With this change Graphite TCP connections are tracked on a per-service
basis. This allows a closing Graphite service to first shutdown any
active connections, thereby unblocking the rest of shutdowm.
This work exposed small shortcomings with the existing Diagnostics
system and that code has alse been tweaked.
Fixes issue #4017
With this change, the generic batcher used by many inputs can now be
buffered. Testing shows that this performance of the Graphite input by
10-100%, with the biggest improvements at lower numbers of connections.
If a timestamp was larger than the max epoch value was sent via
graphite it would cause the timestamp to overflow when it was
marshaled/unmarshaled back from the raft log. The overflow cause
the shard group to get created with the wrong timestamp which cause
a panic when writing the point. The panic was caused because the
timestamp that were supposed to exists in a map created by MapShards
did not actually exist so a nil ShardGroup was used.
The change prevents creating the point with an invalid timestamp. Since
graphite using a timestamp in seconds, the maximum range is known and
can be prevented. This also adds a check for the minimum range as well.
Fixes#3785
This change adds support for diagnostics by decomposing the existing
interface into two interfaces -- one for stats, and the other for
diags. It also adds some basic monitor of system, network, and the Go
runtime.
Through profiling of writes, point.Fields() and point.Name() were called
repeatedly in PointsWriter and the Shard. These calls are somewhat expensive
when writing large batches so we can cache them to avoid wasting CPU cycles.
Using influx_stress with default settings
Before:
Wrote 10000000 points at average rate of 202570
Average response time: 235.450355ms
After:
Wrote 10000000 points at average rate of 246120
Average response time: 182.881008ms
* Capitalize first letter of message
* Log all services staring consistently
* Remove some extraneous log statements in meta.Store
* Log data dirs for meta, data and hinted handoff
Previously there was a batcher per connection and each batcher was
flushed when the connection was closed. This didn't have much of an
effect when multiple clients connected and disconnected since it would
flush the batch immediately. It also did not help UDP traffic.
Instead, there is now a shared batcher for the service so that multiple
connections will not cause frequent flushes.
Provides a little more flexibility in controlling the parsed
metric names for metris like:
servers.localhost.cpu.cpu0.user
Previously, you could only use a single field like "cpu", "user"
or a wildcard to match "cpu.cpu0.user". You can now pull out "cpu"
and "user" and join them together in the metric name using a custom
separator character. By default this is ".".
This adds a sorted search tree for matchining filters to a template
more efficiently. Each filter is split on "." and each element is
added to the tree. Patterns with matching prefixes are added under
the same subtree.
These are tags that can be added at the template level. They
will override any global tags and any parsed tags with the same
name from the metric will override these.
Philip O'Toole
Cory LaNou
Philip O'Toole
Jason Wilder
Gunnar
Vorn Mom
Alexander Morozov