wt/json
1
0 Fork 0
mirror of https://github.com/nlohmann/json.git synced 2026-10-25 12:04:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

json_view benchmarks: compare fairly and state what each row means

Browse Source 
- bench_view: add "(editable)" rows for json_editable_document and a
  parse+dump workload, so the cost of lazy float conversion shows next to the
  parse row (the traverse workload already includes the parse). Check that
  all engines' dumps agree where outputs are comparable.
- compare.py: add --aligned, which also builds and runs with aligned code and
  reports both tables, so code-layout artifacts become visible. Off by
  default; the default output is unchanged. Not run end to end yet.
- README: say which engines are like-for-like peers (yyjson, simdjson DOM) and
  which are mutable reference points (Boost.JSON, json::parse, the editable
  json_view); explain the lazy float conversion and the eager prototype that
  was measured and dropped.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
This commit is contained in:
Niels Lohmann committed 2026-10-25 10:54:04 +01:00
1 parent 9c50bdd140
commit b38c056204
3 files changed
+164 -48
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

tests/benchmarks/json_view/bench_view.cpp
+92 -24
View File
@@ -8,8 +8,9 @@
// Same-feature-set benchmark: read-only JSON documents with random access.
//
// json_view nlohmann/json_view.hpp (fresh document per parse / reused)
// yyjson yyjson_read(): immutable document, random access
// json_view nlohmann/json_view.hpp (fresh document per parse / reused;
// "(editable)": json_editable_document, same read API)
// yyjson yyjson_read(): immutable document, random access
// simdjson DOM dom::parser (reused, as recommended; "fresh": a new parser
// per parse): immutable, random access
// references (different feature sets):
@@ -19,7 +20,11 @@
//
// Workloads: parse (build + free), traverse (visit everything, convert every
// number, touch every string and key), select (a few fields per document),
// dump (compact serialization of the parsed document).
// dump (compact serialization of the parsed document), and parse+dump (a fresh
// document, then its dump, in one timed call). json_view converts floating-point
// numbers lazily (when read or dumped), yyjson and simdjson DOM while parsing:
// for float-heavy documents, traverse (which includes the parse) and parse+dump
// are the fair reading of the parse and dump rows.
// All engines run interleaved in every round, each timed call after an untimed
// one of the same engine; the best round is reported.
#include <nlohmann/json_view.hpp>
@@ -43,6 +48,8 @@
using nlohmann::json;
using nlohmann::json_document;
using nlohmann::json_editable_document;
using nlohmann::json_editable_view;
using nlohmann::json_view;
static volatile double g_sink;
@@ -55,7 +62,8 @@ struct stats
// ---------------- traversal ----------------
static void walk(json_view v, stats& st)
template<class V>
static void walk_view(V v, stats& st)
{
++st.nodes;
switch (v.type())
@@ -64,32 +72,42 @@ static void walk(json_view v, stats& st)
for (auto it = v.begin(); it != v.end(); ++it)
{
st.str += it.key().size();
walk(*it, st);
walk_view<V>(*it, st);
}
break;
case json::value_t::array:
for (const json_view e : v)
for (const V e : v)
{
walk(e, st);
walk_view<V>(e, st);
}
break;
case json::value_t::string:
st.str += v.get_string().size();
break;
case json::value_t::number_integer:
st.num += static_cast<double>(v.get<std::int64_t>());
st.num += static_cast<double>(v.template get<std::int64_t>());
break;
case json::value_t::number_unsigned:
st.num += static_cast<double>(v.get<std::uint64_t>());
st.num += static_cast<double>(v.template get<std::uint64_t>());
break;
case json::value_t::number_float:
st.num += v.get<double>();
st.num += v.template get<double>();
break;
default:
break;
}
}
static void walk(json_view v, stats& st)
{
walk_view<json_view>(v, st);
}
static void walk(json_editable_view v, stats& st)
{
walk_view<json_editable_view>(v, st);
}
static void walk(const json& j, stats& st)
{
++st.nodes;
@@ -300,20 +318,21 @@ static void walk(const boost::json::value& v, stats& st)
// status (one tweet): id, user.screen_name, retweet_count
// rpc: method, params.minuend, id
static double pick(const std::string& name, json_view r)
template<class V>
static double pick_view(const std::string& name, V r)
{
double acc = 0;
if (name == "twitter" || name == "status")
{
auto one = [&](json_view s)
auto one = [&](V s)
{
acc += static_cast<double>(s["id"].get<std::uint64_t>());
acc += static_cast<double>(s["id"].template get<std::uint64_t>());
acc += static_cast<double>(s["user"]["screen_name"].get_string().size());
acc += static_cast<double>(s["retweet_count"].get<std::int64_t>());
acc += static_cast<double>(s["retweet_count"].template get<std::int64_t>());
};
if (name == "twitter")
{
for (const json_view s : r["statuses"])
for (const V s : r["statuses"])
{
one(s);
}
@@ -325,20 +344,20 @@ static double pick(const std::string& name, json_view r)
}
else if (name == "citm_catalog")
{
for (const json_view p : r["performances"])
for (const V p : r["performances"])
{
acc += static_cast<double>(p["id"].get<std::uint64_t>() + p["eventId"].get<std::uint64_t>() + p["seatCategories"].size());
acc += static_cast<double>(p["id"].template get<std::uint64_t>() + p["eventId"].template get<std::uint64_t>() + p["seatCategories"].size());
}
acc += static_cast<double>(r["events"].size());
}
else if (name == "canada")
{
const json_view g = r["features"][0]["geometry"];
const V g = r["features"][0]["geometry"];
acc += static_cast<double>(r["type"].get_string().size() + g["type"].get_string().size() + g["coordinates"].size());
}
else if (name == "jeopardy")
{
for (const json_view q : r)
for (const V q : r)
{
acc += q["round"].get_string() == "Final Jeopardy!" ? 1 : 0;
acc += static_cast<double>(q["category"].get_string().size());
@@ -347,11 +366,21 @@ static double pick(const std::string& name, json_view r)
else if (name == "rpc")
{
acc += static_cast<double>(r["method"].get_string().size());
acc += static_cast<double>(r["params"]["minuend"].get<std::int64_t>() + r["id"].get<std::int64_t>());
acc += static_cast<double>(r["params"]["minuend"].template get<std::int64_t>() + r["id"].template get<std::int64_t>());
}
return acc;
}
static double pick(const std::string& name, json_view r)
{
return pick_view<json_view>(name, r);
}
static double pick(const std::string& name, json_editable_view r)
{
return pick_view<json_editable_view>(name, r);
}
static double pick(const std::string& name, const json& r)
{
double acc = 0;
@@ -634,15 +663,35 @@ int main(int argc, char** argv)
walk(json::parse(dc.text), a);
auto d = json_document::parse(dc.text);
walk(d.root(), b);
auto ed = json_editable_document::parse(dc.text);
stats e;
walk(ed.root(), e);
yyjson_doc* y = yyjson_read(dc.text.data(), dc.text.size(), 0);
walk(yyjson_doc_get_root(y), c);
simdjson::dom::parser p;
walk(p.parse(dc.text).value(), dd);
const bool ok = a.nodes == b.nodes && a.nodes == c.nodes && a.nodes == dd.nodes && a.str == b.str && a.str == c.str && a.str == dd.str
const bool ok = a.nodes == b.nodes && a.nodes == e.nodes && a.str == e.str && std::fabs(a.num - e.num) <= 1e-9 * std::fabs(a.num) && a.nodes == c.nodes && a.nodes == dd.nodes && a.str == b.str && a.str == c.str && a.str == dd.str
&& std::fabs(a.num - b.num) <= 1e-9 * std::fabs(a.num) && std::fabs(a.num - c.num) <= 1e-9 * std::fabs(a.num);
const double pa = pick(dc.name, json::parse(dc.text)), pb = pick(dc.name, d.root()), pc = pick(dc.name, yyjson_doc_get_root(y)), pd = pick(dc.name, p.parse(dc.text).value());
std::printf("check %-13s traverse %s select %s\n", dc.name.c_str(), ok ? "OK" : "MISMATCH", (pa == pb && pa == pc && pa == pd) ? "OK" : "MISMATCH");
const double pa = pick(dc.name, json::parse(dc.text)), pb = pick(dc.name, d.root()), pe = pick(dc.name, ed.root()), pc = pick(dc.name, yyjson_doc_get_root(y)), pd = pick(dc.name, p.parse(dc.text).value());
std::printf("check %-13s traverse %s select %s\n", dc.name.c_str(), ok ? "OK" : "MISMATCH", (pa == pb && pa == pe && pa == pc && pa == pd) ? "OK" : "MISMATCH");
yyjson_doc_free(y);
// the dumps of the engines may format floats differently, so only: every dump is non-empty, and the
// dump of json_view (also editable) and of json::parse parse back to the same number of nodes
const std::string dj = json::parse(dc.text).dump();
const std::string dv = d.root().dump();
const std::string de = ed.root().dump();
std::size_t yn = 0;
yyjson_doc* y2 = yyjson_read(dc.text.data(), dc.text.size(), 0);
char* yo = yyjson_write(y2, 0, &yn);
const bool dumps_ok = !dj.empty() && !dv.empty() && !de.empty() && yo != nullptr && yn > 0 && !simdjson::to_string(p.parse(dc.text).value()).empty();
std::free(yo);
yyjson_doc_free(y2);
stats sj_nodes, sv_nodes, se_nodes;
walk(json::parse(dj), sj_nodes);
walk(json::parse(dv), sv_nodes);
walk(json::parse(de), se_nodes);
std::printf("check %-13s dump %s\n", dc.name.c_str(), (dumps_ok && sj_nodes.nodes == a.nodes && sv_nodes.nodes == a.nodes && se_nodes.nodes == a.nodes) ? "OK" : "MISMATCH");
}
std::FILE* csv = std::fopen("bench_view.csv", "w");
@@ -669,6 +718,7 @@ int main(int argc, char** argv)
workloads.push_back({"parse", {
{"json_view", [&] { auto d = json_document::parse(s); g_sink = static_cast<double>(d.node_count()); }},
{"json_view (reused)", [&] { reused.read(s); g_sink = static_cast<double>(reused.node_count()); }},
{"json_view (editable)", [&] { auto d = json_editable_document::parse(s); g_sink = static_cast<double>(d.root().size()); }},
{"yyjson", [&] { yyjson_doc* d = yyjson_read(s.data(), s.size(), 0); g_sink = static_cast<double>(yyjson_doc_get_val_count(d)); yyjson_doc_free(d); }},
{"simdjson DOM", [&] { auto e = sj.parse(ps).value_unsafe(); g_sink = e.is_object(); }},
{"simdjson DOM (fresh)", [&] { simdjson::dom::parser p; auto e = p.parse(ps).value_unsafe(); g_sink = e.is_object(); }},
@@ -680,6 +730,7 @@ int main(int argc, char** argv)
workloads.push_back({"traverse", {
{"json_view", [&] { auto d = json_document::parse(s); stats st; walk(d.root(), st); g_sink = st.num; }},
{"json_view (reused)", [&] { reused.read(s); stats st; walk(reused.root(), st); g_sink = st.num; }},
{"json_view (editable)", [&] { auto d = json_editable_document::parse(s); stats st; walk(d.root(), st); g_sink = st.num; }},
{"yyjson", [&] { yyjson_doc* d = yyjson_read(s.data(), s.size(), 0); stats st; walk(yyjson_doc_get_root(d), st); g_sink = st.num; yyjson_doc_free(d); }},
{"simdjson DOM", [&] { stats st; walk(sj.parse(ps).value_unsafe(), st); g_sink = st.num; }},
{"simdjson OD", [&] { auto d = od.iterate(ps).value_unsafe(); stats st; walk_od(d.get_value().value_unsafe(), st); g_sink = st.num; }},
@@ -691,15 +742,31 @@ int main(int argc, char** argv)
workloads.push_back({"select", {
{"json_view", [&] { auto d = json_document::parse(s); g_sink = pick(name, d.root()); }},
{"json_view (reused)", [&] { reused.read(s); g_sink = pick(name, reused.root()); }},
{"json_view (editable)", [&] { auto d = json_editable_document::parse(s); g_sink = pick(name, d.root()); }},
{"yyjson", [&] { yyjson_doc* d = yyjson_read(s.data(), s.size(), 0); g_sink = pick(name, yyjson_doc_get_root(d)); yyjson_doc_free(d); }},
{"simdjson DOM", [&] { g_sink = pick(name, sj.parse(ps).value_unsafe()); }},
{"simdjson OD", [&] { auto d = od.iterate(ps).value_unsafe(); g_sink = pick_od(name, d); }},
{"json::parse", [&] { json j = json::parse(s); g_sink = pick(name, j); }},
}});
// pipeline: a fresh document, then a dump of it, in one timed call
// (simdjson DOM reuses its parser, as in the parse row); the traverse
// workload above is already parse+traverse
workloads.push_back({"parse+dump", {
{"json_view", [&] { auto d = json_document::parse(s); std::string o = d.root().dump(); g_sink = static_cast<double>(o.size()); }},
{"json_view (editable)", [&] { auto d = json_editable_document::parse(s); std::string o = d.root().dump(); g_sink = static_cast<double>(o.size()); }},
{"yyjson", [&] { yyjson_doc* d = yyjson_read(s.data(), s.size(), 0); std::size_t n = 0; char* o = yyjson_write(d, 0, &n); g_sink = static_cast<double>(n); std::free(o); yyjson_doc_free(d); }},
{"simdjson DOM", [&] { std::string o = simdjson::to_string(sj.parse(ps).value_unsafe()); g_sink = static_cast<double>(o.size()); }},
#if JSON_VIEW_BENCH_BOOST
{"Boost.JSON", [&] { boost::json::monotonic_resource mr; auto v = boost::json::parse(s, &mr); std::string o = boost::json::serialize(v); g_sink = static_cast<double>(o.size()); }},
#endif
{"json::parse", [&] { json j = json::parse(s); std::string o = j.dump(); g_sink = static_cast<double>(o.size()); }},
}});
{
// serialization of an already parsed document
static json_document vd;
vd.read(s);
static json_editable_document ed = json_editable_document::parse(s);
ed = json_editable_document::parse(s);
static yyjson_doc* yd = nullptr;
if (yd)
{
@@ -713,6 +780,7 @@ int main(int argc, char** argv)
jd = json::parse(s);
workloads.push_back({"dump", {
{"json_view", [&] { std::string o = vd.root().dump(); g_sink = static_cast<double>(o.size()); }},
{"json_view (editable)", [&] { std::string o = ed.root().dump(); g_sink = static_cast<double>(o.size()); }},
{"yyjson", [&] { std::size_t n = 0; char* o = yyjson_write(yd, 0, &n); g_sink = static_cast<double>(n); std::free(o); }},
{"simdjson DOM", [&] { std::string o = simdjson::to_string(se); g_sink = static_cast<double>(o.size()); }},
{"json::parse", [&] { std::string o = jd.dump(); g_sink = static_cast<double>(o.size()); }},
@@ -740,7 +808,7 @@ int main(int argc, char** argv)
}
}
const double ref = best[0];
std::printf("%-13s %-9s", dc.name.c_str(), wl.first.c_str());
std::printf("%-13s %-14s", dc.name.c_str(), wl.first.c_str());
for (std::size_t k = 0; k < wl.second.size(); ++k)
{
const double us = best[k] / 1e3;