Releases: babbel/puma-plugin-telemetry
v1.1.4
v1.1.3
What's Changed
- Cleanup gem setup by @stevenharman in #20
New Contributors
- @stevenharman made their first contribution in #20
Full Changelog: https://github.com/babbel/puma-plugin-telemetry/blob/main/CHANGELOG.md#113
v1.1.2
1.1.1
1.1.0
Out of beta testing, reading for usage. Following is a recap from Alpha & Beta releases.
Added
- new metric:
sockets.backlog
(disabled by default), pulls information from Puma
sockets about the state of their backlogs. This together withqueue.backlog
allows for full insights into total number of requests waiting to be processed config.sockets_telemetry!
option to enable sockets telemetryconfig.socket_parser
option to allow custom parser implementation as needed- Datadog widgets examples under
docs/examples.md
1.1.0.beta
Added
Different ways to parse Socket::Option
. Mainly due to the fact that #inspect
can't generate proper data on AWS Fargate, which runs Amazon Linux 2 with 4.14 kernel. So now besides #inspect
there's also #unpack
that parses binary data and picks proper field.
It depends on the kernel, but new fields are usually added at the end of the tcp_info
struct, so it should more or less stay stable.
You can configure it by passing in config.socket_parser = :inspect
or config.socket_parser = ->(opt) { your implementation }
.
1.1.0.alpha
Added
Socket telemetry, and to be more precise new metric: sockets.backlog
. If enabled it will
pull information from Puma sockets about the state of their backlogs (requests waiting to
be acknowledged by Puma). It will be exposed under sockets-backlog
metric.
You can enable and test it via config.sockets_telemetry!
option.
1.0.0
Added
- Release to Github Packages
- Explicitly flush datadog metrics after publishing them
- Middleware for measuring and tracking request queue time
Changed
- Replace
statsd.batch
with direct calls, as it aggregates metrics interally by default now.
Also#batch
method is deprecated and will be removed in version 6 of Datadog Statsd client.