Add support for Zstd-based compression in LevelDB.

This change implements support for Zstd-based compression in LevelDB. Building
up from the Snappy compression (which has been supported since inception), this
change adds Zstd as an alternate compression algorithm.

We are implementing this to provide alternative options for users who might
have different performance and efficiency requirements. For instance, the
Zstandard website (https://facebook.github.io/zstd/) claims that the Zstd
algorithm can achieve around 30% higher compression ratios than Snappy, with
relatively smaller (~10%) slowdowns in de/compression speeds.

Benchmarking results:

$ blaze-bin/third_party/leveldb/db_bench
LevelDB:    version 1.23
Date:       Thu Feb  2 18:50:06 2023
CPU:        56 * Intel(R) Xeon(R) CPU E5-2690 v4 @ 2.60GHz
CPUCache:   35840 KB
Keys:       16 bytes each
Values:     100 bytes each (50 bytes after compression)
Entries:    1000000
RawSize:    110.6 MB (estimated)
FileSize:   62.9 MB (estimated)
------------------------------------------------
fillseq      :       2.613 micros/op;   42.3 MB/s
fillsync     :    3924.432 micros/op;    0.0 MB/s (1000 ops)
fillrandom   :       3.609 micros/op;   30.7 MB/s
overwrite    :       4.508 micros/op;   24.5 MB/s
readrandom   :       6.136 micros/op; (864322 of 1000000 found)
readrandom   :       5.446 micros/op; (864083 of 1000000 found)
readseq      :       0.180 micros/op;  613.3 MB/s
readreverse  :       0.321 micros/op;  344.7 MB/s
compact      :  827043.000 micros/op;
readrandom   :       4.603 micros/op; (864105 of 1000000 found)
readseq      :       0.169 micros/op;  656.3 MB/s
readreverse  :       0.315 micros/op;  350.8 MB/s
fill100K     :     854.009 micros/op;  111.7 MB/s (1000 ops)
crc32c       :       1.227 micros/op; 3184.0 MB/s (4K per op)
snappycomp   :       3.610 micros/op; 1081.9 MB/s (output: 55.2%)
snappyuncomp :       0.691 micros/op; 5656.3 MB/s
zstdcomp     :      15.731 micros/op;  248.3 MB/s (output: 44.1%)
zstduncomp   :       4.218 micros/op;  926.2 MB/s
PiperOrigin-RevId: 509957778

port/port_config.h.in

@@ -30,4 +30,9 @@
 #cmakedefine01 HAVE_SNAPPY
 #endif  // !defined(HAVE_SNAPPY)
 
-#endif  // STORAGE_LEVELDB_PORT_PORT_CONFIG_H_
+// Define to 1 if you have Zstd.
+#if !defined(HAVE_Zstd)
+#cmakedefine01 HAVE_ZSTD
+#endif  // !defined(HAVE_ZSTD)
+
+#endif  // STORAGE_LEVELDB_PORT_PORT_CONFIG_H_

port/port_example.h

@@ -72,7 +72,7 @@ bool Snappy_GetUncompressedLength(const char* input, size_t length,
                                   size_t* result);
 
 // Attempt to snappy uncompress input[0,input_length-1] into *output.
-// Returns true if successful, false if the input is invalid lightweight
+// Returns true if successful, false if the input is invalid snappy
 // compressed data.
 //
 // REQUIRES: at least the first "n" bytes of output[] must be writable
@@ -81,6 +81,25 @@ bool Snappy_GetUncompressedLength(const char* input, size_t length,
 bool Snappy_Uncompress(const char* input_data, size_t input_length,
                        char* output);
 
+// Store the zstd compression of "input[0,input_length-1]" in *output.
+// Returns false if zstd is not supported by this port.
+bool Zstd_Compress(const char* input, size_t input_length, std::string* output);
+
+// If input[0,input_length-1] looks like a valid zstd compressed
+// buffer, store the size of the uncompressed data in *result and
+// return true.  Else return false.
+bool Zstd_GetUncompressedLength(const char* input, size_t length,
+                                size_t* result);
+
+// Attempt to zstd uncompress input[0,input_length-1] into *output.
+// Returns true if successful, false if the input is invalid zstd
+// compressed data.
+//
+// REQUIRES: at least the first "n" bytes of output[] must be writable
+// where "n" is the result of a successful call to
+// Zstd_GetUncompressedLength.
+bool Zstd_Uncompress(const char* input_data, size_t input_length, char* output);
+
 // ------------------ Miscellaneous -------------------
 
 // If heap profiling is not supported, returns false.

port/port_stdcxx.h

@@ -28,6 +28,9 @@
 #if HAVE_SNAPPY
 #include <snappy.h>
 #endif  // HAVE_SNAPPY
+#if HAVE_ZSTD
+#include <zstd.h>
+#endif  // HAVE_ZSTD
 
 #include <cassert>
 #include <condition_variable>  // NOLINT
@@ -126,6 +129,70 @@ inline bool Snappy_Uncompress(const char* input, size_t length, char* output) {
 #endif  // HAVE_SNAPPY
 }
 
+inline bool Zstd_Compress(const char* input, size_t length,
+                          std::string* output) {
+#if HAVE_ZSTD
+  // Get the MaxCompressedLength.
+  size_t outlen = ZSTD_compressBound(length);
+  if (ZSTD_isError(outlen)) {
+    return false;
+  }
+  output->resize(outlen);
+  ZSTD_CCtx* ctx = ZSTD_createCCtx();
+  outlen = ZSTD_compress2(ctx, &(*output)[0], output->size(), input, length);
+  ZSTD_freeCCtx(ctx);
+  if (ZSTD_isError(outlen)) {
+    return false;
+  }
+  output->resize(outlen);
+  return true;
+#else
+  // Silence compiler warnings about unused arguments.
+  (void)input;
+  (void)length;
+  (void)output;
+  return false;
+#endif  // HAVE_ZSTD
+}
+
+inline bool Zstd_GetUncompressedLength(const char* input, size_t length,
+                                       size_t* result) {
+#if HAVE_ZSTD
+  size_t size = ZSTD_getFrameContentSize(input, length);
+  if (size == 0) return false;
+  *result = size;
+  return true;
+#else
+  // Silence compiler warnings about unused arguments.
+  (void)input;
+  (void)length;
+  (void)result;
+  return false;
+#endif  // HAVE_ZSTD
+}
+
+inline bool Zstd_Uncompress(const char* input, size_t length, char* output) {
+#if HAVE_ZSTD
+  size_t outlen;
+  if (!Zstd_GetUncompressedLength(input, length, &outlen)) {
+    return false;
+  }
+  ZSTD_DCtx* ctx = ZSTD_createDCtx();
+  outlen = ZSTD_decompressDCtx(ctx, output, outlen, input, length);
+  ZSTD_freeDCtx(ctx);
+  if (ZSTD_isError(outlen)) {
+    return false;
+  }
+  return true;
+#else
+  // Silence compiler warnings about unused arguments.
+  (void)input;
+  (void)length;
+  (void)output;
+  return false;
+#endif  // HAVE_ZSTD
+}
+
 inline bool GetHeapProfile(void (*func)(void*, const char*, int), void* arg) {
   // Silence compiler warnings about unused arguments.
   (void)func;