Merge #209

209: Integrate amplitude r=MarinPostma a=irevoire

And merge the sentry and amplitude usage under one “Enable analytics” flag

closes #180


Co-authored-by: Tamo <tamo@meilisearch.com>
Co-authored-by: Irevoire <tamo@meilisearch.com>

meilisearch-http/src/analytics.rs

@@ -1,14 +1,10 @@
 use std::hash::{Hash, Hasher};
-use std::{error, thread};
 use std::time::{Duration, Instant, SystemTime, UNIX_EPOCH};
 
-use log::error;
+use log::debug;
 use serde::Serialize;
-use serde_qs as qs;
 use siphasher::sip::SipHasher;
-use walkdir::WalkDir;
 
-use crate::helpers::EnvSizer;
 use crate::Data;
 use crate::Opt;
 
@@ -22,26 +18,21 @@ struct EventProperties {
 }
 
 impl EventProperties {
-    fn from(data: Data) -> Result<EventProperties, Box<dyn error::Error>> {
-        let mut index_list = Vec::new();
+    async fn from(data: Data) -> anyhow::Result<EventProperties> {
+        let stats = data.index_controller.get_all_stats().await?;
 
-        let reader = data.db.main_read_txn()?;
-
-        for index_uid in data.db.indexes_uids() {
-            if let Some(index) = data.db.open_index(&index_uid) {
-                let number_of_documents = index.main.number_of_documents(&reader)?;
-                index_list.push(number_of_documents);
-            }
-        }
-
-        let database_size = data.env.size();
-
-        let last_update_timestamp = data.db.last_update(&reader)?.map(|u| u.timestamp());
+        let database_size = stats.database_size;
+        let last_update_timestamp = stats.last_update.map(|u| u.timestamp());
+        let number_of_documents = stats
+            .indexes
+            .values()
+            .map(|index| index.number_of_documents)
+            .collect();
 
         Ok(EventProperties {
             database_size,
             last_update_timestamp,
-            number_of_documents: index_list,
+            number_of_documents,
         })
     }
 }
@@ -68,10 +59,10 @@ struct Event<'a> {
 #[derive(Debug, Serialize)]
 struct AmplitudeRequest<'a> {
     api_key: &'a str,
-    event: &'a str,
+    events: Vec<Event<'a>>,
 }
 
-pub fn analytics_sender(data: Data, opt: Opt) {
+pub async fn analytics_sender(data: Data, opt: Opt) {
     let username = whoami::username();
     let hostname = whoami::hostname();
     let platform = whoami::platform();
@@ -93,7 +84,7 @@ pub fn analytics_sender(data: Data, opt: Opt) {
         let time = n.as_secs();
         let event_type = "runtime_tick";
         let elapsed_since_start = first_start.elapsed().as_secs() / 86_400; // One day
-        let event_properties = EventProperties::from(data.clone()).ok();
+        let event_properties = EventProperties::from(data.clone()).await.ok();
         let app_version = env!("CARGO_PKG_VERSION").to_string();
         let app_version = app_version.as_str();
         let user_email = std::env::var("MEILI_USER_EMAIL").ok();
@@ -114,20 +105,22 @@ pub fn analytics_sender(data: Data, opt: Opt) {
             user_properties,
             event_properties,
         };
-        let event = serde_json::to_string(&event).unwrap();
 
         let request = AmplitudeRequest {
             api_key: AMPLITUDE_API_KEY,
-            event: &event,
+            events: vec![event],
         };
 
-        let body = qs::to_string(&request).unwrap();
-        let response = ureq::post("https://api.amplitude.com/httpapi").send_string(&body);
-        if !response.ok() {
-            let body = response.into_string().unwrap();
-            error!("Unsuccessful call to Amplitude: {}", body);
+        let response = reqwest::Client::new()
+            .post("https://api2.amplitude.com/2/httpapi")
+            .timeout(Duration::from_secs(60)) // 1 minute max
+            .json(&request)
+            .send()
+            .await;
+        if let Err(e) = response {
+            debug!("Unsuccessful call to Amplitude: {}", e);
         }
 
-        thread::sleep(Duration::from_secs(3600)) // one hour
+        tokio::time::sleep(Duration::from_secs(3600)).await;
     }
 }

meilisearch-http/src/lib.rs

@@ -6,6 +6,9 @@ mod index_controller;
 pub mod option;
 pub mod routes;
 
+#[cfg(all(not(debug_assertions), feature = "analytics"))]
+pub mod analytics;
+
 pub use self::data::Data;
 pub use option::Opt;
 

meilisearch-http/src/main.rs

@@ -5,12 +5,16 @@ use main_error::MainError;
 use meilisearch_http::{create_app, Data, Opt};
 use structopt::StructOpt;
 
-//mod analytics;
+#[cfg(all(not(debug_assertions), feature = "analytics"))]
+use meilisearch_http::analytics;
 
 #[cfg(target_os = "linux")]
 #[global_allocator]
 static ALLOC: jemallocator::Jemalloc = jemallocator::Jemalloc;
 
+#[cfg(all(not(debug_assertions), feature = "analytics"))]
+const SENTRY_DSN: &str = "https://5ddfa22b95f241198be2271aaf028653@sentry.io/3060337";
+
 #[actix_web::main]
 async fn main() -> Result<(), MainError> {
     let opt = Opt::from_args();
@@ -26,16 +30,17 @@ async fn main() -> Result<(), MainError> {
                         .into(),
                 );
             }
-            #[cfg(all(not(debug_assertions), feature = "sentry"))]
-            if !opt.no_sentry {
-                let logger = sentry::integrations::log::SentryLogger::with_dest(log_builder.build());
+            #[cfg(all(not(debug_assertions), feature = "analytics"))]
+            if !opt.no_analytics {
+                let logger =
+                    sentry::integrations::log::SentryLogger::with_dest(log_builder.build());
                 log::set_boxed_logger(Box::new(logger))
                     .map(|()| log::set_max_level(log::LevelFilter::Info))
                     .unwrap();
 
                 let sentry = sentry::init(sentry::ClientOptions {
                     release: sentry::release_name!(),
-                    dsn: Some(opt.sentry_dsn.parse()?),
+                    dsn: Some(SENTRY_DSN.parse()?),
                     ..Default::default()
                 });
                 // sentry must stay alive as long as possible
@@ -50,25 +55,14 @@ async fn main() -> Result<(), MainError> {
         _ => unreachable!(),
     }
 
-    //if let Some(path) = &opt.import_snapshot {
-    //snapshot::load_snapshot(&opt.db_path, path, opt.ignore_snapshot_if_db_exists, opt.ignore_missing_snapshot)?;
-    //}
-
     let data = Data::new(opt.clone())?;
 
-    //if !opt.no_analytics {
-    //let analytics_data = data.clone();
-    //let analytics_opt = opt.clone();
-    //thread::spawn(move || analytics::analytics_sender(analytics_data, analytics_opt));
-    //}
-
-    //if let Some(path) = &opt.import_dump {
-    //dump::import_dump(&data, path, opt.dump_batch_size)?;
-    //}
-
-    //if opt.schedule_snapshot {
-    //snapshot::schedule_snapshot(data.clone(), &opt.snapshot_dir, opt.snapshot_interval_sec.unwrap_or(86400))?;
-    //}
+    #[cfg(all(not(debug_assertions), feature = "analytics"))]
+    if !opt.no_analytics {
+        let analytics_data = data.clone();
+        let analytics_opt = opt.clone();
+        tokio::task::spawn(analytics::analytics_sender(analytics_data, analytics_opt));
+    }
 
     print_launch_resume(&opt, &data);
 
@@ -127,24 +121,21 @@ pub fn print_launch_resume(opt: &Opt, data: &Data) {
         env!("CARGO_PKG_VERSION").to_string()
     );
 
-    #[cfg(all(not(debug_assertions), feature = "sentry"))]
-    eprintln!(
-        "Sentry DSN:\t\t{:?}",
-        if !opt.no_sentry {
-            &opt.sentry_dsn
+    #[cfg(all(not(debug_assertions), feature = "analytics"))]
+    {
+        if opt.no_analytics {
+            eprintln!("Anonymous telemetry:\t\"Disabled\"");
         } else {
-            "Disabled"
-        }
-    );
+            eprintln!(
+                "
+Thank you for using MeiliSearch!
 
-    eprintln!(
-        "Anonymous telemetry:\t{:?}",
-        if !opt.no_analytics {
-            "Enabled"
-        } else {
-            "Disabled"
+We collect anonymized analytics to improve our product and your experience. To learn more, including how to turn off analytics, visit our dedicated documentation page: https://docs.meilisearch.com/reference/features/configuration.html#analytics
+
+Anonymous telemetry:   \"Enabled\""
+            );
         }
-    );
+    }
 
     eprintln!();
 

meilisearch-http/src/option.rs

@@ -96,21 +96,6 @@ pub struct Opt {
     #[structopt(long, env = "MEILI_MASTER_KEY")]
     pub master_key: Option<String>,
 
-    /// The Sentry DSN to use for error reporting. This defaults to the MeiliSearch Sentry project.
-    /// You can disable sentry all together using the `--no-sentry` flag or `MEILI_NO_SENTRY` environment variable.
-    #[cfg(all(not(debug_assertions), feature = "sentry"))]
-    #[structopt(
-        long,
-        env = "SENTRY_DSN",
-        default_value = "https://5ddfa22b95f241198be2271aaf028653@sentry.io/3060337"
-    )]
-    pub sentry_dsn: String,
-
-    /// Disable Sentry error reporting.
-    #[structopt(long, env = "MEILI_NO_SENTRY")]
-    #[cfg(all(not(debug_assertions), feature = "sentry"))]
-    pub no_sentry: bool,
-
     /// This environment variable must be set to `production` if you are running in production.
     /// If the server is running in development mode more logs will be displayed,
     /// and the master key can be avoided which implies that there is no security on the updates routes.
@@ -119,6 +104,7 @@ pub struct Opt {
     pub env: String,
 
     /// Do not send analytics to Meili.
+    #[cfg(all(not(debug_assertions), feature = "analytics"))]
     #[structopt(long, env = "MEILI_NO_ANALYTICS")]
     pub no_analytics: bool,