rust-performance

1. Algorithm choice      (10x - 1000x)   ← Biggest impact
2. Data structure        (2x - 10x)
3. Reduce allocations    (2x - 5x)
4. Cache optimization    (1.5x - 3x)
5. SIMD/parallelism      (2x - 8x)

// ❌ Bad: grows dynamically
let mut vec = Vec::new();
for i in 0..1000 {
    vec.push(i);
}

// ✅ Good: pre-allocate known size
let mut vec = Vec::with_capacity(1000);
for i in 0..1000 {
    vec.push(i);
}

// ❌ Bad: unnecessary clone
fn process(item: &Item) {
    let data = item.data.clone();
    // use data...
}

// ✅ Good: use reference
fn process(item: &Item) {
    let data = &item.data;
    // use data...
}

// ❌ Bad: multiple database calls
for user_id in user_ids {
    db.update(user_id, status)?;
}

// ✅ Good: batch update
db.update_all(user_ids, status)?;

use smallvec::SmallVec;

// ✅ No heap allocation for ≤16 items
let mut vec: SmallVec<[u8; 16]> = SmallVec::new();

use rayon::prelude::*;

let sum: i32 = data
    .par_iter()
    .map(|x| expensive_computation(x))
    .sum();

// ❌ Problem: multiple AtomicU64 in one struct
struct ShardCounters {
    inflight: AtomicU64,
    completed: AtomicU64,
}

# Perf analysis
perf stat -d your_program
# Look for LLC-load-misses and locked-instrs

# Flamegraph
cargo flamegraph
# Find atomic fetch_add hotspots

// ✅ Each field in separate cache line
#[repr(align(64))]
struct PaddedAtomicU64(AtomicU64);

struct ShardCounters {
    inflight: PaddedAtomicU64,
    completed: PaddedAtomicU64,
}

// ❌ All threads compete for single lock
let shared: Arc<Mutex<HashMap<String, usize>>> =
    Arc::new(Mutex::new(HashMap::new()));

// ✅ Each thread has local HashMap, merge at end
pub fn parallel_count(data: &[String], num_threads: usize)
    -> HashMap<String, usize>
{
    let mut handles = Vec::new();

    for chunk in data.chunks(data.len() / num_threads) {
        handles.push(thread::spawn(move || {
            let mut local = HashMap::new();
            for key in chunk {
                *local.entry(key.clone()).or_insert(0) += 1;
            }
            local  // Return local counts
        }));
    }

    // Merge all local results
    let mut result = HashMap::new();
    for handle in handles {
        for (k, v) in handle.join().unwrap() {
            *result.entry(k).or_insert(0) += v;
        }
    }
    result
}

// Multi-socket server, memory allocated on remote NUMA node
let pool = ArenaPool::new(num_threads);
// Rayon work-stealing causes tasks to run on any thread
// Cross-NUMA access causes severe memory migration latency

// 1. NUMA node binding
let numa_node = detect_numa_node();
let pool = NumaAwarePool::new(numa_node);

// 2. Use unified allocator (jemalloc)
#[global_allocator]
static ALLOC: jemallocator::Jemalloc = jemallocator::Jemalloc;

// 3. Avoid cross-NUMA object clones
// Borrow directly, don't copy data

# Check NUMA topology
numactl --hardware

# Bind to NUMA node
numactl --cpunodebind=0 --membind=0 ./my_program

// ✅ Many reads, few updates
struct Config {
    map: RwLock<HashMap<String, ConfigValue>>,
}

impl Config {
    pub fn get(&self, key: &str) -> Option<ConfigValue> {
        self.map.read().unwrap().get(key).cloned()
    }

    pub fn update(&self, key: String, value: ConfigValue) {
        self.map.write().unwrap().insert(key, value);
    }
}

# Benchmark
cargo bench

# Profile with perf
perf stat -d ./target/release/your_program

# Generate flamegraph
cargo flamegraph --release

# Heap profiling
valgrind --tool=dhat ./target/release/your_program

# Cache analysis
valgrind --tool=cachegrind ./target/release/your_program

# NUMA topology
numactl --hardware

1. Identify symptom (slow, high CPU, high memory)
   ↓
2. Profile with appropriate tool
   - CPU → perf/flamegraph
   - Memory → heaptrack/dhat
   - Cache → cachegrind
   ↓
3. Find hotspot (function/line)
   ↓
4. Understand why it's slow
   - Algorithm? Data structure? Allocation?
   ↓
5. Apply targeted optimization
   ↓
6. Benchmark to confirm improvement
   ↓
7. Repeat if not fast enough