feat: add delta transfer for incremental sync
CI / build-and-test (push) Successful in 28s
CI / build-and-test (pull_request) Successful in 28s

Implement rsync-style delta transfer using rolling checksums (Adler-32 +
xxHash32). When a file exists on both sides but has changed, only the
changed blocks are transmitted instead of the entire file.

- New status codes: STATUS_DELTA_SIGNATURE, STATUS_DELTA_DATA
- Protocol version bumped to 1.2.0
- Server generates block signature, client computes delta
- Auto-fallback to whole-file when delta >= 70% of file size
- Works with zstd compression on delta stream
- Configurable block size (default 8KB, --delta-block flag)
- 13 unit tests covering hashing, signature roundtrip, delta compute/apply,
  file growth/shrink, and decision logic
This commit is contained in:
2026-07-18 20:00:15 +02:00
parent 43ba149ad5
commit e16db56580
13 changed files with 8628 additions and 19 deletions
+28
View File
@@ -1,5 +1,6 @@
#include "client_send.h"
#include "config.h"
#include "delta.h"
#include "log.h"
#include "protocol.h"
#include "transport_tls.h"
@@ -36,6 +37,8 @@ static void print_usage(void) {
printf(" --max-size <n> Skip files larger than n bytes\n");
printf(" --min-size <n> Skip files smaller than n bytes\n");
printf(" --incremental Skip files unchanged since last transfer\n");
printf(" --delta Delta transfer for changed files (requires --incremental)\n");
printf(" --delta-block <n> Delta block size in bytes (default: %d)\n", DELTA_BLOCK_SIZE_DEFAULT);
printf(" -m Enable multithreading\n");
printf(" -s Enable chunk serialization\n");
printf(" -f Enable sendfile (TCP only, not with -c or -s)\n");
@@ -101,6 +104,14 @@ int main(int argc, char *argv[]) {
config->min_size = strtoull(argv[++i], NULL, 10);
} else if (strcmp(argv[i], "--incremental") == 0) {
config->use_incremental = true;
} else if (strcmp(argv[i], "--delta") == 0) {
config->use_delta = true;
} else if (strcmp(argv[i], "--delta-block") == 0 && i + 1 < argc) {
unsigned long long val = strtoull(argv[++i], NULL, 10);
if (val >= DELTA_BLOCK_SIZE_MIN && val <= DELTA_BLOCK_SIZE_MAX)
config->delta_block_size = (uint32_t)val;
else
fprintf(stderr, "Warning: --delta-block value %llu out of range, using default\n", val);
} else if (strcmp(argv[i], "-c") == 0 || strcmp(argv[i], "-z") == 0) {
config->use_compression = true;
log_message(LOG_LEVEL_INFO, "Enabled Compression");
@@ -231,6 +242,23 @@ int main(int argc, char *argv[]) {
config->use_metadata = true;
}
if (config->use_delta && !config->use_incremental) {
fprintf(stderr, "Error: --delta requires --incremental\n");
return 1;
}
if (config->use_delta && config->use_chunk_serialization) {
fprintf(stderr, "Error: --delta cannot be combined with -s (chunk serialization)\n");
return 1;
}
if (config->use_delta && config->use_sendfile) {
fprintf(stderr, "Error: --delta cannot be combined with -f (sendfile)\n");
return 1;
}
if (config->use_delta && !config->use_metadata) {
log_message(LOG_LEVEL_INFO, "Enabling metadata preservation for --delta");
config->use_metadata = true;
}
if (config->use_tls) {
if (!config->tls_cert || !config->tls_key) {
fprintf(stderr, "Error: --tls requires --cert and --key\n");
+72 -7
View File
@@ -1,9 +1,12 @@
#include "client_send.h"
#include "array_list.h"
#include "chunk.h"
#include "compression.h"
#include "config.h"
#include "data.h"
#include "delta.h"
#include "file.h"
#include "metadata.h"
#include "log.h"
#include "multiprocessing.h"
#include "protocol.h"
@@ -19,7 +22,9 @@
#include <threads.h>
#include <time.h>
static int incremental_check(Client *client, File *file) {
static int incremental_check(Client *client, File *file,
DeltaSignature **out_sig) {
*out_sig = NULL;
if (!send_status(client->file_descriptor, STATUS_CHECK)) return -1;
if (!send_str(client->file_descriptor, file->path)) return -1;
unsigned long long fsize = file->data->size;
@@ -33,6 +38,15 @@ static int incremental_check(Client *client, File *file) {
return -1;
}
if (s == STATUS_OK) return 1;
if (s == STATUS_DELTA_SIGNATURE) {
Data *sig_data = receive_data(client->file_descriptor);
if (!sig_data) return -1;
DeltaSignature *sig = delta_signature_deserialize(sig_data);
data_destroy(sig_data);
if (!sig) return -1;
*out_sig = sig;
return 2;
}
if (s != STATUS_NEXT) {
log_message(LOG_LEVEL_ERROR, "Unexpected server status");
return -1;
@@ -40,6 +54,39 @@ static int incremental_check(Client *client, File *file) {
return 0;
}
static int send_delta(Client *client, File *file, DeltaSignature *sig,
Config *config) {
Delta *delta = delta_compute(file->data->data, file->data->size,
sig, config->delta_block_size);
if (!delta) return 1;
if (!delta_is_worthwhile(delta, file->data->size)) {
delta_destroy(delta);
if (!send_status(client->file_descriptor, STATUS_NEXT)) return -1;
return 1;
}
Data *delta_data = delta_serialize(delta);
delta_destroy(delta);
if (!delta_data) return -1;
Data *to_send = delta_data;
if (config->use_compression) {
to_send = data_compress(delta_data, config->compression_level);
data_destroy(delta_data);
if (!to_send) return -1;
}
bool ok = send_status(client->file_descriptor, STATUS_DELTA_DATA) &&
send_data(client->file_descriptor, to_send);
if (ok && config->use_metadata)
ok = metadata_send(client->file_descriptor, file->metadata);
data_destroy(to_send);
return ok ? 0 : -1;
}
int send_chunk(Client *client, Chunk *chunk, Config *config) {
if (config->use_chunk_serialization) {
if (!send_status(client->file_descriptor, STATUS_CHUNK)) return -1;
@@ -55,9 +102,18 @@ int send_chunk(Client *client, Chunk *chunk, Config *config) {
} else if (config->use_sendfile && !config->use_compression) {
for (int i = 0; i < chunk->element_count; i++) {
if (config->use_incremental) {
int rc = incremental_check(client, chunk->items[i]);
if (rc < 0) return -1;
if (rc > 0) continue;
DeltaSignature *sig = NULL;
int rc = incremental_check(client, chunk->items[i], &sig);
if (rc < 0) { delta_signature_destroy(sig); return -1; }
if (rc == 1) { delta_signature_destroy(sig); continue; }
if (rc == 2 && config->use_delta) {
int drc = send_delta(client, chunk->items[i], sig, config);
delta_signature_destroy(sig);
if (drc == 0) continue;
if (drc < 0) return -1;
} else {
delta_signature_destroy(sig);
}
if (!file_send_sendfile(chunk->items[i], client->file_descriptor, config->use_metadata, false))
return -1;
} else {
@@ -69,9 +125,18 @@ int send_chunk(Client *client, Chunk *chunk, Config *config) {
} else {
for (int i = 0; i < chunk->element_count; i++) {
if (config->use_incremental) {
int rc = incremental_check(client, chunk->items[i]);
if (rc < 0) return -1;
if (rc > 0) continue;
DeltaSignature *sig = NULL;
int rc = incremental_check(client, chunk->items[i], &sig);
if (rc < 0) { delta_signature_destroy(sig); return -1; }
if (rc == 1) { delta_signature_destroy(sig); continue; }
if (rc == 2 && config->use_delta) {
int drc = send_delta(client, chunk->items[i], sig, config);
delta_signature_destroy(sig);
if (drc == 0) continue;
if (drc < 0) return -1;
} else {
delta_signature_destroy(sig);
}
if (!file_send_single_calls(chunk->items[i], client->file_descriptor,
config->use_metadata,
config->use_compression ? config->compression_level : 0,
+9
View File
@@ -1,4 +1,5 @@
#include "config.h"
#include "delta.h"
#include "log.h"
#include "protocol.h"
#include "utils.h"
@@ -39,6 +40,8 @@ Config *config_create(char *version, char *send_directory,
config->max_size = 0;
config->min_size = 0;
config->use_incremental = false;
config->use_delta = false;
config->delta_block_size = DELTA_BLOCK_SIZE_DEFAULT;
config->use_tls = false;
config->tls_cert = NULL;
config->tls_key = NULL;
@@ -98,6 +101,8 @@ bool config_send(int file_descriptor, Config *config) {
if (!send_int(file_descriptor, config->use_sendfile)) return false;
if (!send_int(file_descriptor, config->use_delete)) return false;
if (!send_int(file_descriptor, config->use_incremental)) return false;
if (!send_int(file_descriptor, config->use_delta)) return false;
if (!send_int(file_descriptor, (int)config->delta_block_size)) return false;
Status status;
if (!receive_status(file_descriptor, &status)) return false;
if (status != STATUS_OK) {
@@ -145,6 +150,10 @@ Config *config_receive(int file_descriptor) {
config->use_delete = tmp;
if (!receive_int(file_descriptor, &tmp)) goto error;
config->use_incremental = tmp;
if (!receive_int(file_descriptor, &tmp)) goto error;
config->use_delta = tmp;
if (!receive_int(file_descriptor, &tmp)) goto error;
config->delta_block_size = (uint32_t)tmp;
config->show_progress = false;
config->dry_run = false;
config->ssh_port = 22;
+4 -1
View File
@@ -2,6 +2,7 @@
#define CONFIG_H
#include <stdbool.h>
#include <stdint.h>
typedef enum {
TRANSPORT_TCP,
@@ -33,13 +34,15 @@ typedef struct Config {
unsigned long long max_size;
unsigned long long min_size;
bool use_incremental;
bool use_delta;
uint32_t delta_block_size;
bool use_tls;
char *tls_cert;
char *tls_key;
char *tls_ca;
} Config;
#define PROTOCOL_VERSION "1.1.0"
#define PROTOCOL_VERSION "1.2.0"
#define DEFAULT_CHUNK_SIZE (10 * 1024 * 1024)
Config *config_create(char *version, char *send_directory,
+450
View File
@@ -0,0 +1,450 @@
#include "delta.h"
#include "log.h"
#include <stdlib.h>
#include <string.h>
#define XXH_STATIC_LINKING_ONLY
#define XXH_IMPLEMENTATION
#include "xxhash.h"
uint32_t delta_adler32(const void *data, uint32_t len) {
const uint8_t *p = (const uint8_t *)data;
uint32_t s1 = 1;
uint32_t s2 = 0;
for (uint32_t i = 0; i < len; i++) {
s1 = (s1 + p[i]) % DELTA_ADLER32_MODULUS;
s2 = (s2 + s1) % DELTA_ADLER32_MODULUS;
}
return (s2 << 16) | s1;
}
uint32_t delta_xxhash32(const void *data, uint32_t len) {
return XXH32(data, len, 0);
}
DeltaSignature *delta_signature_create(const void *old_file_data,
uint64_t old_file_size,
uint32_t block_size) {
if (old_file_data == NULL || old_file_size == 0 || block_size == 0)
return NULL;
uint32_t block_count = (uint32_t)((old_file_size + block_size - 1) / block_size);
DeltaSignature *sig = malloc(sizeof(DeltaSignature));
if (!sig) return NULL;
sig->file_size = old_file_size;
sig->block_size = block_size;
sig->block_count = block_count;
sig->blocks = malloc(block_count * sizeof(DeltaBlockSig));
if (!sig->blocks) {
free(sig);
return NULL;
}
const uint8_t *data = (const uint8_t *)old_file_data;
for (uint32_t i = 0; i < block_count; i++) {
uint64_t offset = (uint64_t)i * block_size;
uint32_t len = (uint32_t)((old_file_size - offset < block_size)
? (old_file_size - offset)
: block_size);
sig->blocks[i].adler32 = delta_adler32(data + offset, len);
sig->blocks[i].xxhash = delta_xxhash32(data + offset, len);
}
return sig;
}
Data *delta_signature_serialize(const DeltaSignature *sig) {
if (!sig) return NULL;
uint64_t total = sizeof(uint64_t) + sizeof(uint32_t) + sizeof(uint32_t) +
(uint64_t)sig->block_count * (sizeof(uint32_t) + sizeof(uint32_t));
uint8_t *buf = malloc((size_t)total);
if (!buf) return NULL;
size_t pos = 0;
memcpy(buf + pos, &sig->file_size, sizeof(uint64_t));
pos += sizeof(uint64_t);
memcpy(buf + pos, &sig->block_size, sizeof(uint32_t));
pos += sizeof(uint32_t);
memcpy(buf + pos, &sig->block_count, sizeof(uint32_t));
pos += sizeof(uint32_t);
for (uint32_t i = 0; i < sig->block_count; i++) {
memcpy(buf + pos, &sig->blocks[i].adler32, sizeof(uint32_t));
pos += sizeof(uint32_t);
memcpy(buf + pos, &sig->blocks[i].xxhash, sizeof(uint32_t));
pos += sizeof(uint32_t);
}
return data_create(buf, (size_t)total);
}
DeltaSignature *delta_signature_deserialize(const Data *data) {
if (!data || data->size < sizeof(uint64_t) + sizeof(uint32_t) + sizeof(uint32_t))
return NULL;
const uint8_t *buf = (const uint8_t *)data->data;
size_t pos = 0;
DeltaSignature *sig = malloc(sizeof(DeltaSignature));
if (!sig) return NULL;
memcpy(&sig->file_size, buf + pos, sizeof(uint64_t));
pos += sizeof(uint64_t);
memcpy(&sig->block_size, buf + pos, sizeof(uint32_t));
pos += sizeof(uint32_t);
memcpy(&sig->block_count, buf + pos, sizeof(uint32_t));
pos += sizeof(uint32_t);
uint64_t expected = sizeof(uint64_t) + sizeof(uint32_t) + sizeof(uint32_t) +
(uint64_t)sig->block_count * (sizeof(uint32_t) + sizeof(uint32_t));
if (data->size < expected) {
free(sig);
return NULL;
}
sig->blocks = malloc(sig->block_count * sizeof(DeltaBlockSig));
if (!sig->blocks) {
free(sig);
return NULL;
}
for (uint32_t i = 0; i < sig->block_count; i++) {
memcpy(&sig->blocks[i].adler32, buf + pos, sizeof(uint32_t));
pos += sizeof(uint32_t);
memcpy(&sig->blocks[i].xxhash, buf + pos, sizeof(uint32_t));
pos += sizeof(uint32_t);
}
return sig;
}
void delta_signature_destroy(DeltaSignature *sig) {
if (!sig) return;
free(sig->blocks);
free(sig);
}
Delta *delta_compute(const void *new_file_data, uint64_t new_file_size,
const DeltaSignature *sig, uint32_t block_size) {
if (!new_file_data || !sig || new_file_size == 0 || block_size == 0)
return NULL;
const uint8_t *new_data = (const uint8_t *)new_file_data;
uint32_t capacity = 64;
uint32_t count = 0;
DeltaInstruction *instrs = malloc(capacity * sizeof(DeltaInstruction));
if (!instrs) return NULL;
uint64_t literal_start = 0;
bool has_literal = false;
uint64_t i = 0;
while (i < new_file_size) {
uint32_t window_len = (uint32_t)((new_file_size - i < block_size)
? (new_file_size - i)
: block_size);
uint32_t adler = delta_adler32(new_data + i, window_len);
uint32_t xxh = delta_xxhash32(new_data + i, window_len);
bool matched = false;
for (uint32_t j = 0; j < sig->block_count; j++) {
if (adler == sig->blocks[j].adler32 && xxh == sig->blocks[j].xxhash) {
if (has_literal) {
uint32_t lit_len = (uint32_t)(i - literal_start);
if (count == capacity) {
capacity *= 2;
DeltaInstruction *tmp = realloc(instrs, capacity * sizeof(DeltaInstruction));
if (!tmp) { free(instrs); return NULL; }
instrs = tmp;
}
uint8_t *lit_data = malloc(lit_len);
if (!lit_data) { free(instrs); return NULL; }
memcpy(lit_data, new_data + literal_start, lit_len);
instrs[count].type = DELTA_INSTR_LITERAL;
instrs[count].literal.data = lit_data;
instrs[count].literal.length = lit_len;
count++;
has_literal = false;
}
if (count == capacity) {
capacity *= 2;
DeltaInstruction *tmp = realloc(instrs, capacity * sizeof(DeltaInstruction));
if (!tmp) { free(instrs); return NULL; }
instrs = tmp;
}
instrs[count].type = DELTA_INSTR_BLOCK_MATCH;
instrs[count].match.block_index = j;
instrs[count].match.block_offset = 0;
instrs[count].match.length = window_len;
count++;
i += window_len;
matched = true;
break;
}
}
if (!matched) {
if (!has_literal) {
literal_start = i;
has_literal = true;
}
i++;
}
}
if (has_literal) {
uint32_t lit_len = (uint32_t)(new_file_size - literal_start);
if (count == capacity) {
capacity *= 2;
DeltaInstruction *tmp = realloc(instrs, capacity * sizeof(DeltaInstruction));
if (!tmp) { free(instrs); return NULL; }
instrs = tmp;
}
uint8_t *lit_data = malloc(lit_len);
if (!lit_data) { free(instrs); return NULL; }
memcpy(lit_data, new_data + literal_start, lit_len);
instrs[count].type = DELTA_INSTR_LITERAL;
instrs[count].literal.data = lit_data;
instrs[count].literal.length = lit_len;
count++;
}
Delta *delta = malloc(sizeof(Delta));
if (!delta) {
for (uint32_t k = 0; k < count; k++) {
if (instrs[k].type == DELTA_INSTR_LITERAL)
free(instrs[k].literal.data);
}
free(instrs);
return NULL;
}
delta->new_file_size = new_file_size;
delta->instruction_count = count;
delta->instructions = instrs;
delta->delta_size = 0;
for (uint32_t k = 0; k < count; k++) {
delta->delta_size += 1;
if (instrs[k].type == DELTA_INSTR_BLOCK_MATCH) {
delta->delta_size += sizeof(uint32_t) * 3;
} else {
delta->delta_size += sizeof(uint32_t) + instrs[k].literal.length;
}
}
return delta;
}
Data *delta_serialize(const Delta *delta) {
if (!delta) return NULL;
uint64_t total = sizeof(uint64_t) + sizeof(uint32_t) + delta->delta_size;
uint8_t *buf = malloc((size_t)total);
if (!buf) return NULL;
size_t pos = 0;
memcpy(buf + pos, &delta->new_file_size, sizeof(uint64_t));
pos += sizeof(uint64_t);
memcpy(buf + pos, &delta->instruction_count, sizeof(uint32_t));
pos += sizeof(uint32_t);
for (uint32_t i = 0; i < delta->instruction_count; i++) {
uint8_t type = (uint8_t)delta->instructions[i].type;
memcpy(buf + pos, &type, sizeof(uint8_t));
pos += sizeof(uint8_t);
if (delta->instructions[i].type == DELTA_INSTR_BLOCK_MATCH) {
memcpy(buf + pos, &delta->instructions[i].match.block_index, sizeof(uint32_t));
pos += sizeof(uint32_t);
memcpy(buf + pos, &delta->instructions[i].match.block_offset, sizeof(uint32_t));
pos += sizeof(uint32_t);
memcpy(buf + pos, &delta->instructions[i].match.length, sizeof(uint32_t));
pos += sizeof(uint32_t);
} else {
memcpy(buf + pos, &delta->instructions[i].literal.length, sizeof(uint32_t));
pos += sizeof(uint32_t);
memcpy(buf + pos, delta->instructions[i].literal.data,
delta->instructions[i].literal.length);
pos += delta->instructions[i].literal.length;
}
}
return data_create(buf, (size_t)total);
}
Delta *delta_deserialize(const Data *data) {
if (!data || data->size < sizeof(uint64_t) + sizeof(uint32_t))
return NULL;
const uint8_t *buf = (const uint8_t *)data->data;
size_t pos = 0;
Delta *delta = malloc(sizeof(Delta));
if (!delta) return NULL;
memcpy(&delta->new_file_size, buf + pos, sizeof(uint64_t));
pos += sizeof(uint64_t);
memcpy(&delta->instruction_count, buf + pos, sizeof(uint32_t));
pos += sizeof(uint32_t);
delta->instructions = malloc(delta->instruction_count * sizeof(DeltaInstruction));
if (!delta->instructions) {
free(delta);
return NULL;
}
delta->delta_size = 0;
for (uint32_t i = 0; i < delta->instruction_count; i++) {
if (pos >= data->size) {
for (uint32_t k = 0; k < i; k++) {
if (delta->instructions[k].type == DELTA_INSTR_LITERAL)
free(delta->instructions[k].literal.data);
}
free(delta->instructions);
free(delta);
return NULL;
}
uint8_t type;
memcpy(&type, buf + pos, sizeof(uint8_t));
pos += sizeof(uint8_t);
delta->delta_size += 1;
if (type == DELTA_OP_BLOCK_MATCH) {
if (pos + sizeof(uint32_t) * 3 > data->size) {
free(delta->instructions);
free(delta);
return NULL;
}
delta->instructions[i].type = DELTA_INSTR_BLOCK_MATCH;
memcpy(&delta->instructions[i].match.block_index, buf + pos, sizeof(uint32_t));
pos += sizeof(uint32_t);
memcpy(&delta->instructions[i].match.block_offset, buf + pos, sizeof(uint32_t));
pos += sizeof(uint32_t);
memcpy(&delta->instructions[i].match.length, buf + pos, sizeof(uint32_t));
pos += sizeof(uint32_t);
delta->delta_size += sizeof(uint32_t) * 3;
} else if (type == DELTA_OP_LITERAL) {
if (pos + sizeof(uint32_t) > data->size) {
free(delta->instructions);
free(delta);
return NULL;
}
memcpy(&delta->instructions[i].literal.length, buf + pos, sizeof(uint32_t));
pos += sizeof(uint32_t);
uint32_t lit_len = delta->instructions[i].literal.length;
if (pos + lit_len > data->size) {
free(delta->instructions);
free(delta);
return NULL;
}
delta->instructions[i].literal.data = malloc(lit_len);
if (!delta->instructions[i].literal.data) {
free(delta->instructions);
free(delta);
return NULL;
}
memcpy(delta->instructions[i].literal.data, buf + pos, lit_len);
pos += lit_len;
delta->delta_size += sizeof(uint32_t) + lit_len;
} else {
for (uint32_t k = 0; k < i; k++) {
if (delta->instructions[k].type == DELTA_INSTR_LITERAL)
free(delta->instructions[k].literal.data);
}
free(delta->instructions);
free(delta);
return NULL;
}
}
return delta;
}
void *delta_apply(const void *old_data, uint64_t old_size, const Delta *delta,
uint32_t block_size) {
if (!old_data || !delta) return NULL;
void *output = malloc((size_t)delta->new_file_size);
if (!output) return NULL;
uint8_t *out = (uint8_t *)output;
uint8_t *old = (uint8_t *)old_data;
uint64_t out_pos = 0;
for (uint32_t i = 0; i < delta->instruction_count; i++) {
if (delta->instructions[i].type == DELTA_INSTR_BLOCK_MATCH) {
uint64_t src_offset = (uint64_t)delta->instructions[i].match.block_index *
block_size;
src_offset += delta->instructions[i].match.block_offset;
uint32_t len = delta->instructions[i].match.length;
if (src_offset + len > old_size) {
free(output);
return NULL;
}
memcpy(out + out_pos, old + src_offset, len);
out_pos += len;
} else {
uint32_t len = delta->instructions[i].literal.length;
memcpy(out + out_pos, delta->instructions[i].literal.data, len);
out_pos += len;
}
}
if (out_pos != delta->new_file_size) {
free(output);
return NULL;
}
return output;
}
void delta_destroy(Delta *delta) {
if (!delta) return;
for (uint32_t i = 0; i < delta->instruction_count; i++) {
if (delta->instructions[i].type == DELTA_INSTR_LITERAL)
free(delta->instructions[i].literal.data);
}
free(delta->instructions);
free(delta);
}
bool delta_should_attempt(uint64_t old_size, uint64_t new_size) {
if (old_size < DELTA_MIN_FILE_SIZE || new_size < DELTA_MIN_FILE_SIZE)
return false;
if (old_size > DELTA_MAX_FILE_SIZE || new_size > DELTA_MAX_FILE_SIZE)
return false;
double large = (old_size > new_size) ? (double)old_size : (double)new_size;
double small = (old_size > new_size) ? (double)new_size : (double)old_size;
if (small == 0 || large / small > DELTA_MAX_SIZE_RATIO)
return false;
return true;
}
bool delta_is_worthwhile(const Delta *delta, uint64_t new_file_size) {
if (!delta || delta->instruction_count == 0) return false;
bool has_match = false;
for (uint32_t i = 0; i < delta->instruction_count; i++) {
if (delta->instructions[i].type == DELTA_INSTR_BLOCK_MATCH) {
has_match = true;
break;
}
}
if (!has_match) return false;
double ratio = (double)delta->delta_size / (double)new_file_size;
return ratio < DELTA_FALLBACK_RATIO;
}
+81
View File
@@ -0,0 +1,81 @@
#ifndef DELTA_H
#define DELTA_H
#include "data.h"
#include <stdbool.h>
#include <stdint.h>
#include <stddef.h>
#define DELTA_BLOCK_SIZE_DEFAULT 8192U
#define DELTA_BLOCK_SIZE_MIN 1024U
#define DELTA_BLOCK_SIZE_MAX 65536U
#define DELTA_MIN_FILE_SIZE 16384ULL
#define DELTA_MAX_FILE_SIZE (256ULL * 1024 * 1024)
#define DELTA_MAX_SIZE_RATIO 10.0
#define DELTA_FALLBACK_RATIO 0.7
#define DELTA_ADLER32_MODULUS 65521U
#define DELTA_OP_BLOCK_MATCH 0x01
#define DELTA_OP_LITERAL 0x02
typedef struct {
uint32_t adler32;
uint32_t xxhash;
} DeltaBlockSig;
typedef struct {
uint64_t file_size;
uint32_t block_size;
uint32_t block_count;
DeltaBlockSig *blocks;
} DeltaSignature;
typedef enum {
DELTA_INSTR_BLOCK_MATCH = 0x01,
DELTA_INSTR_LITERAL = 0x02
} DeltaInstrType;
typedef struct {
DeltaInstrType type;
union {
struct {
uint32_t block_index;
uint32_t block_offset;
uint32_t length;
} match;
struct {
uint8_t *data;
uint32_t length;
} literal;
};
} DeltaInstruction;
typedef struct {
uint64_t new_file_size;
uint32_t instruction_count;
DeltaInstruction *instructions;
uint64_t delta_size;
} Delta;
DeltaSignature *delta_signature_create(const void *old_file_data,
uint64_t old_file_size,
uint32_t block_size);
Data *delta_signature_serialize(const DeltaSignature *sig);
DeltaSignature *delta_signature_deserialize(const Data *data);
void delta_signature_destroy(DeltaSignature *sig);
Delta *delta_compute(const void *new_file_data, uint64_t new_file_size,
const DeltaSignature *sig, uint32_t block_size);
Data *delta_serialize(const Delta *delta);
Delta *delta_deserialize(const Data *data);
void *delta_apply(const void *old_data, uint64_t old_size, const Delta *delta,
uint32_t block_size);
void delta_destroy(Delta *delta);
bool delta_should_attempt(uint64_t old_size, uint64_t new_size);
bool delta_is_worthwhile(const Delta *delta, uint64_t new_file_size);
uint32_t delta_adler32(const void *data, uint32_t len);
uint32_t delta_xxhash32(const void *data, uint32_t len);
#endif
+198 -10
View File
@@ -10,6 +10,7 @@
#include <unistd.h>
#include "compression.h"
#include "delta.h"
#include "log.h"
#include "config.h"
#include "data.h"
@@ -132,7 +133,8 @@ bool file_save_to_disk(const char *root_directory, File *file) {
return ok;
}
File *receive_incremental_check(int fd, Config *config, bool *skipped) { *skipped = false;
File *receive_incremental_check(int fd, Config *config, bool *skipped) {
*skipped = false;
char *check_path = receive_str(fd);
if (check_path == NULL) { send_status(fd, STATUS_ERROR); return NULL; }
@@ -147,25 +149,211 @@ File *receive_incremental_check(int fd, Config *config, bool *skipped) { *skipp
char *full_path = path_cat(config->receive_root_directory, check_path);
struct stat st;
bool match = false;
if (full_path && stat(full_path, &st) == 0 &&
(unsigned long long)st.st_size == check_size &&
(long long)st.st_mtime == check_mtime) {
match = true;
}
free(full_path);
bool has_old_file = (full_path && stat(full_path, &st) == 0);
unsigned long long old_size = has_old_file ? (unsigned long long)st.st_size : 0;
bool match = has_old_file &&
(unsigned long long)st.st_size == check_size &&
(long long)st.st_mtime == check_mtime;
if (match) {
if (!send_status(fd, STATUS_OK)) { free(check_path); return NULL; }
if (!send_status(fd, STATUS_OK)) { free(full_path); free(check_path); return NULL; }
free(full_path);
free(check_path);
*skipped = true;
return NULL;
}
if (!send_status(fd, STATUS_NEXT)) { free(check_path); return NULL; }
bool try_delta = config->use_delta && has_old_file &&
delta_should_attempt(old_size, check_size);
if (try_delta) {
void *old_data = malloc((size_t)old_size);
if (!old_data) {
try_delta = false;
} else {
FILE *fp = fopen(full_path, "rb");
if (!fp) {
free(old_data);
try_delta = false;
} else {
size_t nread = fread(old_data, 1, (size_t)old_size, fp);
fclose(fp);
if (nread != (size_t)old_size) {
free(old_data);
try_delta = false;
}
}
}
if (try_delta) {
DeltaSignature *sig = delta_signature_create(old_data, old_size,
config->delta_block_size);
if (!sig) {
free(old_data);
try_delta = false;
} else {
Data *sig_data = delta_signature_serialize(sig);
if (!sig_data) {
delta_signature_destroy(sig);
free(old_data);
try_delta = false;
} else {
bool sig_sent = send_status(fd, STATUS_DELTA_SIGNATURE) &&
send_data(fd, sig_data);
data_destroy(sig_data);
if (!sig_sent) {
delta_signature_destroy(sig);
free(old_data);
try_delta = false;
} else {
Status resp;
if (!receive_status(fd, &resp)) {
delta_signature_destroy(sig);
free(old_data);
free(full_path);
free(check_path);
return NULL;
}
if (resp == STATUS_DELTA_DATA) {
Data *delta_data = receive_data(fd);
if (!delta_data) {
delta_signature_destroy(sig);
free(old_data);
send_status(fd, STATUS_ERROR);
free(full_path);
free(check_path);
return NULL;
}
Data *raw_delta = delta_data;
if (config->use_compression) {
raw_delta = data_decompress(delta_data);
data_destroy(delta_data);
if (!raw_delta) {
free(old_data);
delta_signature_destroy(sig);
send_status(fd, STATUS_ERROR);
free(full_path);
free(check_path);
return NULL;
}
}
Delta *delta = delta_deserialize(raw_delta);
data_destroy(raw_delta);
if (!delta) {
free(old_data);
delta_signature_destroy(sig);
send_status(fd, STATUS_ERROR);
free(full_path);
free(check_path);
return NULL;
}
void *new_data = delta_apply(old_data, old_size, delta,
config->delta_block_size);
uint64_t new_size = delta->new_file_size;
delta_destroy(delta);
if (!new_data) {
free(old_data);
delta_signature_destroy(sig);
send_status(fd, STATUS_ERROR);
free(full_path);
free(check_path);
return NULL;
}
File *file = file_create(check_path);
free(check_path);
free(full_path);
if (!file) {
free(new_data);
free(old_data);
delta_signature_destroy(sig);
send_status(fd, STATUS_ERROR);
return NULL;
}
if (config->use_metadata) {
int meta_ok = 1;
file->metadata = metadata_receive(fd, &meta_ok);
if (!meta_ok) {
file_destroy(file);
free(new_data);
free(old_data);
delta_signature_destroy(sig);
send_status(fd, STATUS_ERROR);
return NULL;
}
}
data_destroy(file->data);
file->data = data_create(new_data, (size_t)new_size);
free(old_data);
delta_signature_destroy(sig);
return file;
}
if (resp == STATUS_NEXT) {
delta_signature_destroy(sig);
free(old_data);
File *file = file_create(check_path);
free(check_path);
free(full_path);
if (!file) { send_status(fd, STATUS_ERROR); return NULL; }
if (config->use_metadata) {
int meta_ok = 1;
file->metadata = metadata_receive(fd, &meta_ok);
if (!meta_ok) { file_destroy(file); send_status(fd, STATUS_ERROR); return NULL; }
}
Data *file_data = receive_data(fd);
if (file_data == NULL) {
file_destroy(file);
send_status(fd, STATUS_ERROR);
return NULL;
}
if (config->use_compression) {
Data *uncompressed = data_decompress(file_data);
data_destroy(file_data);
if (uncompressed == NULL) { file_destroy(file); send_status(fd, STATUS_ERROR); return NULL; }
file_data = uncompressed;
}
data_destroy(file->data);
file->data = file_data;
return file;
}
delta_signature_destroy(sig);
free(old_data);
try_delta = false;
}
}
}
}
}
if (!try_delta) {
if (!send_status(fd, STATUS_NEXT)) {
free(full_path);
free(check_path);
return NULL;
}
}
File *file = file_create(check_path);
free(check_path);
free(full_path);
if (file == NULL) { send_status(fd, STATUS_ERROR); return NULL; }
if (config->use_metadata) {
+4
View File
@@ -127,6 +127,10 @@ static const char *status_to_string(Status status) {
return "CHUNK";
case STATUS_CHECK:
return "CHECK";
case STATUS_DELTA_SIGNATURE:
return "DELTA_SIGNATURE";
case STATUS_DELTA_DATA:
return "DELTA_DATA";
default:
return "UNKNOWN";
}
+1 -1
View File
@@ -8,7 +8,7 @@
typedef struct ssl_st SSL;
typedef int Status;
enum NET_STATUS { STATUS_OK, STATUS_ERROR, STATUS_FINISHED, STATUS_NEXT, STATUS_CHUNK, STATUS_MANIFEST, STATUS_CHECK };
enum NET_STATUS { STATUS_OK, STATUS_ERROR, STATUS_FINISHED, STATUS_NEXT, STATUS_CHUNK, STATUS_MANIFEST, STATUS_CHECK, STATUS_DELTA_SIGNATURE, STATUS_DELTA_DATA };
void io_set_fds(int read_fd, int write_fd);
void io_set_bwlimit(unsigned long long bytes_per_sec);
+7490
View File
File diff suppressed because it is too large Load Diff
+2
View File
@@ -2,6 +2,7 @@
#include "test_chunk.h"
#include "test_compression.h"
#include "test_config.h"
#include "test_delta.h"
#include "test_queue.h"
#include "test_scanner.h"
#include "test_shared_utils.h"
@@ -23,6 +24,7 @@ int main() {
RUN_TEST(test_config);
RUN_TEST(test_compression);
RUN_TEST(test_scanner);
RUN_TEST(test_delta);
printf("\n\033[1;36m=== TEST SUMMARY ===\033[0m\n");
printf("Total Tests Run: %d\n", tests_run);
+283
View File
@@ -0,0 +1,283 @@
#include "test_utils.h"
#include "delta.h"
#include <string.h>
#include <stdlib.h>
static void test_adler32_basic() {
const char *data = "Hello";
uint32_t h = delta_adler32(data, 5);
EXPECT_TRUE(h != 0);
uint32_t h2 = delta_adler32(data, 5);
EXPECT_EQ_INT((int)h, (int)h2);
}
static void test_adler32_different_data() {
const char *a = "AAAA";
const char *b = "BBBB";
uint32_t ha = delta_adler32(a, 4);
uint32_t hb = delta_adler32(b, 4);
EXPECT_TRUE(ha != hb);
}
static void test_xxhash32_basic() {
const char *data = "Hello";
uint32_t h = delta_xxhash32(data, 5);
EXPECT_TRUE(h != 0);
uint32_t h2 = delta_xxhash32(data, 5);
EXPECT_EQ_INT((int)h, (int)h2);
}
static void test_xxhash32_different_data() {
const char *a = "AAAA";
const char *b = "BBBB";
uint32_t ha = delta_xxhash32(a, 4);
uint32_t hb = delta_xxhash32(b, 4);
EXPECT_TRUE(ha != hb);
}
static void test_signature_roundtrip() {
char old_data[4096];
for (int i = 0; i < 4096; i++) old_data[i] = (char)(i % 256);
DeltaSignature *sig = delta_signature_create(old_data, 4096, 1024);
EXPECT_NOT_NULL(sig);
EXPECT_EQ_INT((int)sig->block_count, 4);
EXPECT_EQ_INT((int)sig->block_size, 1024);
Data *serialized = delta_signature_serialize(sig);
EXPECT_NOT_NULL(serialized);
DeltaSignature *deserialized = delta_signature_deserialize(serialized);
EXPECT_NOT_NULL(deserialized);
EXPECT_EQ_INT((int)deserialized->block_count, (int)sig->block_count);
EXPECT_EQ_INT((int)deserialized->block_size, (int)sig->block_size);
for (uint32_t i = 0; i < sig->block_count; i++) {
EXPECT_EQ_INT((int)deserialized->blocks[i].adler32, (int)sig->blocks[i].adler32);
EXPECT_EQ_INT((int)deserialized->blocks[i].xxhash, (int)sig->blocks[i].xxhash);
}
delta_signature_destroy(sig);
data_destroy(serialized);
delta_signature_destroy(deserialized);
}
static void test_delta_identical_files() {
char data[2048];
for (int i = 0; i < 2048; i++) data[i] = (char)(i % 128);
DeltaSignature *sig = delta_signature_create(data, 2048, 512);
EXPECT_NOT_NULL(sig);
Delta *delta = delta_compute(data, 2048, sig, 512);
EXPECT_NOT_NULL(delta);
bool has_match = false;
for (uint32_t i = 0; i < delta->instruction_count; i++) {
if (delta->instructions[i].type == DELTA_INSTR_BLOCK_MATCH) {
has_match = true;
break;
}
}
EXPECT_TRUE(has_match);
bool all_match = true;
for (uint32_t i = 0; i < delta->instruction_count; i++) {
if (delta->instructions[i].type != DELTA_INSTR_BLOCK_MATCH) {
all_match = false;
break;
}
}
EXPECT_TRUE(all_match);
delta_signature_destroy(sig);
delta_destroy(delta);
}
static void test_delta_small_edit() {
char old_data[4096];
char new_data[4096];
for (int i = 0; i < 4096; i++) {
old_data[i] = (char)(i % 256);
new_data[i] = old_data[i];
}
new_data[100] = 'X';
new_data[101] = 'Y';
new_data[102] = 'Z';
DeltaSignature *sig = delta_signature_create(old_data, 4096, 1024);
EXPECT_NOT_NULL(sig);
Delta *delta = delta_compute(new_data, 4096, sig, 1024);
EXPECT_NOT_NULL(delta);
uint64_t total_literal = 0;
uint32_t match_count = 0;
for (uint32_t i = 0; i < delta->instruction_count; i++) {
if (delta->instructions[i].type == DELTA_INSTR_LITERAL)
total_literal += delta->instructions[i].literal.length;
else
match_count++;
}
EXPECT_TRUE(match_count > 0);
EXPECT_TRUE(total_literal < 4096);
void *reconstructed = delta_apply(old_data, 4096, delta, 1024);
EXPECT_NOT_NULL(reconstructed);
EXPECT_EQ_INT(memcmp(reconstructed, new_data, 4096), 0);
free(reconstructed);
delta_signature_destroy(sig);
delta_destroy(delta);
}
static void test_delta_completely_different() {
char old_data[4096];
char new_data[4096];
for (int i = 0; i < 4096; i++) {
old_data[i] = (char)(i * 7 + 3);
new_data[i] = (char)(i * 13 + 97);
}
DeltaSignature *sig = delta_signature_create(old_data, 4096, 1024);
EXPECT_NOT_NULL(sig);
Delta *delta = delta_compute(new_data, 4096, sig, 1024);
EXPECT_NOT_NULL(delta);
bool has_match = false;
for (uint32_t i = 0; i < delta->instruction_count; i++) {
if (delta->instructions[i].type == DELTA_INSTR_BLOCK_MATCH) {
has_match = true;
break;
}
}
EXPECT_TRUE(!has_match);
EXPECT_TRUE(!delta_is_worthwhile(delta, 4096));
delta_signature_destroy(sig);
delta_destroy(delta);
}
static void test_delta_serialize_roundtrip() {
char old_data[4096];
char new_data[4096];
for (int i = 0; i < 4096; i++) {
old_data[i] = (char)(i % 256);
new_data[i] = old_data[i];
}
new_data[500] = 'A';
new_data[501] = 'B';
DeltaSignature *sig = delta_signature_create(old_data, 4096, 1024);
Delta *delta = delta_compute(new_data, 4096, sig, 1024);
EXPECT_NOT_NULL(delta);
Data *serialized = delta_serialize(delta);
EXPECT_NOT_NULL(serialized);
Delta *deserialized = delta_deserialize(serialized);
EXPECT_NOT_NULL(deserialized);
EXPECT_EQ_INT((int)deserialized->new_file_size, (int)delta->new_file_size);
EXPECT_EQ_INT((int)deserialized->instruction_count, (int)delta->instruction_count);
void *reconstructed = delta_apply(old_data, 4096, deserialized, 1024);
EXPECT_NOT_NULL(reconstructed);
EXPECT_EQ_INT(memcmp(reconstructed, new_data, 4096), 0);
free(reconstructed);
data_destroy(serialized);
delta_destroy(deserialized);
delta_signature_destroy(sig);
delta_destroy(delta);
}
static void test_delta_file_growth() {
char old_data[2048];
char new_data[3072];
for (int i = 0; i < 2048; i++) old_data[i] = (char)(i % 256);
memcpy(new_data, old_data, 2048);
for (int i = 2048; i < 3072; i++) new_data[i] = (char)(i % 256);
DeltaSignature *sig = delta_signature_create(old_data, 2048, 512);
EXPECT_NOT_NULL(sig);
Delta *delta = delta_compute(new_data, 3072, sig, 512);
EXPECT_NOT_NULL(delta);
void *reconstructed = delta_apply(old_data, 2048, delta, 512);
EXPECT_NOT_NULL(reconstructed);
EXPECT_EQ_INT(delta->new_file_size, 3072);
EXPECT_EQ_INT(memcmp(reconstructed, new_data, 3072), 0);
free(reconstructed);
delta_signature_destroy(sig);
delta_destroy(delta);
}
static void test_delta_file_shrink() {
char old_data[3072];
char new_data[2048];
for (int i = 0; i < 3072; i++) old_data[i] = (char)(i % 256);
for (int i = 0; i < 2048; i++) new_data[i] = old_data[i];
DeltaSignature *sig = delta_signature_create(old_data, 3072, 512);
EXPECT_NOT_NULL(sig);
Delta *delta = delta_compute(new_data, 2048, sig, 512);
EXPECT_NOT_NULL(delta);
void *reconstructed = delta_apply(old_data, 3072, delta, 512);
EXPECT_NOT_NULL(reconstructed);
EXPECT_EQ_INT(delta->new_file_size, 2048);
EXPECT_EQ_INT(memcmp(reconstructed, new_data, 2048), 0);
free(reconstructed);
delta_signature_destroy(sig);
delta_destroy(delta);
}
static void test_should_attempt() {
EXPECT_TRUE(delta_should_attempt(100000, 100000));
EXPECT_TRUE(!delta_should_attempt(100, 100));
EXPECT_TRUE(!delta_should_attempt(100000, 10));
EXPECT_TRUE(!delta_should_attempt(300000000, 300000000));
EXPECT_TRUE(delta_should_attempt(50000, 60000));
EXPECT_TRUE(!delta_should_attempt(50000, 600000));
}
static void test_is_worthwhile() {
Delta d;
d.instruction_count = 1;
DeltaInstruction instr;
instr.type = DELTA_INSTR_BLOCK_MATCH;
d.instructions = &instr;
d.delta_size = 100;
EXPECT_TRUE(delta_is_worthwhile(&d, 1000));
d.delta_size = 800;
EXPECT_TRUE(!delta_is_worthwhile(&d, 1000));
d.instruction_count = 1;
instr.type = DELTA_INSTR_LITERAL;
EXPECT_TRUE(!delta_is_worthwhile(&d, 1000));
EXPECT_TRUE(!delta_is_worthwhile(NULL, 1000));
}
void test_delta() {
test_adler32_basic();
test_adler32_different_data();
test_xxhash32_basic();
test_xxhash32_different_data();
test_signature_roundtrip();
test_delta_identical_files();
test_delta_small_edit();
test_delta_completely_different();
test_delta_serialize_roundtrip();
test_delta_file_growth();
test_delta_file_shrink();
test_should_attempt();
test_is_worthwhile();
}
+6
View File
@@ -0,0 +1,6 @@
#ifndef TEST_DELTA_H
#define TEST_DELTA_H
void test_delta(void);
#endif