trying to do some work.

From 2.4.24 onward, mpm-event is smarter and it is able to handle graceful terminations in a much better way. Some of the improvements are:

  • Allow the use of all the scoreboard slots up to ServerLimit. MaxRequestWorkers and ThreadsPerChild are used to limit the amount of active processes, meanwhile ServerLimit takes also into account the ones doing a graceful close to allow extra slots when needed. The idea is to use ServerLimit to instruct httpd about how many overall processes are tolerated before impacting the system resources.
  • Force gracefully finishing processes to close their connections in keep-alive state.
  • During graceful shutdown, if there are more running worker threads than open connections for a given process, terminate these threads to free resources faster (which may be needed for new processes).
  • If the scoreboard is full, prevent more processes to finish gracefully due to reduced load until old processes have terminated (otherwise the situation would get worse once the load increases again).

The behavior described in the last point is completely observable via mod_status in the connection summary table through two new columns: "Slot" and "Stopping". The former indicates the PID and the latter if the process is stopping or not; the extra state "Yes (old gen)" indicates a process still running after a graceful restart.

top

Limitations

The improved connection handling may not work for certain connection filters that have declared themselves as incompatible with event. In these cases, this MPM will fall back to the behavior of the worker MPM and reserve one worker thread per connection. All modules shipped with the server are compatible with the event MPM.

A similar restriction is currently present for requests involving an output filter that needs to read and/or modify the whole response body, like for example mod_ssl, mod_deflate, or mod_include. If the connection to the client blocks while the filter is processing the data, and the amount of data produced by the filter is too big to be buffered in memory, the thread used for the request is not freed while httpd waits until the pending data is sent to the client.

The MPM assumes that the underlying apr_pollset implementation is reasonably threadsafe. This enables the MPM to avoid excessive high level locking, or having to wake up the listener thread in order to send it a keep-alive socket. This is currently only compatible with KQueue and EPoll.

top

Requirements

This MPM depends on APR's atomic compare-and-swap operations for thread synchronization. If you are compiling for an x86 target and you don't need to support 386s, or you are compiling for a SPARC and you don't need to run on pre-UltraSPARC chips, add --enable-nonportable-atomics=yes to the configure script's arguments. This will cause APR to implement atomic operations using efficient opcodes not available in older CPUs.

This MPM does not perform well on older platforms which lack good threading, but the requirement for EPoll or KQueue makes this moot.

  • To use this MPM on FreeBSD, FreeBSD 5.3 or higher is recommended. However, it is possible to run this MPM on FreeBSD 5.2.1, if you use libkse (see man libmap.conf).
  • For NetBSD, at least version 2.0 is recommended.
  • For Linux, a 2.6 kernel is recommended. It is also necessary to ensure that your version of glibc has been compiled with support for EPoll.
top

AsyncRequestWorkerFactor Directive

Description:Limit concurrent connections per process
Syntax:AsyncRequestWorkerFactor factor
Default:2
Context:server config
Status:MPM
Module:event
Compatibility:Available in version 2.3.13 and later

The event MPM handles some connections in an asynchronous way, where request worker threads are only allocated for short periods of time as needed, and other connections with one request worker thread reserved per connection. This can lead to situations where all workers are tied up and no worker thread is available to handle new work on established async connections.

To mitigate this problem, the event MPM does two things: Firstly, it limits the number of connections accepted per process, depending on the number of idle request workers. Secondly, if all workers are busy, it will close connections in keep-alive state even if the keep-alive timeout has not expired. This allows the respective clients to reconnect to a different process which may still have worker threads available.

This directive can be used to fine-tune the per-process connection limit. A process will only accept new connections if the current number of connections (not counting connections in the "closing" state) is lower than:

ThreadsPerChild + (AsyncRequestWorkerFactor * number of idle workers)

This means the absolute maximum numbers of concurrent connections is:

(AsyncRequestWorkerFactor + 1) * MaxRequestWorkers

MaxRequestWorkers was called MaxClients prior to version 2.3.13. The above value shows that the old name did not accurately describe its meaning for the event MPM.

AsyncRequestWorkerFactor can take non-integer arguments, e.g "1.5".

Available Languages:  en  |  fr 

top

Comments

Notice:
This is not a Q&A section. Comments placed here should be pointed towards suggestions on improving the documentation or server, and may be removed again by our moderators if they are either implemented or considered invalid/off-topic. Questions on how to manage the Apache HTTP Server should be directed at either our IRC channel, #httpd, on Freenode, or sent to our mailing lists.