Add an option to redact object data in heap snapshots

Currently, this only applies to strings, which are the only type of
object for which we emit content in the heap snapshot.

Author: kpamnany

src/gc-heap-snapshot.cpp

@@ -182,6 +182,7 @@ struct HeapSnapshot {
 // global heap snapshot, mutated by garbage collector
 // when snapshotting is on.
 int gc_heap_snapshot_enabled = 0;
+int gc_heap_snapshot_redact_data = 0;
 HeapSnapshot *g_snapshot = nullptr;
 // mutex for gc-heap-snapshot.
 jl_mutex_t heapsnapshot_lock;
@@ -195,7 +196,7 @@ void _add_synthetic_root_entries(HeapSnapshot *snapshot) JL_NOTSAFEPOINT;
 
 
 JL_DLLEXPORT void jl_gc_take_heap_snapshot(ios_t *nodes, ios_t *edges,
-    ios_t *strings, ios_t *json, char all_one)
+    ios_t *strings, ios_t *json, char all_one, char redact_data)
 {
     HeapSnapshot snapshot;
     snapshot.nodes = nodes;
@@ -207,6 +208,7 @@ JL_DLLEXPORT void jl_gc_take_heap_snapshot(ios_t *nodes, ios_t *edges,
 
     // Enable snapshotting
     g_snapshot = &snapshot;
+    gc_heap_snapshot_redact_data = redact_data;
     gc_heap_snapshot_enabled = true;
 
     _add_synthetic_root_entries(&snapshot);
@@ -216,6 +218,7 @@ JL_DLLEXPORT void jl_gc_take_heap_snapshot(ios_t *nodes, ios_t *edges,
 
     // Disable snapshotting
     gc_heap_snapshot_enabled = false;
+    gc_heap_snapshot_redact_data = 0;
     g_snapshot = nullptr;
 
     jl_mutex_unlock(&heapsnapshot_lock);
@@ -328,7 +331,7 @@ size_t record_node_to_gc_snapshot(jl_value_t *a) JL_NOTSAFEPOINT
 
     if (jl_is_string(a)) {
         node_type = "String";
-        name = jl_string_data(a);
+        name = gc_heap_snapshot_redact_data ? "<redacted>" : jl_string_data(a);
         self_size = jl_string_len(a);
     }
     else if (jl_is_symbol(a)) {

src/gc-heap-snapshot.h

@@ -122,7 +122,7 @@ static inline void gc_heap_snapshot_record_finlist(jl_value_t *finlist, size_t i
 // Functions to call from Julia to take heap snapshot
 // ---------------------------------------------------------------------
 JL_DLLEXPORT void jl_gc_take_heap_snapshot(ios_t *nodes, ios_t *edges,
-    ios_t *strings, ios_t *json, char all_one);
+    ios_t *strings, ios_t *json, char all_one, char redact_data);
 
 
 #ifdef __cplusplus

stdlib/Profile/src/Profile.jl

@@ -1250,8 +1250,10 @@ end
 
 
 """
-    Profile.take_heap_snapshot(filepath::String, all_one::Bool=false, streaming=false)
-    Profile.take_heap_snapshot(all_one::Bool=false; dir::String, streaming=false)
+    Profile.take_heap_snapshot(filepath::String, all_one::Bool=false,
+                               redact_data::Bool=false; streaming::Bool=false)
+    Profile.take_heap_snapshot(all_one::Bool=false, redact_data:Bool=false;
+                               dir::String=nothing)
 
 Write a snapshot of the heap, in the JSON format expected by the Chrome
 Devtools Heap Snapshot viewer (.heapsnapshot extension) to a file
@@ -1262,6 +1264,8 @@ full file path, or IO stream.
 If `all_one` is true, then report the size of every object as one so they can be easily
 counted. Otherwise, report the actual size.
 
+If `redact_data` is true, then do not emit the contents of any object.
+
 If `streaming` is true, we will stream the snapshot data out into four files, using filepath
 as the prefix, to avoid having to hold the entire snapshot in memory. This option should be
 used for any setting where your memory is constrained. These files can then be reassembled
@@ -1277,28 +1281,28 @@ backwards-compatibility) and your process is killed, note that this will always
 parts in the same directory as your provided filepath, so you can still reconstruct the
 snapshot after the fact, via `assemble_snapshot()`.
 """
-function take_heap_snapshot(filepath::AbstractString, all_one::Bool=false; streaming::Bool=false)
+function take_heap_snapshot(filepath::AbstractString, all_one::Bool=false, redact_data::Bool=false; streaming::Bool=false)
     if streaming
-        _stream_heap_snapshot(filepath, all_one)
+        _stream_heap_snapshot(filepath, all_one, redact_data)
     else
         # Support the legacy, non-streaming mode, by first streaming the parts, then
         # reassembling it after we're done.
         prefix = filepath
-        _stream_heap_snapshot(prefix, all_one)
+        _stream_heap_snapshot(prefix, all_one, redact_data)
         Profile.HeapSnapshot.assemble_snapshot(prefix, filepath)
         Profile.HeapSnapshot.cleanup_streamed_files(prefix)
     end
     return filepath
 end
-function take_heap_snapshot(io::IO, all_one::Bool=false)
+function take_heap_snapshot(io::IO, all_one::Bool=false, redact_data::Bool=false)
     # Support the legacy, non-streaming mode, by first streaming the parts to a tempdir,
     # then reassembling it after we're done.
     dir = tempdir()
     prefix = joinpath(dir, "snapshot")
-    _stream_heap_snapshot(prefix, all_one)
+    _stream_heap_snapshot(prefix, all_one, redact_data)
     Profile.HeapSnapshot.assemble_snapshot(prefix, io)
 end
-function _stream_heap_snapshot(prefix::AbstractString, all_one::Bool)
+function _stream_heap_snapshot(prefix::AbstractString, all_one::Bool, redact_data::Bool)
     # Nodes and edges are binary files
     open("$prefix.nodes", "w") do nodes
         open("$prefix.edges", "w") do edges
@@ -1311,9 +1315,9 @@ function _stream_heap_snapshot(prefix::AbstractString, all_one::Bool)
                     Base.@_lock_ios(json,
                         ccall(:jl_gc_take_heap_snapshot,
                             Cvoid,
-                            (Ptr{Cvoid},Ptr{Cvoid},Ptr{Cvoid},Ptr{Cvoid}, Cchar),
+                            (Ptr{Cvoid},Ptr{Cvoid},Ptr{Cvoid},Ptr{Cvoid}, Cchar, Cchar),
                             nodes.handle, edges.handle, strings.handle, json.handle,
-                            Cchar(all_one))
+                            Cchar(all_one), Cchar(redact_data))
                     )
                     )
                     )
@@ -1323,7 +1327,7 @@ function _stream_heap_snapshot(prefix::AbstractString, all_one::Bool)
         end
     end
 end
-function take_heap_snapshot(all_one::Bool=false; dir::Union{Nothing,S}=nothing) where {S <: AbstractString}
+function take_heap_snapshot(all_one::Bool=false, redact_data::Bool=false; dir::Union{Nothing,S}=nothing) where {S <: AbstractString}
     fname = "$(getpid())_$(time_ns()).heapsnapshot"
     if isnothing(dir)
         wd = pwd()
@@ -1338,7 +1342,7 @@ function take_heap_snapshot(all_one::Bool=false; dir::Union{Nothing,S}=nothing)
     else
         fpath = joinpath(expanduser(dir), fname)
     end
-    return take_heap_snapshot(fpath, all_one)
+    return take_heap_snapshot(fpath, all_one, redact_data)
 end
 
 """