<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Transport on Momo Engineering Journal</title><link>/categories/transport/</link><description>Recent content in Transport on Momo Engineering Journal</description><image><title>Momo Engineering Journal</title><url>/images/og-image.png</url><link>/images/og-image.png</link></image><generator>Hugo</generator><language>en-us</language><lastBuildDate>Tue, 20 Oct 2026 21:08:58 -0600</lastBuildDate><atom:link href="/categories/transport/index.xml" rel="self" type="application/rss+xml"/><item><title>⚡ Bolt: Zero-Allocation SigV4 Canonical Headers</title><link>/posts/057-bolt-sigv4-zero-alloc-headers/</link><pubDate>Thu, 15 Oct 2026 11:43:50 +0000</pubDate><guid>/posts/057-bolt-sigv4-zero-alloc-headers/</guid><description>Every authenticated S3 request rebuilds a SigV4 canonical-headers block — and the two obvious ways to write it (strings.Split and Header.Get) each allocate on the hottest authorization path. This post walks through replacing both with an IndexByte scan and an EqualFold lookup, and the golden-equivalence test that proves the rewrite is byte-identical for every request AWS clients actually send.</description></item><item><title>⚡ Bolt: Zero-Allocation Parsing of ETag Lists</title><link>/posts/052-bolt-etag-matches-zero-alloc/</link><pubDate>Tue, 06 Oct 2026 11:16:37 +0000</pubDate><guid>/posts/052-bolt-etag-matches-zero-alloc/</guid><description>How we removed the heap allocation from ETag list parsing on the S3 conditional-request path by replacing strings.Split with a strings.IndexByte scan. Teaches: what If-Match/If-None-Match actually carry, why Split allocates per request, and how a microbenchmark proves the win.</description></item><item><title>🐜 Adaptive Systems: Ant-Colony Routing and Epigenetic Concurrency</title><link>/posts/052-adaptive-systems-foundations/</link><pubDate>Tue, 06 Oct 2026 05:19:24 +0000</pubDate><guid>/posts/052-adaptive-systems-foundations/</guid><description>How Momo replaces static concurrency limits and rigid replica selection with bio-inspired adaptive mechanisms: Ant Colony pheromone-based replica exploration and Epigenetic host-capacity admission.</description></item><item><title>⚡ Bolt: Zero-Allocation Parsing of AWS Chunked Headers</title><link>/posts/051-bolt-aws-chunked-zero-alloc/</link><pubDate>Thu, 01 Oct 2026 11:32:41 +0000</pubDate><guid>/posts/051-bolt-aws-chunked-zero-alloc/</guid><description>How we removed the last heap allocation from the aws-chunked ingest path by replacing strings.Split and strings.TrimPrefix with a strings.IndexByte scan. Teaches: what a streaming S3 upload body looks like, why Split allocates per chunk, and how a microbenchmark proves the win.</description></item><item><title>⚡ Bolt: Eliminating the Last Remaining S3 XML Time Allocation</title><link>/posts/048-bolt-listparts-appendformat/</link><pubDate>Tue, 08 Sep 2026 11:29:58 +0000</pubDate><guid>/posts/048-bolt-listparts-appendformat/</guid><description>How we eliminated the final per-response heap allocation in S3 XML rendering by swapping time.Format for time.AppendFormat in the ListParts handler. Teaches: the stack-buffer time formatting pattern, why Format allocates, and how microbenchmarks prove the win.</description></item><item><title>⚡ Bolt: Eliminating Time Formatting Allocations in S3 HTTP Responses</title><link>/posts/047-bolt-s3-copyresult-time-alloc/</link><pubDate>Sun, 30 Aug 2026 11:20:58 +0000</pubDate><guid>/posts/047-bolt-s3-copyresult-time-alloc/</guid><description>How we optimized S3 XML responses by replacing time.Format with time.AppendFormat to eliminate heap allocations. Teaches: stack-buffer time formatting pattern, hot path identification via pprof.</description></item><item><title>Transport Evolution: TCP, QUIC, and the Wire Protocol</title><link>/posts/003-transport-tcp-to-quic/</link><pubDate>Tue, 11 Aug 2026 04:02:50 +0000</pubDate><guid>/posts/003-transport-tcp-to-quic/</guid><description>Momo&amp;rsquo;s transport layer grew from TCP to a QUIC/TLS 1.3 fan-out — fixing handshake, ACK framing, deadlines, and TLS identity along the way.</description></item></channel></rss>