* zhanghailiang (zhang.zhanghaili...@huawei.com) wrote:
> We should not load PVM's state directly into SVM, because there maybe some
> errors happen when SVM is receving data, which will break SVM.
>
> We need to ensure receving all data before load the state into SVM. We use
> an extra memory to cache these data (PVM's ram). The ram cache in secondary
> side
> is initially the same as SVM/PVM's memory. And in the process of checkpoint,
> we cache the dirty pages of PVM into this ram cache firstly, so this ram cache
> always the same as PVM's memory at every checkpoint, then we flush this
> cached ram
> to SVM after we receive all PVM's state.
>
> Signed-off-by: zhanghailiang <zhang.zhanghaili...@huawei.com>
> Signed-off-by: Li Zhijian <lizhij...@cn.fujitsu.com>
> Signed-off-by: Gonglei <arei.gong...@huawei.com>
> ---
> v11:
> - Rename 'host_cache' to 'colo_cache' (Dave's suggestion)
> v10:
> - Split the process of dirty pages recording into a new patch
> ---
> include/exec/ram_addr.h | 1 +
> include/migration/migration.h | 4 +++
> migration/colo.c | 10 +++++++
> migration/ram.c | 69
> ++++++++++++++++++++++++++++++++++++++++++-
> 4 files changed, 83 insertions(+), 1 deletion(-)
>
> diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h
> index 7115154..bb44f66 100644
> --- a/include/exec/ram_addr.h
> +++ b/include/exec/ram_addr.h
> @@ -26,6 +26,7 @@ struct RAMBlock {
> struct rcu_head rcu;
> struct MemoryRegion *mr;
> uint8_t *host;
> + uint8_t *colo_cache; /* For colo, VM's ram cache */
> ram_addr_t offset;
> ram_addr_t used_length;
> ram_addr_t max_length;
> diff --git a/include/migration/migration.h b/include/migration/migration.h
> index ba5bcec..e41372d 100644
> --- a/include/migration/migration.h
> +++ b/include/migration/migration.h
> @@ -332,4 +332,8 @@ int ram_save_queue_pages(MigrationState *ms, const char
> *rbname,
> PostcopyState postcopy_state_get(void);
> /* Set the state and return the old state */
> PostcopyState postcopy_state_set(PostcopyState new_state);
> +
> +/* ram cache */
> +int colo_init_ram_cache(void);
> +void colo_release_ram_cache(void);
> #endif
> diff --git a/migration/colo.c b/migration/colo.c
> index 012d8e5..6e933fa 100644
> --- a/migration/colo.c
> +++ b/migration/colo.c
> @@ -304,6 +304,12 @@ void *colo_process_incoming_thread(void *opaque)
> qemu_set_block(qemu_get_fd(mis->from_src_file));
>
>
> + ret = colo_init_ram_cache();
> + if (ret < 0) {
> + error_report("Failed to initialize ram cache");
> + goto out;
> + }
> +
> ret = colo_ctl_put(mis->to_src_file, COLO_COMMAND_CHECKPOINT_READY, 0);
> if (ret < 0) {
> goto out;
> @@ -353,6 +359,10 @@ out:
> strerror(-ret));
> }
>
> + qemu_mutex_lock_iothread();
> + colo_release_ram_cache();
> + qemu_mutex_unlock_iothread();
> +
> if (mis->to_src_file) {
> qemu_fclose(mis->to_src_file);
> }
> diff --git a/migration/ram.c b/migration/ram.c
> index a161620..9d946a1 100644
> --- a/migration/ram.c
> +++ b/migration/ram.c
> @@ -223,6 +223,7 @@ static RAMBlock *last_sent_block;
> static ram_addr_t last_offset;
> static QemuMutex migration_bitmap_mutex;
> static uint64_t migration_dirty_pages;
> +static bool ram_cache_enable;
> static uint32_t last_version;
> static bool ram_bulk_stage;
>
> @@ -2175,6 +2176,16 @@ static inline void
> *host_from_ram_block_offset(RAMBlock *block,
> return block->host + offset;
> }
>
> +static inline void *colo_cache_from_block_offset(RAMBlock *block,
> + ram_addr_t offset)
> +{
> + if (!block) {
> + return NULL;
> + }
> +
> + return block->colo_cache + offset;
> +}
> +
> /*
> * If a page (or a whole RDMA chunk) has been
> * determined to be zero, then zap it.
> @@ -2454,7 +2465,12 @@ static int ram_load(QEMUFile *f, void *opaque, int
> version_id)
> RAM_SAVE_FLAG_COMPRESS_PAGE | RAM_SAVE_FLAG_XBZRLE)) {
> RAMBlock *block = ram_block_from_stream(f, addr, flags);
>
> - host = host_from_ram_block_offset(block, addr);
> + /* After going into COLO, we should load the Page into
> colo_cache */
> + if (ram_cache_enable) {
> + host = colo_cache_from_block_offset(block, addr);
> + } else {
> + host = host_from_ram_block_offset(block, addr);
> + }
> if (!host) {
> error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
> ret = -EINVAL;
> @@ -2550,6 +2566,57 @@ static int ram_load(QEMUFile *f, void *opaque, int
> version_id)
> return ret;
> }
>
> +/*
> + * colo cache: this is for secondary VM, we cache the whole
> + * memory of the secondary VM, it will be called after first migration.
> + */
> +int colo_init_ram_cache(void)
> +{
> + RAMBlock *block;
> +
> + rcu_read_lock();
> + QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
> + block->colo_cache = qemu_anon_ram_alloc(block->used_length, NULL);
> + if (!block->colo_cache) {
> + error_report("%s: Can't alloc memory for colo cache of block %s,"
> + "size %zu", __func__, block->idstr,
> + block->used_length);
Minor one that I didn't spot before; I think that has to be RAM_ADDR_FMT
instead of %zu
However, other than that;
Reviewed-by: Dr. David Alan Gilbert <dgilb...@redhat.com>
Dave
> + goto out_locked;
> + }
> + memcpy(block->colo_cache, block->host, block->used_length);
> + }
> + rcu_read_unlock();
> + ram_cache_enable = true;
> + return 0;
> +
> +out_locked:
> + QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
> + if (block->colo_cache) {
> + qemu_anon_ram_free(block->colo_cache, block->used_length);
> + block->colo_cache = NULL;
> + }
> + }
> +
> + rcu_read_unlock();
> + return -errno;
> +}
> +
> +void colo_release_ram_cache(void)
> +{
> + RAMBlock *block;
> +
> + ram_cache_enable = false;
> +
> + rcu_read_lock();
> + QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
> + if (block->colo_cache) {
> + qemu_anon_ram_free(block->colo_cache, block->used_length);
> + block->colo_cache = NULL;
> + }
> + }
> + rcu_read_unlock();
> +}
> +
> static SaveVMHandlers savevm_ram_handlers = {
> .save_live_setup = ram_save_setup,
> .save_live_iterate = ram_save_iterate,
> --
> 1.8.3.1
>
>
--
Dr. David Alan Gilbert / dgilb...@redhat.com / Manchester, UK
