mirror of
https://github.com/meilisearch/MeiliSearch
synced 2025-07-03 11:57:07 +02:00
Merge branch 'main' into cymruu/payload-unit-test
This commit is contained in:
commit
9015a8e8d9
107 changed files with 3889 additions and 2136 deletions
|
@ -5,7 +5,7 @@ use actix_web::HttpRequest;
|
|||
use meilisearch_types::InstanceUid;
|
||||
use serde_json::Value;
|
||||
|
||||
use super::{find_user_id, Analytics, DocumentDeletionKind};
|
||||
use super::{find_user_id, Analytics, DocumentDeletionKind, DocumentFetchKind};
|
||||
use crate::routes::indexes::documents::UpdateDocumentsQuery;
|
||||
use crate::routes::tasks::TasksFilterQuery;
|
||||
use crate::Opt;
|
||||
|
@ -71,6 +71,8 @@ impl Analytics for MockAnalytics {
|
|||
_request: &HttpRequest,
|
||||
) {
|
||||
}
|
||||
fn get_fetch_documents(&self, _documents_query: &DocumentFetchKind, _request: &HttpRequest) {}
|
||||
fn post_fetch_documents(&self, _documents_query: &DocumentFetchKind, _request: &HttpRequest) {}
|
||||
fn get_tasks(&self, _query: &TasksFilterQuery, _request: &HttpRequest) {}
|
||||
fn health_seen(&self, _request: &HttpRequest) {}
|
||||
}
|
||||
|
|
|
@ -67,6 +67,12 @@ pub enum DocumentDeletionKind {
|
|||
PerFilter,
|
||||
}
|
||||
|
||||
#[derive(Copy, Clone, Debug, PartialEq, Eq)]
|
||||
pub enum DocumentFetchKind {
|
||||
PerDocumentId,
|
||||
Normal { with_filter: bool, limit: usize, offset: usize },
|
||||
}
|
||||
|
||||
pub trait Analytics: Sync + Send {
|
||||
fn instance_uid(&self) -> Option<&InstanceUid>;
|
||||
|
||||
|
@ -90,6 +96,12 @@ pub trait Analytics: Sync + Send {
|
|||
request: &HttpRequest,
|
||||
);
|
||||
|
||||
// this method should be called to aggregate a fetch documents request
|
||||
fn get_fetch_documents(&self, documents_query: &DocumentFetchKind, request: &HttpRequest);
|
||||
|
||||
// this method should be called to aggregate a fetch documents request
|
||||
fn post_fetch_documents(&self, documents_query: &DocumentFetchKind, request: &HttpRequest);
|
||||
|
||||
// this method should be called to aggregate a add documents request
|
||||
fn delete_documents(&self, kind: DocumentDeletionKind, request: &HttpRequest);
|
||||
|
||||
|
|
|
@ -23,7 +23,9 @@ use tokio::select;
|
|||
use tokio::sync::mpsc::{self, Receiver, Sender};
|
||||
use uuid::Uuid;
|
||||
|
||||
use super::{config_user_id_path, DocumentDeletionKind, MEILISEARCH_CONFIG_PATH};
|
||||
use super::{
|
||||
config_user_id_path, DocumentDeletionKind, DocumentFetchKind, MEILISEARCH_CONFIG_PATH,
|
||||
};
|
||||
use crate::analytics::Analytics;
|
||||
use crate::option::{default_http_addr, IndexerOpts, MaxMemory, MaxThreads, ScheduleSnapshot};
|
||||
use crate::routes::indexes::documents::UpdateDocumentsQuery;
|
||||
|
@ -72,6 +74,8 @@ pub enum AnalyticsMsg {
|
|||
AggregateAddDocuments(DocumentsAggregator),
|
||||
AggregateDeleteDocuments(DocumentsDeletionAggregator),
|
||||
AggregateUpdateDocuments(DocumentsAggregator),
|
||||
AggregateGetFetchDocuments(DocumentsFetchAggregator),
|
||||
AggregatePostFetchDocuments(DocumentsFetchAggregator),
|
||||
AggregateTasks(TasksAggregator),
|
||||
AggregateHealth(HealthAggregator),
|
||||
}
|
||||
|
@ -139,6 +143,8 @@ impl SegmentAnalytics {
|
|||
add_documents_aggregator: DocumentsAggregator::default(),
|
||||
delete_documents_aggregator: DocumentsDeletionAggregator::default(),
|
||||
update_documents_aggregator: DocumentsAggregator::default(),
|
||||
get_fetch_documents_aggregator: DocumentsFetchAggregator::default(),
|
||||
post_fetch_documents_aggregator: DocumentsFetchAggregator::default(),
|
||||
get_tasks_aggregator: TasksAggregator::default(),
|
||||
health_aggregator: HealthAggregator::default(),
|
||||
});
|
||||
|
@ -205,6 +211,16 @@ impl super::Analytics for SegmentAnalytics {
|
|||
let _ = self.sender.try_send(AnalyticsMsg::AggregateUpdateDocuments(aggregate));
|
||||
}
|
||||
|
||||
fn get_fetch_documents(&self, documents_query: &DocumentFetchKind, request: &HttpRequest) {
|
||||
let aggregate = DocumentsFetchAggregator::from_query(documents_query, request);
|
||||
let _ = self.sender.try_send(AnalyticsMsg::AggregateGetFetchDocuments(aggregate));
|
||||
}
|
||||
|
||||
fn post_fetch_documents(&self, documents_query: &DocumentFetchKind, request: &HttpRequest) {
|
||||
let aggregate = DocumentsFetchAggregator::from_query(documents_query, request);
|
||||
let _ = self.sender.try_send(AnalyticsMsg::AggregatePostFetchDocuments(aggregate));
|
||||
}
|
||||
|
||||
fn get_tasks(&self, query: &TasksFilterQuery, request: &HttpRequest) {
|
||||
let aggregate = TasksAggregator::from_query(query, request);
|
||||
let _ = self.sender.try_send(AnalyticsMsg::AggregateTasks(aggregate));
|
||||
|
@ -225,6 +241,7 @@ impl super::Analytics for SegmentAnalytics {
|
|||
struct Infos {
|
||||
env: String,
|
||||
experimental_enable_metrics: bool,
|
||||
experimental_reduce_indexing_memory_usage: bool,
|
||||
db_path: bool,
|
||||
import_dump: bool,
|
||||
dump_dir: bool,
|
||||
|
@ -258,6 +275,7 @@ impl From<Opt> for Infos {
|
|||
let Opt {
|
||||
db_path,
|
||||
experimental_enable_metrics,
|
||||
experimental_reduce_indexing_memory_usage,
|
||||
http_addr,
|
||||
master_key: _,
|
||||
env,
|
||||
|
@ -300,6 +318,7 @@ impl From<Opt> for Infos {
|
|||
Self {
|
||||
env,
|
||||
experimental_enable_metrics,
|
||||
experimental_reduce_indexing_memory_usage,
|
||||
db_path: db_path != PathBuf::from("./data.ms"),
|
||||
import_dump: import_dump.is_some(),
|
||||
dump_dir: dump_dir != PathBuf::from("dumps/"),
|
||||
|
@ -338,6 +357,8 @@ pub struct Segment {
|
|||
add_documents_aggregator: DocumentsAggregator,
|
||||
delete_documents_aggregator: DocumentsDeletionAggregator,
|
||||
update_documents_aggregator: DocumentsAggregator,
|
||||
get_fetch_documents_aggregator: DocumentsFetchAggregator,
|
||||
post_fetch_documents_aggregator: DocumentsFetchAggregator,
|
||||
get_tasks_aggregator: TasksAggregator,
|
||||
health_aggregator: HealthAggregator,
|
||||
}
|
||||
|
@ -400,6 +421,8 @@ impl Segment {
|
|||
Some(AnalyticsMsg::AggregateAddDocuments(agreg)) => self.add_documents_aggregator.aggregate(agreg),
|
||||
Some(AnalyticsMsg::AggregateDeleteDocuments(agreg)) => self.delete_documents_aggregator.aggregate(agreg),
|
||||
Some(AnalyticsMsg::AggregateUpdateDocuments(agreg)) => self.update_documents_aggregator.aggregate(agreg),
|
||||
Some(AnalyticsMsg::AggregateGetFetchDocuments(agreg)) => self.get_fetch_documents_aggregator.aggregate(agreg),
|
||||
Some(AnalyticsMsg::AggregatePostFetchDocuments(agreg)) => self.post_fetch_documents_aggregator.aggregate(agreg),
|
||||
Some(AnalyticsMsg::AggregateTasks(agreg)) => self.get_tasks_aggregator.aggregate(agreg),
|
||||
Some(AnalyticsMsg::AggregateHealth(agreg)) => self.health_aggregator.aggregate(agreg),
|
||||
None => (),
|
||||
|
@ -450,6 +473,10 @@ impl Segment {
|
|||
.into_event(&self.user, "Documents Deleted");
|
||||
let update_documents = std::mem::take(&mut self.update_documents_aggregator)
|
||||
.into_event(&self.user, "Documents Updated");
|
||||
let get_fetch_documents = std::mem::take(&mut self.get_fetch_documents_aggregator)
|
||||
.into_event(&self.user, "Documents Fetched GET");
|
||||
let post_fetch_documents = std::mem::take(&mut self.post_fetch_documents_aggregator)
|
||||
.into_event(&self.user, "Documents Fetched POST");
|
||||
let get_tasks =
|
||||
std::mem::take(&mut self.get_tasks_aggregator).into_event(&self.user, "Tasks Seen");
|
||||
let health =
|
||||
|
@ -473,6 +500,12 @@ impl Segment {
|
|||
if let Some(update_documents) = update_documents {
|
||||
let _ = self.batcher.push(update_documents).await;
|
||||
}
|
||||
if let Some(get_fetch_documents) = get_fetch_documents {
|
||||
let _ = self.batcher.push(get_fetch_documents).await;
|
||||
}
|
||||
if let Some(post_fetch_documents) = post_fetch_documents {
|
||||
let _ = self.batcher.push(post_fetch_documents).await;
|
||||
}
|
||||
if let Some(get_tasks) = get_tasks {
|
||||
let _ = self.batcher.push(get_tasks).await;
|
||||
}
|
||||
|
@ -1135,3 +1168,76 @@ impl HealthAggregator {
|
|||
})
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Default, Serialize)]
|
||||
pub struct DocumentsFetchAggregator {
|
||||
#[serde(skip)]
|
||||
timestamp: Option<OffsetDateTime>,
|
||||
|
||||
// context
|
||||
#[serde(rename = "user-agent")]
|
||||
user_agents: HashSet<String>,
|
||||
|
||||
#[serde(rename = "requests.max_limit")]
|
||||
total_received: usize,
|
||||
|
||||
// a call on ../documents/:doc_id
|
||||
per_document_id: bool,
|
||||
// if a filter was used
|
||||
per_filter: bool,
|
||||
|
||||
// pagination
|
||||
#[serde(rename = "pagination.max_limit")]
|
||||
max_limit: usize,
|
||||
#[serde(rename = "pagination.max_offset")]
|
||||
max_offset: usize,
|
||||
}
|
||||
|
||||
impl DocumentsFetchAggregator {
|
||||
pub fn from_query(query: &DocumentFetchKind, request: &HttpRequest) -> Self {
|
||||
let (limit, offset) = match query {
|
||||
DocumentFetchKind::PerDocumentId => (1, 0),
|
||||
DocumentFetchKind::Normal { limit, offset, .. } => (*limit, *offset),
|
||||
};
|
||||
Self {
|
||||
timestamp: Some(OffsetDateTime::now_utc()),
|
||||
user_agents: extract_user_agents(request).into_iter().collect(),
|
||||
total_received: 1,
|
||||
per_document_id: matches!(query, DocumentFetchKind::PerDocumentId),
|
||||
per_filter: matches!(query, DocumentFetchKind::Normal { with_filter, .. } if *with_filter),
|
||||
max_limit: limit,
|
||||
max_offset: offset,
|
||||
}
|
||||
}
|
||||
|
||||
/// Aggregate one [DocumentsFetchAggregator] into another.
|
||||
pub fn aggregate(&mut self, other: Self) {
|
||||
if self.timestamp.is_none() {
|
||||
self.timestamp = other.timestamp;
|
||||
}
|
||||
for user_agent in other.user_agents {
|
||||
self.user_agents.insert(user_agent);
|
||||
}
|
||||
|
||||
self.total_received = self.total_received.saturating_add(other.total_received);
|
||||
self.per_document_id |= other.per_document_id;
|
||||
self.per_filter |= other.per_filter;
|
||||
|
||||
self.max_limit = self.max_limit.max(other.max_limit);
|
||||
self.max_offset = self.max_offset.max(other.max_offset);
|
||||
}
|
||||
|
||||
pub fn into_event(self, user: &User, event_name: &str) -> Option<Track> {
|
||||
// if we had no timestamp it means we never encountered any events and
|
||||
// thus we don't need to send this event.
|
||||
let timestamp = self.timestamp?;
|
||||
|
||||
Some(Track {
|
||||
timestamp: Some(timestamp),
|
||||
user: user.clone(),
|
||||
event: event_name.to_string(),
|
||||
properties: serde_json::to_value(self).ok()?,
|
||||
..Default::default()
|
||||
})
|
||||
}
|
||||
}
|
||||
|
|
|
@ -61,7 +61,7 @@ impl ErrorCode for MeilisearchHttpError {
|
|||
MeilisearchHttpError::MissingPayload(_) => Code::MissingPayload,
|
||||
MeilisearchHttpError::InvalidContentType(_, _) => Code::InvalidContentType,
|
||||
MeilisearchHttpError::DocumentNotFound(_) => Code::DocumentNotFound,
|
||||
MeilisearchHttpError::EmptyFilter => Code::InvalidDocumentDeleteFilter,
|
||||
MeilisearchHttpError::EmptyFilter => Code::InvalidDocumentFilter,
|
||||
MeilisearchHttpError::InvalidExpression(_, _) => Code::InvalidSearchFilter,
|
||||
MeilisearchHttpError::PayloadTooLarge(_) => Code::PayloadTooLarge,
|
||||
MeilisearchHttpError::SwapIndexPayloadWrongLength(_) => Code::InvalidSwapIndexes,
|
||||
|
|
|
@ -232,6 +232,7 @@ fn open_or_create_database_unchecked(
|
|||
dumps_path: opt.dump_dir.clone(),
|
||||
task_db_size: opt.max_task_db_size.get_bytes() as usize,
|
||||
index_base_map_size: opt.max_index_size.get_bytes() as usize,
|
||||
enable_mdb_writemap: opt.experimental_reduce_indexing_memory_usage,
|
||||
indexer_config: (&opt.indexer_options).try_into()?,
|
||||
autobatching_enabled: true,
|
||||
max_number_of_tasks: 1_000_000,
|
||||
|
|
|
@ -29,6 +29,11 @@ fn setup(opt: &Opt) -> anyhow::Result<()> {
|
|||
async fn main() -> anyhow::Result<()> {
|
||||
let (opt, config_read_from) = Opt::try_build()?;
|
||||
|
||||
anyhow::ensure!(
|
||||
!(cfg!(windows) && opt.experimental_reduce_indexing_memory_usage),
|
||||
"The `experimental-reduce-indexing-memory-usage` flag is not supported on Windows"
|
||||
);
|
||||
|
||||
setup(&opt)?;
|
||||
|
||||
match (opt.env.as_ref(), &opt.master_key) {
|
||||
|
|
|
@ -4,20 +4,32 @@ use prometheus::{
|
|||
register_int_gauge_vec, HistogramVec, IntCounterVec, IntGauge, IntGaugeVec,
|
||||
};
|
||||
|
||||
const HTTP_RESPONSE_TIME_CUSTOM_BUCKETS: &[f64; 14] = &[
|
||||
0.0005, 0.0008, 0.00085, 0.0009, 0.00095, 0.001, 0.00105, 0.0011, 0.00115, 0.0012, 0.0015,
|
||||
0.002, 0.003, 1.0,
|
||||
];
|
||||
/// Create evenly distributed buckets
|
||||
fn create_buckets() -> [f64; 29] {
|
||||
(0..10)
|
||||
.chain((10..100).step_by(10))
|
||||
.chain((100..=1000).step_by(100))
|
||||
.map(|i| i as f64 / 1000.)
|
||||
.collect::<Vec<_>>()
|
||||
.try_into()
|
||||
.unwrap()
|
||||
}
|
||||
|
||||
lazy_static! {
|
||||
pub static ref HTTP_REQUESTS_TOTAL: IntCounterVec = register_int_counter_vec!(
|
||||
opts!("http_requests_total", "HTTP requests total"),
|
||||
pub static ref HTTP_RESPONSE_TIME_CUSTOM_BUCKETS: [f64; 29] = create_buckets();
|
||||
pub static ref MEILISEARCH_HTTP_REQUESTS_TOTAL: IntCounterVec = register_int_counter_vec!(
|
||||
opts!("meilisearch_http_requests_total", "Meilisearch HTTP requests total"),
|
||||
&["method", "path"]
|
||||
)
|
||||
.expect("Can't create a metric");
|
||||
pub static ref MEILISEARCH_DB_SIZE_BYTES: IntGauge =
|
||||
register_int_gauge!(opts!("meilisearch_db_size_bytes", "Meilisearch Db Size In Bytes"))
|
||||
register_int_gauge!(opts!("meilisearch_db_size_bytes", "Meilisearch DB Size In Bytes"))
|
||||
.expect("Can't create a metric");
|
||||
pub static ref MEILISEARCH_USED_DB_SIZE_BYTES: IntGauge = register_int_gauge!(opts!(
|
||||
"meilisearch_used_db_size_bytes",
|
||||
"Meilisearch Used DB Size In Bytes"
|
||||
))
|
||||
.expect("Can't create a metric");
|
||||
pub static ref MEILISEARCH_INDEX_COUNT: IntGauge =
|
||||
register_int_gauge!(opts!("meilisearch_index_count", "Meilisearch Index Count"))
|
||||
.expect("Can't create a metric");
|
||||
|
@ -26,11 +38,16 @@ lazy_static! {
|
|||
&["index"]
|
||||
)
|
||||
.expect("Can't create a metric");
|
||||
pub static ref HTTP_RESPONSE_TIME_SECONDS: HistogramVec = register_histogram_vec!(
|
||||
pub static ref MEILISEARCH_HTTP_RESPONSE_TIME_SECONDS: HistogramVec = register_histogram_vec!(
|
||||
"http_response_time_seconds",
|
||||
"HTTP response times",
|
||||
&["method", "path"],
|
||||
HTTP_RESPONSE_TIME_CUSTOM_BUCKETS.to_vec()
|
||||
)
|
||||
.expect("Can't create a metric");
|
||||
pub static ref MEILISEARCH_NB_TASKS: IntGaugeVec = register_int_gauge_vec!(
|
||||
opts!("meilisearch_nb_tasks", "Meilisearch Number of tasks"),
|
||||
&["kind", "value"]
|
||||
)
|
||||
.expect("Can't create a metric");
|
||||
}
|
||||
|
|
|
@ -52,11 +52,11 @@ where
|
|||
if is_registered_resource {
|
||||
let request_method = req.method().to_string();
|
||||
histogram_timer = Some(
|
||||
crate::metrics::HTTP_RESPONSE_TIME_SECONDS
|
||||
crate::metrics::MEILISEARCH_HTTP_RESPONSE_TIME_SECONDS
|
||||
.with_label_values(&[&request_method, request_path])
|
||||
.start_timer(),
|
||||
);
|
||||
crate::metrics::HTTP_REQUESTS_TOTAL
|
||||
crate::metrics::MEILISEARCH_HTTP_REQUESTS_TOTAL
|
||||
.with_label_values(&[&request_method, request_path])
|
||||
.inc();
|
||||
}
|
||||
|
|
|
@ -48,6 +48,8 @@ const MEILI_IGNORE_DUMP_IF_DB_EXISTS: &str = "MEILI_IGNORE_DUMP_IF_DB_EXISTS";
|
|||
const MEILI_DUMP_DIR: &str = "MEILI_DUMP_DIR";
|
||||
const MEILI_LOG_LEVEL: &str = "MEILI_LOG_LEVEL";
|
||||
const MEILI_EXPERIMENTAL_ENABLE_METRICS: &str = "MEILI_EXPERIMENTAL_ENABLE_METRICS";
|
||||
const MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE: &str =
|
||||
"MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE";
|
||||
|
||||
const DEFAULT_CONFIG_FILE_PATH: &str = "./config.toml";
|
||||
const DEFAULT_DB_PATH: &str = "./data.ms";
|
||||
|
@ -293,6 +295,11 @@ pub struct Opt {
|
|||
#[serde(default)]
|
||||
pub experimental_enable_metrics: bool,
|
||||
|
||||
/// Experimental RAM reduction during indexing, do not use in production, see: <https://github.com/meilisearch/product/discussions/652>
|
||||
#[clap(long, env = MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE)]
|
||||
#[serde(default)]
|
||||
pub experimental_reduce_indexing_memory_usage: bool,
|
||||
|
||||
#[serde(flatten)]
|
||||
#[clap(flatten)]
|
||||
pub indexer_options: IndexerOpts,
|
||||
|
@ -385,6 +392,7 @@ impl Opt {
|
|||
#[cfg(all(not(debug_assertions), feature = "analytics"))]
|
||||
no_analytics,
|
||||
experimental_enable_metrics: enable_metrics_route,
|
||||
experimental_reduce_indexing_memory_usage: reduce_indexing_memory_usage,
|
||||
} = self;
|
||||
export_to_env_if_not_present(MEILI_DB_PATH, db_path);
|
||||
export_to_env_if_not_present(MEILI_HTTP_ADDR, http_addr);
|
||||
|
@ -426,6 +434,10 @@ impl Opt {
|
|||
MEILI_EXPERIMENTAL_ENABLE_METRICS,
|
||||
enable_metrics_route.to_string(),
|
||||
);
|
||||
export_to_env_if_not_present(
|
||||
MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE,
|
||||
reduce_indexing_memory_usage.to_string(),
|
||||
);
|
||||
indexer_options.export_to_env();
|
||||
}
|
||||
|
||||
|
|
|
@ -29,7 +29,7 @@ use tempfile::tempfile;
|
|||
use tokio::fs::File;
|
||||
use tokio::io::{AsyncSeekExt, AsyncWriteExt, BufWriter};
|
||||
|
||||
use crate::analytics::{Analytics, DocumentDeletionKind};
|
||||
use crate::analytics::{Analytics, DocumentDeletionKind, DocumentFetchKind};
|
||||
use crate::error::MeilisearchHttpError;
|
||||
use crate::error::PayloadError::ReceivePayload;
|
||||
use crate::extractors::authentication::policies::*;
|
||||
|
@ -97,10 +97,14 @@ pub async fn get_document(
|
|||
index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_GET }>, Data<IndexScheduler>>,
|
||||
document_param: web::Path<DocumentParam>,
|
||||
params: AwebQueryParameter<GetDocument, DeserrQueryParamError>,
|
||||
req: HttpRequest,
|
||||
analytics: web::Data<dyn Analytics>,
|
||||
) -> Result<HttpResponse, ResponseError> {
|
||||
let DocumentParam { index_uid, document_id } = document_param.into_inner();
|
||||
let index_uid = IndexUid::try_from(index_uid)?;
|
||||
|
||||
analytics.get_fetch_documents(&DocumentFetchKind::PerDocumentId, &req);
|
||||
|
||||
let GetDocument { fields } = params.into_inner();
|
||||
let attributes_to_retrieve = fields.merge_star_and_none();
|
||||
|
||||
|
@ -161,16 +165,31 @@ pub async fn documents_by_query_post(
|
|||
index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_GET }>, Data<IndexScheduler>>,
|
||||
index_uid: web::Path<String>,
|
||||
body: AwebJson<BrowseQuery, DeserrJsonError>,
|
||||
req: HttpRequest,
|
||||
analytics: web::Data<dyn Analytics>,
|
||||
) -> Result<HttpResponse, ResponseError> {
|
||||
debug!("called with body: {:?}", body);
|
||||
|
||||
documents_by_query(&index_scheduler, index_uid, body.into_inner())
|
||||
let body = body.into_inner();
|
||||
|
||||
analytics.post_fetch_documents(
|
||||
&DocumentFetchKind::Normal {
|
||||
with_filter: body.filter.is_some(),
|
||||
limit: body.limit,
|
||||
offset: body.offset,
|
||||
},
|
||||
&req,
|
||||
);
|
||||
|
||||
documents_by_query(&index_scheduler, index_uid, body)
|
||||
}
|
||||
|
||||
pub async fn get_documents(
|
||||
index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_GET }>, Data<IndexScheduler>>,
|
||||
index_uid: web::Path<String>,
|
||||
params: AwebQueryParameter<BrowseQueryGet, DeserrQueryParamError>,
|
||||
req: HttpRequest,
|
||||
analytics: web::Data<dyn Analytics>,
|
||||
) -> Result<HttpResponse, ResponseError> {
|
||||
debug!("called with params: {:?}", params);
|
||||
|
||||
|
@ -191,6 +210,15 @@ pub async fn get_documents(
|
|||
filter,
|
||||
};
|
||||
|
||||
analytics.get_fetch_documents(
|
||||
&DocumentFetchKind::Normal {
|
||||
with_filter: query.filter.is_some(),
|
||||
limit: query.limit,
|
||||
offset: query.offset,
|
||||
},
|
||||
&req,
|
||||
);
|
||||
|
||||
documents_by_query(&index_scheduler, index_uid, query)
|
||||
}
|
||||
|
||||
|
@ -458,7 +486,7 @@ pub async fn delete_documents_batch(
|
|||
#[derive(Debug, Deserr)]
|
||||
#[deserr(error = DeserrJsonError, rename_all = camelCase, deny_unknown_fields)]
|
||||
pub struct DocumentDeletionByFilter {
|
||||
#[deserr(error = DeserrJsonError<InvalidDocumentDeleteFilter>)]
|
||||
#[deserr(error = DeserrJsonError<InvalidDocumentFilter>, missing_field_error = DeserrJsonError::missing_document_filter)]
|
||||
filter: Value,
|
||||
}
|
||||
|
||||
|
@ -480,8 +508,8 @@ pub async fn delete_documents_by_filter(
|
|||
|| -> Result<_, ResponseError> {
|
||||
Ok(crate::search::parse_filter(&filter)?.ok_or(MeilisearchHttpError::EmptyFilter)?)
|
||||
}()
|
||||
// and whatever was the error, the error code should always be an InvalidDocumentDeleteFilter
|
||||
.map_err(|err| ResponseError::from_msg(err.message, Code::InvalidDocumentDeleteFilter))?;
|
||||
// and whatever was the error, the error code should always be an InvalidDocumentFilter
|
||||
.map_err(|err| ResponseError::from_msg(err.message, Code::InvalidDocumentFilter))?;
|
||||
let task = KindWithContent::DocumentDeletionByFilter { index_uid, filter_expr: filter };
|
||||
|
||||
let task: SummarizedTaskView =
|
||||
|
@ -540,7 +568,12 @@ fn retrieve_documents<S: AsRef<str>>(
|
|||
};
|
||||
|
||||
let candidates = if let Some(filter) = filter {
|
||||
filter.evaluate(&rtxn, index)?
|
||||
filter.evaluate(&rtxn, index).map_err(|err| match err {
|
||||
milli::Error::UserError(milli::UserError::InvalidFilter(_)) => {
|
||||
ResponseError::from_msg(err.to_string(), Code::InvalidDocumentFilter)
|
||||
}
|
||||
e => e.into(),
|
||||
})?
|
||||
} else {
|
||||
index.documents_ids(&rtxn)?
|
||||
};
|
||||
|
|
|
@ -17,7 +17,7 @@ pub fn configure(config: &mut web::ServiceConfig) {
|
|||
|
||||
pub async fn get_metrics(
|
||||
index_scheduler: GuardedData<ActionPolicy<{ actions::METRICS_GET }>, Data<IndexScheduler>>,
|
||||
auth_controller: GuardedData<ActionPolicy<{ actions::METRICS_GET }>, Data<AuthController>>,
|
||||
auth_controller: Data<AuthController>,
|
||||
) -> Result<HttpResponse, ResponseError> {
|
||||
let auth_filters = index_scheduler.filters();
|
||||
if !auth_filters.all_indexes_authorized() {
|
||||
|
@ -28,10 +28,10 @@ pub async fn get_metrics(
|
|||
return Err(error);
|
||||
}
|
||||
|
||||
let response =
|
||||
create_all_stats((*index_scheduler).clone(), (*auth_controller).clone(), auth_filters)?;
|
||||
let response = create_all_stats((*index_scheduler).clone(), auth_controller, auth_filters)?;
|
||||
|
||||
crate::metrics::MEILISEARCH_DB_SIZE_BYTES.set(response.database_size as i64);
|
||||
crate::metrics::MEILISEARCH_USED_DB_SIZE_BYTES.set(response.used_database_size as i64);
|
||||
crate::metrics::MEILISEARCH_INDEX_COUNT.set(response.indexes.len() as i64);
|
||||
|
||||
for (index, value) in response.indexes.iter() {
|
||||
|
@ -40,6 +40,14 @@ pub async fn get_metrics(
|
|||
.set(value.number_of_documents as i64);
|
||||
}
|
||||
|
||||
for (kind, value) in index_scheduler.get_stats()? {
|
||||
for (value, count) in value {
|
||||
crate::metrics::MEILISEARCH_NB_TASKS
|
||||
.with_label_values(&[&kind, &value])
|
||||
.set(count as i64);
|
||||
}
|
||||
}
|
||||
|
||||
let encoder = TextEncoder::new();
|
||||
let mut buffer = vec![];
|
||||
encoder.encode(&prometheus::gather(), &mut buffer).expect("Failed to encode metrics");
|
||||
|
|
|
@ -231,6 +231,8 @@ pub async fn running() -> HttpResponse {
|
|||
#[serde(rename_all = "camelCase")]
|
||||
pub struct Stats {
|
||||
pub database_size: u64,
|
||||
#[serde(skip)]
|
||||
pub used_database_size: u64,
|
||||
#[serde(serialize_with = "time::serde::rfc3339::option::serialize")]
|
||||
pub last_update: Option<OffsetDateTime>,
|
||||
pub indexes: BTreeMap<String, indexes::IndexStats>,
|
||||
|
@ -259,6 +261,7 @@ pub fn create_all_stats(
|
|||
let mut last_task: Option<OffsetDateTime> = None;
|
||||
let mut indexes = BTreeMap::new();
|
||||
let mut database_size = 0;
|
||||
let mut used_database_size = 0;
|
||||
|
||||
for index_uid in index_scheduler.index_names()? {
|
||||
// Accumulate the size of all indexes, even unauthorized ones, so
|
||||
|
@ -266,6 +269,7 @@ pub fn create_all_stats(
|
|||
// See <https://github.com/meilisearch/meilisearch/pull/3541#discussion_r1126747643> for context.
|
||||
let stats = index_scheduler.index_stats(&index_uid)?;
|
||||
database_size += stats.inner_stats.database_size;
|
||||
used_database_size += stats.inner_stats.used_database_size;
|
||||
|
||||
if !filters.is_index_authorized(&index_uid) {
|
||||
continue;
|
||||
|
@ -278,10 +282,14 @@ pub fn create_all_stats(
|
|||
}
|
||||
|
||||
database_size += index_scheduler.size()?;
|
||||
used_database_size += index_scheduler.used_size()?;
|
||||
database_size += auth_controller.size()?;
|
||||
database_size += index_scheduler.compute_update_file_size()?;
|
||||
used_database_size += auth_controller.used_size()?;
|
||||
let update_file_size = index_scheduler.compute_update_file_size()?;
|
||||
database_size += update_file_size;
|
||||
used_database_size += update_file_size;
|
||||
|
||||
let stats = Stats { database_size, last_update: last_task, indexes };
|
||||
let stats = Stats { database_size, used_database_size, last_update: last_task, indexes };
|
||||
Ok(stats)
|
||||
}
|
||||
|
||||
|
|
|
@ -99,7 +99,7 @@ pub struct DetailsView {
|
|||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub deleted_tasks: Option<Option<u64>>,
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub original_filter: Option<String>,
|
||||
pub original_filter: Option<Option<String>>,
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub dump_uid: Option<Option<String>>,
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
|
@ -131,12 +131,13 @@ impl From<Details> for DetailsView {
|
|||
} => DetailsView {
|
||||
provided_ids: Some(received_document_ids),
|
||||
deleted_documents: Some(deleted_documents),
|
||||
original_filter: Some(None),
|
||||
..DetailsView::default()
|
||||
},
|
||||
Details::DocumentDeletionByFilter { original_filter, deleted_documents } => {
|
||||
DetailsView {
|
||||
provided_ids: Some(0),
|
||||
original_filter: Some(original_filter),
|
||||
original_filter: Some(Some(original_filter)),
|
||||
deleted_documents: Some(deleted_documents),
|
||||
..DetailsView::default()
|
||||
}
|
||||
|
@ -148,7 +149,7 @@ impl From<Details> for DetailsView {
|
|||
DetailsView {
|
||||
matched_tasks: Some(matched_tasks),
|
||||
canceled_tasks: Some(canceled_tasks),
|
||||
original_filter: Some(original_filter),
|
||||
original_filter: Some(Some(original_filter)),
|
||||
..DetailsView::default()
|
||||
}
|
||||
}
|
||||
|
@ -156,7 +157,7 @@ impl From<Details> for DetailsView {
|
|||
DetailsView {
|
||||
matched_tasks: Some(matched_tasks),
|
||||
deleted_tasks: Some(deleted_tasks),
|
||||
original_filter: Some(original_filter),
|
||||
original_filter: Some(Some(original_filter)),
|
||||
..DetailsView::default()
|
||||
}
|
||||
}
|
||||
|
@ -729,7 +730,7 @@ mod tests {
|
|||
let err = deserr_query_params::<TaskDeletionOrCancelationQuery>(params).unwrap_err();
|
||||
snapshot!(meili_snap::json_string!(err), @r###"
|
||||
{
|
||||
"message": "Invalid value in parameter `types`: `createIndex` is not a valid task type. Available types are `documentAdditionOrUpdate`, `documentDeletion`, `documentDeletionByFilter`, `settingsUpdate`, `indexCreation`, `indexDeletion`, `indexUpdate`, `indexSwap`, `taskCancelation`, `taskDeletion`, `dumpCreation`, `snapshotCreation`.",
|
||||
"message": "Invalid value in parameter `types`: `createIndex` is not a valid task type. Available types are `documentAdditionOrUpdate`, `documentDeletion`, `settingsUpdate`, `indexCreation`, `indexDeletion`, `indexUpdate`, `indexSwap`, `taskCancelation`, `taskDeletion`, `dumpCreation`, `snapshotCreation`.",
|
||||
"code": "invalid_task_types",
|
||||
"type": "invalid_request",
|
||||
"link": "https://docs.meilisearch.com/errors#invalid_task_types"
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue