Skip to content
Sign up

flagon-io/g1t

public
0
279 linesCodeBlameRaw
1//! Reading a page's worth of rows in one round trip.
2//!
3//! A pull request's page used to cost about twenty queries one after
4//! another: the repository, the pull request, its issue, then where it
5//! stands (its progress, settings, statuses, verdicts and queue entry),
6//! its comments and checks. Each is a round trip to the database, and from most places a
7//! round trip is 20 to 40 ms. Here they go as one D1 batch, keyed by the
8//! repository's id and the pull request's number, and the batch starts
9//! while the repos service is still deciding whether the viewer may see
10//! the repository ([`Work::repo_then`]).
11//!
12//! The helpers that answer those questions (`settings`, `statuses`,
13//! `approvals_gap` and the rest) look here first, so the
14//! code that decides a pull request's lifecycle is the same code whether
15//! its rows were batched or read one at a time. Only reads are kept; a
16//! helper that writes and reads back (mergeability) reads the database.
17
18use std::cell::RefCell;
19use std::collections::HashMap;
20use std::future::Future;
21use std::rc::Rc;
22
23use g1t_contracts::repos::{Repo, RepoPath};
24use g1t_contracts::{Outcome, Viewer};
25use serde::de::DeserializeOwned;
26use worker::wasm_bindgen::JsValue;
27use worker::{D1PreparedStatement, D1Result, Result};
28
29use crate::rows::PULL_COLUMNS;
30use crate::{ISSUE_COLUMNS, Work};
31
32/// The pull request's id, from the batch's `?1` (repository) and `?2` (number).
33const PULL_ID: &str = "(SELECT id FROM pulls WHERE repo_id = ?1 AND number = ?2)";
34
35/// Each statement of a pull request's batch, in order.
36#[derive(Clone, Copy)]
37pub(crate) enum Slot {
38 Pull,
39 Issue,
40 Comments,
41 Verdicts,
42 Runs,
43 Statuses,
44 Settings,
45 Others,
46 Queued,
47 Rulesets,
48 Adopted,
49}
50
51/// How many runs `latest_checks` and `earlier_checks` show together.
52pub(crate) const RECENT_RUNS: u32 = 11;
53
54/// One pull request's rows, as read for this request.
55pub(crate) struct Prefetched {
56 pub(crate) pull_id: String,
57 pub(crate) repo_id: String,
58 /// The workspace its rulesets were read for, lowercase.
59 pub(crate) namespace: String,
60 /// Its head commit when read, which its statuses are for.
61 pub(crate) head: Option<String>,
62 results: Vec<D1Result>,
63}
64
65impl Prefetched {
66 /// A slot's rows, as the helper that reads them would have.
67 pub(crate) fn rows<T: DeserializeOwned>(&self, slot: Slot) -> Result<Vec<T>> {
68 match self.results.get(slot as usize) {
69 Some(result) => result.results::<T>(),
70 None => Ok(Vec::new()),
71 }
72 }
73
74 /// A slot's first row.
75 pub(crate) fn first<T: DeserializeOwned>(&self, slot: Slot) -> Result<Option<T>> {
76 Ok(self.rows::<T>(slot)?.into_iter().next())
77 }
78}
79
80#[derive(serde::Deserialize)]
81struct IdRow {
82 id: String,
83 head_commit: Option<String>,
84}
85
86thread_local! {
87 /// Repository ids by path, as the repos service last answered: a guess
88 /// that lets a page's batch start before the answer comes. Never
89 /// trusted: nothing read with a guess is used unless the repos service
90 /// then says the viewer may see that very repository.
91 static REPO_IDS: RefCell<HashMap<String, String>> = RefCell::new(HashMap::new());
92}
93
94/// Guesses kept at most; the map is emptied past this.
95const MAX_GUESSES: usize = 1024;
96
97fn path_key(path: &RepoPath) -> String {
98 format!("{}/{}", path.namespace.to_lowercase(), path.name.to_lowercase())
99}
100
101fn guess(path: &RepoPath) -> Option<String> {
102 REPO_IDS.with(|ids| ids.borrow().get(&path_key(path)).cloned())
103}
104
105fn learn(path: &RepoPath, id: Option<&str>) {
106 REPO_IDS.with(|ids| {
107 let mut ids = ids.borrow_mut();
108 match id {
109 Some(id) => {
110 if ids.len() >= MAX_GUESSES {
111 ids.clear();
112 }
113 ids.insert(path_key(path), id.to_owned());
114 }
115 None => {
116 ids.remove(&path_key(path));
117 }
118 }
119 });
120}
121
122impl Work {
123 /// The repository at `path` if `viewer` may see it, and what `load`
124 /// reads for it. When this isolate has seen the repository before,
125 /// `load` starts with its id at once, beside the access check, instead
126 /// of after it: one round trip instead of two. What it read is
127 /// discarded unless the check passes for that same repository.
128 pub(crate) async fn repo_then<T, F, Fut>(&self, path: &RepoPath, viewer: &Viewer, load: F) -> Result<Outcome<(Repo, T)>>
129 where
130 F: Fn(String) -> Fut,
131 Fut: Future<Output = Result<T>>,
132 {
133 let guessed = guess(path);
134 let (found, early) = match &guessed {
135 Some(id) => {
136 let (found, early) = futures_util::future::join(self.repo(path, viewer), load(id.clone())).await;
137 (found?, Some(early))
138 }
139 None => (self.repo(path, viewer).await?, None),
140 };
141 let repo = match found {
142 Outcome::Ok(repo) => repo,
143 Outcome::Fail(failure) => {
144 learn(path, None);
145 return Ok(Outcome::Fail(failure));
146 }
147 };
148 if let (Some(id), Some(Ok(value))) = (&guessed, early)
149 && *id == repo.id
150 {
151 return Ok(Outcome::Ok((repo, value)));
152 }
153 learn(path, Some(&repo.id));
154 let value = load(repo.id.clone()).await?;
155 Ok(Outcome::Ok((repo, value)))
156 }
157
158 fn statement(&self, sql: &str, binds: &[JsValue]) -> Result<D1PreparedStatement> {
159 self.db.prepare(sql).bind(binds)
160 }
161
162 /// Everything a pull request's page and its lifecycle read, in one
163 /// batch. `None` when there is no such pull request.
164 pub(crate) async fn prefetch_pull(&self, repo_id: String, namespace: String, number: u32) -> Result<Option<Prefetched>> {
165 let key = || -> [JsValue; 2] { [repo_id.as_str().into(), number.into()] };
166 let with = |extra: JsValue| -> [JsValue; 3] { [repo_id.as_str().into(), number.into(), extra] };
167 let repo_only = || -> [JsValue; 1] { [repo_id.as_str().into()] };
168 let statements = vec![
169 // Slot::Pull: the row, with everything the lifecycle tracks on it.
170 self.statement(&format!("SELECT {PULL_COLUMNS} FROM pulls WHERE repo_id = ?1 AND number = ?2"), &key())?,
171 // Slot::Issue
172 self.statement(
173 &format!(
174 "SELECT {ISSUE_COLUMNS} FROM issues
175 WHERE repo_id = ?1 AND number = (SELECT issue_number FROM pulls WHERE repo_id = ?1 AND number = ?2)"
176 ),
177 &key(),
178 )?,
179 // Slot::Comments (lib.rs `comments`)
180 self.statement("SELECT * FROM comments WHERE repo_id = ?1 AND number = ?2 ORDER BY id LIMIT 500", &key())?,
181 // Slot::Verdicts: every verdict, oldest first, for the approval
182 // rule, a person's request for changes and a person's approval.
183 self.statement(
184 "SELECT author_id, author_name, verdict, created_at FROM comments
185 WHERE repo_id = ?1 AND number = ?2 AND verdict IS NOT NULL ORDER BY id",
186 &key(),
187 )?,
188 // Slot::Runs: the latest and the ten before it (checks.rs).
189 self.statement(
190 &format!("SELECT * FROM check_runs WHERE pull_id = {PULL_ID} ORDER BY id DESC LIMIT ?3"),
191 &with(RECENT_RUNS.into()),
192 )?,
193 // Slot::Statuses: on its head (statuses.rs `statuses`).
194 self.statement(
195 "SELECT context, state, description, target_url, updated_at, source, check_run_id FROM commit_statuses
196 WHERE repo_id = ?1 AND sha = (SELECT head_commit FROM pulls WHERE repo_id = ?1 AND number = ?2)
197 ORDER BY context",
198 &key(),
199 )?,
200 // Slot::Settings (settings.rs `settings`)
201 self.statement("SELECT * FROM repo_settings WHERE repo_id = ?1", &repo_only())?,
202 // Slot::Others (reviews.rs `overlaps`)
203 self.statement(
204 "SELECT number, title, issue_number, files FROM pulls
205 WHERE repo_id = ?1 AND number != ?2 AND status IN ('draft', 'open')
206 ORDER BY number LIMIT 200",
207 &key(),
208 )?,
209 // Slot::Queued (queue.rs `queued_entry`)
210 self.statement(
211 &format!(
212 "SELECT * FROM queue_entries
213 WHERE pull_id = {PULL_ID} AND state IN ('waiting', 'testing', 'passed') LIMIT 1"
214 ),
215 &key(),
216 )?,
217 // Slot::Rulesets and Slot::Adopted (rulesets.rs `rulesets_for`)
218 self.statement(crate::rulesets::prefetch_sql().0, &[repo_id.as_str().into(), namespace.to_lowercase().into()])?,
219 self.statement(crate::rulesets::prefetch_sql().1, &repo_only())?,
220 ];
221 let count = statements.len() as u32;
222 let results = self.timing.db(count, self.db.batch(statements)).await?;
223 let Some(row) = results
224 .first()
225 .map(|result| result.results::<IdRow>())
226 .transpose()?
227 .and_then(|rows| rows.into_iter().next())
228 else {
229 return Ok(None);
230 };
231 Ok(Some(Prefetched {
232 pull_id: row.id,
233 repo_id,
234 namespace: namespace.to_lowercase(),
235 head: row.head_commit,
236 results,
237 }))
238 }
239
240 /// The rows read for pull request `pull_id` in this request, if any.
241 pub(crate) fn prefetched_pull(&self, pull_id: &str) -> Option<Rc<Prefetched>> {
242 self.prefetched
243 .borrow()
244 .as_ref()
245 .filter(|found| found.pull_id == pull_id)
246 .cloned()
247 }
248
249 /// The rows read in this request for a pull request of `repo_id`.
250 pub(crate) fn prefetched_repo(&self, repo_id: &str) -> Option<Rc<Prefetched>> {
251 self.prefetched
252 .borrow()
253 .as_ref()
254 .filter(|found| found.repo_id == repo_id)
255 .cloned()
256 }
257
258 /// Keeps `found` for the rest of this request.
259 pub(crate) fn keep_prefetched(&self, found: Option<Prefetched>) {
260 *self.prefetched.borrow_mut() = found.map(Rc::new);
261 }
262}
263
264#[cfg(test)]
265mod tests {
266 use super::*;
267
268 fn at(namespace: &str, name: &str) -> RepoPath {
269 RepoPath { namespace: namespace.to_owned(), name: name.to_owned() }
270 }
271
272 #[test]
273 fn guesses_ignore_case_and_are_forgotten_on_refusal() {
274 learn(&at("Flagon-IO", "G1T"), Some("repo_1"));
275 assert_eq!(guess(&at("flagon-io", "g1t")).as_deref(), Some("repo_1"));
276 learn(&at("flagon-io", "g1t"), None);
277 assert_eq!(guess(&at("flagon-io", "g1t")), None);
278 }
279}