From e8276cb4e9e0168e0339bbc74b8caaf7ddcf2c0d Mon Sep 17 00:00:00 2001
From: Collin Lefeber <hello@cfebs.com>
Date: Wed, 19 Jun 2024 14:53:44 -0400
Subject: [PATCH] build_a_blog: bench

---
 bench.sh              | 22 ++++++++++++++++
 posts/build_a_blog.md | 59 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 81 insertions(+)
 create mode 100755 bench.sh

diff --git a/bench.sh b/bench.sh
new file mode 100755
index 0000000..e6ba179
--- /dev/null
+++ b/bench.sh
@@ -0,0 +1,22 @@
+#!/usr/bin/env bash
+
+amt=$1
+if [[ -z "$amt" ]]; then
+	echo "ERROR: pass number of test posts for bench" 1>&2
+	exit 1
+fi
+
+echo "INFO: removing old __bench files" 1>&2
+rm -f ./posts/*__bench*
+for i in $(seq 1 "$amt"); do
+	cp ./posts/build_a_blog.md ./posts/build_a_blog_${i}__bench.md
+done
+
+
+echo "INFO: number of *.md files $(find ./posts/ -iname '*.md' | wc -l)" 1>&2
+echo "INFO: number of *.html files $(find ./posts/ -iname '*.html' | wc -l)" 1>&2
+echo "INFO: running" 1>&2
+time -p python main.py 2>/dev/null
+echo "INFO: number of *.html files $(find ./posts/ -iname '*.html' | wc -l)" 1>&2
+echo "INFO: cleanup __bench files" 1>&2
+rm -f ./posts/*__bench*
diff --git a/posts/build_a_blog.md b/posts/build_a_blog.md
index a6d0216..5091768 100644
--- a/posts/build_a_blog.md
+++ b/posts/build_a_blog.md
@@ -652,6 +652,7 @@ It's not great software.
 * Using adhoc dicts for generic structures
 * Relies on system python version and packages.
 * Does not offer anything a tool like [hugo][hugo] does not already offer.
+* Probably slow in extreme cases.
 
 But, it's ~150 lines of python with 1 external dependency.
 
@@ -733,6 +734,64 @@ html should get generated, but not in the index or xml
 0
 ```
 
+### 2024-06-19, is it slow?
+
+Quick benchmark script `bench.sh`
+
+```shell
+#!/usr/bin/env bash
+
+amt=$1
+if [[ -z "$amt" ]]; then
+	echo "ERROR: pass number of test posts for bench" 1>&2
+	exit 1
+fi
+
+echo "INFO: removing old __bench files" 1>&2
+rm -f ./posts/*__bench*
+for i in $(seq 1 "$amt"); do
+	cp ./posts/build_a_blog.md ./posts/build_a_blog_${i}__bench.md
+done
+
+
+echo "INFO: number of *.md files $(find ./posts/ -iname '*.md' | wc -l)" 1>&2
+echo "INFO: number of *.html files $(find ./posts/ -iname '*.html' | wc -l)" 1>&2
+echo "INFO: running" 1>&2
+time -p python main.py 2>/dev/null
+echo "INFO: number of *.html files $(find ./posts/ -iname '*.html' | wc -l)" 1>&2
+echo "INFO: cleanup __bench files" 1>&2
+rm -f ./posts/*__bench*
+```
+
+```shell
+❯ ./bench.sh 100
+INFO: removing old __bench files
+INFO: number of *.md files 102
+INFO: number of *.html files 2
+INFO: running
+real 0.94
+user 0.92
+sys 0.02
+INFO: number of *.html files 102
+INFO: cleanup __bench files
+
+❯ ./bench.sh 1000
+INFO: removing old __bench files
+INFO: number of *.md files 1002
+INFO: number of *.html files 2
+INFO: running
+real 8.45
+user 8.31
+sys 0.12
+INFO: number of *.html files 1002
+INFO: cleanup __bench files
+```
+
+So approx 0.8s per 100 posts which starts to get a bit painful in the thousands.
+
+Will be a fun future idea to try to solve.
+
+
 [1]: https://crystal-lang.org/
 [2]: https://github.com/crystal-lang/crystal/releases/tag/0.31.0
 [3]: https://pkgs.alpinelinux.org/package/edge/main/x86_64/py3-markdown