diff options
| author | Loïc Hoguin <[email protected]> | 2019-07-18 12:12:37 +0200 |
|---|---|---|
| committer | Loïc Hoguin <[email protected]> | 2019-07-18 12:12:37 +0200 |
| commit | 89674ca1a4ed90cb33b41f442284181c7f7048b1 (patch) | |
| tree | 8eabfa0aed7e464c75976c7cfb4435765d9da97a /articles | |
| parent | f6830fecd00bc9041057ddeec7453b640863d8f5 (diff) | |
| download | ninenines.eu-89674ca1a4ed90cb33b41f442284181c7f7048b1.tar.gz ninenines.eu-89674ca1a4ed90cb33b41f442284181c7f7048b1.tar.bz2 ninenines.eu-89674ca1a4ed90cb33b41f442284181c7f7048b1.zip | |
Fix typo
Diffstat (limited to 'articles')
| -rw-r--r-- | articles/index.html | 2 | ||||
| -rw-r--r-- | articles/index.xml | 2 | ||||
| -rw-r--r-- | articles/ranch-2.0.0-rc.1/index.html | 2 |
3 files changed, 3 insertions, 3 deletions
diff --git a/articles/index.html b/articles/index.html index 05b4ead7..0d248e49 100644 --- a/articles/index.html +++ b/articles/index.html @@ -76,7 +76,7 @@ <p>Ranch 2.0.0-rc.1 has been released! We are getting very close to releasing Ranch 2.0! As most of the tremendous programming work was done by contributor Jan Uhlig, I will yield the floor and let him describe what went into this great release. -In Ranch 1.x, there is only one supervisor per Ranch listener to start and manage connection processes. Under high load (many clients rapidly connecting and/or disconnecting), the message queue of this one supervisor could becomes congested, leading to declining accept rates or a stalled listener.</p> +In Ranch 1.x, there is only one supervisor per Ranch listener to start and manage connection processes. Under high load (many clients rapidly connecting and/or disconnecting), the message queue of this one supervisor could become congested, leading to declining accept rates or a stalled listener.</p> <p style="text-align:right"> <a class="read_more" href="https://ninenines.eu/articles/ranch-2.0.0-rc.1/">Read More</a> diff --git a/articles/index.xml b/articles/index.xml index c2270ff5..6b7675ff 100644 --- a/articles/index.xml +++ b/articles/index.xml @@ -19,7 +19,7 @@ <guid>https://ninenines.eu/articles/ranch-2.0.0-rc.1/</guid> <description>Ranch 2.0.0-rc.1 has been released! We are getting very close to releasing Ranch 2.0! As most of the tremendous programming work was done by contributor Jan Uhlig, I will yield the floor and let him describe what went into this great release. -In Ranch 1.x, there is only one supervisor per Ranch listener to start and manage connection processes. Under high load (many clients rapidly connecting and/or disconnecting), the message queue of this one supervisor could becomes congested, leading to declining accept rates or a stalled listener.</description> +In Ranch 1.x, there is only one supervisor per Ranch listener to start and manage connection processes. Under high load (many clients rapidly connecting and/or disconnecting), the message queue of this one supervisor could become congested, leading to declining accept rates or a stalled listener.</description> </item> <item> diff --git a/articles/ranch-2.0.0-rc.1/index.html b/articles/ranch-2.0.0-rc.1/index.html index 29a987fd..40553ff5 100644 --- a/articles/ranch-2.0.0-rc.1/index.html +++ b/articles/ranch-2.0.0-rc.1/index.html @@ -71,7 +71,7 @@ <p>Ranch <code>2.0.0-rc.1</code> has been released!</p> <p>We are getting very close to releasing Ranch 2.0! As most of the tremendous programming work was done by contributor Jan Uhlig, I will yield the floor and let him describe what went into this great release.</p> -<p>In Ranch 1.x, there is only one supervisor per Ranch listener to start and manage connection processes. Under high load (many clients rapidly connecting and/or disconnecting), the message queue of this one supervisor could becomes congested, leading to declining accept rates or a stalled listener.</p> +<p>In Ranch 1.x, there is only one supervisor per Ranch listener to start and manage connection processes. Under high load (many clients rapidly connecting and/or disconnecting), the message queue of this one supervisor could become congested, leading to declining accept rates or a stalled listener.</p> <p>Ranch 2.0 introduces the <code>num_conns_sups</code> option (defaulting to the number of acceptors), which allows the message load to be divided between the specified number of connection supervisors. This improves accept concurrency at the same time.</p> <p>Another bottleneck is a possible congestion of the syn queue of a listening socket. The reason is located within the operating system's TCP/IP implementation, and on Linux the <code>SO_REUSEPORT</code> socket option was introduced to address it. What it boils down to is that you can have more than just one socket listening on the same port, causing the sockets to be load-balanced when accepting connections.</p> <p>Ranch 1.x always uses a single listening socket per listener, shared between the acceptors. With a trick, starting multiple Ranch listeners on the same port, it is already possible to make use of the <code>SO_REUSEPORT</code> feature. But that's not ideal.</p> |