vdm/core/tests/io/sparse_file_test.cpp

#include "vdm/io/sparse_file.hpp"

#include <fcntl.h>
#include <unistd.h>

#include <array>
#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <string>
#include <thread>
#include <vector>

#include "vtest.hpp"

using vdm::Error;
using vdm::io::SparseFile;

namespace {

struct TempPath {
    std::string path;
    TempPath() {
        const char *dir = std::getenv("TMPDIR");
        path = (dir ? dir : "/tmp");
        path += "/vdm_sparse_test_XXXXXX";
        int fd = ::mkstemp(path.data());
        if (fd >= 0) {
            ::close(fd);
            ::unlink(path.c_str());  // we only wanted a unique name
        }
    }
    ~TempPath() { ::unlink(path.c_str()); }
};

std::vector<std::byte> read_all(const std::string &path) {
    int fd = ::open(path.c_str(), O_RDONLY);
    if (fd < 0)
        return {};
    std::vector<std::byte> out;
    std::array<std::byte, 4096> buf{};
    for (;;) {
        ssize_t n = ::read(fd, buf.data(), buf.size());
        if (n <= 0)
            break;
        out.insert(out.end(), buf.begin(), buf.begin() + n);
    }
    ::close(fd);
    return out;
}

std::uint64_t file_size(const std::string &path) {
    int fd = ::open(path.c_str(), O_RDONLY);
    if (fd < 0)
        return 0;
    off_t end = ::lseek(fd, 0, SEEK_END);
    ::close(fd);
    return end < 0 ? 0 : static_cast<std::uint64_t>(end);
}

vdm::ConstByteSpan bytes(const char *s) {
    return {reinterpret_cast<const std::byte *>(s), std::strlen(s)};
}

}  // namespace

VT_TEST(sparse_open_preallocates_full_size) {
    TempPath tp;
    SparseFile f;
    auto r = f.open(tp.path, {.total_size = 1 << 20});
    VT_REQUIRE(r.has_value());
    VT_CHECK(f.is_open());
    VT_CHECK_EQ(file_size(tp.path), 1u << 20);
    // /tmp is usually a real fs; if it's tmpfs, preallocated() is false and that's fine.
    VT_CHECK(f.close().has_value());
}

VT_TEST(sparse_write_at_absolute_offsets) {
    TempPath tp;
    SparseFile f;
    VT_REQUIRE(f.open(tp.path, {.total_size = 64}).has_value());

    VT_CHECK(f.write_at(10, bytes("hello")).has_value());
    VT_CHECK(f.write_at(40, bytes("world")).has_value());
    VT_CHECK(f.sync().has_value());

    auto data = read_all(tp.path);
    VT_REQUIRE(data.size() == 64);
    VT_CHECK_EQ(std::memcmp(data.data() + 10, "hello", 5), 0);
    VT_CHECK_EQ(std::memcmp(data.data() + 40, "world", 5), 0);
    f.close().value();
}

VT_TEST(sparse_write_past_end_grows_file) {
    TempPath tp;
    SparseFile f;
    VT_REQUIRE(f.open(tp.path, {.total_size = 16}).has_value());
    VT_CHECK(f.write_at(1000, bytes("tail")).has_value());
    VT_CHECK_EQ(file_size(tp.path), 1004u);
    f.close().value();
}

VT_TEST(sparse_resize_trims) {
    TempPath tp;
    SparseFile f;
    VT_REQUIRE(f.open(tp.path, {.total_size = 4096}).has_value());
    VT_CHECK(f.resize(100).has_value());
    VT_CHECK_EQ(file_size(tp.path), 100u);
    f.close().value();
}

VT_TEST(sparse_open_bad_path_is_path_rejected) {
    SparseFile f;
    auto r = f.open("/vdm_no_such_dir_xyz/file.part", {.total_size = 10});
    VT_REQUIRE(!r.has_value());
    VT_CHECK_EQ(r.error().code, Error::path_rejected);
    VT_CHECK(!f.is_open());
}

VT_TEST(sparse_symlinked_target_is_rejected) {
    // A symlink swapped in as the final path component after DAEMON's canonicalise-and-check
    // must not be followed: the open is O_NOFOLLOW, so it fails with ELOOP -> path_rejected
    // rather than redirecting our writes through the link.
    TempPath link;    // the download target the caller hands us
    TempPath target;  // where the symlink points (would-be victim, outside allowed roots)
    VT_REQUIRE(::symlink(target.path.c_str(), link.path.c_str()) == 0);

    SparseFile f;
    auto r = f.open(link.path, {.total_size = 4096});
    VT_REQUIRE(!r.has_value());
    VT_CHECK_EQ(r.error().code, Error::path_rejected);
    VT_CHECK(!f.is_open());
    // the link target was never created/written through
    VT_CHECK_EQ(::access(target.path.c_str(), F_OK), -1);
}

VT_TEST(sparse_ops_on_closed_file_error) {
    SparseFile f;
    VT_CHECK_EQ(f.write_at(0, bytes("x")).error().code, Error::internal);
    VT_CHECK_EQ(f.sync().error().code, Error::internal);
    VT_CHECK(f.close().has_value());  // close on a closed file is ok
}

VT_TEST(sparse_advise_dontneed_is_safe) {
    TempPath tp;
    SparseFile f;
    VT_REQUIRE(f.open(tp.path, {.total_size = 8192}).has_value());
    VT_CHECK(f.write_at(0, bytes("data")).has_value());
    VT_CHECK(f.sync().has_value());
    f.advise_dontneed(0, 4096);  // must not crash / must be a no-op-safe call
    f.advise_dontneed(0, 0);
    f.close().value();
}

VT_TEST(sparse_move_transfers_fd) {
    TempPath tp;
    SparseFile a;
    VT_REQUIRE(a.open(tp.path, {.total_size = 32}).has_value());
    SparseFile b = std::move(a);
    VT_CHECK(!a.is_open());
    VT_CHECK(b.is_open());
    VT_CHECK(b.write_at(0, bytes("moved")).has_value());
    b.close().value();
}

VT_TEST(sparse_concurrent_nonoverlapping_writes) {
    TempPath tp;
    SparseFile f;
    constexpr int kSegs = 8;
    constexpr std::size_t kSeg = 64 * 1024;
    VT_REQUIRE(f.open(tp.path, {.total_size = kSegs * kSeg}).has_value());

    std::vector<std::jthread> ts;
    for (int s = 0; s < kSegs; ++s) {
        ts.emplace_back([&, s] {
            std::vector<std::byte> chunk(kSeg, static_cast<std::byte>('A' + s));
            for (std::size_t off = 0; off < kSeg; off += 4096) {
                auto r = f.write_at(static_cast<std::uint64_t>(s) * kSeg + off,
                                    vdm::ConstByteSpan(chunk.data() + off, 4096));
                if (!r.has_value())
                    VT_FAIL("concurrent write_at failed");
            }
        });
    }
    ts.clear();  // join
    VT_CHECK(f.sync().has_value());

    auto data = read_all(tp.path);
    VT_REQUIRE(data.size() == kSegs * kSeg);
    for (int s = 0; s < kSegs; ++s) {
        bool ok = true;
        for (std::size_t i = 0; i < kSeg; ++i)
            if (data[s * kSeg + i] != static_cast<std::byte>('A' + s))
                ok = false;
        VT_CHECK(ok);
    }
    f.close().value();
}