qemu-e2k/block/qcow2.h
Kevin Wolf f214978a42 qcow2: Order concurrent AIO requests on the same unallocated cluster
When two AIO requests write to the same cluster, and this cluster is
unallocated, currently both requests allocate a new cluster and the second one
merges the first one when it is completed. This means an cluster allocation, a
read and a cluster deallocation which cause some overhead. If we simply let the
second request wait until the first one is done, we improve overall performance
with AIO requests (specifially, qcow2/virtio combinations).

This patch maintains a list of in-flight requests that have allocated new
clusters. A second request touching the same cluster is limited so that it
either doesn't touch the allocation of the first request (so it can have a
non-overlapping allocation) or it waits for the first request to complete.

Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2009-09-09 17:31:26 -05:00

215 lines
6.8 KiB
C

/*
* Block driver for the QCOW version 2 format
*
* Copyright (c) 2004-2006 Fabrice Bellard
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#ifndef BLOCK_QCOW2_H
#define BLOCK_QCOW2_H
#include "aes.h"
//#define DEBUG_ALLOC
//#define DEBUG_ALLOC2
//#define DEBUG_EXT
#define QCOW_MAGIC (('Q' << 24) | ('F' << 16) | ('I' << 8) | 0xfb)
#define QCOW_VERSION 2
#define QCOW_CRYPT_NONE 0
#define QCOW_CRYPT_AES 1
#define QCOW_MAX_CRYPT_CLUSTERS 32
/* indicate that the refcount of the referenced cluster is exactly one. */
#define QCOW_OFLAG_COPIED (1LL << 63)
/* indicate that the cluster is compressed (they never have the copied flag) */
#define QCOW_OFLAG_COMPRESSED (1LL << 62)
#define REFCOUNT_SHIFT 1 /* refcount size is 2 bytes */
#define MIN_CLUSTER_BITS 9
#define MAX_CLUSTER_BITS 16
#define L2_CACHE_SIZE 16
typedef struct QCowHeader {
uint32_t magic;
uint32_t version;
uint64_t backing_file_offset;
uint32_t backing_file_size;
uint32_t cluster_bits;
uint64_t size; /* in bytes */
uint32_t crypt_method;
uint32_t l1_size; /* XXX: save number of clusters instead ? */
uint64_t l1_table_offset;
uint64_t refcount_table_offset;
uint32_t refcount_table_clusters;
uint32_t nb_snapshots;
uint64_t snapshots_offset;
} QCowHeader;
typedef struct QCowSnapshot {
uint64_t l1_table_offset;
uint32_t l1_size;
char *id_str;
char *name;
uint32_t vm_state_size;
uint32_t date_sec;
uint32_t date_nsec;
uint64_t vm_clock_nsec;
} QCowSnapshot;
typedef struct BDRVQcowState {
BlockDriverState *hd;
int cluster_bits;
int cluster_size;
int cluster_sectors;
int l2_bits;
int l2_size;
int l1_size;
int l1_vm_state_index;
int csize_shift;
int csize_mask;
uint64_t cluster_offset_mask;
uint64_t l1_table_offset;
uint64_t *l1_table;
uint64_t *l2_cache;
uint64_t l2_cache_offsets[L2_CACHE_SIZE];
uint32_t l2_cache_counts[L2_CACHE_SIZE];
uint8_t *cluster_cache;
uint8_t *cluster_data;
uint64_t cluster_cache_offset;
LIST_HEAD(QCowClusterAlloc, QCowL2Meta) cluster_allocs;
uint64_t *refcount_table;
uint64_t refcount_table_offset;
uint32_t refcount_table_size;
uint64_t refcount_block_cache_offset;
uint16_t *refcount_block_cache;
int64_t free_cluster_index;
int64_t free_byte_offset;
uint32_t crypt_method; /* current crypt method, 0 if no key yet */
uint32_t crypt_method_header;
AES_KEY aes_encrypt_key;
AES_KEY aes_decrypt_key;
uint64_t snapshots_offset;
int snapshots_size;
int nb_snapshots;
QCowSnapshot *snapshots;
} BDRVQcowState;
/* XXX: use std qcow open function ? */
typedef struct QCowCreateState {
int cluster_size;
int cluster_bits;
uint16_t *refcount_block;
uint64_t *refcount_table;
int64_t l1_table_offset;
int64_t refcount_table_offset;
int64_t refcount_block_offset;
} QCowCreateState;
struct QCowAIOCB;
/* XXX This could be private for qcow2-cluster.c */
typedef struct QCowL2Meta
{
uint64_t offset;
int n_start;
int nb_available;
int nb_clusters;
struct QCowL2Meta *depends_on;
LIST_HEAD(QCowAioDependencies, QCowAIOCB) dependent_requests;
LIST_ENTRY(QCowL2Meta) next_in_flight;
} QCowL2Meta;
static inline int size_to_clusters(BDRVQcowState *s, int64_t size)
{
return (size + (s->cluster_size - 1)) >> s->cluster_bits;
}
static inline int64_t align_offset(int64_t offset, int n)
{
offset = (offset + n - 1) & ~(n - 1);
return offset;
}
// FIXME Need qcow2_ prefix to global functions
/* qcow2.c functions */
int qcow2_backing_read1(BlockDriverState *bs,
int64_t sector_num, uint8_t *buf, int nb_sectors);
/* qcow2-refcount.c functions */
int qcow2_refcount_init(BlockDriverState *bs);
void qcow2_refcount_close(BlockDriverState *bs);
int64_t qcow2_alloc_clusters(BlockDriverState *bs, int64_t size);
int64_t qcow2_alloc_bytes(BlockDriverState *bs, int size);
void qcow2_free_clusters(BlockDriverState *bs,
int64_t offset, int64_t size);
void qcow2_free_any_clusters(BlockDriverState *bs,
uint64_t cluster_offset, int nb_clusters);
void qcow2_create_refcount_update(QCowCreateState *s, int64_t offset,
int64_t size);
int qcow2_update_snapshot_refcount(BlockDriverState *bs,
int64_t l1_table_offset, int l1_size, int addend);
int qcow2_check_refcounts(BlockDriverState *bs);
/* qcow2-cluster.c functions */
int qcow2_grow_l1_table(BlockDriverState *bs, int min_size);
void qcow2_l2_cache_reset(BlockDriverState *bs);
int qcow2_decompress_cluster(BDRVQcowState *s, uint64_t cluster_offset);
void qcow2_encrypt_sectors(BDRVQcowState *s, int64_t sector_num,
uint8_t *out_buf, const uint8_t *in_buf,
int nb_sectors, int enc,
const AES_KEY *key);
uint64_t qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
int *num);
uint64_t qcow2_alloc_cluster_offset(BlockDriverState *bs,
uint64_t offset,
int n_start, int n_end,
int *num, QCowL2Meta *m);
uint64_t qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs,
uint64_t offset,
int compressed_size);
int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, uint64_t cluster_offset,
QCowL2Meta *m);
/* qcow2-snapshot.c functions */
int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info);
int qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id);
int qcow2_snapshot_delete(BlockDriverState *bs, const char *snapshot_id);
int qcow2_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab);
void qcow2_free_snapshots(BlockDriverState *bs);
int qcow2_read_snapshots(BlockDriverState *bs);
#endif