From 3ca1cec8bbff0846784e8ccb51204eb3ca78688d Mon Sep 17 00:00:00 2001
From: Emelie Graven <emelie@graven.dev>
Date: Tue, 5 Apr 2022 13:11:32 +0200
Subject: [PATCH] Formalize planning document, update DB logic

---
 README.md        | 31 +++++++++++++++++++
 ingest/src/db.rs | 78 +++++++++++++++++++++++++++++++++++++-----------
 2 files changed, 91 insertions(+), 18 deletions(-)

diff --git a/README.md b/README.md
index e69de29..92f877b 100644
--- a/README.md
+++ b/README.md
@@ -0,0 +1,31 @@
+# Grimhilde
+
+## Usecase
+At dotsrc, mirror statistics are currently generated by the [mirror_stats](https://gitlab.com/dotSRC/mirror_stats) go program. While this approach works decently, it could do with improved granularity, and working with the very large json blobs it generates can be taxing.
+
+Grimhilde is a proposed replacement, currently in development.
+
+## Planning & Structure
+By using the `log_format` directive in our nginx configuration, the access log output can be
+customized to include only the data we need in machine-readable form rather than the default
+hunman-readable form. Different logging facilities can also be configured, including logging over
+the syslog protocol. Grimhilde emulates a syslog server by opening a local UDP socket, enabling fast
+and reliable communication between nginx and Grimhilde.
+
+Each request processed by nginx is sent to Grimhilde, where its details are stored in a Postgresql
+database. As the DotSrc mirror processes millions of requests each day, the amount of data we need
+to store would quickly become untenable if stored traditionally. The proposed way around this is to
+assign each unique piece of data in every request (request path, referrer, hostname, etc) an ID, and
+only store it once, replacing any subsequent identical data with references to the initial copy.
+
+While this will massively decrease the amount of data stored, the database will still grow large
+with time. The proposed solution to this is to limit the length of time the data is stored, and to
+use the API to generate static views of interest prior to purging data older than f.x. three months.
+This will allow staff members to generate advanced reports on realtime data to see and respond to
+problematic trends, while also retaining interesting historical usage data to be published publicly
+for years to come.
+
+## Todo
+* [ ] Write tests
+* [ ] Implement the GraphQL API for fetching statistics
+* [ ] Find an appropriate solution for generating reports based on data from the API
diff --git a/ingest/src/db.rs b/ingest/src/db.rs
index f28a99c..e33cff5 100644
--- a/ingest/src/db.rs
+++ b/ingest/src/db.rs
@@ -20,26 +20,66 @@ pub async fn insert(pool: &PgPool, req: Request) -> Result<(), Box<dyn StdError>
 	let mut trans = pool.begin().await?;
 
 	// Get the id's for deduplicated values. Insert a value if one is missing.
-	let path_id = sqlx::query!(
-		"INSERT INTO paths (path) VALUES ($1) ON CONFLICT DO NOTHING RETURNING id",
+	sqlx::query!(
+		"INSERT INTO paths (path) VALUES ($1) ON CONFLICT DO NOTHING",
 		&req.path,
-	).fetch_one(&mut *trans).await?.id;
-	let remote_id = sqlx::query!(
-		"INSERT INTO remote_addresses (addr) VALUES ($1) ON CONFLICT DO NOTHING RETURNING id",
-		req.addr)
-	.fetch_one(&mut *trans).await?.id;
-	let host_id = sqlx::query!(
-		"INSERT INTO hosts (host) VALUES ($1) ON CONFLICT DO NOTHING RETURNING id",
-		&req.host)
-	.fetch_one(&mut *trans).await?.id;
-	let user_agent_id = sqlx::query!(
-		"INSERT INTO user_agents (agent) VALUES ($1) ON CONFLICT DO NOTHING RETURNING id",
+	)
+	.execute(&mut *trans)
+	.await?;
+	sqlx::query!(
+		"INSERT INTO remote_addresses (addr) VALUES ($1) ON CONFLICT DO NOTHING",
+		&req.addr
+	)
+	.execute(&mut *trans)
+	.await?;
+	sqlx::query!(
+		"INSERT INTO hosts (host) VALUES ($1) ON CONFLICT DO NOTHING",
+		&req.host
+	)
+	.execute(&mut *trans)
+	.await?;
+	sqlx::query!(
+		"INSERT INTO user_agents (agent) VALUES ($1) ON CONFLICT DO NOTHING",
 		&req.user_agent,
-	).fetch_one(&mut *trans).await?.id;
-	let referrer_id = sqlx::query!(
-		"INSERT INTO referrers (referrer) VALUES ($1) ON CONFLICT DO NOTHING RETURNING id",
+	)
+	.execute(&mut *trans)
+	.await?;
+	sqlx::query!(
+		"INSERT INTO referrers (referrer) VALUES ($1) ON CONFLICT DO NOTHING",
 		&req.referrer,
-	).fetch_one(&mut *trans).await?.id;
+	)
+	.execute(&mut *trans)
+	.await?;
+
+	let path_id = sqlx::query!("SELECT id FROM paths WHERE path = ($1)", &req.path)
+		.fetch_one(&mut *trans)
+		.await?
+		.id;
+	let path_id = sqlx::query!(
+		"SELECT id FROM remote_addresses WHERE addr = ($1)",
+		&req.addr
+	)
+	.fetch_one(&mut *trans)
+	.await?
+	.id;
+	let path_id = sqlx::query!("SELECT id FROM hosts WHERE host = ($1)", &req.host)
+		.fetch_one(&mut *trans)
+		.await?
+		.id;
+	let path_id = sqlx::query!(
+		"SELECT id FROM user_agents WHERE agent = ($1)",
+		&req.user_agent
+	)
+	.fetch_one(&mut *trans)
+	.await?
+	.id;
+	let path_id = sqlx::query!(
+		"SELECT id FROM referrers WHERE referrer = ($1)",
+		&req.referrer
+	)
+	.fetch_one(&mut *trans)
+	.await?
+	.id;
 
 	sqlx::query!(
 		"INSERT INTO hits (size, path, remote, host, user_agent, referrer, secure, time) \
@@ -52,7 +92,9 @@ pub async fn insert(pool: &PgPool, req: Request) -> Result<(), Box<dyn StdError>
 		referrer_id,
 		req.secure,
 		req.timestamp,
-	).execute(&mut *trans).await?;
+	)
+	.execute(&mut *trans)
+	.await?;
 
 	trans.commit().await?;
 	Ok(())