markbase/docs/fuse_poc/markbase_v12_final.c

#define FUSE_USE_VERSION 31
#include <fuse3/fuse.h>
#include <stdio.h>
#include <string.h>
#include <errno.h>
#include <fcntl.h>
#include <sqlite3.h>
#include <stdlib.h>
#include <sys/stat.h>
#include <unistd.h>
#include <pthread.h>

static sqlite3 *db = NULL;
static const char *db_path = "/Users/accusys/markbase/data/users/warren.sqlite";
static pthread_mutex_t db_mutex = PTHREAD_MUTEX_INITIALIZER;

// Large buffer for optimized reading
#define READ_CHUNK_SIZE 262144  // 256KB chunks

typedef struct {
    char node_id[64];
    char file_path[512];
    long file_size;
} FileCacheEntry;

#define CACHE_SIZE 200
static FileCacheEntry file_cache[CACHE_SIZE];
static int cache_count = 0;

typedef struct {
    char node_id[64];
    char node_type[20];
    long file_size;
} NodeCacheEntry;

#define NODE_CACHE_SIZE 500
static NodeCacheEntry node_cache[NODE_CACHE_SIZE];
static int node_cache_count = 0;

static int init_db() {
    if (sqlite3_open_v2(db_path, &db, SQLITE_OPEN_READONLY | SQLITE_OPEN_NOMUTEX, NULL) != SQLITE_OK) {
        fprintf(stderr, "Cannot open database\n");
        return -1;
    }
    printf("Database opened\n");
    return 0;
}

static FileCacheEntry* cache_lookup(const char *node_id) {
    for (int i = 0; i < cache_count; i++) {
        if (strcmp(file_cache[i].node_id, node_id) == 0) {
            return &file_cache[i];
        }
    }
    return NULL;
}

static void cache_insert(const char *node_id, const char *file_path, long file_size) {
    for (int i = 0; i < cache_count; i++) {
        if (strcmp(file_cache[i].node_id, node_id) == 0) return;
    }
    
    if (cache_count < CACHE_SIZE) {
        strcpy(file_cache[cache_count].node_id, node_id);
        strcpy(file_cache[cache_count].file_path, file_path);
        file_cache[cache_count].file_size = file_size;
        cache_count++;
    }
}

static NodeCacheEntry* node_cache_lookup(const char *node_id) {
    for (int i = 0; i < node_cache_count; i++) {
        if (strcmp(node_cache[i].node_id, node_id) == 0) {
            return &node_cache[i];
        }
    }
    return NULL;
}

static void *mb_init(struct fuse_conn_info *conn, struct fuse_config *cfg) {
    (void) conn;
    cfg->kernel_cache = 1;
    
    init_db();
    
    // Pre-cache largest files
    const char *sql = "SELECT f.file_uuid, l.location, f.file_size "
                      "FROM file_nodes f JOIN file_locations l ON f.file_uuid = l.file_uuid "
                      "ORDER BY f.file_size DESC LIMIT 200";
    sqlite3_stmt *stmt;
    
    if (sqlite3_prepare_v2(db, sql, -1, &stmt, NULL) == SQLITE_OK) {
        while (sqlite3_step(stmt) == SQLITE_ROW) {
            cache_insert(
                (const char*)sqlite3_column_text(stmt, 0),
                (const char*)sqlite3_column_text(stmt, 1),
                sqlite3_column_int64(stmt, 2)
            );
        }
        sqlite3_finalize(stmt);
        printf("Pre-cached %d files\n", cache_count);
    }
    
    return NULL;
}

static void mb_destroy(void *userdata) {
    (void) userdata;
    if (db) sqlite3_close(db);
}

static char* find_node_id(const char *path) {
    if (strcmp(path, "/") == 0) return NULL;
    
    char *path_copy = strdup(path);
    char *components[20];
    int depth = 0;
    
    char *token = strtok(path_copy + 1, "/");
    while (token && depth < 20) {
        components[depth++] = strdup(token);
        token = strtok(NULL, "/");
    }
    free(path_copy);
    
    if (depth == 0) return NULL;
    
    char *current_parent_id = NULL;
    
    for (int level = 0; level < depth; level++) {
        const char *sql;
        sqlite3_stmt *stmt;
        
        if (level == 0) {
            sql = "SELECT node_id, node_type, file_size FROM file_nodes WHERE label = ? AND (parent_id IS NULL OR parent_id = '')";
        } else {
            sql = "SELECT node_id, node_type, file_size FROM file_nodes WHERE label = ? AND parent_id = ?";
        }
        
        if (sqlite3_prepare_v2(db, sql, -1, &stmt, NULL) != SQLITE_OK) {
            for (int i = 0; i < depth; i++) free(components[i]);
            if (current_parent_id) free(current_parent_id);
            return NULL;
        }
        
        sqlite3_bind_text(stmt, 1, components[level], -1, SQLITE_STATIC);
        if (level > 0 && current_parent_id) {
            sqlite3_bind_text(stmt, 2, current_parent_id, -1, SQLITE_STATIC);
        }
        
        if (sqlite3_step(stmt) != SQLITE_ROW) {
            sqlite3_finalize(stmt);
            for (int i = 0; i < depth; i++) free(components[i]);
            if (current_parent_id) free(current_parent_id);
            return NULL;
        }
        
        const char *found_node_id = (const char*)sqlite3_column_text(stmt, 0);
        if (node_cache_count < NODE_CACHE_SIZE) {
            strcpy(node_cache[node_cache_count].node_id, found_node_id);
            strcpy(node_cache[node_cache_count].node_type, (const char*)sqlite3_column_text(stmt, 1));
            node_cache[node_cache_count].file_size = sqlite3_column_int64(stmt, 2);
            node_cache_count++;
        }
        
        if (current_parent_id) free(current_parent_id);
        current_parent_id = strdup(found_node_id);
        
        sqlite3_finalize(stmt);
    }
    
    for (int i = 0; i < depth; i++) free(components[i]);
    return current_parent_id;
}

static int mb_getattr(const char *path, struct stat *stbuf, struct fuse_file_info *fi) {
    (void) fi;
    memset(stbuf, 0, sizeof(struct stat));
    
    if (strcmp(path, "/") == 0) {
        stbuf->st_mode = S_IFDIR | 0755;
        stbuf->st_nlink = 2;
        return 0;
    }
    
    char *node_id = find_node_id(path);
    if (!node_id) return -ENOENT;
    
    NodeCacheEntry *cached_node = node_cache_lookup(node_id);
    if (cached_node) {
        if (strcmp(cached_node->node_type, "folder") == 0) {
            stbuf->st_mode = S_IFDIR | 0755;
            stbuf->st_nlink = 2;
        } else {
            stbuf->st_mode = S_IFREG | 0444;
            stbuf->st_nlink = 1;
            stbuf->st_size = cached_node->file_size;
        }
        free(node_id);
        return 0;
    }
    
    const char *sql = "SELECT node_type, file_size FROM file_nodes WHERE node_id = ?";
    sqlite3_stmt *stmt;
    
    if (sqlite3_prepare_v2(db, sql, -1, &stmt, NULL) == SQLITE_OK) {
        sqlite3_bind_text(stmt, 1, node_id, -1, SQLITE_STATIC);
        if (sqlite3_step(stmt) == SQLITE_ROW) {
            const char *node_type = (const char*)sqlite3_column_text(stmt, 0);
            long file_size = sqlite3_column_int64(stmt, 1);
            
            if (strcmp(node_type, "folder") == 0) {
                stbuf->st_mode = S_IFDIR | 0755;
                stbuf->st_nlink = 2;
            } else {
                stbuf->st_mode = S_IFREG | 0444;
                stbuf->st_nlink = 1;
                stbuf->st_size = file_size;
            }
        }
        sqlite3_finalize(stmt);
    }
    
    free(node_id);
    return 0;
}

static int mb_readdir(const char *path, void *buf, fuse_fill_dir_t filler,
                     off_t offset, struct fuse_file_info *fi,
                     enum fuse_readdir_flags flags) {
    (void) offset; (void) fi; (void) flags;
    
    filler(buf, ".", NULL, 0, FUSE_FILL_DIR_DEFAULTS);
    filler(buf, "..", NULL, 0, FUSE_FILL_DIR_DEFAULTS);
    
    if (strcmp(path, "/") == 0) {
        sqlite3_stmt *stmt;
        if (sqlite3_prepare_v2(db, "SELECT label FROM file_nodes WHERE parent_id IS NULL OR parent_id = ''", 
                                -1, &stmt, NULL) == SQLITE_OK) {
            while (sqlite3_step(stmt) == SQLITE_ROW) {
                filler(buf, (const char*)sqlite3_column_text(stmt, 0), NULL, 0, FUSE_FILL_DIR_DEFAULTS);
            }
            sqlite3_finalize(stmt);
        }
        return 0;
    }
    
    char *parent_node_id = find_node_id(path);
    if (!parent_node_id) return -ENOENT;
    
    sqlite3_stmt *stmt;
    if (sqlite3_prepare_v2(db, "SELECT label FROM file_nodes WHERE parent_id = ?", -1, &stmt, NULL) == SQLITE_OK) {
        sqlite3_bind_text(stmt, 1, parent_node_id, -1, SQLITE_STATIC);
        while (sqlite3_step(stmt) == SQLITE_ROW) {
            filler(buf, (const char*)sqlite3_column_text(stmt, 0), NULL, 0, FUSE_FILL_DIR_DEFAULTS);
        }
        sqlite3_finalize(stmt);
    }
    
    free(parent_node_id);
    return 0;
}

static int mb_open(const char *path, struct fuse_file_info *fi) {
    if ((fi->flags & O_ACCMODE) != O_RDONLY) return -EACCES;
    char *node_id = find_node_id(path);
    if (!node_id) return -ENOENT;
    free(node_id);
    return 0;
}

static int mb_read(const char *path, char *buf, size_t size, off_t offset,
                   struct fuse_file_info *fi) {
    (void) fi;
    
    char *node_id = find_node_id(path);
    if (!node_id) return -ENOENT;
    
    FileCacheEntry *cached = cache_lookup(node_id);
    char *file_path = NULL;
    
    if (cached) {
        file_path = strdup(cached->file_path);
    } else {
        sqlite3_stmt *stmt;
        if (sqlite3_prepare_v2(db, "SELECT location FROM file_locations WHERE file_uuid = ? LIMIT 1", 
                                -1, &stmt, NULL) != SQLITE_OK) {
            free(node_id);
            return -EIO;
        }
        
        sqlite3_bind_text(stmt, 1, node_id, -1, SQLITE_STATIC);
        if (sqlite3_step(stmt) != SQLITE_ROW) {
            sqlite3_finalize(stmt);
            free(node_id);
            return -ENOENT;
        }
        
        file_path = strdup((const char*)sqlite3_column_text(stmt, 0));
        sqlite3_finalize(stmt);
        
        cache_insert(node_id, file_path, 0);
    }
    
    free(node_id);
    
    FILE *fp = fopen(file_path, "rb");
    if (!fp) {
        free(file_path);
        return -ENOENT;
    }
    
    fseek(fp, offset, SEEK_SET);
    
    size_t total_read = 0;
    while (total_read < size) {
        size_t chunk = (size - total_read > READ_CHUNK_SIZE) ? READ_CHUNK_SIZE : size - total_read;
        size_t bytes = fread(buf + total_read, 1, chunk, fp);
        total_read += bytes;
        if (bytes < chunk) break;
    }
    
    fclose(fp);
    free(file_path);
    
    return total_read;
}

static const struct fuse_operations mb_oper = {
    .init = mb_init,
    .destroy = mb_destroy,
    .getattr = mb_getattr,
    .readdir = mb_readdir,
    .open = mb_open,
    .read = mb_read,
};

int main(int argc, char *argv[]) {
    printf("MarkBase FUSE v12.0 - Final Optimized\n");
    printf("====================================\n");
    printf("Features:\n");
    printf("  - Large read chunks (256KB)\n");
    printf("  - Pre-cache 200 files\n");
    printf("  - Kernel caching\n");
    printf("  - Minimal mutex locking\n");
    printf("\n");
    return fuse_main(argc, argv, &mb_oper, NULL);
}