fast-prometheus 0.3.1 → 0.3.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: cc4b46dd402452acfca0d58f4f3230850c4ef19101f8d84027cc903877451efc
-  data.tar.gz: eb10abc576793f118af30ee6ea4ce44b5339939d5906816b4f92d3e14af64762
+  metadata.gz: 25cba069a74bd1f00499ff8d2c3a3feb84e9646b1447de704d2dff860dc5cea4
+  data.tar.gz: 533131b2461c719cb5525695a5abdc26b474bc6ce9fe35ba338855a698e887a3
 SHA512:
-  metadata.gz: 393888fd071c19df54148a57187c415d3397107a51b96e0d442b5931be691aea0ca23f3570daaf0654b644993f8f5da8ae1b97be8da864c96b01e7948c2f90c9
-  data.tar.gz: 7a842a1b2381f9b43c38a378c676b77d692619d74d6df7ac6ff979a783a041e248a8b7afcd7f2ec3cd569bf5be386500fffbd7efaad2ce729cf8f9bded0c6791
+  metadata.gz: c0a779b8563993d01400a7587852f2ec65c65621facd1bd3e9c44d39404e44eff0656a137a12f6a8da1b60b902d6bfe897b35ab82627064c8238f005171d0623
+  data.tar.gz: 8b9c2ce522dc9360c40f1779b7e4240370e5a7dbe4e6b333f9c39583bf2ba5a43805aa4b523763322ca62716b23c619047291beff28cb5b33abe88ad7874f96c

data/CHANGELOG.md

@@ -7,6 +7,20 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.3.2] - 2026-09-19
+
+### Changed
+
+- `Formats::Protobuf.render` writes each family and each series straight
+  into the output behind a length prefix reserved first and filled in after
+  (`Fast::Protowire::Wire.reserve_length` / `close_length` /
+  `append_length_delimited_from`), instead of encoding the family header
+  to a String and copying every series out of a scratch buffer. Same
+  bytes; at 36,000 series x 12 labels a render went from 0.151 s and 29
+  objects to 0.144 s and 24, a protobuf scrape over HTTP from 0.162 s to
+  0.151 s (0.200 s to 0.192 s with gzip). Benchmarks page and README
+  updated.
+
 ## [0.3.1] - 2026-09-19
 
 ### Changed

data/README.md

@@ -94,13 +94,13 @@ Single process, locked, thread-safe by default (`benchmark-ips` and allocation
 comparisons against `prometheus-client` and `google-protobuf`; see
 [the benchmarks page](docs/explanation/benchmarks.md) for the full runs and conditions):
 
-- A protobuf scrape of 36,000 series renders in **29 objects**, where the
+- A protobuf scrape of 36,000 series renders in **24 objects**, where the
   `google-protobuf` encoder needed 3.5 million Ruby objects and 504k native arenas, and
   in a hundredth of the GC time; taking the snapshot it reads is 1 ms and one Hash per metric
 - The text renderer allocates **66x fewer objects** than prometheus-client's formatter
   for the same body, and renders it 3.2x faster at 36,000 series
-- Bound counter and gauge writes allocate nothing and are **1.4x** faster than
-  prometheus-client's; histogram observe is **3.0x** faster and summary observe **3.2x**
+- Bound counter and gauge writes allocate nothing and are **1.45x** faster than
+  prometheus-client's; histogram observe is **3.1x** faster and summary observe **3.3x**
 - Native histogram observe runs at **1.32M i/s** with no prometheus-client equivalent
 
 ## Development

data/lib/fast/prometheus/formats/protobuf.rb

@@ -12,10 +12,10 @@ module Fast
       # Each family's header is a declared Proto::MetricFamily; the series
       # under it are written straight to the wire with Fast::Protowire::Wire,
       # no LabelPair/Metric/Counter objects, because a scrape's series count
-      # is the one thing here that is large. A series' bytes go into one
-      # scratch buffer reused for the whole render and are copied under the
-      # family's metric tag, so rendering allocates per series only what
-      # Array#pack needs for a double. Native histograms, few and irregular,
+      # is the one thing here that is large. Each series' bytes are written
+      # straight into the output behind a length prefix filled in after them,
+      # so rendering allocates nothing per series and copies nothing. Native
+      # histograms, few and irregular,
       # still go through Proto::Histogram. Bytes are identical to what the
       # declared classes (and google-protobuf) produce; the tests check.
       module Protobuf
@@ -64,32 +64,31 @@ module Fast
         DOUBLE_SIZE = 9
         private_constant :DOUBLE_SIZE
 
-        # One varint-length-prefixed MetricFamily frame per metric.
+        # One varint-length-prefixed MetricFamily frame per metric, each
+        # written straight into the output behind a length prefix reserved
+        # first and filled in after (see Fast::Protowire::Wire).
         def self.render(snapshot)
-          scratch = String.new
-          snapshot.metrics.each_with_object(String.new) do |ms, buffer|
-            family = encode_metric_family(ms, scratch)
-            Fast::Protowire::Wire.append_varint(buffer, family.bytesize)
-            buffer << family
+          snapshot.metrics.each_with_object(String.new) do |ms, out|
+            start = Fast::Protowire::Wire.reserve_length(out)
+            append_metric_family(out, ms)
+            Fast::Protowire::Wire.close_length(out, start)
           end
         end
 
         # A family's bytes are its header (name, help, type) followed by one
-        # metric entry per series, each written into +scratch+ and copied.
-        private_class_method def self.encode_metric_family(metric_snapshot, scratch)
-          header = Proto::MetricFamily.new(name: metric_snapshot.name.name, help: metric_snapshot.docstring,
-                                           type: TYPE_MAP.fetch(metric_snapshot.type))
+        # metric entry per series, in place. A family's series are alike, so
+        # the entry prefix width carries from one to the next.
+        private_class_method def self.append_metric_family(out, metric_snapshot)
+          Proto::MetricFamily.new(name: metric_snapshot.name.name, help: metric_snapshot.docstring,
+                                  type: TYPE_MAP.fetch(metric_snapshot.type)).encode(out)
           type = metric_snapshot.type
           names = metric_snapshot.label_names
-          buffer = header.encode
+          width = 1
           metric_snapshot.series.each_pair do |values, value|
-            scratch.clear
-            append_metric(scratch, names, values, value, type)
-            buffer << FAMILY_METRIC
-            Fast::Protowire::Wire.append_varint(buffer, scratch.bytesize)
-            buffer << scratch
+            width = Fast::Protowire::Wire.append_length_delimited_from(out, FAMILY_METRIC, width) do |buffer|
+              append_metric(buffer, names, values, value, type)
+            end
           end
-          buffer
         end
 
         # Metric: labels (1) then the one value field for the type, in

data/lib/fast/prometheus/version.rb

@@ -2,6 +2,6 @@
 
 module Fast
   module Prometheus
-    VERSION = "0.3.1"
+    VERSION = "0.3.2"
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: fast-prometheus
 version: !ruby/object:Gem::Version
-  version: 0.3.1
+  version: 0.3.2
 platform: ruby
 authors:
 - Eric Jacobs