| 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 | |
| 18 | use std::cell::RefCell; |
| 19 | use std::collections::HashMap; |
| 20 | use std::future::Future; |
| 21 | use std::rc::Rc; |
| 22 | |
| 23 | use g1t_contracts::repos::{Repo, RepoPath}; |
| 24 | use g1t_contracts::{Outcome, Viewer}; |
| 25 | use serde::de::DeserializeOwned; |
| 26 | use worker::wasm_bindgen::JsValue; |
| 27 | use worker::{D1PreparedStatement, D1Result, Result}; |
| 28 | |
| 29 | use crate::rows::PULL_COLUMNS; |
| 30 | use crate::{ISSUE_COLUMNS, Work}; |
| 31 | |
| 32 | /// The pull request's id, from the batch's `?1` (repository) and `?2` (number). |
| 33 | const 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)] |
| 37 | pub(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 | Reactions, |
| 50 | } |
| 51 | |
| 52 | /// How many runs `latest_checks` and `earlier_checks` show together. |
| 53 | pub(crate) const RECENT_RUNS: u32 = 11; |
| 54 | |
| 55 | /// One pull request's rows, as read for this request. |
| 56 | pub(crate) struct Prefetched { |
| 57 | pub(crate) pull_id: String, |
| 58 | pub(crate) repo_id: String, |
| 59 | /// The workspace its rulesets were read for, lowercase. |
| 60 | pub(crate) namespace: String, |
| 61 | /// Its head commit when read, which its statuses are for. |
| 62 | pub(crate) head: Option<String>, |
| 63 | results: Vec<D1Result>, |
| 64 | } |
| 65 | |
| 66 | impl Prefetched { |
| 67 | /// A slot's rows, as the helper that reads them would have. |
| 68 | pub(crate) fn rows<T: DeserializeOwned>(&self, slot: Slot) -> Result<Vec<T>> { |
| 69 | match self.results.get(slot as usize) { |
| 70 | Some(result) => result.results::<T>(), |
| 71 | None => Ok(Vec::new()), |
| 72 | } |
| 73 | } |
| 74 | |
| 75 | /// A slot's first row. |
| 76 | pub(crate) fn first<T: DeserializeOwned>(&self, slot: Slot) -> Result<Option<T>> { |
| 77 | Ok(self.rows::<T>(slot)?.into_iter().next()) |
| 78 | } |
| 79 | } |
| 80 | |
| 81 | #[derive(serde::Deserialize)] |
| 82 | struct IdRow { |
| 83 | id: String, |
| 84 | head_commit: Option<String>, |
| 85 | } |
| 86 | |
| 87 | thread_local! { |
| 88 | /// Repository ids by path, as the repos service last answered: a guess |
| 89 | /// that lets a page's batch start before the answer comes. Never |
| 90 | /// trusted: nothing read with a guess is used unless the repos service |
| 91 | /// then says the viewer may see that very repository. |
| 92 | static REPO_IDS: RefCell<HashMap<String, String>> = RefCell::new(HashMap::new()); |
| 93 | } |
| 94 | |
| 95 | /// Guesses kept at most; the map is emptied past this. |
| 96 | const MAX_GUESSES: usize = 1024; |
| 97 | |
| 98 | fn path_key(path: &RepoPath) -> String { |
| 99 | format!("{}/{}", path.namespace.to_lowercase(), path.name.to_lowercase()) |
| 100 | } |
| 101 | |
| 102 | fn guess(path: &RepoPath) -> Option<String> { |
| 103 | REPO_IDS.with(|ids| ids.borrow().get(&path_key(path)).cloned()) |
| 104 | } |
| 105 | |
| 106 | fn learn(path: &RepoPath, id: Option<&str>) { |
| 107 | REPO_IDS.with(|ids| { |
| 108 | let mut ids = ids.borrow_mut(); |
| 109 | match id { |
| 110 | Some(id) => { |
| 111 | if ids.len() >= MAX_GUESSES { |
| 112 | ids.clear(); |
| 113 | } |
| 114 | ids.insert(path_key(path), id.to_owned()); |
| 115 | } |
| 116 | None => { |
| 117 | ids.remove(&path_key(path)); |
| 118 | } |
| 119 | } |
| 120 | }); |
| 121 | } |
| 122 | |
| 123 | impl Work { |
| 124 | /// The repository at `path` if `viewer` may see it, and what `load` |
| 125 | /// reads for it. When this isolate has seen the repository before, |
| 126 | /// `load` starts with its id at once, beside the access check, instead |
| 127 | /// of after it: one round trip instead of two. What it read is |
| 128 | /// discarded unless the check passes for that same repository. |
| 129 | pub(crate) async fn repo_then<T, F, Fut>(&self, path: &RepoPath, viewer: &Viewer, load: F) -> Result<Outcome<(Repo, T)>> |
| 130 | where |
| 131 | F: Fn(String) -> Fut, |
| 132 | Fut: Future<Output = Result<T>>, |
| 133 | { |
| 134 | let guessed = guess(path); |
| 135 | let (found, early) = match &guessed { |
| 136 | Some(id) => { |
| 137 | let (found, early) = futures_util::future::join(self.repo(path, viewer), load(id.clone())).await; |
| 138 | (found?, Some(early)) |
| 139 | } |
| 140 | None => (self.repo(path, viewer).await?, None), |
| 141 | }; |
| 142 | let repo = match found { |
| 143 | Outcome::Ok(repo) => repo, |
| 144 | Outcome::Fail(failure) => { |
| 145 | learn(path, None); |
| 146 | return Ok(Outcome::Fail(failure)); |
| 147 | } |
| 148 | }; |
| 149 | if let (Some(id), Some(Ok(value))) = (&guessed, early) |
| 150 | && *id == repo.id |
| 151 | { |
| 152 | return Ok(Outcome::Ok((repo, value))); |
| 153 | } |
| 154 | learn(path, Some(&repo.id)); |
| 155 | let value = load(repo.id.clone()).await?; |
| 156 | Ok(Outcome::Ok((repo, value))) |
| 157 | } |
| 158 | |
| 159 | fn statement(&self, sql: &str, binds: &[JsValue]) -> Result<D1PreparedStatement> { |
| 160 | self.db.prepare(sql).bind(binds) |
| 161 | } |
| 162 | |
| 163 | /// Everything a pull request's page and its lifecycle read, in one |
| 164 | /// batch. `None` when there is no such pull request. |
| 165 | pub(crate) async fn prefetch_pull(&self, repo_id: String, namespace: String, number: u32) -> Result<Option<Prefetched>> { |
| 166 | let key = || -> [JsValue; 2] { [repo_id.as_str().into(), number.into()] }; |
| 167 | let with = |extra: JsValue| -> [JsValue; 3] { [repo_id.as_str().into(), number.into(), extra] }; |
| 168 | let repo_only = || -> [JsValue; 1] { [repo_id.as_str().into()] }; |
| 169 | let statements = vec![ |
| 170 | // Slot::Pull: the row, with everything the lifecycle tracks on it. |
| 171 | self.statement(&format!("SELECT {PULL_COLUMNS} FROM pulls WHERE repo_id = ?1 AND number = ?2"), &key())?, |
| 172 | // Slot::Issue |
| 173 | self.statement( |
| 174 | &format!( |
| 175 | "SELECT {ISSUE_COLUMNS} FROM issues |
| 176 | WHERE repo_id = ?1 AND number = (SELECT issue_number FROM pulls WHERE repo_id = ?1 AND number = ?2)" |
| 177 | ), |
| 178 | &key(), |
| 179 | )?, |
| 180 | // Slot::Comments (lib.rs `comments`) |
| 181 | self.statement("SELECT * FROM comments WHERE repo_id = ?1 AND number = ?2 ORDER BY id LIMIT 500", &key())?, |
| 182 | // Slot::Verdicts: every verdict, oldest first, for the approval |
| 183 | // rule, a person's request for changes and a person's approval. |
| 184 | self.statement( |
| 185 | "SELECT author_id, author_name, verdict, created_at FROM comments |
| 186 | WHERE repo_id = ?1 AND number = ?2 AND verdict IS NOT NULL ORDER BY id", |
| 187 | &key(), |
| 188 | )?, |
| 189 | // Slot::Runs: the latest and the ten before it (checks.rs). |
| 190 | self.statement( |
| 191 | &format!("SELECT * FROM check_runs WHERE pull_id = {PULL_ID} ORDER BY id DESC LIMIT ?3"), |
| 192 | &with(RECENT_RUNS.into()), |
| 193 | )?, |
| 194 | // Slot::Statuses: on its head (statuses.rs `statuses`). |
| 195 | self.statement( |
| 196 | "SELECT context, state, description, target_url, updated_at, source, check_run_id FROM commit_statuses |
| 197 | WHERE repo_id = ?1 AND sha = (SELECT head_commit FROM pulls WHERE repo_id = ?1 AND number = ?2) |
| 198 | ORDER BY context", |
| 199 | &key(), |
| 200 | )?, |
| 201 | // Slot::Settings (settings.rs `settings`) |
| 202 | self.statement("SELECT * FROM repo_settings WHERE repo_id = ?1", &repo_only())?, |
| 203 | // Slot::Others (reviews.rs `overlaps`) |
| 204 | self.statement( |
| 205 | "SELECT number, title, issue_number, files FROM pulls |
| 206 | WHERE repo_id = ?1 AND number != ?2 AND status IN ('draft', 'open') |
| 207 | ORDER BY number LIMIT 200", |
| 208 | &key(), |
| 209 | )?, |
| 210 | // Slot::Queued (queue.rs `queued_entry`) |
| 211 | self.statement( |
| 212 | &format!( |
| 213 | "SELECT * FROM queue_entries |
| 214 | WHERE pull_id = {PULL_ID} AND state IN ('waiting', 'testing', 'passed') LIMIT 1" |
| 215 | ), |
| 216 | &key(), |
| 217 | )?, |
| 218 | // Slot::Rulesets and Slot::Adopted (rulesets.rs `rulesets_for`) |
| 219 | self.statement(crate::rulesets::prefetch_sql().0, &[repo_id.as_str().into(), namespace.to_lowercase().into()])?, |
| 220 | self.statement(crate::rulesets::prefetch_sql().1, &repo_only())?, |
| 221 | // Slot::Reactions (reactions.rs `THREAD_SQL`) |
| 222 | self.statement(crate::reactions::THREAD_SQL, &key())?, |
| 223 | ]; |
| 224 | let count = statements.len() as u32; |
| 225 | let results = self.timing.db(count, self.db.batch(statements)).await?; |
| 226 | let Some(row) = results |
| 227 | .first() |
| 228 | .map(|result| result.results::<IdRow>()) |
| 229 | .transpose()? |
| 230 | .and_then(|rows| rows.into_iter().next()) |
| 231 | else { |
| 232 | return Ok(None); |
| 233 | }; |
| 234 | Ok(Some(Prefetched { |
| 235 | pull_id: row.id, |
| 236 | repo_id, |
| 237 | namespace: namespace.to_lowercase(), |
| 238 | head: row.head_commit, |
| 239 | results, |
| 240 | })) |
| 241 | } |
| 242 | |
| 243 | /// The rows read for pull request `pull_id` in this request, if any. |
| 244 | pub(crate) fn prefetched_pull(&self, pull_id: &str) -> Option<Rc<Prefetched>> { |
| 245 | self.prefetched |
| 246 | .borrow() |
| 247 | .as_ref() |
| 248 | .filter(|found| found.pull_id == pull_id) |
| 249 | .cloned() |
| 250 | } |
| 251 | |
| 252 | /// The rows read in this request for a pull request of `repo_id`. |
| 253 | pub(crate) fn prefetched_repo(&self, repo_id: &str) -> Option<Rc<Prefetched>> { |
| 254 | self.prefetched |
| 255 | .borrow() |
| 256 | .as_ref() |
| 257 | .filter(|found| found.repo_id == repo_id) |
| 258 | .cloned() |
| 259 | } |
| 260 | |
| 261 | /// Keeps `found` for the rest of this request. |
| 262 | pub(crate) fn keep_prefetched(&self, found: Option<Prefetched>) { |
| 263 | *self.prefetched.borrow_mut() = found.map(Rc::new); |
| 264 | } |
| 265 | } |
| 266 | |
| 267 | #[cfg(test)] |
| 268 | mod tests { |
| 269 | use super::*; |
| 270 | |
| 271 | fn at(namespace: &str, name: &str) -> RepoPath { |
| 272 | RepoPath { namespace: namespace.to_owned(), name: name.to_owned() } |
| 273 | } |
| 274 | |
| 275 | #[test] |
| 276 | fn guesses_ignore_case_and_are_forgotten_on_refusal() { |
| 277 | learn(&at("Flagon-IO", "G1T"), Some("repo_1")); |
| 278 | assert_eq!(guess(&at("flagon-io", "g1t")).as_deref(), Some("repo_1")); |
| 279 | learn(&at("flagon-io", "g1t"), None); |
| 280 | assert_eq!(guess(&at("flagon-io", "g1t")), None); |
| 281 | } |
| 282 | } |