Meilisearch 如何在不到一分钟内更新包含数百万个向量嵌入的数据库

let mut available_ids = available_ids.into_iter();

roots.into_par_iter().for_each(|root| {
    // stuff
    let next_id = available_ids.next();
    // stuff
});

let mut available_ids = Mutex::new(available_ids.into_iter());

roots.into_par_iter().for_each(|root| {
    // stuff
    let next_id = available_ids.lock().unwrap().next();
    // stuff
});

pub fn split_ids_in(available: RoaringBitmap, n: usize) -> Vec<RoaringBitmap> {
    // Define the number of elements per sub-bitmap
    let chunk_size = available.len() / n as u64;
    let mut ret = Vec::new();

    let mut iter = available.into_iter();
    for _ in 0..(n - 1) {
        // Create a roaring bitmap of `chunk_size` elements from the iterator without consuming it
        let available: RoaringBitmap = iter.by_ref().take(chunk_size as usize).collect();
        ret.push(available);
    }
    // the last element is going to contain everything remaining
    ret.extend(iter);

    ret
}

let available_ids = split_ids_in(available_ids, roots.len());

roots.into_par_iter().zip(available_ids).for_each(|(root, available_ids)| {
    let mut available_ids = available_ids.into_iter();
    // stuff
    let next_id = available_ids.next();
    // Here, we can use the available_ids without any locks or inter-thread synchronization
    // stuff
});

/// A concurrent ID generator that will never return the same ID twice.
pub struct ConcurrentNodeIds {
    /// The current tree node ID we should use if no other IDs are available.
    current: AtomicU32,
    /// The total number of tree node IDs used.
    used: AtomicU64,

    /// A list of IDs to exhaust before picking IDs from `current`.
    available: RoaringBitmap,
    /// The current Nth ID to select in the bitmap.
    select_in_bitmap: AtomicU32,
    /// Tells if you should look in the roaring bitmap or if all the IDs are already exhausted.
    look_into_bitmap: AtomicBool,
}

impl ConcurrentNodeIds {
    /// Creates an ID generator returning unique IDs, avoiding the specified used IDs.
    pub fn new(used: RoaringBitmap) -> ConcurrentNodeIds {
        let last_id = used.max().map_or(0, |id| id + 1);
        let used_ids = used.len();
        let available = RoaringBitmap::from_sorted_iter(0..last_id).unwrap() - used;

        ConcurrentNodeIds {
            current: AtomicU32::new(last_id),
            used: AtomicU64::new(used_ids),
            select_in_bitmap: AtomicU32::new(0),
            look_into_bitmap: AtomicBool::new(!available.is_empty()),
            available,
        }
    }

    /// Returns a new unique ID and increases the count of IDs used.
    pub fn next(&self) -> Result<u32> {
        if self.look_into_bitmap.load(Ordering::Relaxed) {
            let current = self.select_in_bitmap.fetch_add(1, Ordering::Relaxed);
            match self.available.select(current) {
                Some(id) => Ok(id),
                None => {
                    self.look_into_bitmap.store(false, Ordering::Relaxed);
                    Ok(self.current.fetch_add(1, Ordering::Relaxed))
                }
            }
        } else {
            Ok(self.current.fetch_add(1, Ordering::Relaxed))
        }
    }
}