undesired fetches: regex-based reporting

Summary:
We want to be able to report more than just on one prefix. Instead, let's add a regex-based reporting. To make deployment easier, let's keep both options for now and later just remove prefix-based one.

Note: this diff also changes how a situation with absent `undesired_path_prefix_to_log` is treated. Previously, if `undesired_path_prefix_to_log` is absent, but `"undesired_path_repo_name_to_log": "fbsource"`, it would report every path. Now it won't report any, which I think is a saner behavior. If we do ever want to report every path, we can just add `.*` as a regex.

Reviewed By: StanislavGlebik

Differential Revision: D23447800

fbshipit-source-id: 059109b44256f5703843625b7ab725a243a13056

eden/mononoke/mononoke_types/src/path.rs

@@ -19,6 +19,7 @@ use bytes::Bytes;
 use lazy_static::lazy_static;
 use quickcheck::{Arbitrary, Gen};
 use rand::{seq::SliceRandom, Rng};
+use regex::Regex;
 use serde_derive::{Deserialize, Serialize};
 
 use crate::bonsai_changeset::BonsaiChangeset;
@@ -609,6 +610,11 @@ impl MPath {
             current: Some(self),
         }
     }
+
+    pub fn matches_regex(&self, re: &Regex) -> bool {
+        let s: String = format!("{}", self);
+        re.is_match(&s)
+    }
 }
 
 impl AsRef<[MPathElement]> for MPath {

eden/mononoke/repo_client/Cargo.toml

@@ -52,6 +52,7 @@ lazy_static = "1.0"
 maplit = "1.0"
 percent-encoding = "2.1"
 rand = { version = "0.7", features = ["small_rng"] }
+regex = "1.3.7"
 serde_json = "1.0"
 slog = { version = "2.5", features = ["max_level_debug"] }
 thiserror = "1.0"

eden/mononoke/repo_client/src/client/mod.rs

@@ -59,6 +59,7 @@ use mercurial_types::{
 use metaconfig_types::{RepoClientKnobs, RepoReadOnly};
 use mononoke_repo::{MononokeRepo, SqlStreamingCloneConfig};
 use rand::{self, Rng};
+use regex::Regex;
 use remotefilelog::{
     create_getpack_v1_blob, create_getpack_v2_blob, get_unordered_file_history_for_multiple_nodes,
     GetpackBlobInfo,
@@ -66,7 +67,7 @@ use remotefilelog::{
 use revisionstore_types::Metadata;
 use scuba_ext::ScubaSampleBuilderExt;
 use serde_json::{self, json};
-use slog::{debug, info, o};
+use slog::{debug, error, info, o};
 use stats::prelude::*;
 use std::collections::{BTreeMap, HashMap, HashSet};
 use std::convert::TryInto;
@@ -288,6 +289,7 @@ struct UndesiredPathLogger {
     ctx: CoreContext,
     repo_needs_logging: bool,
     path_prefix_to_log: Option<MPath>,
+    path_regex_to_log: Option<Regex>,
 }
 
 impl UndesiredPathLogger {
@@ -302,10 +304,29 @@ impl UndesiredPathLogger {
             None
         };
 
+        let path_regex_to_log = if repo_needs_logging
+            && !tunables.get_undesired_path_regex_to_log().is_empty()
+        {
+            Some(
+                Regex::new(tunables.get_undesired_path_regex_to_log().as_str()).map_err(|e| {
+                    error!(
+                        ctx.logger(),
+                        "Error initializing undesired path regex for {}: {}",
+                        repo.name(),
+                        e
+                    );
+                    e
+                })?,
+            )
+        } else {
+            None
+        };
+
         Ok(Self {
             ctx,
             repo_needs_logging,
             path_prefix_to_log,
+            path_regex_to_log,
         })
     }
 
@@ -341,7 +362,17 @@ impl UndesiredPathLogger {
 
     fn should_log(&self, path: Option<&MPath>) -> bool {
         if self.repo_needs_logging {
-            MPath::is_prefix_of_opt(self.path_prefix_to_log.as_ref(), MPath::iter_opt(path))
+            let op1 = match self.path_prefix_to_log.as_ref() {
+                None => false,
+                Some(prefix) => prefix.is_prefix_of(MPath::iter_opt(path)),
+            };
+
+            let op2 = match (path, self.path_regex_to_log.as_ref()) {
+                (Some(path), Some(re)) => path.matches_regex(re),
+                _ => false,
+            };
+
+            op1 || op2
         } else {
             false
         }

eden/mononoke/tunables/src/lib.rs

@@ -71,6 +71,7 @@ pub struct MononokeTunables {
     // in a particular repo
     undesired_path_repo_name_to_log: TunableString,
     undesired_path_prefix_to_log: TunableString,
+    undesired_path_regex_to_log: TunableString,
     pushrebase_disable_rebased_commit_validation: AtomicBool,
     filenodes_disabled: AtomicBool,
     skiplist_max_skips_without_yield: AtomicI64,