On 01.04.2016 0:56, Sage Weil wrote:
How about this:
// in the onode:
map<uint64_t, bluestore_lextent_t> data_map;
map<int, bluestore_blob_t> blob_map;
// in the enode
map<int, bluestore_blob_t> blob_map;
struct bluestore_lextent_t {
enum {
FLAG_SHARED = 1, ///< pextent lives in enode
};
uint64_t logical_length; ///< length of logical bytes we represent
uint32_t pextent_id; ///< id of pextent in onode or enode
And I'd prefer 64-bit integer for this field as 4 Gb overwrites can
overflow the corresponding counter. That's just 4Tb data written by 4K
blocks.
uint32_t x_off, x_len; ///< relative portion of pextent with our data
uint32_t flags; ///< FLAG_*
};
struct bluestore_pextent_t {
uint64_t offset; ///< offset on disk
uint64_t length; ///< length on disk
};
struct bluestore_blob_t {
enum {
CSUM_XXHASH32 = 1,
CSUM_XXHASH64 = 2,
CSUM_CRC32C = 3,
CSUM_CRC16 = 4,
};
enum {
FLAG_IMMUTABLE = 1, ///< no overwrites allowed
FLAG_COMPRESSED = 2, ///< extent is compressed; alg is in first byte of data
};
enum {
COMP_ZLIB = 1,
COMP_SNAPPY = 2,
COMP_LZO = 3,
};
vector<bluestore_pextent_t> extents; ///< extents on disk
uint32_t logical_length; ///< uncompressed length
uint32_t flags; ///< FLAG_*
uint8_t csum_type; ///< CSUM_*
uint8_t csum_block_order;
uint16_t num_refs; ///< reference count (always 1 when in onode)
vector<char> csum_data; ///< opaque vector of csum data
uint32_t get_ondisk_length() const {
uint32_t len = 0;
for (auto &p : extentes) {
len += p.length;
}
return len;
}
uint32_t get_csum_block_size() const {
return 1 << csum_block_order;
}
size_t get_csum_value_size() const {
switch (csum_type) {
case CSUM_XXHASH32: return 4;
case CSUM_XXHASH64: return 8;
case CSUM_CRC32C: return 4;
case CSUM_CRC16: return 2;
default: return 0;
}
}
// assert (ondisk_length / csum_block_size) * csum_value_size ==
// csum_data.length()
};
--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
