src: embed zstd dictionary for further compile cache size wins#16

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
anonrig merged 1 commit into from
Jun 12, 2026
Merged

src: embed zstd dictionary for further compile cache size wins #16

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
72 changes: 72 additions & 0 deletions benchmark/misc/compile-cache-timing.js
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,72 @@
'use strict';

// Startup benchmark for the compile cache (including the zstd dictionary).
// Compares no-cache / cold-cache / warm-cache for two workloads:
// big - one large module (the typescript.js fixture)
// many - many small modules (generated here, side-effect-free)
// The modules are generated into a temp dir so the benchmark is self-contained
// and reproducible, and never executes unrelated code.

const common = require('../common.js');
const { spawnSync } = require('child_process');
const fs = require('fs');
const os = require('os');
const path = require('path');

const bench = common.createBenchmark(main, {
workload: ['big', 'many'],
cache: ['none', 'cold', 'warm'],
n: [30],
});

const BIG = path.resolve(__dirname, '../../test/fixtures/snapshot/typescript.js');

// Generate `count` small, side-effect-free modules and return the require()
// code that loads them all in one child.
function makeManyModules(dir, count) {
fs.mkdirSync(dir, { recursive: true });
const reqs = [];
for (let i = 0; i < count; i++) {
const file = path.join(dir, `mod-${i}.js`);
fs.writeFileSync(
file,
`'use strict';\n` +
`module.exports = function value${i}(a, b) {\n` +
` const sum = a + b + ${i};\n` +
` return { id: ${i}, sum, label: 'module-${i}' };\n` +
`};\n`);
reqs.push(`require(${JSON.stringify(file)});`);
}
return reqs.join('');
}

function run(cmd, args, cacheDir) {
const env = { ...process.env };
if (cacheDir) env.NODE_COMPILE_CACHE = cacheDir;
else delete env.NODE_COMPILE_CACHE;
const child = spawnSync(cmd, args, { env, stdio: 'ignore' });
if (child.error) throw child.error;
}

function main({ n, workload, cache }) {
const cmd = process.execPath || process.argv[0];
const tmp = fs.mkdtempSync(path.join(os.tmpdir(), 'cc-bench-'));
const args = workload === 'big' ?
[BIG] :
['-e', makeManyModules(path.join(tmp, 'mods'), 120)];
const cacheDir = cache === 'none' ? null : path.join(tmp, 'cache');

try {
if (cache === 'warm') run(cmd, args, cacheDir); // populate once
bench.start();
for (let i = 0; i < n; i++) {
if (cache === 'cold' && cacheDir) {
fs.rmSync(cacheDir, { recursive: true, force: true });
}
run(cmd, args, cacheDir);
}
bench.end(n);
} finally {
fs.rmSync(tmp, { recursive: true, force: true });
}
}
17 changes: 17 additions & 0 deletions node.gyp
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -1110,6 +1110,22 @@
'<@(linked_module_files)',
],
},
{
'action_name': 'generate_compile_cache_zstd_dict',
'inputs': [
'src/compile_cache_zstd.dict',
'tools/generate_compile_cache_dict.py',
],
'outputs': [
'<(SHARED_INTERMEDIATE_DIR)/compile_cache_zstd_dict.h',
],
'action': [
'<(python)',
'tools/generate_compile_cache_dict.py',
'src/compile_cache_zstd.dict',
'<@(_outputs)',
],
},
],
}, # node_base
{
Expand All@@ -1123,6 +1139,7 @@
'src',
'deps/v8/include',
'deps/uv/include',
'<(SHARED_INTERMEDIATE_DIR)', # for compile_cache_zstd_dict.h etc.
],

'dependencies': [
Expand Down
72 changes: 68 additions & 4 deletions src/compile_cache.cc
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -11,6 +11,10 @@
#include "util.h"
#include "zlib.h"
#include "zstd.h"
// kCompileCacheZstdDict + kCompileCacheZstdDictSize come from the header
// generated at build time by the GYP action (from src/compile_cache_zstd.dict).
// The include directory (SHARED_INTERMEDIATE_DIR) is added by node.gyp.
#include "compile_cache_zstd_dict.h"

#ifdef NODE_IMPLEMENTS_POSIX_CREDENTIALS
#include <unistd.h> // getuid
Expand All@@ -28,6 +32,29 @@ using v8::ScriptCompiler;
using v8::String;

namespace {
// The compile-cache zstd dictionary is immutable and embedded in the binary,
// so the prepared CDict/DDict are created once and shared across all handlers
// (and all Environments/Workers) instead of per handler. They live for the
// lifetime of the process. Returns nullptr if preparation fails, in which
// case callers fall back to plain (dictionary-less) zstd.
ZSTD_CDict* GetCompileCacheCDict() {
static ZSTD_CDict* cdict =
ZSTD_createCDict(kCompileCacheZstdDict, kCompileCacheZstdDictSize, 1);
return cdict;
}

ZSTD_DDict* GetCompileCacheDDict() {
static ZSTD_DDict* ddict =
ZSTD_createDDict(kCompileCacheZstdDict, kCompileCacheZstdDictSize);
return ddict;
}

// The dictionary only helps small/medium caches; for larger inputs zstd's own
// adaptive model dominates and the dictionary never wins, so we skip the
// (otherwise wasted) second compression above this raw size. Decompression is
// unaffected: a single DDict decodes both dict-assisted and plain frames.
constexpr uint32_t kCompileCacheDictMaxRawSize = 256 * 1024;

std::string Uint32ToHex(uint32_t crc) {
std::string str;
str.reserve(8);
Expand DownExpand Up@@ -266,10 +293,20 @@ void CompileCacheHandler::ReadCacheFile(CompileCacheEntry* entry) {
Debug("failed to create zstd context\n");
return;
}
// Decompress directly into the buffer handed to V8.
// Decompress directly into the buffer handed to V8. The embedded
// dictionary is referenced via a shared, prepared DDict; plain frames
// (which carry no dictID) decompress correctly with it as well.
std::unique_ptr<uint8_t[]> raw_data(new uint8_t[raw_size]);
size_t decompressed_size = ZSTD_decompressDCtx(
zstd_dctx_, raw_data.get(), raw_size, disk_data.get(), cache_size);
ZSTD_DDict* ddict = GetCompileCacheDDict();
size_t decompressed_size;
if (ddict != nullptr) {
decompressed_size = ZSTD_decompress_usingDDict(
zstd_dctx_, raw_data.get(), raw_size, disk_data.get(), cache_size,
ddict);
} else {
decompressed_size = ZSTD_decompressDCtx(
zstd_dctx_, raw_data.get(), raw_size, disk_data.get(), cache_size);
}
if (ZSTD_isError(decompressed_size)) {
Debug("decompression failed: %s\n", ZSTD_getErrorName(decompressed_size));
return;
Expand DownExpand Up@@ -508,16 +545,43 @@ void CompileCacheHandler::Persist() {
// shutdown and should add as little overhead as possible. If the data
// is not compressible, store it uncompressed, which is indicated by
// the cache size being equal to the uncompressed size in the headers.
//
// We also try the embedded trained dictionary and keep whichever frame is
// smaller (still subject to the "only store if < raw" policy). The
// dictionary mainly helps the small/medium caches that dominate real
// compile cache usage; for inputs where plain zstd already wins we keep
// the plain frame.
char* cache_ptr = raw_ptr;
uint32_t cache_size = raw_size;
std::unique_ptr<uint8_t[]> compressed;
std::unique_ptr<uint8_t[]> compressed_dict;
if (cctx != nullptr || (cctx = ZSTD_createCCtx()) != nullptr) {
size_t compressed_bound = ZSTD_compressBound(raw_size);
compressed.reset(new uint8_t[compressed_bound]);
size_t compressed_size = ZSTD_compressCCtx(
cctx, compressed.get(), compressed_bound, raw_ptr, raw_size, 1);
char* best_ptr = reinterpret_cast<char*>(compressed.get());
// Only attempt the dictionary for small/medium entries (see
// kCompileCacheDictMaxRawSize); for large blobs it never wins and the
// extra compression would be wasted work.
ZSTD_CDict* cdict = raw_size <= kCompileCacheDictMaxRawSize
? GetCompileCacheCDict()
: nullptr;
if (cdict != nullptr) {
// Compress into a separate buffer so the selected frame's bytes and
// size always stay in sync (the plain buffer is left untouched).
compressed_dict.reset(new uint8_t[compressed_bound]);
size_t dict_size = ZSTD_compress_usingCDict(
cctx, compressed_dict.get(), compressed_bound, raw_ptr, raw_size,
cdict);
if (!ZSTD_isError(dict_size) &&
(ZSTD_isError(compressed_size) || dict_size < compressed_size)) {
compressed_size = dict_size;
best_ptr = reinterpret_cast<char*>(compressed_dict.get());
}
}
if (!ZSTD_isError(compressed_size) && compressed_size < raw_size) {
cache_ptr = reinterpret_cast<char*>(compressed.get());
cache_ptr = best_ptr;
cache_size = static_cast<uint32_t>(compressed_size);
}
}
Expand Down
Binary file addedsrc/compile_cache_zstd.dict
View file
Open in desktop
Binary file not shown.
80 changes: 80 additions & 0 deletions test/parallel/test-compile-cache-success.js
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -64,3 +64,83 @@ const path = require('path');
}
});
}

// Exercise the dictionary-compressed path (added on top of #63861) for many
// small modules, which is where the embedded dictionary helps most. We write
// the cache, then read it back and assert every entry is accepted - this
// proves each dict-compressed frame decompresses to exactly the bytes that
// were persisted.
{
tmpdir.refresh();
const dir = tmpdir.resolve('.compile_cache_dir');

// Generate a handful of small modules so the dictionary path is exercised.
const count = 8;
const modules = [];
for (let i = 0; i < count; i++) {
const file = tmpdir.resolve(`mod-${i}.js`);
fs.writeFileSync(
file,
`'use strict';\n` +
`module.exports = function value${i}(a, b) {\n` +
` const sum = a + b + ${i};\n` +
` return { id: ${i}, sum, label: 'module-${i}' };\n` +
`};\n`);
modules.push(file);
}
const reqCode = modules.map((m) => `require(${JSON.stringify(m)});`).join('');

// First run writes the cache for every module.
spawnSyncAndAssert(
process.execPath,
['-e', reqCode],
{
env: {
...process.env,
NODE_DEBUG_NATIVE: 'COMPILE_CACHE',
NODE_COMPILE_CACHE: dir
},
cwd: tmpdir.path
},
{
stderr(output) {
for (const m of modules) {
const name = path.basename(m).replace(/[.]/g, '\\.');
assert.match(output, new RegExp(`writing cache for .*${name}.*success`));
}
return true;
}
});

const cacheDirs = fs.readdirSync(dir);
assert.strictEqual(cacheDirs.length, 1);
// At least one entry per module (the `-e` runner is cached too).
const entries = fs.readdirSync(path.join(dir, cacheDirs[0]));
assert(entries.length >= count, `expected >= ${count} entries, got ${entries.length}`);

// Second run reads every cached entry back; "was accepted" only happens when
// the decompressed bytes match the freshly produced in-memory cache, so this
// is a full roundtrip check of the dictionary-compressed entries.
spawnSyncAndAssert(
process.execPath,
['-e', reqCode],
{
env: {
...process.env,
NODE_DEBUG_NATIVE: 'COMPILE_CACHE',
NODE_COMPILE_CACHE: dir
},
cwd: tmpdir.path
},
{
stderr(output) {
for (const m of modules) {
const name = path.basename(m).replace(/[.]/g, '\\.');
assert.match(
output,
new RegExp(`cache for .*${name} was accepted, keeping the in-memory entry`));
}
return true;
}
});
}
37 changes: 37 additions & 0 deletions tools/generate_compile_cache_dict.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,37 @@
#!/usr/bin/env python
"""Generate compile_cache_zstd_dict.h from a trained zstd .dict file.

Invoked by the GYP action in node.gyp at build time. Only the small binary
.dict (src/compile_cache_zstd.dict) is checked into the repository; the C
array it produces is generated into SHARED_INTERMEDIATE_DIR.
"""
import os
import sys


def main(dict_path, out_path):
with open(dict_path, 'rb') as f:
data = f.read()

lines = [
'// Generated by tools/generate_compile_cache_dict.py',
'// from %s' % os.path.basename(dict_path),
'// The .dict file is the source of truth; do not edit by hand.',
'',
'static const unsigned char kCompileCacheZstdDict[] = {',
]
for i in range(0, len(data), 12):
chunk = data[i:i + 12]
lines.append(' %s,' % ', '.join('0x%02x' % b for b in chunk))
lines.append('};')
lines.append('static const size_t kCompileCacheZstdDictSize = %d;' %
len(data))

with open(out_path, 'w') as f:
f.write('\n'.join(lines) + '\n')


if __name__ == '__main__':
if len(sys.argv) != 3:
sys.exit('Usage: %s <input.dict> <output.h>' % sys.argv[0])
main(sys.argv[1], sys.argv[2])
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Add copy buttons to all 
 blocks\n(function() {\n function addCopyButtons() {\n document.querySelectorAll('pre code').forEach(function(codeBlock) {\n if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;\n codeBlock.parentElement.setAttribute('data-copy-added', 'true');\n \n var btn = document.createElement('button');\n btn.textContent = 'Copy';\n btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';\n btn.onmouseover = function() { this.style.opacity = '1'; };\n btn.onmouseout = function() { this.style.opacity = '0.7'; };\n btn.onclick = function() {\n navigator.clipboard.writeText(codeBlock.textContent).then(function() {\n btn.textContent = 'Copied!';\n setTimeout(function() { btn.textContent = 'Copy'; }, 1500);\n });\n };\n codeBlock.parentElement.style.position = 'relative';\n codeBlock.parentElement.appendChild(btn);\n });\n }\n \n addCopyButtons();\n \n // Re-run on dynamic content\n var observer = new MutationObserver(addCopyButtons);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Add Copy Buttons to Code Blocks");
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '

Skip to content
src: embed zstd dictionary for further compile cache size wins#16

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

anonrig
merged 1 commit into

from

Jun 12, 2026
 Merged


src: embed zstd dictionary for further compile cache size wins
#16
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


72 changes: 72 additions & 0 deletions
benchmark/misc/compile-cache-timing.js

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,72 @@
'use strict';

// Startup benchmark for the compile cache (including the zstd dictionary).
// Compares no-cache / cold-cache / warm-cache for two workloads:
// big - one large module (the typescript.js fixture)
// many - many small modules (generated here, side-effect-free)
// The modules are generated into a temp dir so the benchmark is self-contained
// and reproducible, and never executes unrelated code.

const common = require('../common.js');
const { spawnSync } = require('child_process');
const fs = require('fs');
const os = require('os');
const path = require('path');

const bench = common.createBenchmark(main, {
 workload: ['big', 'many'],
 cache: ['none', 'cold', 'warm'],
 n: [30],
});

const BIG = path.resolve(__dirname, '../../test/fixtures/snapshot/typescript.js');

// Generate `count` small, side-effect-free modules and return the require()
// code that loads them all in one child.
function makeManyModules(dir, count) {
 fs.mkdirSync(dir, { recursive: true });
 const reqs = [];
 for (let i = 0; i < count; i++) {
 const file = path.join(dir, `mod-${i}.js`);
 fs.writeFileSync(
 file,
 `'use strict';\n` +
 `module.exports = function value${i}(a, b) {\n` +
 ` const sum = a + b + ${i};\n` +
 ` return { id: ${i}, sum, label: 'module-${i}' };\n` +
 `};\n`);
 reqs.push(`require(${JSON.stringify(file)});`);
 }
 return reqs.join('');
}

function run(cmd, args, cacheDir) {
 const env = { ...process.env };
 if (cacheDir) env.NODE_COMPILE_CACHE = cacheDir;
 else delete env.NODE_COMPILE_CACHE;
 const child = spawnSync(cmd, args, { env, stdio: 'ignore' });
 if (child.error) throw child.error;
}

function main({ n, workload, cache }) {
 const cmd = process.execPath || process.argv[0];
 const tmp = fs.mkdtempSync(path.join(os.tmpdir(), 'cc-bench-'));
 const args = workload === 'big' ?
 [BIG] :
 ['-e', makeManyModules(path.join(tmp, 'mods'), 120)];
 const cacheDir = cache === 'none' ? null : path.join(tmp, 'cache');

 try {
 if (cache === 'warm') run(cmd, args, cacheDir); // populate once
 bench.start();
 for (let i = 0; i < n; i++) {
 if (cache === 'cold' && cacheDir) {
 fs.rmSync(cacheDir, { recursive: true, force: true });
 }
 run(cmd, args, cacheDir);
 }
 bench.end(n);
 } finally {
 fs.rmSync(tmp, { recursive: true, force: true });
 }
}

17 changes: 17 additions & 0 deletions
node.gyp

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -1110,6 +1110,22 @@
 '<@(linked_module_files)',
 ],
 },
 {
 'action_name': 'generate_compile_cache_zstd_dict',
 'inputs': [
 'src/compile_cache_zstd.dict',
 'tools/generate_compile_cache_dict.py',
 ],
 'outputs': [
 '<(SHARED_INTERMEDIATE_DIR)/compile_cache_zstd_dict.h',
 ],
 'action': [
 '<(python)',
 'tools/generate_compile_cache_dict.py',
 'src/compile_cache_zstd.dict',
 '<@(_outputs)',
 ],
 },
 ],
 }, # node_base
 {
Expand All@@ -1123,6 +1139,7 @@
 'src',
 'deps/v8/include',
 'deps/uv/include',
 '<(SHARED_INTERMEDIATE_DIR)', # for compile_cache_zstd_dict.h etc.
 ],

 'dependencies': [
Expand Down

72 changes: 68 additions & 4 deletions
src/compile_cache.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -11,6 +11,10 @@
#include "util.h"
#include "zlib.h"
#include "zstd.h"
// kCompileCacheZstdDict + kCompileCacheZstdDictSize come from the header
// generated at build time by the GYP action (from src/compile_cache_zstd.dict).
// The include directory (SHARED_INTERMEDIATE_DIR) is added by node.gyp.
#include "compile_cache_zstd_dict.h"

#ifdef NODE_IMPLEMENTS_POSIX_CREDENTIALS
#include <unistd.h> // getuid
Expand All@@ -28,6 +32,29 @@ using v8::ScriptCompiler;
using v8::String;

namespace {
// The compile-cache zstd dictionary is immutable and embedded in the binary,
// so the prepared CDict/DDict are created once and shared across all handlers
// (and all Environments/Workers) instead of per handler. They live for the
// lifetime of the process. Returns nullptr if preparation fails, in which
// case callers fall back to plain (dictionary-less) zstd.
ZSTD_CDict* GetCompileCacheCDict() {
 static ZSTD_CDict* cdict =
 ZSTD_createCDict(kCompileCacheZstdDict, kCompileCacheZstdDictSize, 1);
 return cdict;
}

ZSTD_DDict* GetCompileCacheDDict() {
 static ZSTD_DDict* ddict =
 ZSTD_createDDict(kCompileCacheZstdDict, kCompileCacheZstdDictSize);
 return ddict;
}

// The dictionary only helps small/medium caches; for larger inputs zstd's own
// adaptive model dominates and the dictionary never wins, so we skip the
// (otherwise wasted) second compression above this raw size. Decompression is
// unaffected: a single DDict decodes both dict-assisted and plain frames.
constexpr uint32_t kCompileCacheDictMaxRawSize = 256 * 1024;

std::string Uint32ToHex(uint32_t crc) {
 std::string str;
 str.reserve(8);
Expand DownExpand Up@@ -266,10 +293,20 @@ void CompileCacheHandler::ReadCacheFile(CompileCacheEntry* entry) {
 Debug("failed to create zstd context\n");
 return;
 }
 // Decompress directly into the buffer handed to V8.
 // Decompress directly into the buffer handed to V8. The embedded
 // dictionary is referenced via a shared, prepared DDict; plain frames
 // (which carry no dictID) decompress correctly with it as well.
 std::unique_ptr<uint8_t[]> raw_data(new uint8_t[raw_size]);
 size_t decompressed_size = ZSTD_decompressDCtx(
 zstd_dctx_, raw_data.get(), raw_size, disk_data.get(), cache_size);
 ZSTD_DDict* ddict = GetCompileCacheDDict();
 size_t decompressed_size;
 if (ddict != nullptr) {
 decompressed_size = ZSTD_decompress_usingDDict(
 zstd_dctx_, raw_data.get(), raw_size, disk_data.get(), cache_size,
 ddict);
 } else {
 decompressed_size = ZSTD_decompressDCtx(
 zstd_dctx_, raw_data.get(), raw_size, disk_data.get(), cache_size);
 }
 if (ZSTD_isError(decompressed_size)) {
 Debug("decompression failed: %s\n", ZSTD_getErrorName(decompressed_size));
 return;
Expand DownExpand Up@@ -508,16 +545,43 @@ void CompileCacheHandler::Persist() {
 // shutdown and should add as little overhead as possible. If the data
 // is not compressible, store it uncompressed, which is indicated by
 // the cache size being equal to the uncompressed size in the headers.
 //
 // We also try the embedded trained dictionary and keep whichever frame is
 // smaller (still subject to the "only store if < raw" policy). The
 // dictionary mainly helps the small/medium caches that dominate real
 // compile cache usage; for inputs where plain zstd already wins we keep
 // the plain frame.
 char* cache_ptr = raw_ptr;
 uint32_t cache_size = raw_size;
 std::unique_ptr<uint8_t[]> compressed;
 std::unique_ptr<uint8_t[]> compressed_dict;
 if (cctx != nullptr || (cctx = ZSTD_createCCtx()) != nullptr) {
 size_t compressed_bound = ZSTD_compressBound(raw_size);
 compressed.reset(new uint8_t[compressed_bound]);
 size_t compressed_size = ZSTD_compressCCtx(
 cctx, compressed.get(), compressed_bound, raw_ptr, raw_size, 1);
 char* best_ptr = reinterpret_cast<char*>(compressed.get());
 // Only attempt the dictionary for small/medium entries (see
 // kCompileCacheDictMaxRawSize); for large blobs it never wins and the
 // extra compression would be wasted work.
 ZSTD_CDict* cdict = raw_size <= kCompileCacheDictMaxRawSize
 ? GetCompileCacheCDict()
 : nullptr;
 if (cdict != nullptr) {
 // Compress into a separate buffer so the selected frame's bytes and
 // size always stay in sync (the plain buffer is left untouched).
 compressed_dict.reset(new uint8_t[compressed_bound]);
 size_t dict_size = ZSTD_compress_usingCDict(
 cctx, compressed_dict.get(), compressed_bound, raw_ptr, raw_size,
 cdict);
 if (!ZSTD_isError(dict_size) &&
 (ZSTD_isError(compressed_size) || dict_size < compressed_size)) {
 compressed_size = dict_size;
 best_ptr = reinterpret_cast<char*>(compressed_dict.get());
 }
 }
 if (!ZSTD_isError(compressed_size) && compressed_size < raw_size) {
 cache_ptr = reinterpret_cast<char*>(compressed.get());
 cache_ptr = best_ptr;
 cache_size = static_cast<uint32_t>(compressed_size);
 }
 }
Expand Down
Binary file addedsrc/compile_cache_zstd.dict

View file


Open in desktop


Binary file not shown.


80 changes: 80 additions & 0 deletions
test/parallel/test-compile-cache-success.js

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -64,3 +64,83 @@ const path = require('path');
 }
 });
}

// Exercise the dictionary-compressed path (added on top of #63861) for many
// small modules, which is where the embedded dictionary helps most. We write
// the cache, then read it back and assert every entry is accepted - this
// proves each dict-compressed frame decompresses to exactly the bytes that
// were persisted.
{
 tmpdir.refresh();
 const dir = tmpdir.resolve('.compile_cache_dir');

 // Generate a handful of small modules so the dictionary path is exercised.
 const count = 8;
 const modules = [];
 for (let i = 0; i < count; i++) {
 const file = tmpdir.resolve(`mod-${i}.js`);
 fs.writeFileSync(
 file,
 `'use strict';\n` +
 `module.exports = function value${i}(a, b) {\n` +
 ` const sum = a + b + ${i};\n` +
 ` return { id: ${i}, sum, label: 'module-${i}' };\n` +
 `};\n`);
 modules.push(file);
 }
 const reqCode = modules.map((m) => `require(${JSON.stringify(m)});`).join('');

 // First run writes the cache for every module.
 spawnSyncAndAssert(
 process.execPath,
 ['-e', reqCode],
 {
 env: {
 ...process.env,
 NODE_DEBUG_NATIVE: 'COMPILE_CACHE',
 NODE_COMPILE_CACHE: dir
 },
 cwd: tmpdir.path
 },
 {
 stderr(output) {
 for (const m of modules) {
 const name = path.basename(m).replace(/[.]/g, '\\.');
 assert.match(output, new RegExp(`writing cache for .*${name}.*success`));
 }
 return true;
 }
 });

 const cacheDirs = fs.readdirSync(dir);
 assert.strictEqual(cacheDirs.length, 1);
 // At least one entry per module (the `-e` runner is cached too).
 const entries = fs.readdirSync(path.join(dir, cacheDirs[0]));
 assert(entries.length >= count, `expected >= ${count} entries, got ${entries.length}`);

 // Second run reads every cached entry back; "was accepted" only happens when
 // the decompressed bytes match the freshly produced in-memory cache, so this
 // is a full roundtrip check of the dictionary-compressed entries.
 spawnSyncAndAssert(
 process.execPath,
 ['-e', reqCode],
 {
 env: {
 ...process.env,
 NODE_DEBUG_NATIVE: 'COMPILE_CACHE',
 NODE_COMPILE_CACHE: dir
 },
 cwd: tmpdir.path
 },
 {
 stderr(output) {
 for (const m of modules) {
 const name = path.basename(m).replace(/[.]/g, '\\.');
 assert.match(
 output,
 new RegExp(`cache for .*${name} was accepted, keeping the in-memory entry`));
 }
 return true;
 }
 });
}

37 changes: 37 additions & 0 deletions
tools/generate_compile_cache_dict.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,37 @@
#!/usr/bin/env python
"""Generate compile_cache_zstd_dict.h from a trained zstd .dict file.

Invoked by the GYP action in node.gyp at build time. Only the small binary
.dict (src/compile_cache_zstd.dict) is checked into the repository; the C
array it produces is generated into SHARED_INTERMEDIATE_DIR.
"""
import os
import sys


def main(dict_path, out_path):
 with open(dict_path, 'rb') as f:
 data = f.read()

 lines = [
 '// Generated by tools/generate_compile_cache_dict.py',
 '// from %s' % os.path.basename(dict_path),
 '// The .dict file is the source of truth; do not edit by hand.',
 '',
 'static const unsigned char kCompileCacheZstdDict[] = {',
 ]
 for i in range(0, len(data), 12):
 chunk = data[i:i + 12]
 lines.append(' %s,' % ', '.join('0x%02x' % b for b in chunk))
 lines.append('};')
 lines.append('static const size_t kCompileCacheZstdDictSize = %d;' %
 len(data))

 with open(out_path, 'w') as f:
 f.write('\n'.join(lines) + '\n')


if __name__ == '__main__':
 if len(sys.argv) != 3:
 sys.exit('Usage: %s <input.dict> <output.h>' % sys.argv[0])
 main(sys.argv[1], sys.argv[2])

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Force GitHub README to respect dark mode\n(function() {\n var style = document.createElement('style');\n style.textContent = '\n .markdown-body {\n color-scheme: dark light;\n }\n .markdown-body pre { background: #161b22 !important; }\n .markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }\n .markdown-body table th, .markdown-body table td { border-color: #30363d !important; }\n .markdown-body img { background: #0d1117; }\n .markdown-body blockquote { border-left-color: #8b949e; }\n .markdown-body hr { border-color: #30363d; }\n ';\n document.head.appendChild(style);\n})();", "GitHub Dark Mode README Fix");
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
src: embed zstd dictionary for further compile cache size wins#16

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

anonrig
merged 1 commit into

from

Jun 12, 2026
 Merged


src: embed zstd dictionary for further compile cache size wins
#16
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


72 changes: 72 additions & 0 deletions
benchmark/misc/compile-cache-timing.js

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,72 @@
'use strict';

// Startup benchmark for the compile cache (including the zstd dictionary).
// Compares no-cache / cold-cache / warm-cache for two workloads:
// big - one large module (the typescript.js fixture)
// many - many small modules (generated here, side-effect-free)
// The modules are generated into a temp dir so the benchmark is self-contained
// and reproducible, and never executes unrelated code.

const common = require('../common.js');
const { spawnSync } = require('child_process');
const fs = require('fs');
const os = require('os');
const path = require('path');

const bench = common.createBenchmark(main, {
 workload: ['big', 'many'],
 cache: ['none', 'cold', 'warm'],
 n: [30],
});

const BIG = path.resolve(__dirname, '../../test/fixtures/snapshot/typescript.js');

// Generate `count` small, side-effect-free modules and return the require()
// code that loads them all in one child.
function makeManyModules(dir, count) {
 fs.mkdirSync(dir, { recursive: true });
 const reqs = [];
 for (let i = 0; i < count; i++) {
 const file = path.join(dir, `mod-${i}.js`);
 fs.writeFileSync(
 file,
 `'use strict';\n` +
 `module.exports = function value${i}(a, b) {\n` +
 ` const sum = a + b + ${i};\n` +
 ` return { id: ${i}, sum, label: 'module-${i}' };\n` +
 `};\n`);
 reqs.push(`require(${JSON.stringify(file)});`);
 }
 return reqs.join('');
}

function run(cmd, args, cacheDir) {
 const env = { ...process.env };
 if (cacheDir) env.NODE_COMPILE_CACHE = cacheDir;
 else delete env.NODE_COMPILE_CACHE;
 const child = spawnSync(cmd, args, { env, stdio: 'ignore' });
 if (child.error) throw child.error;
}

function main({ n, workload, cache }) {
 const cmd = process.execPath || process.argv[0];
 const tmp = fs.mkdtempSync(path.join(os.tmpdir(), 'cc-bench-'));
 const args = workload === 'big' ?
 [BIG] :
 ['-e', makeManyModules(path.join(tmp, 'mods'), 120)];
 const cacheDir = cache === 'none' ? null : path.join(tmp, 'cache');

 try {
 if (cache === 'warm') run(cmd, args, cacheDir); // populate once
 bench.start();
 for (let i = 0; i < n; i++) {
 if (cache === 'cold' && cacheDir) {
 fs.rmSync(cacheDir, { recursive: true, force: true });
 }
 run(cmd, args, cacheDir);
 }
 bench.end(n);
 } finally {
 fs.rmSync(tmp, { recursive: true, force: true });
 }
}

17 changes: 17 additions & 0 deletions
node.gyp

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -1110,6 +1110,22 @@
 '<@(linked_module_files)',
 ],
 },
 {
 'action_name': 'generate_compile_cache_zstd_dict',
 'inputs': [
 'src/compile_cache_zstd.dict',
 'tools/generate_compile_cache_dict.py',
 ],
 'outputs': [
 '<(SHARED_INTERMEDIATE_DIR)/compile_cache_zstd_dict.h',
 ],
 'action': [
 '<(python)',
 'tools/generate_compile_cache_dict.py',
 'src/compile_cache_zstd.dict',
 '<@(_outputs)',
 ],
 },
 ],
 }, # node_base
 {
Expand All@@ -1123,6 +1139,7 @@
 'src',
 'deps/v8/include',
 'deps/uv/include',
 '<(SHARED_INTERMEDIATE_DIR)', # for compile_cache_zstd_dict.h etc.
 ],

 'dependencies': [
Expand Down

72 changes: 68 additions & 4 deletions
src/compile_cache.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -11,6 +11,10 @@
#include "util.h"
#include "zlib.h"
#include "zstd.h"
// kCompileCacheZstdDict + kCompileCacheZstdDictSize come from the header
// generated at build time by the GYP action (from src/compile_cache_zstd.dict).
// The include directory (SHARED_INTERMEDIATE_DIR) is added by node.gyp.
#include "compile_cache_zstd_dict.h"

#ifdef NODE_IMPLEMENTS_POSIX_CREDENTIALS
#include <unistd.h> // getuid
Expand All@@ -28,6 +32,29 @@ using v8::ScriptCompiler;
using v8::String;

namespace {
// The compile-cache zstd dictionary is immutable and embedded in the binary,
// so the prepared CDict/DDict are created once and shared across all handlers
// (and all Environments/Workers) instead of per handler. They live for the
// lifetime of the process. Returns nullptr if preparation fails, in which
// case callers fall back to plain (dictionary-less) zstd.
ZSTD_CDict* GetCompileCacheCDict() {
 static ZSTD_CDict* cdict =
 ZSTD_createCDict(kCompileCacheZstdDict, kCompileCacheZstdDictSize, 1);
 return cdict;
}

ZSTD_DDict* GetCompileCacheDDict() {
 static ZSTD_DDict* ddict =
 ZSTD_createDDict(kCompileCacheZstdDict, kCompileCacheZstdDictSize);
 return ddict;
}

// The dictionary only helps small/medium caches; for larger inputs zstd's own
// adaptive model dominates and the dictionary never wins, so we skip the
// (otherwise wasted) second compression above this raw size. Decompression is
// unaffected: a single DDict decodes both dict-assisted and plain frames.
constexpr uint32_t kCompileCacheDictMaxRawSize = 256 * 1024;

std::string Uint32ToHex(uint32_t crc) {
 std::string str;
 str.reserve(8);
Expand DownExpand Up@@ -266,10 +293,20 @@ void CompileCacheHandler::ReadCacheFile(CompileCacheEntry* entry) {
 Debug("failed to create zstd context\n");
 return;
 }
 // Decompress directly into the buffer handed to V8.
 // Decompress directly into the buffer handed to V8. The embedded
 // dictionary is referenced via a shared, prepared DDict; plain frames
 // (which carry no dictID) decompress correctly with it as well.
 std::unique_ptr<uint8_t[]> raw_data(new uint8_t[raw_size]);
 size_t decompressed_size = ZSTD_decompressDCtx(
 zstd_dctx_, raw_data.get(), raw_size, disk_data.get(), cache_size);
 ZSTD_DDict* ddict = GetCompileCacheDDict();
 size_t decompressed_size;
 if (ddict != nullptr) {
 decompressed_size = ZSTD_decompress_usingDDict(
 zstd_dctx_, raw_data.get(), raw_size, disk_data.get(), cache_size,
 ddict);
 } else {
 decompressed_size = ZSTD_decompressDCtx(
 zstd_dctx_, raw_data.get(), raw_size, disk_data.get(), cache_size);
 }
 if (ZSTD_isError(decompressed_size)) {
 Debug("decompression failed: %s\n", ZSTD_getErrorName(decompressed_size));
 return;
Expand DownExpand Up@@ -508,16 +545,43 @@ void CompileCacheHandler::Persist() {
 // shutdown and should add as little overhead as possible. If the data
 // is not compressible, store it uncompressed, which is indicated by
 // the cache size being equal to the uncompressed size in the headers.
 //
 // We also try the embedded trained dictionary and keep whichever frame is
 // smaller (still subject to the "only store if < raw" policy). The
 // dictionary mainly helps the small/medium caches that dominate real
 // compile cache usage; for inputs where plain zstd already wins we keep
 // the plain frame.
 char* cache_ptr = raw_ptr;
 uint32_t cache_size = raw_size;
 std::unique_ptr<uint8_t[]> compressed;
 std::unique_ptr<uint8_t[]> compressed_dict;
 if (cctx != nullptr || (cctx = ZSTD_createCCtx()) != nullptr) {
 size_t compressed_bound = ZSTD_compressBound(raw_size);
 compressed.reset(new uint8_t[compressed_bound]);
 size_t compressed_size = ZSTD_compressCCtx(
 cctx, compressed.get(), compressed_bound, raw_ptr, raw_size, 1);
 char* best_ptr = reinterpret_cast<char*>(compressed.get());
 // Only attempt the dictionary for small/medium entries (see
 // kCompileCacheDictMaxRawSize); for large blobs it never wins and the
 // extra compression would be wasted work.
 ZSTD_CDict* cdict = raw_size <= kCompileCacheDictMaxRawSize
 ? GetCompileCacheCDict()
 : nullptr;
 if (cdict != nullptr) {
 // Compress into a separate buffer so the selected frame's bytes and
 // size always stay in sync (the plain buffer is left untouched).
 compressed_dict.reset(new uint8_t[compressed_bound]);
 size_t dict_size = ZSTD_compress_usingCDict(
 cctx, compressed_dict.get(), compressed_bound, raw_ptr, raw_size,
 cdict);
 if (!ZSTD_isError(dict_size) &&
 (ZSTD_isError(compressed_size) || dict_size < compressed_size)) {
 compressed_size = dict_size;
 best_ptr = reinterpret_cast<char*>(compressed_dict.get());
 }
 }
 if (!ZSTD_isError(compressed_size) && compressed_size < raw_size) {
 cache_ptr = reinterpret_cast<char*>(compressed.get());
 cache_ptr = best_ptr;
 cache_size = static_cast<uint32_t>(compressed_size);
 }
 }
Expand Down
Binary file addedsrc/compile_cache_zstd.dict

View file


Open in desktop


Binary file not shown.


80 changes: 80 additions & 0 deletions
test/parallel/test-compile-cache-success.js

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -64,3 +64,83 @@ const path = require('path');
 }
 });
}

// Exercise the dictionary-compressed path (added on top of #63861) for many
// small modules, which is where the embedded dictionary helps most. We write
// the cache, then read it back and assert every entry is accepted - this
// proves each dict-compressed frame decompresses to exactly the bytes that
// were persisted.
{
 tmpdir.refresh();
 const dir = tmpdir.resolve('.compile_cache_dir');

 // Generate a handful of small modules so the dictionary path is exercised.
 const count = 8;
 const modules = [];
 for (let i = 0; i < count; i++) {
 const file = tmpdir.resolve(`mod-${i}.js`);
 fs.writeFileSync(
 file,
 `'use strict';\n` +
 `module.exports = function value${i}(a, b) {\n` +
 ` const sum = a + b + ${i};\n` +
 ` return { id: ${i}, sum, label: 'module-${i}' };\n` +
 `};\n`);
 modules.push(file);
 }
 const reqCode = modules.map((m) => `require(${JSON.stringify(m)});`).join('');

 // First run writes the cache for every module.
 spawnSyncAndAssert(
 process.execPath,
 ['-e', reqCode],
 {
 env: {
 ...process.env,
 NODE_DEBUG_NATIVE: 'COMPILE_CACHE',
 NODE_COMPILE_CACHE: dir
 },
 cwd: tmpdir.path
 },
 {
 stderr(output) {
 for (const m of modules) {
 const name = path.basename(m).replace(/[.]/g, '\\.');
 assert.match(output, new RegExp(`writing cache for .*${name}.*success`));
 }
 return true;
 }
 });

 const cacheDirs = fs.readdirSync(dir);
 assert.strictEqual(cacheDirs.length, 1);
 // At least one entry per module (the `-e` runner is cached too).
 const entries = fs.readdirSync(path.join(dir, cacheDirs[0]));
 assert(entries.length >= count, `expected >= ${count} entries, got ${entries.length}`);

 // Second run reads every cached entry back; "was accepted" only happens when
 // the decompressed bytes match the freshly produced in-memory cache, so this
 // is a full roundtrip check of the dictionary-compressed entries.
 spawnSyncAndAssert(
 process.execPath,
 ['-e', reqCode],
 {
 env: {
 ...process.env,
 NODE_DEBUG_NATIVE: 'COMPILE_CACHE',
 NODE_COMPILE_CACHE: dir
 },
 cwd: tmpdir.path
 },
 {
 stderr(output) {
 for (const m of modules) {
 const name = path.basename(m).replace(/[.]/g, '\\.');
 assert.match(
 output,
 new RegExp(`cache for .*${name} was accepted, keeping the in-memory entry`));
 }
 return true;
 }
 });
}

37 changes: 37 additions & 0 deletions
tools/generate_compile_cache_dict.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,37 @@
#!/usr/bin/env python
"""Generate compile_cache_zstd_dict.h from a trained zstd .dict file.

Invoked by the GYP action in node.gyp at build time. Only the small binary
.dict (src/compile_cache_zstd.dict) is checked into the repository; the C
array it produces is generated into SHARED_INTERMEDIATE_DIR.
"""
import os
import sys


def main(dict_path, out_path):
 with open(dict_path, 'rb') as f:
 data = f.read()

 lines = [
 '// Generated by tools/generate_compile_cache_dict.py',
 '// from %s' % os.path.basename(dict_path),
 '// The .dict file is the source of truth; do not edit by hand.',
 '',
 'static const unsigned char kCompileCacheZstdDict[] = {',
 ]
 for i in range(0, len(data), 12):
 chunk = data[i:i + 12]
 lines.append(' %s,' % ', '.join('0x%02x' % b for b in chunk))
 lines.append('};')
 lines.append('static const size_t kCompileCacheZstdDictSize = %d;' %
 len(data))

 with open(out_path, 'w') as f:
 f.write('\n'.join(lines) + '\n')


if __name__ == '__main__':
 if len(sys.argv) != 3:
 sys.exit('Usage: %s <input.dict> <output.h>' % sys.argv[0])
 main(sys.argv[1], sys.argv[2])

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Highlight search terms from Google/DuckDuckGo/Bing referrer\n(function() {\n var ref = document.referrer;\n var terms = [];\n \n if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {\n var url = new URL(ref);\n var q = url.searchParams.get('q') || url.searchParams.get('p');\n if (q) {\n terms = q.split(/\\s+/).filter(function(t) { return t.length > 2; });\n }\n }\n \n if (terms.length === 0) return;\n \n var style = document.createElement('style');\n style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';\n document.head.appendChild(style);\n \n function highlight(node) {\n if (node.nodeType === 3) { // text node\n var text = node.textContent;\n var found = false;\n terms.forEach(function(term) {\n var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\\]\\\\]/g, '\\\\') + ')', 'gi');\n if (regex.test(text)) {\n found = true;\n var frag = document.createDocumentFragment();\n var parts = text.split(regex);\n parts.forEach(function(part, i) {\n if (i % 2 === 0) {\n frag.appendChild(document.createTextNode(part));\n } else {\n var span = document.createElement('span');\n span.className = 'userscript-highlight';\n span.textContent = part;\n frag.appendChild(span);\n }\n });\n node.parentNode.replaceChild(frag, node);\n }\n });\n } else if (node.nodeType === 1 && node.childNodes) { // element\n var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];\n if (!skipTags.includes(node.tagName)) {\n Array.from(node.childNodes).forEach(highlight);\n }\n }\n }\n \n highlight(document.body);\n \n // Re-highlight on dynamic content\n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1 || node.nodeType === 3) highlight(node);\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Highlight Search Terms");
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
src: embed zstd dictionary for further compile cache size wins#16

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

anonrig
merged 1 commit into

from

Jun 12, 2026
 Merged


src: embed zstd dictionary for further compile cache size wins
#16
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


72 changes: 72 additions & 0 deletions
benchmark/misc/compile-cache-timing.js

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,72 @@
'use strict';

// Startup benchmark for the compile cache (including the zstd dictionary).
// Compares no-cache / cold-cache / warm-cache for two workloads:
// big - one large module (the typescript.js fixture)
// many - many small modules (generated here, side-effect-free)
// The modules are generated into a temp dir so the benchmark is self-contained
// and reproducible, and never executes unrelated code.

const common = require('../common.js');
const { spawnSync } = require('child_process');
const fs = require('fs');
const os = require('os');
const path = require('path');

const bench = common.createBenchmark(main, {
 workload: ['big', 'many'],
 cache: ['none', 'cold', 'warm'],
 n: [30],
});

const BIG = path.resolve(__dirname, '../../test/fixtures/snapshot/typescript.js');

// Generate `count` small, side-effect-free modules and return the require()
// code that loads them all in one child.
function makeManyModules(dir, count) {
 fs.mkdirSync(dir, { recursive: true });
 const reqs = [];
 for (let i = 0; i < count; i++) {
 const file = path.join(dir, `mod-${i}.js`);
 fs.writeFileSync(
 file,
 `'use strict';\n` +
 `module.exports = function value${i}(a, b) {\n` +
 ` const sum = a + b + ${i};\n` +
 ` return { id: ${i}, sum, label: 'module-${i}' };\n` +
 `};\n`);
 reqs.push(`require(${JSON.stringify(file)});`);
 }
 return reqs.join('');
}

function run(cmd, args, cacheDir) {
 const env = { ...process.env };
 if (cacheDir) env.NODE_COMPILE_CACHE = cacheDir;
 else delete env.NODE_COMPILE_CACHE;
 const child = spawnSync(cmd, args, { env, stdio: 'ignore' });
 if (child.error) throw child.error;
}

function main({ n, workload, cache }) {
 const cmd = process.execPath || process.argv[0];
 const tmp = fs.mkdtempSync(path.join(os.tmpdir(), 'cc-bench-'));
 const args = workload === 'big' ?
 [BIG] :
 ['-e', makeManyModules(path.join(tmp, 'mods'), 120)];
 const cacheDir = cache === 'none' ? null : path.join(tmp, 'cache');

 try {
 if (cache === 'warm') run(cmd, args, cacheDir); // populate once
 bench.start();
 for (let i = 0; i < n; i++) {
 if (cache === 'cold' && cacheDir) {
 fs.rmSync(cacheDir, { recursive: true, force: true });
 }
 run(cmd, args, cacheDir);
 }
 bench.end(n);
 } finally {
 fs.rmSync(tmp, { recursive: true, force: true });
 }
}

17 changes: 17 additions & 0 deletions
node.gyp

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -1110,6 +1110,22 @@
 '<@(linked_module_files)',
 ],
 },
 {
 'action_name': 'generate_compile_cache_zstd_dict',
 'inputs': [
 'src/compile_cache_zstd.dict',
 'tools/generate_compile_cache_dict.py',
 ],
 'outputs': [
 '<(SHARED_INTERMEDIATE_DIR)/compile_cache_zstd_dict.h',
 ],
 'action': [
 '<(python)',
 'tools/generate_compile_cache_dict.py',
 'src/compile_cache_zstd.dict',
 '<@(_outputs)',
 ],
 },
 ],
 }, # node_base
 {
Expand All@@ -1123,6 +1139,7 @@
 'src',
 'deps/v8/include',
 'deps/uv/include',
 '<(SHARED_INTERMEDIATE_DIR)', # for compile_cache_zstd_dict.h etc.
 ],

 'dependencies': [
Expand Down

72 changes: 68 additions & 4 deletions
src/compile_cache.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -11,6 +11,10 @@
#include "util.h"
#include "zlib.h"
#include "zstd.h"
// kCompileCacheZstdDict + kCompileCacheZstdDictSize come from the header
// generated at build time by the GYP action (from src/compile_cache_zstd.dict).
// The include directory (SHARED_INTERMEDIATE_DIR) is added by node.gyp.
#include "compile_cache_zstd_dict.h"

#ifdef NODE_IMPLEMENTS_POSIX_CREDENTIALS
#include <unistd.h> // getuid
Expand All@@ -28,6 +32,29 @@ using v8::ScriptCompiler;
using v8::String;

namespace {
// The compile-cache zstd dictionary is immutable and embedded in the binary,
// so the prepared CDict/DDict are created once and shared across all handlers
// (and all Environments/Workers) instead of per handler. They live for the
// lifetime of the process. Returns nullptr if preparation fails, in which
// case callers fall back to plain (dictionary-less) zstd.
ZSTD_CDict* GetCompileCacheCDict() {
 static ZSTD_CDict* cdict =
 ZSTD_createCDict(kCompileCacheZstdDict, kCompileCacheZstdDictSize, 1);
 return cdict;
}

ZSTD_DDict* GetCompileCacheDDict() {
 static ZSTD_DDict* ddict =
 ZSTD_createDDict(kCompileCacheZstdDict, kCompileCacheZstdDictSize);
 return ddict;
}

// The dictionary only helps small/medium caches; for larger inputs zstd's own
// adaptive model dominates and the dictionary never wins, so we skip the
// (otherwise wasted) second compression above this raw size. Decompression is
// unaffected: a single DDict decodes both dict-assisted and plain frames.
constexpr uint32_t kCompileCacheDictMaxRawSize = 256 * 1024;

std::string Uint32ToHex(uint32_t crc) {
 std::string str;
 str.reserve(8);
Expand DownExpand Up@@ -266,10 +293,20 @@ void CompileCacheHandler::ReadCacheFile(CompileCacheEntry* entry) {
 Debug("failed to create zstd context\n");
 return;
 }
 // Decompress directly into the buffer handed to V8.
 // Decompress directly into the buffer handed to V8. The embedded
 // dictionary is referenced via a shared, prepared DDict; plain frames
 // (which carry no dictID) decompress correctly with it as well.
 std::unique_ptr<uint8_t[]> raw_data(new uint8_t[raw_size]);
 size_t decompressed_size = ZSTD_decompressDCtx(
 zstd_dctx_, raw_data.get(), raw_size, disk_data.get(), cache_size);
 ZSTD_DDict* ddict = GetCompileCacheDDict();
 size_t decompressed_size;
 if (ddict != nullptr) {
 decompressed_size = ZSTD_decompress_usingDDict(
 zstd_dctx_, raw_data.get(), raw_size, disk_data.get(), cache_size,
 ddict);
 } else {
 decompressed_size = ZSTD_decompressDCtx(
 zstd_dctx_, raw_data.get(), raw_size, disk_data.get(), cache_size);
 }
 if (ZSTD_isError(decompressed_size)) {
 Debug("decompression failed: %s\n", ZSTD_getErrorName(decompressed_size));
 return;
Expand DownExpand Up@@ -508,16 +545,43 @@ void CompileCacheHandler::Persist() {
 // shutdown and should add as little overhead as possible. If the data
 // is not compressible, store it uncompressed, which is indicated by
 // the cache size being equal to the uncompressed size in the headers.
 //
 // We also try the embedded trained dictionary and keep whichever frame is
 // smaller (still subject to the "only store if < raw" policy). The
 // dictionary mainly helps the small/medium caches that dominate real
 // compile cache usage; for inputs where plain zstd already wins we keep
 // the plain frame.
 char* cache_ptr = raw_ptr;
 uint32_t cache_size = raw_size;
 std::unique_ptr<uint8_t[]> compressed;
 std::unique_ptr<uint8_t[]> compressed_dict;
 if (cctx != nullptr || (cctx = ZSTD_createCCtx()) != nullptr) {
 size_t compressed_bound = ZSTD_compressBound(raw_size);
 compressed.reset(new uint8_t[compressed_bound]);
 size_t compressed_size = ZSTD_compressCCtx(
 cctx, compressed.get(), compressed_bound, raw_ptr, raw_size, 1);
 char* best_ptr = reinterpret_cast<char*>(compressed.get());
 // Only attempt the dictionary for small/medium entries (see
 // kCompileCacheDictMaxRawSize); for large blobs it never wins and the
 // extra compression would be wasted work.
 ZSTD_CDict* cdict = raw_size <= kCompileCacheDictMaxRawSize
 ? GetCompileCacheCDict()
 : nullptr;
 if (cdict != nullptr) {
 // Compress into a separate buffer so the selected frame's bytes and
 // size always stay in sync (the plain buffer is left untouched).
 compressed_dict.reset(new uint8_t[compressed_bound]);
 size_t dict_size = ZSTD_compress_usingCDict(
 cctx, compressed_dict.get(), compressed_bound, raw_ptr, raw_size,
 cdict);
 if (!ZSTD_isError(dict_size) &&
 (ZSTD_isError(compressed_size) || dict_size < compressed_size)) {
 compressed_size = dict_size;
 best_ptr = reinterpret_cast<char*>(compressed_dict.get());
 }
 }
 if (!ZSTD_isError(compressed_size) && compressed_size < raw_size) {
 cache_ptr = reinterpret_cast<char*>(compressed.get());
 cache_ptr = best_ptr;
 cache_size = static_cast<uint32_t>(compressed_size);
 }
 }
Expand Down
Binary file addedsrc/compile_cache_zstd.dict

View file


Open in desktop


Binary file not shown.


80 changes: 80 additions & 0 deletions
test/parallel/test-compile-cache-success.js

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -64,3 +64,83 @@ const path = require('path');
 }
 });
}

// Exercise the dictionary-compressed path (added on top of #63861) for many
// small modules, which is where the embedded dictionary helps most. We write
// the cache, then read it back and assert every entry is accepted - this
// proves each dict-compressed frame decompresses to exactly the bytes that
// were persisted.
{
 tmpdir.refresh();
 const dir = tmpdir.resolve('.compile_cache_dir');

 // Generate a handful of small modules so the dictionary path is exercised.
 const count = 8;
 const modules = [];
 for (let i = 0; i < count; i++) {
 const file = tmpdir.resolve(`mod-${i}.js`);
 fs.writeFileSync(
 file,
 `'use strict';\n` +
 `module.exports = function value${i}(a, b) {\n` +
 ` const sum = a + b + ${i};\n` +
 ` return { id: ${i}, sum, label: 'module-${i}' };\n` +
 `};\n`);
 modules.push(file);
 }
 const reqCode = modules.map((m) => `require(${JSON.stringify(m)});`).join('');

 // First run writes the cache for every module.
 spawnSyncAndAssert(
 process.execPath,
 ['-e', reqCode],
 {
 env: {
 ...process.env,
 NODE_DEBUG_NATIVE: 'COMPILE_CACHE',
 NODE_COMPILE_CACHE: dir
 },
 cwd: tmpdir.path
 },
 {
 stderr(output) {
 for (const m of modules) {
 const name = path.basename(m).replace(/[.]/g, '\\.');
 assert.match(output, new RegExp(`writing cache for .*${name}.*success`));
 }
 return true;
 }
 });

 const cacheDirs = fs.readdirSync(dir);
 assert.strictEqual(cacheDirs.length, 1);
 // At least one entry per module (the `-e` runner is cached too).
 const entries = fs.readdirSync(path.join(dir, cacheDirs[0]));
 assert(entries.length >= count, `expected >= ${count} entries, got ${entries.length}`);

 // Second run reads every cached entry back; "was accepted" only happens when
 // the decompressed bytes match the freshly produced in-memory cache, so this
 // is a full roundtrip check of the dictionary-compressed entries.
 spawnSyncAndAssert(
 process.execPath,
 ['-e', reqCode],
 {
 env: {
 ...process.env,
 NODE_DEBUG_NATIVE: 'COMPILE_CACHE',
 NODE_COMPILE_CACHE: dir
 },
 cwd: tmpdir.path
 },
 {
 stderr(output) {
 for (const m of modules) {
 const name = path.basename(m).replace(/[.]/g, '\\.');
 assert.match(
 output,
 new RegExp(`cache for .*${name} was accepted, keeping the in-memory entry`));
 }
 return true;
 }
 });
}

37 changes: 37 additions & 0 deletions
tools/generate_compile_cache_dict.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,37 @@
#!/usr/bin/env python
"""Generate compile_cache_zstd_dict.h from a trained zstd .dict file.

Invoked by the GYP action in node.gyp at build time. Only the small binary
.dict (src/compile_cache_zstd.dict) is checked into the repository; the C
array it produces is generated into SHARED_INTERMEDIATE_DIR.
"""
import os
import sys


def main(dict_path, out_path):
 with open(dict_path, 'rb') as f:
 data = f.read()

 lines = [
 '// Generated by tools/generate_compile_cache_dict.py',
 '// from %s' % os.path.basename(dict_path),
 '// The .dict file is the source of truth; do not edit by hand.',
 '',
 'static const unsigned char kCompileCacheZstdDict[] = {',
 ]
 for i in range(0, len(data), 12):
 chunk = data[i:i + 12]
 lines.append(' %s,' % ', '.join('0x%02x' % b for b in chunk))
 lines.append('};')
 lines.append('static const size_t kCompileCacheZstdDictSize = %d;' %
 len(data))

 with open(out_path, 'w') as f:
 f.write('\n'.join(lines) + '\n')


if __name__ == '__main__':
 if len(sys.argv) != 3:
 sys.exit('Usage: %s <input.dict> <output.h>' % sys.argv[0])
 main(sys.argv[1], sys.argv[2])

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Strip utm_, fbclid, gclid, etc. from all links on page\n(function() {\n var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',\n 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',\n 'ref', 'ref_src', 'source', 'medium', 'campaign'];\n \n function cleanUrl(url) {\n try {\n var u = new URL(url, window.location.origin);\n var changed = false;\n trackingParams.forEach(function(p) {\n if (u.searchParams.has(p)) {\n u.searchParams.delete(p);\n changed = true;\n }\n });\n return changed ? u.toString() : url;\n } catch (e) {\n return url;\n }\n }\n \n function cleanLinks() {\n document.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n \n cleanLinks();\n \n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1) {\n if (node.tagName === 'A') cleanLinks();\n node.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Remove Tracking Parameters from Links");
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '

Skip to content
src: embed zstd dictionary for further compile cache size wins#16

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

anonrig
merged 1 commit into

from

Jun 12, 2026
 Merged


src: embed zstd dictionary for further compile cache size wins
#16
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


72 changes: 72 additions & 0 deletions
benchmark/misc/compile-cache-timing.js

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,72 @@
'use strict';

// Startup benchmark for the compile cache (including the zstd dictionary).
// Compares no-cache / cold-cache / warm-cache for two workloads:
// big - one large module (the typescript.js fixture)
// many - many small modules (generated here, side-effect-free)
// The modules are generated into a temp dir so the benchmark is self-contained
// and reproducible, and never executes unrelated code.

const common = require('../common.js');
const { spawnSync } = require('child_process');
const fs = require('fs');
const os = require('os');
const path = require('path');

const bench = common.createBenchmark(main, {
 workload: ['big', 'many'],
 cache: ['none', 'cold', 'warm'],
 n: [30],
});

const BIG = path.resolve(__dirname, '../../test/fixtures/snapshot/typescript.js');

// Generate `count` small, side-effect-free modules and return the require()
// code that loads them all in one child.
function makeManyModules(dir, count) {
 fs.mkdirSync(dir, { recursive: true });
 const reqs = [];
 for (let i = 0; i < count; i++) {
 const file = path.join(dir, `mod-${i}.js`);
 fs.writeFileSync(
 file,
 `'use strict';\n` +
 `module.exports = function value${i}(a, b) {\n` +
 ` const sum = a + b + ${i};\n` +
 ` return { id: ${i}, sum, label: 'module-${i}' };\n` +
 `};\n`);
 reqs.push(`require(${JSON.stringify(file)});`);
 }
 return reqs.join('');
}

function run(cmd, args, cacheDir) {
 const env = { ...process.env };
 if (cacheDir) env.NODE_COMPILE_CACHE = cacheDir;
 else delete env.NODE_COMPILE_CACHE;
 const child = spawnSync(cmd, args, { env, stdio: 'ignore' });
 if (child.error) throw child.error;
}

function main({ n, workload, cache }) {
 const cmd = process.execPath || process.argv[0];
 const tmp = fs.mkdtempSync(path.join(os.tmpdir(), 'cc-bench-'));
 const args = workload === 'big' ?
 [BIG] :
 ['-e', makeManyModules(path.join(tmp, 'mods'), 120)];
 const cacheDir = cache === 'none' ? null : path.join(tmp, 'cache');

 try {
 if (cache === 'warm') run(cmd, args, cacheDir); // populate once
 bench.start();
 for (let i = 0; i < n; i++) {
 if (cache === 'cold' && cacheDir) {
 fs.rmSync(cacheDir, { recursive: true, force: true });
 }
 run(cmd, args, cacheDir);
 }
 bench.end(n);
 } finally {
 fs.rmSync(tmp, { recursive: true, force: true });
 }
}

17 changes: 17 additions & 0 deletions
node.gyp

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -1110,6 +1110,22 @@
 '<@(linked_module_files)',
 ],
 },
 {
 'action_name': 'generate_compile_cache_zstd_dict',
 'inputs': [
 'src/compile_cache_zstd.dict',
 'tools/generate_compile_cache_dict.py',
 ],
 'outputs': [
 '<(SHARED_INTERMEDIATE_DIR)/compile_cache_zstd_dict.h',
 ],
 'action': [
 '<(python)',
 'tools/generate_compile_cache_dict.py',
 'src/compile_cache_zstd.dict',
 '<@(_outputs)',
 ],
 },
 ],
 }, # node_base
 {
Expand All@@ -1123,6 +1139,7 @@
 'src',
 'deps/v8/include',
 'deps/uv/include',
 '<(SHARED_INTERMEDIATE_DIR)', # for compile_cache_zstd_dict.h etc.
 ],

 'dependencies': [
Expand Down

72 changes: 68 additions & 4 deletions
src/compile_cache.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -11,6 +11,10 @@
#include "util.h"
#include "zlib.h"
#include "zstd.h"
// kCompileCacheZstdDict + kCompileCacheZstdDictSize come from the header
// generated at build time by the GYP action (from src/compile_cache_zstd.dict).
// The include directory (SHARED_INTERMEDIATE_DIR) is added by node.gyp.
#include "compile_cache_zstd_dict.h"

#ifdef NODE_IMPLEMENTS_POSIX_CREDENTIALS
#include <unistd.h> // getuid
Expand All@@ -28,6 +32,29 @@ using v8::ScriptCompiler;
using v8::String;

namespace {
// The compile-cache zstd dictionary is immutable and embedded in the binary,
// so the prepared CDict/DDict are created once and shared across all handlers
// (and all Environments/Workers) instead of per handler. They live for the
// lifetime of the process. Returns nullptr if preparation fails, in which
// case callers fall back to plain (dictionary-less) zstd.
ZSTD_CDict* GetCompileCacheCDict() {
 static ZSTD_CDict* cdict =
 ZSTD_createCDict(kCompileCacheZstdDict, kCompileCacheZstdDictSize, 1);
 return cdict;
}

ZSTD_DDict* GetCompileCacheDDict() {
 static ZSTD_DDict* ddict =
 ZSTD_createDDict(kCompileCacheZstdDict, kCompileCacheZstdDictSize);
 return ddict;
}

// The dictionary only helps small/medium caches; for larger inputs zstd's own
// adaptive model dominates and the dictionary never wins, so we skip the
// (otherwise wasted) second compression above this raw size. Decompression is
// unaffected: a single DDict decodes both dict-assisted and plain frames.
constexpr uint32_t kCompileCacheDictMaxRawSize = 256 * 1024;

std::string Uint32ToHex(uint32_t crc) {
 std::string str;
 str.reserve(8);
Expand DownExpand Up@@ -266,10 +293,20 @@ void CompileCacheHandler::ReadCacheFile(CompileCacheEntry* entry) {
 Debug("failed to create zstd context\n");
 return;
 }
 // Decompress directly into the buffer handed to V8.
 // Decompress directly into the buffer handed to V8. The embedded
 // dictionary is referenced via a shared, prepared DDict; plain frames
 // (which carry no dictID) decompress correctly with it as well.
 std::unique_ptr<uint8_t[]> raw_data(new uint8_t[raw_size]);
 size_t decompressed_size = ZSTD_decompressDCtx(
 zstd_dctx_, raw_data.get(), raw_size, disk_data.get(), cache_size);
 ZSTD_DDict* ddict = GetCompileCacheDDict();
 size_t decompressed_size;
 if (ddict != nullptr) {
 decompressed_size = ZSTD_decompress_usingDDict(
 zstd_dctx_, raw_data.get(), raw_size, disk_data.get(), cache_size,
 ddict);
 } else {
 decompressed_size = ZSTD_decompressDCtx(
 zstd_dctx_, raw_data.get(), raw_size, disk_data.get(), cache_size);
 }
 if (ZSTD_isError(decompressed_size)) {
 Debug("decompression failed: %s\n", ZSTD_getErrorName(decompressed_size));
 return;
Expand DownExpand Up@@ -508,16 +545,43 @@ void CompileCacheHandler::Persist() {
 // shutdown and should add as little overhead as possible. If the data
 // is not compressible, store it uncompressed, which is indicated by
 // the cache size being equal to the uncompressed size in the headers.
 //
 // We also try the embedded trained dictionary and keep whichever frame is
 // smaller (still subject to the "only store if < raw" policy). The
 // dictionary mainly helps the small/medium caches that dominate real
 // compile cache usage; for inputs where plain zstd already wins we keep
 // the plain frame.
 char* cache_ptr = raw_ptr;
 uint32_t cache_size = raw_size;
 std::unique_ptr<uint8_t[]> compressed;
 std::unique_ptr<uint8_t[]> compressed_dict;
 if (cctx != nullptr || (cctx = ZSTD_createCCtx()) != nullptr) {
 size_t compressed_bound = ZSTD_compressBound(raw_size);
 compressed.reset(new uint8_t[compressed_bound]);
 size_t compressed_size = ZSTD_compressCCtx(
 cctx, compressed.get(), compressed_bound, raw_ptr, raw_size, 1);
 char* best_ptr = reinterpret_cast<char*>(compressed.get());
 // Only attempt the dictionary for small/medium entries (see
 // kCompileCacheDictMaxRawSize); for large blobs it never wins and the
 // extra compression would be wasted work.
 ZSTD_CDict* cdict = raw_size <= kCompileCacheDictMaxRawSize
 ? GetCompileCacheCDict()
 : nullptr;
 if (cdict != nullptr) {
 // Compress into a separate buffer so the selected frame's bytes and
 // size always stay in sync (the plain buffer is left untouched).
 compressed_dict.reset(new uint8_t[compressed_bound]);
 size_t dict_size = ZSTD_compress_usingCDict(
 cctx, compressed_dict.get(), compressed_bound, raw_ptr, raw_size,
 cdict);
 if (!ZSTD_isError(dict_size) &&
 (ZSTD_isError(compressed_size) || dict_size < compressed_size)) {
 compressed_size = dict_size;
 best_ptr = reinterpret_cast<char*>(compressed_dict.get());
 }
 }
 if (!ZSTD_isError(compressed_size) && compressed_size < raw_size) {
 cache_ptr = reinterpret_cast<char*>(compressed.get());
 cache_ptr = best_ptr;
 cache_size = static_cast<uint32_t>(compressed_size);
 }
 }
Expand Down
Binary file addedsrc/compile_cache_zstd.dict

View file


Open in desktop


Binary file not shown.


80 changes: 80 additions & 0 deletions
test/parallel/test-compile-cache-success.js

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -64,3 +64,83 @@ const path = require('path');
 }
 });
}

// Exercise the dictionary-compressed path (added on top of #63861) for many
// small modules, which is where the embedded dictionary helps most. We write
// the cache, then read it back and assert every entry is accepted - this
// proves each dict-compressed frame decompresses to exactly the bytes that
// were persisted.
{
 tmpdir.refresh();
 const dir = tmpdir.resolve('.compile_cache_dir');

 // Generate a handful of small modules so the dictionary path is exercised.
 const count = 8;
 const modules = [];
 for (let i = 0; i < count; i++) {
 const file = tmpdir.resolve(`mod-${i}.js`);
 fs.writeFileSync(
 file,
 `'use strict';\n` +
 `module.exports = function value${i}(a, b) {\n` +
 ` const sum = a + b + ${i};\n` +
 ` return { id: ${i}, sum, label: 'module-${i}' };\n` +
 `};\n`);
 modules.push(file);
 }
 const reqCode = modules.map((m) => `require(${JSON.stringify(m)});`).join('');

 // First run writes the cache for every module.
 spawnSyncAndAssert(
 process.execPath,
 ['-e', reqCode],
 {
 env: {
 ...process.env,
 NODE_DEBUG_NATIVE: 'COMPILE_CACHE',
 NODE_COMPILE_CACHE: dir
 },
 cwd: tmpdir.path
 },
 {
 stderr(output) {
 for (const m of modules) {
 const name = path.basename(m).replace(/[.]/g, '\\.');
 assert.match(output, new RegExp(`writing cache for .*${name}.*success`));
 }
 return true;
 }
 });

 const cacheDirs = fs.readdirSync(dir);
 assert.strictEqual(cacheDirs.length, 1);
 // At least one entry per module (the `-e` runner is cached too).
 const entries = fs.readdirSync(path.join(dir, cacheDirs[0]));
 assert(entries.length >= count, `expected >= ${count} entries, got ${entries.length}`);

 // Second run reads every cached entry back; "was accepted" only happens when
 // the decompressed bytes match the freshly produced in-memory cache, so this
 // is a full roundtrip check of the dictionary-compressed entries.
 spawnSyncAndAssert(
 process.execPath,
 ['-e', reqCode],
 {
 env: {
 ...process.env,
 NODE_DEBUG_NATIVE: 'COMPILE_CACHE',
 NODE_COMPILE_CACHE: dir
 },
 cwd: tmpdir.path
 },
 {
 stderr(output) {
 for (const m of modules) {
 const name = path.basename(m).replace(/[.]/g, '\\.');
 assert.match(
 output,
 new RegExp(`cache for .*${name} was accepted, keeping the in-memory entry`));
 }
 return true;
 }
 });
}

37 changes: 37 additions & 0 deletions
tools/generate_compile_cache_dict.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,37 @@
#!/usr/bin/env python
"""Generate compile_cache_zstd_dict.h from a trained zstd .dict file.

Invoked by the GYP action in node.gyp at build time. Only the small binary
.dict (src/compile_cache_zstd.dict) is checked into the repository; the C
array it produces is generated into SHARED_INTERMEDIATE_DIR.
"""
import os
import sys


def main(dict_path, out_path):
 with open(dict_path, 'rb') as f:
 data = f.read()

 lines = [
 '// Generated by tools/generate_compile_cache_dict.py',
 '// from %s' % os.path.basename(dict_path),
 '// The .dict file is the source of truth; do not edit by hand.',
 '',
 'static const unsigned char kCompileCacheZstdDict[] = {',
 ]
 for i in range(0, len(data), 12):
 chunk = data[i:i + 12]
 lines.append(' %s,' % ', '.join('0x%02x' % b for b in chunk))
 lines.append('};')
 lines.append('static const size_t kCompileCacheZstdDictSize = %d;' %
 len(data))

 with open(out_path, 'w') as f:
 f.write('\n'.join(lines) + '\n')


if __name__ == '__main__':
 if len(sys.argv) != 3:
 sys.exit('Usage: %s <input.dict> <output.h>' % sys.argv[0])
 main(sys.argv[1], sys.argv[2])

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Auto-enable theater mode on YouTube\n(function() {\n function tryTheater() {\n var btn = document.querySelector('button[aria-label=\"Theater mode\"], ytd-player #player button[title=\"Theater mode\"]');\n if (btn && !btn.classList.contains('activated')) {\n btn.click();\n }\n }\n \n // Try immediately\n tryTheater();\n \n // Try after navigation (SPA)\n var lastUrl = location.href;\n setInterval(function() {\n if (location.href !== lastUrl) {\n lastUrl = location.href;\n setTimeout(tryTheater, 500);\n }\n }, 1000);\n \n // Also try on player load\n var observer = new MutationObserver(tryTheater);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "YouTube Theater Mode Default");
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
src: embed zstd dictionary for further compile cache size wins#16

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

anonrig
merged 1 commit into

from

Jun 12, 2026
 Merged


src: embed zstd dictionary for further compile cache size wins
#16
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


72 changes: 72 additions & 0 deletions
benchmark/misc/compile-cache-timing.js

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,72 @@
'use strict';

// Startup benchmark for the compile cache (including the zstd dictionary).
// Compares no-cache / cold-cache / warm-cache for two workloads:
// big - one large module (the typescript.js fixture)
// many - many small modules (generated here, side-effect-free)
// The modules are generated into a temp dir so the benchmark is self-contained
// and reproducible, and never executes unrelated code.

const common = require('../common.js');
const { spawnSync } = require('child_process');
const fs = require('fs');
const os = require('os');
const path = require('path');

const bench = common.createBenchmark(main, {
 workload: ['big', 'many'],
 cache: ['none', 'cold', 'warm'],
 n: [30],
});

const BIG = path.resolve(__dirname, '../../test/fixtures/snapshot/typescript.js');

// Generate `count` small, side-effect-free modules and return the require()
// code that loads them all in one child.
function makeManyModules(dir, count) {
 fs.mkdirSync(dir, { recursive: true });
 const reqs = [];
 for (let i = 0; i < count; i++) {
 const file = path.join(dir, `mod-${i}.js`);
 fs.writeFileSync(
 file,
 `'use strict';\n` +
 `module.exports = function value${i}(a, b) {\n` +
 ` const sum = a + b + ${i};\n` +
 ` return { id: ${i}, sum, label: 'module-${i}' };\n` +
 `};\n`);
 reqs.push(`require(${JSON.stringify(file)});`);
 }
 return reqs.join('');
}

function run(cmd, args, cacheDir) {
 const env = { ...process.env };
 if (cacheDir) env.NODE_COMPILE_CACHE = cacheDir;
 else delete env.NODE_COMPILE_CACHE;
 const child = spawnSync(cmd, args, { env, stdio: 'ignore' });
 if (child.error) throw child.error;
}

function main({ n, workload, cache }) {
 const cmd = process.execPath || process.argv[0];
 const tmp = fs.mkdtempSync(path.join(os.tmpdir(), 'cc-bench-'));
 const args = workload === 'big' ?
 [BIG] :
 ['-e', makeManyModules(path.join(tmp, 'mods'), 120)];
 const cacheDir = cache === 'none' ? null : path.join(tmp, 'cache');

 try {
 if (cache === 'warm') run(cmd, args, cacheDir); // populate once
 bench.start();
 for (let i = 0; i < n; i++) {
 if (cache === 'cold' && cacheDir) {
 fs.rmSync(cacheDir, { recursive: true, force: true });
 }
 run(cmd, args, cacheDir);
 }
 bench.end(n);
 } finally {
 fs.rmSync(tmp, { recursive: true, force: true });
 }
}

17 changes: 17 additions & 0 deletions
node.gyp

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -1110,6 +1110,22 @@
 '<@(linked_module_files)',
 ],
 },
 {
 'action_name': 'generate_compile_cache_zstd_dict',
 'inputs': [
 'src/compile_cache_zstd.dict',
 'tools/generate_compile_cache_dict.py',
 ],
 'outputs': [
 '<(SHARED_INTERMEDIATE_DIR)/compile_cache_zstd_dict.h',
 ],
 'action': [
 '<(python)',
 'tools/generate_compile_cache_dict.py',
 'src/compile_cache_zstd.dict',
 '<@(_outputs)',
 ],
 },
 ],
 }, # node_base
 {
Expand All@@ -1123,6 +1139,7 @@
 'src',
 'deps/v8/include',
 'deps/uv/include',
 '<(SHARED_INTERMEDIATE_DIR)', # for compile_cache_zstd_dict.h etc.
 ],

 'dependencies': [
Expand Down

72 changes: 68 additions & 4 deletions
src/compile_cache.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -11,6 +11,10 @@
#include "util.h"
#include "zlib.h"
#include "zstd.h"
// kCompileCacheZstdDict + kCompileCacheZstdDictSize come from the header
// generated at build time by the GYP action (from src/compile_cache_zstd.dict).
// The include directory (SHARED_INTERMEDIATE_DIR) is added by node.gyp.
#include "compile_cache_zstd_dict.h"

#ifdef NODE_IMPLEMENTS_POSIX_CREDENTIALS
#include <unistd.h> // getuid
Expand All@@ -28,6 +32,29 @@ using v8::ScriptCompiler;
using v8::String;

namespace {
// The compile-cache zstd dictionary is immutable and embedded in the binary,
// so the prepared CDict/DDict are created once and shared across all handlers
// (and all Environments/Workers) instead of per handler. They live for the
// lifetime of the process. Returns nullptr if preparation fails, in which
// case callers fall back to plain (dictionary-less) zstd.
ZSTD_CDict* GetCompileCacheCDict() {
 static ZSTD_CDict* cdict =
 ZSTD_createCDict(kCompileCacheZstdDict, kCompileCacheZstdDictSize, 1);
 return cdict;
}

ZSTD_DDict* GetCompileCacheDDict() {
 static ZSTD_DDict* ddict =
 ZSTD_createDDict(kCompileCacheZstdDict, kCompileCacheZstdDictSize);
 return ddict;
}

// The dictionary only helps small/medium caches; for larger inputs zstd's own
// adaptive model dominates and the dictionary never wins, so we skip the
// (otherwise wasted) second compression above this raw size. Decompression is
// unaffected: a single DDict decodes both dict-assisted and plain frames.
constexpr uint32_t kCompileCacheDictMaxRawSize = 256 * 1024;

std::string Uint32ToHex(uint32_t crc) {
 std::string str;
 str.reserve(8);
Expand DownExpand Up@@ -266,10 +293,20 @@ void CompileCacheHandler::ReadCacheFile(CompileCacheEntry* entry) {
 Debug("failed to create zstd context\n");
 return;
 }
 // Decompress directly into the buffer handed to V8.
 // Decompress directly into the buffer handed to V8. The embedded
 // dictionary is referenced via a shared, prepared DDict; plain frames
 // (which carry no dictID) decompress correctly with it as well.
 std::unique_ptr<uint8_t[]> raw_data(new uint8_t[raw_size]);
 size_t decompressed_size = ZSTD_decompressDCtx(
 zstd_dctx_, raw_data.get(), raw_size, disk_data.get(), cache_size);
 ZSTD_DDict* ddict = GetCompileCacheDDict();
 size_t decompressed_size;
 if (ddict != nullptr) {
 decompressed_size = ZSTD_decompress_usingDDict(
 zstd_dctx_, raw_data.get(), raw_size, disk_data.get(), cache_size,
 ddict);
 } else {
 decompressed_size = ZSTD_decompressDCtx(
 zstd_dctx_, raw_data.get(), raw_size, disk_data.get(), cache_size);
 }
 if (ZSTD_isError(decompressed_size)) {
 Debug("decompression failed: %s\n", ZSTD_getErrorName(decompressed_size));
 return;
Expand DownExpand Up@@ -508,16 +545,43 @@ void CompileCacheHandler::Persist() {
 // shutdown and should add as little overhead as possible. If the data
 // is not compressible, store it uncompressed, which is indicated by
 // the cache size being equal to the uncompressed size in the headers.
 //
 // We also try the embedded trained dictionary and keep whichever frame is
 // smaller (still subject to the "only store if < raw" policy). The
 // dictionary mainly helps the small/medium caches that dominate real
 // compile cache usage; for inputs where plain zstd already wins we keep
 // the plain frame.
 char* cache_ptr = raw_ptr;
 uint32_t cache_size = raw_size;
 std::unique_ptr<uint8_t[]> compressed;
 std::unique_ptr<uint8_t[]> compressed_dict;
 if (cctx != nullptr || (cctx = ZSTD_createCCtx()) != nullptr) {
 size_t compressed_bound = ZSTD_compressBound(raw_size);
 compressed.reset(new uint8_t[compressed_bound]);
 size_t compressed_size = ZSTD_compressCCtx(
 cctx, compressed.get(), compressed_bound, raw_ptr, raw_size, 1);
 char* best_ptr = reinterpret_cast<char*>(compressed.get());
 // Only attempt the dictionary for small/medium entries (see
 // kCompileCacheDictMaxRawSize); for large blobs it never wins and the
 // extra compression would be wasted work.
 ZSTD_CDict* cdict = raw_size <= kCompileCacheDictMaxRawSize
 ? GetCompileCacheCDict()
 : nullptr;
 if (cdict != nullptr) {
 // Compress into a separate buffer so the selected frame's bytes and
 // size always stay in sync (the plain buffer is left untouched).
 compressed_dict.reset(new uint8_t[compressed_bound]);
 size_t dict_size = ZSTD_compress_usingCDict(
 cctx, compressed_dict.get(), compressed_bound, raw_ptr, raw_size,
 cdict);
 if (!ZSTD_isError(dict_size) &&
 (ZSTD_isError(compressed_size) || dict_size < compressed_size)) {
 compressed_size = dict_size;
 best_ptr = reinterpret_cast<char*>(compressed_dict.get());
 }
 }
 if (!ZSTD_isError(compressed_size) && compressed_size < raw_size) {
 cache_ptr = reinterpret_cast<char*>(compressed.get());
 cache_ptr = best_ptr;
 cache_size = static_cast<uint32_t>(compressed_size);
 }
 }
Expand Down
Binary file addedsrc/compile_cache_zstd.dict

View file


Open in desktop


Binary file not shown.


80 changes: 80 additions & 0 deletions
test/parallel/test-compile-cache-success.js

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -64,3 +64,83 @@ const path = require('path');
 }
 });
}

// Exercise the dictionary-compressed path (added on top of #63861) for many
// small modules, which is where the embedded dictionary helps most. We write
// the cache, then read it back and assert every entry is accepted - this
// proves each dict-compressed frame decompresses to exactly the bytes that
// were persisted.
{
 tmpdir.refresh();
 const dir = tmpdir.resolve('.compile_cache_dir');

 // Generate a handful of small modules so the dictionary path is exercised.
 const count = 8;
 const modules = [];
 for (let i = 0; i < count; i++) {
 const file = tmpdir.resolve(`mod-${i}.js`);
 fs.writeFileSync(
 file,
 `'use strict';\n` +
 `module.exports = function value${i}(a, b) {\n` +
 ` const sum = a + b + ${i};\n` +
 ` return { id: ${i}, sum, label: 'module-${i}' };\n` +
 `};\n`);
 modules.push(file);
 }
 const reqCode = modules.map((m) => `require(${JSON.stringify(m)});`).join('');

 // First run writes the cache for every module.
 spawnSyncAndAssert(
 process.execPath,
 ['-e', reqCode],
 {
 env: {
 ...process.env,
 NODE_DEBUG_NATIVE: 'COMPILE_CACHE',
 NODE_COMPILE_CACHE: dir
 },
 cwd: tmpdir.path
 },
 {
 stderr(output) {
 for (const m of modules) {
 const name = path.basename(m).replace(/[.]/g, '\\.');
 assert.match(output, new RegExp(`writing cache for .*${name}.*success`));
 }
 return true;
 }
 });

 const cacheDirs = fs.readdirSync(dir);
 assert.strictEqual(cacheDirs.length, 1);
 // At least one entry per module (the `-e` runner is cached too).
 const entries = fs.readdirSync(path.join(dir, cacheDirs[0]));
 assert(entries.length >= count, `expected >= ${count} entries, got ${entries.length}`);

 // Second run reads every cached entry back; "was accepted" only happens when
 // the decompressed bytes match the freshly produced in-memory cache, so this
 // is a full roundtrip check of the dictionary-compressed entries.
 spawnSyncAndAssert(
 process.execPath,
 ['-e', reqCode],
 {
 env: {
 ...process.env,
 NODE_DEBUG_NATIVE: 'COMPILE_CACHE',
 NODE_COMPILE_CACHE: dir
 },
 cwd: tmpdir.path
 },
 {
 stderr(output) {
 for (const m of modules) {
 const name = path.basename(m).replace(/[.]/g, '\\.');
 assert.match(
 output,
 new RegExp(`cache for .*${name} was accepted, keeping the in-memory entry`));
 }
 return true;
 }
 });
}

37 changes: 37 additions & 0 deletions
tools/generate_compile_cache_dict.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,37 @@
#!/usr/bin/env python
"""Generate compile_cache_zstd_dict.h from a trained zstd .dict file.

Invoked by the GYP action in node.gyp at build time. Only the small binary
.dict (src/compile_cache_zstd.dict) is checked into the repository; the C
array it produces is generated into SHARED_INTERMEDIATE_DIR.
"""
import os
import sys


def main(dict_path, out_path):
 with open(dict_path, 'rb') as f:
 data = f.read()

 lines = [
 '// Generated by tools/generate_compile_cache_dict.py',
 '// from %s' % os.path.basename(dict_path),
 '// The .dict file is the source of truth; do not edit by hand.',
 '',
 'static const unsigned char kCompileCacheZstdDict[] = {',
 ]
 for i in range(0, len(data), 12):
 chunk = data[i:i + 12]
 lines.append(' %s,' % ', '.join('0x%02x' % b for b in chunk))
 lines.append('};')
 lines.append('static const size_t kCompileCacheZstdDictSize = %d;' %
 len(data))

 with open(out_path, 'w') as f:
 f.write('\n'.join(lines) + '\n')


if __name__ == '__main__':
 if len(sys.argv) != 3:
 sys.exit('Usage: %s <input.dict> <output.h>' % sys.argv[0])
 main(sys.argv[1], sys.argv[2])

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Remove or un-stick sticky/fixed headers that block content\n(function() {\n function unstick() {\n document.querySelectorAll('header, nav, [role=\"banner\"], .header, .navbar, .sticky, .fixed-top, [style*=\"position: fixed\"], [style*=\"position:sticky\"]').forEach(function(el) {\n if (el.style.position === 'fixed' || el.style.position === 'sticky' || \n getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {\n el.style.position = 'static';\n el.style.top = 'auto';\n el.style.zIndex = 'auto';\n }\n });\n }\n \n unstick();\n \n var observer = new MutationObserver(unstick);\n observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });\n})();", "Kill Sticky Headers");
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
src: embed zstd dictionary for further compile cache size wins#16

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

anonrig
merged 1 commit into

from

Jun 12, 2026
 Merged


src: embed zstd dictionary for further compile cache size wins
#16
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


72 changes: 72 additions & 0 deletions
benchmark/misc/compile-cache-timing.js

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,72 @@
'use strict';

// Startup benchmark for the compile cache (including the zstd dictionary).
// Compares no-cache / cold-cache / warm-cache for two workloads:
// big - one large module (the typescript.js fixture)
// many - many small modules (generated here, side-effect-free)
// The modules are generated into a temp dir so the benchmark is self-contained
// and reproducible, and never executes unrelated code.

const common = require('../common.js');
const { spawnSync } = require('child_process');
const fs = require('fs');
const os = require('os');
const path = require('path');

const bench = common.createBenchmark(main, {
 workload: ['big', 'many'],
 cache: ['none', 'cold', 'warm'],
 n: [30],
});

const BIG = path.resolve(__dirname, '../../test/fixtures/snapshot/typescript.js');

// Generate `count` small, side-effect-free modules and return the require()
// code that loads them all in one child.
function makeManyModules(dir, count) {
 fs.mkdirSync(dir, { recursive: true });
 const reqs = [];
 for (let i = 0; i < count; i++) {
 const file = path.join(dir, `mod-${i}.js`);
 fs.writeFileSync(
 file,
 `'use strict';\n` +
 `module.exports = function value${i}(a, b) {\n` +
 ` const sum = a + b + ${i};\n` +
 ` return { id: ${i}, sum, label: 'module-${i}' };\n` +
 `};\n`);
 reqs.push(`require(${JSON.stringify(file)});`);
 }
 return reqs.join('');
}

function run(cmd, args, cacheDir) {
 const env = { ...process.env };
 if (cacheDir) env.NODE_COMPILE_CACHE = cacheDir;
 else delete env.NODE_COMPILE_CACHE;
 const child = spawnSync(cmd, args, { env, stdio: 'ignore' });
 if (child.error) throw child.error;
}

function main({ n, workload, cache }) {
 const cmd = process.execPath || process.argv[0];
 const tmp = fs.mkdtempSync(path.join(os.tmpdir(), 'cc-bench-'));
 const args = workload === 'big' ?
 [BIG] :
 ['-e', makeManyModules(path.join(tmp, 'mods'), 120)];
 const cacheDir = cache === 'none' ? null : path.join(tmp, 'cache');

 try {
 if (cache === 'warm') run(cmd, args, cacheDir); // populate once
 bench.start();
 for (let i = 0; i < n; i++) {
 if (cache === 'cold' && cacheDir) {
 fs.rmSync(cacheDir, { recursive: true, force: true });
 }
 run(cmd, args, cacheDir);
 }
 bench.end(n);
 } finally {
 fs.rmSync(tmp, { recursive: true, force: true });
 }
}

17 changes: 17 additions & 0 deletions
node.gyp

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -1110,6 +1110,22 @@
 '<@(linked_module_files)',
 ],
 },
 {
 'action_name': 'generate_compile_cache_zstd_dict',
 'inputs': [
 'src/compile_cache_zstd.dict',
 'tools/generate_compile_cache_dict.py',
 ],
 'outputs': [
 '<(SHARED_INTERMEDIATE_DIR)/compile_cache_zstd_dict.h',
 ],
 'action': [
 '<(python)',
 'tools/generate_compile_cache_dict.py',
 'src/compile_cache_zstd.dict',
 '<@(_outputs)',
 ],
 },
 ],
 }, # node_base
 {
Expand All@@ -1123,6 +1139,7 @@
 'src',
 'deps/v8/include',
 'deps/uv/include',
 '<(SHARED_INTERMEDIATE_DIR)', # for compile_cache_zstd_dict.h etc.
 ],

 'dependencies': [
Expand Down

72 changes: 68 additions & 4 deletions
src/compile_cache.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -11,6 +11,10 @@
#include "util.h"
#include "zlib.h"
#include "zstd.h"
// kCompileCacheZstdDict + kCompileCacheZstdDictSize come from the header
// generated at build time by the GYP action (from src/compile_cache_zstd.dict).
// The include directory (SHARED_INTERMEDIATE_DIR) is added by node.gyp.
#include "compile_cache_zstd_dict.h"

#ifdef NODE_IMPLEMENTS_POSIX_CREDENTIALS
#include <unistd.h> // getuid
Expand All@@ -28,6 +32,29 @@ using v8::ScriptCompiler;
using v8::String;

namespace {
// The compile-cache zstd dictionary is immutable and embedded in the binary,
// so the prepared CDict/DDict are created once and shared across all handlers
// (and all Environments/Workers) instead of per handler. They live for the
// lifetime of the process. Returns nullptr if preparation fails, in which
// case callers fall back to plain (dictionary-less) zstd.
ZSTD_CDict* GetCompileCacheCDict() {
 static ZSTD_CDict* cdict =
 ZSTD_createCDict(kCompileCacheZstdDict, kCompileCacheZstdDictSize, 1);
 return cdict;
}

ZSTD_DDict* GetCompileCacheDDict() {
 static ZSTD_DDict* ddict =
 ZSTD_createDDict(kCompileCacheZstdDict, kCompileCacheZstdDictSize);
 return ddict;
}

// The dictionary only helps small/medium caches; for larger inputs zstd's own
// adaptive model dominates and the dictionary never wins, so we skip the
// (otherwise wasted) second compression above this raw size. Decompression is
// unaffected: a single DDict decodes both dict-assisted and plain frames.
constexpr uint32_t kCompileCacheDictMaxRawSize = 256 * 1024;

std::string Uint32ToHex(uint32_t crc) {
 std::string str;
 str.reserve(8);
Expand DownExpand Up@@ -266,10 +293,20 @@ void CompileCacheHandler::ReadCacheFile(CompileCacheEntry* entry) {
 Debug("failed to create zstd context\n");
 return;
 }
 // Decompress directly into the buffer handed to V8.
 // Decompress directly into the buffer handed to V8. The embedded
 // dictionary is referenced via a shared, prepared DDict; plain frames
 // (which carry no dictID) decompress correctly with it as well.
 std::unique_ptr<uint8_t[]> raw_data(new uint8_t[raw_size]);
 size_t decompressed_size = ZSTD_decompressDCtx(
 zstd_dctx_, raw_data.get(), raw_size, disk_data.get(), cache_size);
 ZSTD_DDict* ddict = GetCompileCacheDDict();
 size_t decompressed_size;
 if (ddict != nullptr) {
 decompressed_size = ZSTD_decompress_usingDDict(
 zstd_dctx_, raw_data.get(), raw_size, disk_data.get(), cache_size,
 ddict);
 } else {
 decompressed_size = ZSTD_decompressDCtx(
 zstd_dctx_, raw_data.get(), raw_size, disk_data.get(), cache_size);
 }
 if (ZSTD_isError(decompressed_size)) {
 Debug("decompression failed: %s\n", ZSTD_getErrorName(decompressed_size));
 return;
Expand DownExpand Up@@ -508,16 +545,43 @@ void CompileCacheHandler::Persist() {
 // shutdown and should add as little overhead as possible. If the data
 // is not compressible, store it uncompressed, which is indicated by
 // the cache size being equal to the uncompressed size in the headers.
 //
 // We also try the embedded trained dictionary and keep whichever frame is
 // smaller (still subject to the "only store if < raw" policy). The
 // dictionary mainly helps the small/medium caches that dominate real
 // compile cache usage; for inputs where plain zstd already wins we keep
 // the plain frame.
 char* cache_ptr = raw_ptr;
 uint32_t cache_size = raw_size;
 std::unique_ptr<uint8_t[]> compressed;
 std::unique_ptr<uint8_t[]> compressed_dict;
 if (cctx != nullptr || (cctx = ZSTD_createCCtx()) != nullptr) {
 size_t compressed_bound = ZSTD_compressBound(raw_size);
 compressed.reset(new uint8_t[compressed_bound]);
 size_t compressed_size = ZSTD_compressCCtx(
 cctx, compressed.get(), compressed_bound, raw_ptr, raw_size, 1);
 char* best_ptr = reinterpret_cast<char*>(compressed.get());
 // Only attempt the dictionary for small/medium entries (see
 // kCompileCacheDictMaxRawSize); for large blobs it never wins and the
 // extra compression would be wasted work.
 ZSTD_CDict* cdict = raw_size <= kCompileCacheDictMaxRawSize
 ? GetCompileCacheCDict()
 : nullptr;
 if (cdict != nullptr) {
 // Compress into a separate buffer so the selected frame's bytes and
 // size always stay in sync (the plain buffer is left untouched).
 compressed_dict.reset(new uint8_t[compressed_bound]);
 size_t dict_size = ZSTD_compress_usingCDict(
 cctx, compressed_dict.get(), compressed_bound, raw_ptr, raw_size,
 cdict);
 if (!ZSTD_isError(dict_size) &&
 (ZSTD_isError(compressed_size) || dict_size < compressed_size)) {
 compressed_size = dict_size;
 best_ptr = reinterpret_cast<char*>(compressed_dict.get());
 }
 }
 if (!ZSTD_isError(compressed_size) && compressed_size < raw_size) {
 cache_ptr = reinterpret_cast<char*>(compressed.get());
 cache_ptr = best_ptr;
 cache_size = static_cast<uint32_t>(compressed_size);
 }
 }
Expand Down
Binary file addedsrc/compile_cache_zstd.dict

View file


Open in desktop


Binary file not shown.


80 changes: 80 additions & 0 deletions
test/parallel/test-compile-cache-success.js

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -64,3 +64,83 @@ const path = require('path');
 }
 });
}

// Exercise the dictionary-compressed path (added on top of #63861) for many
// small modules, which is where the embedded dictionary helps most. We write
// the cache, then read it back and assert every entry is accepted - this
// proves each dict-compressed frame decompresses to exactly the bytes that
// were persisted.
{
 tmpdir.refresh();
 const dir = tmpdir.resolve('.compile_cache_dir');

 // Generate a handful of small modules so the dictionary path is exercised.
 const count = 8;
 const modules = [];
 for (let i = 0; i < count; i++) {
 const file = tmpdir.resolve(`mod-${i}.js`);
 fs.writeFileSync(
 file,
 `'use strict';\n` +
 `module.exports = function value${i}(a, b) {\n` +
 ` const sum = a + b + ${i};\n` +
 ` return { id: ${i}, sum, label: 'module-${i}' };\n` +
 `};\n`);
 modules.push(file);
 }
 const reqCode = modules.map((m) => `require(${JSON.stringify(m)});`).join('');

 // First run writes the cache for every module.
 spawnSyncAndAssert(
 process.execPath,
 ['-e', reqCode],
 {
 env: {
 ...process.env,
 NODE_DEBUG_NATIVE: 'COMPILE_CACHE',
 NODE_COMPILE_CACHE: dir
 },
 cwd: tmpdir.path
 },
 {
 stderr(output) {
 for (const m of modules) {
 const name = path.basename(m).replace(/[.]/g, '\\.');
 assert.match(output, new RegExp(`writing cache for .*${name}.*success`));
 }
 return true;
 }
 });

 const cacheDirs = fs.readdirSync(dir);
 assert.strictEqual(cacheDirs.length, 1);
 // At least one entry per module (the `-e` runner is cached too).
 const entries = fs.readdirSync(path.join(dir, cacheDirs[0]));
 assert(entries.length >= count, `expected >= ${count} entries, got ${entries.length}`);

 // Second run reads every cached entry back; "was accepted" only happens when
 // the decompressed bytes match the freshly produced in-memory cache, so this
 // is a full roundtrip check of the dictionary-compressed entries.
 spawnSyncAndAssert(
 process.execPath,
 ['-e', reqCode],
 {
 env: {
 ...process.env,
 NODE_DEBUG_NATIVE: 'COMPILE_CACHE',
 NODE_COMPILE_CACHE: dir
 },
 cwd: tmpdir.path
 },
 {
 stderr(output) {
 for (const m of modules) {
 const name = path.basename(m).replace(/[.]/g, '\\.');
 assert.match(
 output,
 new RegExp(`cache for .*${name} was accepted, keeping the in-memory entry`));
 }
 return true;
 }
 });
}

37 changes: 37 additions & 0 deletions
tools/generate_compile_cache_dict.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,37 @@
#!/usr/bin/env python
"""Generate compile_cache_zstd_dict.h from a trained zstd .dict file.

Invoked by the GYP action in node.gyp at build time. Only the small binary
.dict (src/compile_cache_zstd.dict) is checked into the repository; the C
array it produces is generated into SHARED_INTERMEDIATE_DIR.
"""
import os
import sys


def main(dict_path, out_path):
 with open(dict_path, 'rb') as f:
 data = f.read()

 lines = [
 '// Generated by tools/generate_compile_cache_dict.py',
 '// from %s' % os.path.basename(dict_path),
 '// The .dict file is the source of truth; do not edit by hand.',
 '',
 'static const unsigned char kCompileCacheZstdDict[] = {',
 ]
 for i in range(0, len(data), 12):
 chunk = data[i:i + 12]
 lines.append(' %s,' % ', '.join('0x%02x' % b for b in chunk))
 lines.append('};')
 lines.append('static const size_t kCompileCacheZstdDictSize = %d;' %
 len(data))

 with open(out_path, 'w') as f:
 f.write('\n'.join(lines) + '\n')


if __name__ == '__main__':
 if len(sys.argv) != 3:
 sys.exit('Usage: %s <input.dict> <output.h>' % sys.argv[0])
 main(sys.argv[1], sys.argv[2])

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Universal Dark Mode - works on any site\n(function() {\n var enabled = true;\n \n function applyDarkMode() {\n if (!enabled) return;\n \n // Create style element if it doesn't exist\n var style = document.getElementById('universal-dark-mode-style');\n if (!style) {\n style = document.createElement('style');\n style.id = 'universal-dark-mode-style';\n document.head.appendChild(style);\n }\n \n // Dark mode CSS - inverts colors but preserves images/video\n style.textContent = '\n /* Invert everything except media */\n html {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #1a1a2e !important;\n }\n \n /* Restore images, videos, iframes, canvas */\n img, video, iframe, canvas, svg, picture, [style*=\"background-image\"] {\n filter: invert(1) hue-rotate(180deg) !important;\n }\n \n /* Preserve specific elements that should not be inverted */\n .no-dark-mode, .no-dark-mode *,\n [data-theme=\"light\"], [data-theme=\"light\"],\n .ace_editor, .ace_editor *,\n .CodeMirror, .CodeMirror *,\n .monaco-editor, .monaco-editor *,\n .markdown-body pre, .markdown-body pre *,\n .highlight, .highlight *,\n pre code, pre code * {\n filter: none !important;\n }\n \n /* Fix common UI elements */\n .modal, .popup, .dropdown-menu, .tooltip, .popover {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #2d2d44 !important;\n border-color: #444 !important;\n }\n \n /* Scrollbars */\n ::-webkit-scrollbar { background: #1a1a2e !important; }\n ::-webkit-scrollbar-thumb { background: #444 !important; }\n ::-webkit-scrollbar-thumb:hover { background: #555 !important; }\n \n /* Selection */\n ::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ';\n }\n \n function removeDarkMode() {\n var style = document.getElementById('universal-dark-mode-style');\n if (style) style.remove();\n }\n \n // Toggle with Alt+Shift+D\n document.addEventListener('keydown', function(e) {\n if (e.altKey && e.shiftKey && e.key === 'D') {\n e.preventDefault();\n enabled = !enabled;\n if (enabled) {\n applyDarkMode();\n console.log('[Universal Dark Mode] Enabled');\n } else {\n removeDarkMode();\n console.log('[Universal Dark Mode] Disabled');\n }\n }\n });\n \n // Apply on load\n applyDarkMode();\n \n // Re-apply on dynamic content\n var observer = new MutationObserver(function(mutations) {\n if (enabled && !document.getElementById('universal-dark-mode-style')) {\n applyDarkMode();\n }\n });\n observer.observe(document.head, { childList: true });\n \n console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');\n})();", "Universal Dark Mode");
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();

Skip to content
src: embed zstd dictionary for further compile cache size wins#16

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

anonrig
merged 1 commit into

from

Jun 12, 2026
 Merged


src: embed zstd dictionary for further compile cache size wins
#16
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


72 changes: 72 additions & 0 deletions
benchmark/misc/compile-cache-timing.js

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,72 @@
'use strict';

// Startup benchmark for the compile cache (including the zstd dictionary).
// Compares no-cache / cold-cache / warm-cache for two workloads:
// big - one large module (the typescript.js fixture)
// many - many small modules (generated here, side-effect-free)
// The modules are generated into a temp dir so the benchmark is self-contained
// and reproducible, and never executes unrelated code.

const common = require('../common.js');
const { spawnSync } = require('child_process');
const fs = require('fs');
const os = require('os');
const path = require('path');

const bench = common.createBenchmark(main, {
 workload: ['big', 'many'],
 cache: ['none', 'cold', 'warm'],
 n: [30],
});

const BIG = path.resolve(__dirname, '../../test/fixtures/snapshot/typescript.js');

// Generate `count` small, side-effect-free modules and return the require()
// code that loads them all in one child.
function makeManyModules(dir, count) {
 fs.mkdirSync(dir, { recursive: true });
 const reqs = [];
 for (let i = 0; i < count; i++) {
 const file = path.join(dir, `mod-${i}.js`);
 fs.writeFileSync(
 file,
 `'use strict';\n` +
 `module.exports = function value${i}(a, b) {\n` +
 ` const sum = a + b + ${i};\n` +
 ` return { id: ${i}, sum, label: 'module-${i}' };\n` +
 `};\n`);
 reqs.push(`require(${JSON.stringify(file)});`);
 }
 return reqs.join('');
}

function run(cmd, args, cacheDir) {
 const env = { ...process.env };
 if (cacheDir) env.NODE_COMPILE_CACHE = cacheDir;
 else delete env.NODE_COMPILE_CACHE;
 const child = spawnSync(cmd, args, { env, stdio: 'ignore' });
 if (child.error) throw child.error;
}

function main({ n, workload, cache }) {
 const cmd = process.execPath || process.argv[0];
 const tmp = fs.mkdtempSync(path.join(os.tmpdir(), 'cc-bench-'));
 const args = workload === 'big' ?
 [BIG] :
 ['-e', makeManyModules(path.join(tmp, 'mods'), 120)];
 const cacheDir = cache === 'none' ? null : path.join(tmp, 'cache');

 try {
 if (cache === 'warm') run(cmd, args, cacheDir); // populate once
 bench.start();
 for (let i = 0; i < n; i++) {
 if (cache === 'cold' && cacheDir) {
 fs.rmSync(cacheDir, { recursive: true, force: true });
 }
 run(cmd, args, cacheDir);
 }
 bench.end(n);
 } finally {
 fs.rmSync(tmp, { recursive: true, force: true });
 }
}

17 changes: 17 additions & 0 deletions
node.gyp

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -1110,6 +1110,22 @@
 '<@(linked_module_files)',
 ],
 },
 {
 'action_name': 'generate_compile_cache_zstd_dict',
 'inputs': [
 'src/compile_cache_zstd.dict',
 'tools/generate_compile_cache_dict.py',
 ],
 'outputs': [
 '<(SHARED_INTERMEDIATE_DIR)/compile_cache_zstd_dict.h',
 ],
 'action': [
 '<(python)',
 'tools/generate_compile_cache_dict.py',
 'src/compile_cache_zstd.dict',
 '<@(_outputs)',
 ],
 },
 ],
 }, # node_base
 {
Expand All@@ -1123,6 +1139,7 @@
 'src',
 'deps/v8/include',
 'deps/uv/include',
 '<(SHARED_INTERMEDIATE_DIR)', # for compile_cache_zstd_dict.h etc.
 ],

 'dependencies': [
Expand Down

72 changes: 68 additions & 4 deletions
src/compile_cache.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -11,6 +11,10 @@
#include "util.h"
#include "zlib.h"
#include "zstd.h"
// kCompileCacheZstdDict + kCompileCacheZstdDictSize come from the header
// generated at build time by the GYP action (from src/compile_cache_zstd.dict).
// The include directory (SHARED_INTERMEDIATE_DIR) is added by node.gyp.
#include "compile_cache_zstd_dict.h"

#ifdef NODE_IMPLEMENTS_POSIX_CREDENTIALS
#include <unistd.h> // getuid
Expand All@@ -28,6 +32,29 @@ using v8::ScriptCompiler;
using v8::String;

namespace {
// The compile-cache zstd dictionary is immutable and embedded in the binary,
// so the prepared CDict/DDict are created once and shared across all handlers
// (and all Environments/Workers) instead of per handler. They live for the
// lifetime of the process. Returns nullptr if preparation fails, in which
// case callers fall back to plain (dictionary-less) zstd.
ZSTD_CDict* GetCompileCacheCDict() {
 static ZSTD_CDict* cdict =
 ZSTD_createCDict(kCompileCacheZstdDict, kCompileCacheZstdDictSize, 1);
 return cdict;
}

ZSTD_DDict* GetCompileCacheDDict() {
 static ZSTD_DDict* ddict =
 ZSTD_createDDict(kCompileCacheZstdDict, kCompileCacheZstdDictSize);
 return ddict;
}

// The dictionary only helps small/medium caches; for larger inputs zstd's own
// adaptive model dominates and the dictionary never wins, so we skip the
// (otherwise wasted) second compression above this raw size. Decompression is
// unaffected: a single DDict decodes both dict-assisted and plain frames.
constexpr uint32_t kCompileCacheDictMaxRawSize = 256 * 1024;

std::string Uint32ToHex(uint32_t crc) {
 std::string str;
 str.reserve(8);
Expand DownExpand Up@@ -266,10 +293,20 @@ void CompileCacheHandler::ReadCacheFile(CompileCacheEntry* entry) {
 Debug("failed to create zstd context\n");
 return;
 }
 // Decompress directly into the buffer handed to V8.
 // Decompress directly into the buffer handed to V8. The embedded
 // dictionary is referenced via a shared, prepared DDict; plain frames
 // (which carry no dictID) decompress correctly with it as well.
 std::unique_ptr<uint8_t[]> raw_data(new uint8_t[raw_size]);
 size_t decompressed_size = ZSTD_decompressDCtx(
 zstd_dctx_, raw_data.get(), raw_size, disk_data.get(), cache_size);
 ZSTD_DDict* ddict = GetCompileCacheDDict();
 size_t decompressed_size;
 if (ddict != nullptr) {
 decompressed_size = ZSTD_decompress_usingDDict(
 zstd_dctx_, raw_data.get(), raw_size, disk_data.get(), cache_size,
 ddict);
 } else {
 decompressed_size = ZSTD_decompressDCtx(
 zstd_dctx_, raw_data.get(), raw_size, disk_data.get(), cache_size);
 }
 if (ZSTD_isError(decompressed_size)) {
 Debug("decompression failed: %s\n", ZSTD_getErrorName(decompressed_size));
 return;
Expand DownExpand Up@@ -508,16 +545,43 @@ void CompileCacheHandler::Persist() {
 // shutdown and should add as little overhead as possible. If the data
 // is not compressible, store it uncompressed, which is indicated by
 // the cache size being equal to the uncompressed size in the headers.
 //
 // We also try the embedded trained dictionary and keep whichever frame is
 // smaller (still subject to the "only store if < raw" policy). The
 // dictionary mainly helps the small/medium caches that dominate real
 // compile cache usage; for inputs where plain zstd already wins we keep
 // the plain frame.
 char* cache_ptr = raw_ptr;
 uint32_t cache_size = raw_size;
 std::unique_ptr<uint8_t[]> compressed;
 std::unique_ptr<uint8_t[]> compressed_dict;
 if (cctx != nullptr || (cctx = ZSTD_createCCtx()) != nullptr) {
 size_t compressed_bound = ZSTD_compressBound(raw_size);
 compressed.reset(new uint8_t[compressed_bound]);
 size_t compressed_size = ZSTD_compressCCtx(
 cctx, compressed.get(), compressed_bound, raw_ptr, raw_size, 1);
 char* best_ptr = reinterpret_cast<char*>(compressed.get());
 // Only attempt the dictionary for small/medium entries (see
 // kCompileCacheDictMaxRawSize); for large blobs it never wins and the
 // extra compression would be wasted work.
 ZSTD_CDict* cdict = raw_size <= kCompileCacheDictMaxRawSize
 ? GetCompileCacheCDict()
 : nullptr;
 if (cdict != nullptr) {
 // Compress into a separate buffer so the selected frame's bytes and
 // size always stay in sync (the plain buffer is left untouched).
 compressed_dict.reset(new uint8_t[compressed_bound]);
 size_t dict_size = ZSTD_compress_usingCDict(
 cctx, compressed_dict.get(), compressed_bound, raw_ptr, raw_size,
 cdict);
 if (!ZSTD_isError(dict_size) &&
 (ZSTD_isError(compressed_size) || dict_size < compressed_size)) {
 compressed_size = dict_size;
 best_ptr = reinterpret_cast<char*>(compressed_dict.get());
 }
 }
 if (!ZSTD_isError(compressed_size) && compressed_size < raw_size) {
 cache_ptr = reinterpret_cast<char*>(compressed.get());
 cache_ptr = best_ptr;
 cache_size = static_cast<uint32_t>(compressed_size);
 }
 }
Expand Down
Binary file addedsrc/compile_cache_zstd.dict

View file


Open in desktop


Binary file not shown.


80 changes: 80 additions & 0 deletions
test/parallel/test-compile-cache-success.js

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -64,3 +64,83 @@ const path = require('path');
 }
 });
}

// Exercise the dictionary-compressed path (added on top of #63861) for many
// small modules, which is where the embedded dictionary helps most. We write
// the cache, then read it back and assert every entry is accepted - this
// proves each dict-compressed frame decompresses to exactly the bytes that
// were persisted.
{
 tmpdir.refresh();
 const dir = tmpdir.resolve('.compile_cache_dir');

 // Generate a handful of small modules so the dictionary path is exercised.
 const count = 8;
 const modules = [];
 for (let i = 0; i < count; i++) {
 const file = tmpdir.resolve(`mod-${i}.js`);
 fs.writeFileSync(
 file,
 `'use strict';\n` +
 `module.exports = function value${i}(a, b) {\n` +
 ` const sum = a + b + ${i};\n` +
 ` return { id: ${i}, sum, label: 'module-${i}' };\n` +
 `};\n`);
 modules.push(file);
 }
 const reqCode = modules.map((m) => `require(${JSON.stringify(m)});`).join('');

 // First run writes the cache for every module.
 spawnSyncAndAssert(
 process.execPath,
 ['-e', reqCode],
 {
 env: {
 ...process.env,
 NODE_DEBUG_NATIVE: 'COMPILE_CACHE',
 NODE_COMPILE_CACHE: dir
 },
 cwd: tmpdir.path
 },
 {
 stderr(output) {
 for (const m of modules) {
 const name = path.basename(m).replace(/[.]/g, '\\.');
 assert.match(output, new RegExp(`writing cache for .*${name}.*success`));
 }
 return true;
 }
 });

 const cacheDirs = fs.readdirSync(dir);
 assert.strictEqual(cacheDirs.length, 1);
 // At least one entry per module (the `-e` runner is cached too).
 const entries = fs.readdirSync(path.join(dir, cacheDirs[0]));
 assert(entries.length >= count, `expected >= ${count} entries, got ${entries.length}`);

 // Second run reads every cached entry back; "was accepted" only happens when
 // the decompressed bytes match the freshly produced in-memory cache, so this
 // is a full roundtrip check of the dictionary-compressed entries.
 spawnSyncAndAssert(
 process.execPath,
 ['-e', reqCode],
 {
 env: {
 ...process.env,
 NODE_DEBUG_NATIVE: 'COMPILE_CACHE',
 NODE_COMPILE_CACHE: dir
 },
 cwd: tmpdir.path
 },
 {
 stderr(output) {
 for (const m of modules) {
 const name = path.basename(m).replace(/[.]/g, '\\.');
 assert.match(
 output,
 new RegExp(`cache for .*${name} was accepted, keeping the in-memory entry`));
 }
 return true;
 }
 });
}

37 changes: 37 additions & 0 deletions
tools/generate_compile_cache_dict.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,37 @@
#!/usr/bin/env python
"""Generate compile_cache_zstd_dict.h from a trained zstd .dict file.

Invoked by the GYP action in node.gyp at build time. Only the small binary
.dict (src/compile_cache_zstd.dict) is checked into the repository; the C
array it produces is generated into SHARED_INTERMEDIATE_DIR.
"""
import os
import sys


def main(dict_path, out_path):
 with open(dict_path, 'rb') as f:
 data = f.read()

 lines = [
 '// Generated by tools/generate_compile_cache_dict.py',
 '// from %s' % os.path.basename(dict_path),
 '// The .dict file is the source of truth; do not edit by hand.',
 '',
 'static const unsigned char kCompileCacheZstdDict[] = {',
 ]
 for i in range(0, len(data), 12):
 chunk = data[i:i + 12]
 lines.append(' %s,' % ', '.join('0x%02x' % b for b in chunk))
 lines.append('};')
 lines.append('static const size_t kCompileCacheZstdDictSize = %d;' %
 len(data))

 with open(out_path, 'w') as f:
 f.write('\n'.join(lines) + '\n')


if __name__ == '__main__':
 if len(sys.argv) != 3:
 sys.exit('Usage: %s <input.dict> <output.h>' % sys.argv[0])
 main(sys.argv[1], sys.argv[2])