tuning the wording and adding a spaceusage benchmark

README.md

@@ -59,10 +59,9 @@ For serialization, there is a choice between an unpacked and a packed format.
 The unpacked format is roughly of the same size as in-core data, but uses most
 efficient memory copy operations.
 
-The packed format avoids storing zero bytes and is considered near optimal (it
-can not be compressed further by zlib and its required space is very close to
-the theoretical lower limit), but it needs to copy individual words, so it
-should be expected to be somewhat slower.
+The packed format avoids storing zero bytes and relies on a bitset to locate them, so it
+should be expected to be somewhat slower. The packed format might be smaller or larger.
+When in doubt, prefer the regular (unpacked) format.
 
 The two formats use slightly different APIs.
 
@@ -77,11 +76,13 @@ You may serialize and deserialize in unpacked format as follows:
   free(buffer);
 ```
 
+This should be the default.
+
 To serialize and deserialize in packed format, use the `_pack_bytes()`,
 `_pack()` and `_unpack()` functions. The latter two have an additional `size_t`
 argument for the buffer length. `_pack()` can be used with a buffer of arbitrary
 size, it returns the used space if serialization fit into the buffer or 0
-otherwise.
+otherwise. Note that the packed format will be slower and may not save space.
 
 For example:
 

benchmarks/CMakeLists.txt

@@ -1,2 +1,5 @@
 add_executable(bench bench.c)
 target_link_libraries(bench PUBLIC xor_singleheader)
+
+add_executable(spaceusage spaceusage.c)
+target_link_libraries(spaceusage PUBLIC xor_singleheader)

benchmarks/spaceusage.c

@@ -0,0 +1,119 @@
+#include "binaryfusefilter.h"
+#include "xorfilter.h"
+#include <stdlib.h>
+#include <iso646.h>
+
+typedef struct {
+  size_t standard;
+  size_t pack;
+} sizes;
+
+sizes fuse16(size_t n) {
+  binary_fuse16_t filter = {0};
+  if (! binary_fuse16_allocate(n, &filter)) {
+    printf("allocation failed\n");
+    return (sizes) {0, 0};
+  }
+  uint64_t* big_set = malloc(n * sizeof(uint64_t));
+  for(size_t i = 0; i < n; i++) {
+    big_set[i] = i;
+  }
+  bool is_ok = binary_fuse16_populate(big_set, n, &filter);
+  if(! is_ok ) {
+    printf("populating failed\n");
+  }
+  free(big_set);
+  sizes s = {
+    .standard = binary_fuse16_serialization_bytes(&filter),
+    .pack = binary_fuse16_pack_bytes(&filter)
+  };
+  binary_fuse16_free(&filter);
+  return s;
+}
+
+sizes fuse8(size_t n) {
+  binary_fuse8_t filter = {0};
+  if (! binary_fuse8_allocate(n, &filter)) {
+    printf("allocation failed\n");
+    return (sizes) {0, 0};
+  }
+  uint64_t* big_set = malloc(n * sizeof(uint64_t));
+  for(size_t i = 0; i < n; i++) {
+    big_set[i] = i;
+  }
+  bool is_ok = binary_fuse8_populate(big_set, n, &filter);
+  if(! is_ok ) {
+    printf("populating failed\n");
+  }
+  free(big_set);
+  sizes s = {
+    .standard = binary_fuse8_serialization_bytes(&filter),
+    .pack = binary_fuse8_pack_bytes(&filter)
+  };
+  binary_fuse8_free(&filter);
+  return s;
+}
+
+sizes xor16(size_t n) {
+  xor16_t filter = {0};
+  if (! xor16_allocate(n, &filter)) {
+    printf("allocation failed\n");
+    return (sizes) {0, 0};
+  }
+  uint64_t* big_set = malloc(n * sizeof(uint64_t));
+  for(size_t i = 0; i < n; i++) {
+    big_set[i] = i;
+  }
+  bool is_ok = xor16_populate(big_set, n, &filter);
+  if(! is_ok ) {
+    printf("populating failed\n");
+  }
+  free(big_set);
+  sizes s = {
+    .standard = xor16_serialization_bytes(&filter),
+    .pack = xor16_pack_bytes(&filter)
+  };
+  xor16_free(&filter);
+  return s;
+}
+
+sizes xor8(size_t n) {
+  xor8_t filter = {0};
+  if (! xor8_allocate(n, &filter)) {
+    printf("allocation failed\n");
+    return (sizes) {0, 0};
+  }
+  uint64_t* big_set = malloc(n * sizeof(uint64_t));
+  for(size_t i = 0; i < n; i++) {
+    big_set[i] = i;
+  }
+  bool is_ok = xor8_populate(big_set, n, &filter);
+  if(! is_ok ) {
+    printf("populating failed\n");
+  }
+  free(big_set);
+  sizes s = {
+    .standard = xor8_serialization_bytes(&filter),
+    .pack = xor8_pack_bytes(&filter)
+  };
+  xor8_free(&filter);
+
+  return s;
+}
+
+int main() {
+    for (size_t n = 10; n <= 10000000; n *= 2) {
+        printf("%-10zu ", n);  // Align number to 10 characters wide
+        sizes f16 = fuse16(n);
+        sizes f8 = fuse8(n);
+        sizes x16 = xor16(n);
+        sizes x8 = xor8(n);
+
+        printf("fuse16: %5.2f %5.2f   ", (double)f16.standard * 8.0 / n, (double)f16.pack * 8.0 / n);
+        printf("fuse8: %5.2f %5.2f   ", (double)f8.standard  * 8.0 / n, (double)f8.pack  * 8.0 / n);
+        printf("xor16: %5.2f %5.2f   ", (double)x16.standard  * 8.0 / n, (double)x16.pack  * 8.0 / n);
+        printf("xor8: %5.2f %5.2f   ", (double)x8.standard  * 8.0 / n, (double)x8.pack  * 8.0 / n);
+        printf("\n");
+    }
+    return EXIT_SUCCESS;
+}

tests/CMakeLists.txt

@@ -14,9 +14,9 @@ else() # *nix
   -Wall -Wextra -Wshadow  -Wcast-qual -Wconversion -Wsign-conversion -Werror)
 
   if (NOT MINGW) # sanitizers are not supported under mingw
-    list(APPEND TEST_COMPILE_OPTIONS -fsanitize=address,undefined,leak) 
+    list(APPEND TEST_COMPILE_OPTIONS -fsanitize=address,undefined) 
     # sanitsizers need to be specified at link time as well
-    target_link_options(unit PRIVATE -fsanitize=address,leak,undefined)
+    target_link_options(unit PRIVATE -fsanitize=address,undefined)
   endif()
 endif()