implement interaction plans

This commit is contained in:
alpaylan 2024-12-17 18:24:39 -05:00
parent 53ecedaceb
commit 7d4d803a13
5 changed files with 414 additions and 78 deletions

View file

@ -2,6 +2,7 @@ use anarchist_readable_name_generator_lib::readable_name_custom;
use rand::Rng;
pub mod query;
pub mod plan;
pub mod table;
pub trait Arbitrary {
@ -12,10 +13,39 @@ pub trait ArbitraryFrom<T> {
fn arbitrary_from<R: Rng>(rng: &mut R, t: &T) -> Self;
}
pub(crate) fn frequency<'a, T, R: rand::Rng>(choices: Vec<(usize, Box<dyn FnOnce(&mut R) -> T + 'a>)>, rng: &mut R) -> T {
let total = choices.iter().map(|(weight, _)| weight).sum::<usize>();
let mut choice = rng.gen_range(0..total);
for (weight, f) in choices {
if choice < weight {
return f(rng);
}
choice -= weight;
}
unreachable!()
}
pub(crate) fn one_of<T, R: rand::Rng>(choices: Vec<Box<dyn Fn(&mut R) -> T>>, rng: &mut R) -> T {
let index = rng.gen_range(0..choices.len());
choices[index](rng)
}
pub(crate) fn pick<'a, T, R: rand::Rng>(choices: &'a Vec<T>, rng: &mut R) -> &'a T {
let index = rng.gen_range(0..choices.len());
&choices[index]
}
pub(crate) fn pick_index<R: rand::Rng>(choices: usize, rng: &mut R) -> usize {
rng.gen_range(0..choices)
}
fn gen_random_text<T: Rng>(rng: &mut T) -> String {
let big_text = rng.gen_ratio(1, 1000);
if big_text {
let max_size: u64 = 2 * 1024 * 1024 * 1024;
// let max_size: u64 = 2 * 1024 * 1024 * 1024;
let max_size: u64 = 2 * 1024; // todo: change this back to 2 * 1024 * 1024 * 1024
let size = rng.gen_range(1024..max_size);
let mut name = String::new();
for i in 0..size {

View file

@ -0,0 +1,339 @@
use std::{f32::consts::E, fmt::Display, os::macos::raw::stat, rc::Rc};
use limbo_core::{Connection, Result, RowResult};
use rand::SeedableRng;
use rand_chacha::ChaCha8Rng;
use crate::{
model::{
query::{Create, Insert, Predicate, Query, Select},
table::Value,
},
SimulatorEnv, SimulatorOpts,
};
use crate::generation::{frequency, Arbitrary, ArbitraryFrom};
use super::{pick, pick_index};
pub(crate) type ResultSet = Vec<Vec<Value>>;
pub(crate) struct InteractionPlan {
pub(crate) plan: Vec<Interaction>,
pub(crate) stack: Vec<ResultSet>,
}
impl Display for InteractionPlan {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
for interaction in &self.plan {
match interaction {
Interaction::Query(query) => write!(f, "{};\n", query)?,
Interaction::Assertion(assertion) => write!(f, "-- ASSERT: {};\n", assertion.message)?,
}
}
Ok(())
}
}
#[derive(Debug)]
pub(crate) struct InteractionStats {
pub(crate) read_count: usize,
pub(crate) write_count: usize,
pub(crate) delete_count: usize,
}
impl Display for InteractionStats {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
write!(
f,
"Read: {}, Write: {}, Delete: {}",
self.read_count, self.write_count, self.delete_count
)
}
}
pub(crate) enum Interaction {
Query(Query),
Assertion(Assertion),
}
impl Display for Interaction {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
match self {
Interaction::Query(query) => write!(f, "{}", query),
Interaction::Assertion(assertion) => write!(f, "ASSERT: {}", assertion.message),
}
}
}
pub(crate) struct Assertion {
pub(crate) func: Box<dyn Fn(&Vec<ResultSet>) -> bool>,
pub(crate) message: String,
}
pub(crate) struct Interactions(Vec<Interaction>);
impl Interactions {
pub(crate) fn shadow(&self, env: &mut SimulatorEnv) {
for interaction in &self.0 {
match interaction {
Interaction::Query(query) => match query {
Query::Create(create) => {
env.tables.push(create.table.clone());
}
Query::Insert(insert) => {
let table = env
.tables
.iter_mut()
.find(|t| t.name == insert.table)
.unwrap();
table.rows.push(insert.values.clone());
}
Query::Delete(_) => todo!(),
Query::Select(_) => {}
},
Interaction::Assertion(_) => {}
}
}
}
}
impl InteractionPlan {
pub(crate) fn new() -> Self {
InteractionPlan {
plan: Vec::new(),
stack: Vec::new(),
}
}
pub(crate) fn push(&mut self, interaction: Interaction) {
self.plan.push(interaction);
}
pub(crate) fn stats(&self) -> InteractionStats {
let mut read = 0;
let mut write = 0;
let mut delete = 0;
for interaction in &self.plan {
match interaction {
Interaction::Query(query) => match query {
Query::Select(_) => read += 1,
Query::Insert(_) => write += 1,
Query::Delete(_) => delete += 1,
Query::Create(_) => {}
},
Interaction::Assertion(_) => {}
}
}
InteractionStats {
read_count: read,
write_count: write,
delete_count: delete,
}
}
}
impl ArbitraryFrom<SimulatorEnv> for InteractionPlan {
fn arbitrary_from<R: rand::Rng>(rng: &mut R, env: &SimulatorEnv) -> Self {
let mut plan = InteractionPlan::new();
let mut env = SimulatorEnv {
opts: env.opts.clone(),
tables: vec![],
connections: vec![],
io: env.io.clone(),
db: env.db.clone(),
rng: ChaCha8Rng::seed_from_u64(rng.next_u64()),
};
let num_interactions = rng.gen_range(0..env.opts.max_interactions);
// First create at least one table
let create_query = Create::arbitrary(rng);
env.tables.push(create_query.table.clone());
plan.push(Interaction::Query(Query::Create(create_query)));
while plan.plan.len() < num_interactions {
log::debug!(
"Generating interaction {}/{}",
plan.plan.len(),
num_interactions
);
let interactions = Interactions::arbitrary_from(rng, &(&env, plan.stats()));
interactions.shadow(&mut env);
plan.plan.extend(interactions.0.into_iter());
}
log::info!("Generated plan with {} interactions", plan.plan.len());
plan
}
}
impl Interaction {
pub(crate) fn execute_query(&self, conn: &mut Rc<Connection>) -> Result<ResultSet> {
match self {
Interaction::Query(query) => {
let query_str = query.to_string();
let rows = conn.query(&query_str);
if rows.is_err() {
let err = rows.err();
log::error!(
"Error running query '{}': {:?}",
&query_str[0..query_str.len().min(4096)],
err
);
return Err(err.unwrap());
}
let rows = rows.unwrap();
assert!(rows.is_some());
let mut rows = rows.unwrap();
let mut out = Vec::new();
while let Ok(row) = rows.next_row() {
match row {
RowResult::Row(row) => {
let mut r = Vec::new();
for el in &row.values {
let v = match el {
limbo_core::Value::Null => Value::Null,
limbo_core::Value::Integer(i) => Value::Integer(*i),
limbo_core::Value::Float(f) => Value::Float(*f),
limbo_core::Value::Text(t) => Value::Text(t.to_string()),
limbo_core::Value::Blob(b) => Value::Blob(b.to_vec()),
};
r.push(v);
}
out.push(r);
}
RowResult::IO => {}
RowResult::Done => {
break;
}
}
}
Ok(out)
}
Interaction::Assertion(_) => {
unreachable!("unexpected: this function should only be called on queries")
}
}
}
pub(crate) fn execute_assertion(&self, stack: &Vec<ResultSet>) -> Result<()> {
match self {
Interaction::Query(_) => {
unreachable!("unexpected: this function should only be called on assertions")
}
Interaction::Assertion(assertion) => {
if !assertion.func.as_ref()(stack) {
return Err(limbo_core::LimboError::InternalError(
assertion.message.clone(),
));
}
Ok(())
}
}
}
}
fn property_insert_select<R: rand::Rng>(rng: &mut R, env: &SimulatorEnv) -> Interactions {
// Get a random table
let table = pick(&env.tables, rng);
// Pick a random column
let column_index = pick_index(table.columns.len(), rng);
let column = &table.columns[column_index].clone();
// Generate a random value of the column type
let value = Value::arbitrary_from(rng, &column.column_type);
// Create a whole new row
let mut row = Vec::new();
for (i, column) in table.columns.iter().enumerate() {
if i == column_index {
row.push(value.clone());
} else {
let value = Value::arbitrary_from(rng, &column.column_type);
row.push(value);
}
}
// Insert the row
let insert_query = Interaction::Query(Query::Insert(Insert {
table: table.name.clone(),
values: row.clone(),
}));
// Select the row
let select_query = Interaction::Query(Query::Select(Select {
table: table.name.clone(),
predicate: Predicate::Eq(column.name.clone(), value.clone()),
}));
// Check that the row is there
let assertion = Interaction::Assertion(Assertion {
message: format!(
"row [{:?}] not found in table {} after inserting ({} = {})",
row.iter().map(|v| v.to_string()).collect::<Vec<String>>(),
table.name,
column.name,
value,
),
func: Box::new(move |stack: &Vec<ResultSet>| {
let rows = stack.last().unwrap();
rows.iter().any(|r| r == &row)
}),
});
Interactions(vec![insert_query, select_query, assertion])
}
fn create_table<R: rand::Rng>(rng: &mut R, env: &SimulatorEnv) -> Interactions {
let create_query = Interaction::Query(Query::Create(Create::arbitrary(rng)));
Interactions(vec![create_query])
}
fn random_read<R: rand::Rng>(rng: &mut R, env: &SimulatorEnv) -> Interactions {
let select_query = Interaction::Query(Query::Select(Select::arbitrary_from(rng, &env.tables)));
Interactions(vec![select_query])
}
fn random_write<R: rand::Rng>(rng: &mut R, env: &SimulatorEnv) -> Interactions {
let table = pick(&env.tables, rng);
let insert_query = Interaction::Query(Query::Insert(Insert::arbitrary_from(rng, table)));
Interactions(vec![insert_query])
}
impl ArbitraryFrom<(&SimulatorEnv, InteractionStats)> for Interactions {
fn arbitrary_from<R: rand::Rng>(
rng: &mut R,
(env, stats): &(&SimulatorEnv, InteractionStats),
) -> Self {
let remaining_read =
((((env.opts.max_interactions * env.opts.read_percent) as f64) / 100.0) as usize)
.saturating_sub(stats.read_count);
let remaining_write = ((((env.opts.max_interactions * env.opts.write_percent) as f64)
/ 100.0) as usize)
.saturating_sub(stats.write_count);
frequency(
vec![
(
usize::min(remaining_read, remaining_write),
Box::new(|rng: &mut R| property_insert_select(rng, env)),
),
(
remaining_read,
Box::new(|rng: &mut R| random_read(rng, env)),
),
(
remaining_write,
Box::new(|rng: &mut R| random_write(rng, env)),
),
(1, Box::new(|rng: &mut R| create_table(rng, env))),
],
rng,
)
}
}

View file

@ -13,7 +13,7 @@ impl Arbitrary for Name {
impl Arbitrary for Table {
fn arbitrary<R: Rng>(rng: &mut R) -> Self {
let name = Name::arbitrary(rng).0;
let columns = (1..rng.gen_range(1..128))
let columns = (1..=rng.gen_range(1..10))
.map(|_| Column::arbitrary(rng))
.collect();
Table {

View file

@ -1,4 +1,5 @@
use generation::{Arbitrary, ArbitraryFrom};
use generation::plan::{Interaction, ResultSet};
use generation::{pick, pick_index, Arbitrary, ArbitraryFrom};
use limbo_core::{Connection, Database, File, OpenFlags, PlatformIO, Result, RowResult, IO};
use model::query::{Insert, Predicate, Query, Select};
use model::table::{Column, Name, Table, Value};
@ -6,6 +7,7 @@ use properties::{property_insert_select, property_select_all};
use rand::prelude::*;
use rand_chacha::ChaCha8Rng;
use std::cell::RefCell;
use std::io::Write;
use std::rc::Rc;
use std::sync::Arc;
use tempfile::TempDir;
@ -29,13 +31,7 @@ enum SimConnection {
Disconnected,
}
#[derive(Debug, Copy, Clone)]
enum SimulatorMode {
Random,
Workload,
}
#[derive(Debug)]
#[derive(Debug, Clone)]
struct SimulatorOpts {
ticks: usize,
max_connections: usize,
@ -45,7 +41,7 @@ struct SimulatorOpts {
read_percent: usize,
write_percent: usize,
delete_percent: usize,
mode: SimulatorMode,
max_interactions: usize,
page_size: usize,
}
@ -77,8 +73,8 @@ fn main() {
read_percent,
write_percent,
delete_percent,
mode: SimulatorMode::Workload,
page_size: 4096, // TODO: randomize this too
max_interactions: rng.gen_range(0..10000),
};
let io = Arc::new(SimulatorIO::new(seed, opts.page_size).unwrap());
@ -104,10 +100,20 @@ fn main() {
println!("Initial opts {:?}", env.opts);
for _ in 0..env.opts.ticks {
let connection_index = env.rng.gen_range(0..env.opts.max_connections);
log::info!("Generating database interaction plan...");
let mut plan = generation::plan::InteractionPlan::arbitrary_from(&mut env.rng.clone(), &env);
log::info!("{}", plan.stats());
for interaction in &plan.plan {
let connection_index = pick_index(env.connections.len(), &mut env.rng);
let mut connection = env.connections[connection_index].clone();
if matches!(connection, SimConnection::Disconnected) {
connection = SimConnection::Connected(env.db.connect());
env.connections[connection_index] = connection.clone();
}
match &mut connection {
SimConnection::Connected(conn) => {
let disconnect = env.rng.gen_ratio(1, 100);
@ -116,10 +122,20 @@ fn main() {
let _ = conn.close();
env.connections[connection_index] = SimConnection::Disconnected;
} else {
match process_connection(&mut env, conn) {
Ok(_) => {}
match process_connection(conn, interaction, &mut plan.stack) {
Ok(_) => {
log::info!("connection {} processed", connection_index);
}
Err(err) => {
log::error!("error {}", err);
log::debug!("db is at {:?}", path);
// save the interaction plan
let mut path = TempDir::new().unwrap().into_path();
path.push("simulator.plan");
let mut f = std::fs::File::create(path.clone()).unwrap();
f.write(plan.to_string().as_bytes()).unwrap();
log::debug!("plan saved at {:?}", path);
log::debug!("seed was {}", seed);
break;
}
}
@ -130,73 +146,24 @@ fn main() {
env.connections[connection_index] = SimConnection::Connected(env.db.connect());
}
}
}
env.io.print_stats();
}
fn process_connection(env: &mut SimulatorEnv, conn: &mut Rc<Connection>) -> Result<()> {
if env.tables.is_empty() {
maybe_add_table(env, conn)?;
}
match env.opts.mode {
SimulatorMode::Random => {
match env.rng.gen_range(0..2) {
// Randomly insert a value and check that the select result contains it.
0 => property_insert_select(env, conn),
// Check that the current state of the in-memory table is the same as the one in the
// database.
1 => property_select_all(env, conn),
// Perform a random query, update the in-memory table with the result.
2 => {
let table_index = env.rng.gen_range(0..env.tables.len());
let query = Query::arbitrary_from(&mut env.rng, &env.tables[table_index]);
let rows = get_all_rows(env, conn, query.to_string().as_str())?;
env.tables[table_index].rows = rows;
}
_ => unreachable!(),
}
fn process_connection(conn: &mut Rc<Connection>, interaction: &Interaction, stack: &mut Vec<ResultSet>) -> Result<()> {
match interaction {
generation::plan::Interaction::Query(_) => {
log::debug!("{}", interaction);
let results = interaction.execute_query(conn)?;
log::debug!("{:?}", results);
stack.push(results);
}
SimulatorMode::Workload => {
let picked = env.rng.gen_range(0..100);
if env.rng.gen_ratio(1, 100) {
maybe_add_table(env, conn)?;
}
if picked < env.opts.read_percent {
let query = Select::arbitrary_from(&mut env.rng, &env.tables);
let _ = get_all_rows(env, conn, Query::Select(query).to_string().as_str())?;
} else if picked < env.opts.read_percent + env.opts.write_percent {
let table_index = env.rng.gen_range(0..env.tables.len());
let column_index = env.rng.gen_range(0..env.tables[table_index].columns.len());
let column = &env.tables[table_index].columns[column_index].clone();
let mut rng = env.rng.clone();
let value = Value::arbitrary_from(&mut rng, &column.column_type);
let mut row = Vec::new();
for (i, column) in env.tables[table_index].columns.iter().enumerate() {
if i == column_index {
row.push(value.clone());
} else {
let value = Value::arbitrary_from(&mut rng, &column.column_type);
row.push(value);
}
}
let query = Query::Insert(Insert {
table: env.tables[table_index].name.clone(),
values: row.clone(),
});
let _ = get_all_rows(env, conn, query.to_string().as_str())?;
env.tables[table_index].rows.push(row.clone());
} else {
let table_index = env.rng.gen_range(0..env.tables.len());
let query = Query::Select(Select {
table: env.tables[table_index].name.clone(),
predicate: Predicate::And(Vec::new()),
});
let _ = get_all_rows(env, conn, query.to_string().as_str())?;
}
generation::plan::Interaction::Assertion(_) => {
interaction.execute_assertion(stack)?;
}
}

View file

@ -10,7 +10,7 @@ impl Deref for Name {
}
}
#[derive(Debug)]
#[derive(Debug, Clone)]
pub(crate) struct Table {
pub(crate) rows: Vec<Vec<Value>>,
pub(crate) name: String,