世祺 0423d5801c Initial commit (by Create-Cloudflare CLI) | 1 年之前 | |
---|---|---|
.. | ||
lib | 1 年之前 | |
LICENSE | 1 年之前 | |
package.json | 1 年之前 | |
readme.md | 1 年之前 |
Node's
server.close()
the way you probably expected it to work by default.
const server = stoppable(http.createServer(handler))
server.stop()
Stoppable stops accepting new connections and closes existing, idle connections (including keep-alives) without killing requests that are in-flight.
Node.js v4.x is unofficially supported.
yarn add stoppable
(or use npm)
constructor
stoppable(server, grace)
Decorates the server instance with a stop
method.
Returns the server instance, so can be chained, or can be run as a standalone statement.
grace
defaults to Infinity (don't force-close).
If you want to immediately kill all sockets you can use a grace of 0.
stop()
server.stop(callback)
Closes the server.
server.close
function to auto-register a 'close' event.
The first agrument is an error, and the second argument is a boolean that indicates whether it stopped gracefully.grace
could be specified on stop
, but it's better to match the existing server.close
API.FIN
packets first.stop
method.There's no way to provide this functionality without bookkeeping on connection, disconnection, request, and response. However, Stoppable strives to do minimal work in hot code paths and to use optimal data structures.
I'd be interested to see real-world performance benchmarks; the simple loopback artillery benchmark included in the lib shows very little overhead from using a stoppable server:
Scenarios launched: 10000
Scenarios completed: 10000
Requests completed: 10000
RPS sent: 939.85
Request latency:
min: 0.5
max: 51.3
median: 2.1
p95: 3.7
p99: 15.3
Scenario duration:
min: 1
max: 60.7
median: 3.6
p95: 7.6
p99: 19
Scenario counts:
0: 10000 (100%)
Codes:
200: 10000
Scenarios launched: 10000
Scenarios completed: 10000
Requests completed: 10000
RPS sent: 940.73
Request latency:
min: 0.5
max: 43.4
median: 2.1
p95: 3.8
p99: 15.5
Scenario duration:
min: 1.1
max: 57
median: 3.7
p95: 8
p99: 19.4
Scenario counts:
0: 10000 (100%)
Codes:
200: 10000
MIT