From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:34177) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1d1qXF-00013d-NP for qemu-devel@nongnu.org; Sat, 22 Apr 2017 04:36:54 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1d1qXD-0003tz-C0 for qemu-devel@nongnu.org; Sat, 22 Apr 2017 04:36:53 -0400 Received: from szxga01-in.huawei.com ([45.249.212.187]:3512 helo=dggrg01-dlp.huawei.com) by eggs.gnu.org with esmtps (TLS1.0:RSA_ARCFOUR_SHA1:16) (Exim 4.71) (envelope-from ) id 1d1qXC-0003s5-Gc for qemu-devel@nongnu.org; Sat, 22 Apr 2017 04:36:51 -0400 From: zhanghailiang Date: Sat, 22 Apr 2017 16:35:23 +0800 Message-ID: <1492850128-17472-14-git-send-email-zhang.zhanghailiang@huawei.com> In-Reply-To: <1492850128-17472-1-git-send-email-zhang.zhanghailiang@huawei.com> References: <1492850128-17472-1-git-send-email-zhang.zhanghailiang@huawei.com> MIME-Version: 1.0 Content-Type: text/plain Subject: [Qemu-devel] [PATCH RESEND v2 13/18] COLO: Separate the process of saving/loading ram and device state List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: qemu-devel@nongnu.org, dgilbert@redhat.com Cc: quintela@redhat.com, zhangchen.fnst@cn.fujitsu.com, zhanghailiang , Li Zhijian We separate the process of saving/loading ram and device state when do checkpoint. We add new helpers for save/load ram/device. With this change, we can directly transfer RAM from primary side to secondary side without using channel-buffer as assistant, which also reduce the size of extra memory was used during checkpoint. Besides, we move the colo_flush_ram_cache to the proper position after the above change. Cc: Juan Quintela Signed-off-by: zhanghailiang Signed-off-by: Li Zhijian Reviewed-by: Dr. David Alan Gilbert --- migration/colo.c | 49 +++++++++++++++++++++++++++++++++++++++---------- migration/ram.c | 5 ----- migration/savevm.c | 4 ++++ 3 files changed, 43 insertions(+), 15 deletions(-) diff --git a/migration/colo.c b/migration/colo.c index e62da93..8e27a4c 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -357,11 +357,20 @@ static int colo_do_checkpoint_transaction(MigrationState *s, goto out; } + colo_send_message(s->to_dst_file, COLO_MESSAGE_VMSTATE_SEND, &local_err); + if (local_err) { + goto out; + } + /* Disable block migration */ s->params.blk = 0; s->params.shared = 0; - qemu_savevm_state_header(fb); - qemu_savevm_state_begin(fb, &s->params); + qemu_savevm_state_begin(s->to_dst_file, &s->params); + ret = qemu_file_get_error(s->to_dst_file); + if (ret < 0) { + error_report("Save VM state begin error"); + goto out; + } /* We call this API although this may do nothing on primary side. */ qemu_mutex_lock_iothread(); @@ -372,15 +381,21 @@ static int colo_do_checkpoint_transaction(MigrationState *s, } qemu_mutex_lock_iothread(); - qemu_savevm_state_complete_precopy(fb, false); + /* + * Only save VM's live state, which not including device state. + * TODO: We may need a timeout mechanism to prevent COLO process + * to be blocked here. + */ + qemu_savevm_live_state(s->to_dst_file); + /* Note: device state is saved into buffer */ + ret = qemu_save_device_state(fb); qemu_mutex_unlock_iothread(); - - qemu_fflush(fb); - - colo_send_message(s->to_dst_file, COLO_MESSAGE_VMSTATE_SEND, &local_err); - if (local_err) { + if (ret < 0) { + error_report("Save device state error"); goto out; } + qemu_fflush(fb); + /* * We need the size of the VMstate data in Secondary side, * With which we can decide how much data should be read. @@ -621,6 +636,7 @@ void *colo_process_incoming_thread(void *opaque) uint64_t total_size; uint64_t value; Error *local_err = NULL; + int ret; qemu_sem_init(&mis->colo_incoming_sem, 0); @@ -693,6 +709,17 @@ void *colo_process_incoming_thread(void *opaque) goto out; } + ret = qemu_loadvm_state_begin(mis->from_src_file); + if (ret < 0) { + error_report("Load vm state begin error, ret=%d", ret); + goto out; + } + ret = qemu_loadvm_state_main(mis->from_src_file, mis); + if (ret < 0) { + error_report("Load VM's live state (ram) error"); + goto out; + } + value = colo_receive_message_value(mis->from_src_file, COLO_MESSAGE_VMSTATE_SIZE, &local_err); if (local_err) { @@ -726,8 +753,10 @@ void *colo_process_incoming_thread(void *opaque) qemu_mutex_lock_iothread(); qemu_system_reset(VMRESET_SILENT); vmstate_loading = true; - if (qemu_loadvm_state(fb) < 0) { - error_report("COLO: loadvm failed"); + colo_flush_ram_cache(); + ret = qemu_load_device_state(fb); + if (ret < 0) { + error_report("COLO: load device state failed"); qemu_mutex_unlock_iothread(); goto out; } diff --git a/migration/ram.c b/migration/ram.c index df10d4b..f171a82 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -2602,7 +2602,6 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id) bool postcopy_running = postcopy_state_get() >= POSTCOPY_INCOMING_LISTENING; /* ADVISE is earlier, it shows the source has the postcopy capability on */ bool postcopy_advised = postcopy_state_get() >= POSTCOPY_INCOMING_ADVISE; - bool need_flush = false; seq_iter++; @@ -2637,7 +2636,6 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id) /* After going into COLO, we should load the Page into colo_cache */ if (migration_incoming_in_colo_state()) { host = colo_cache_from_block_offset(block, addr); - need_flush = true; } else { host = host_from_ram_block_offset(block, addr); } @@ -2745,9 +2743,6 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id) rcu_read_unlock(); trace_ram_load_complete(ret, seq_iter); - if (!ret && ram_cache_enable && need_flush) { - colo_flush_ram_cache(); - } return ret; } diff --git a/migration/savevm.c b/migration/savevm.c index 8c2ce0b..60d346c 100644 --- a/migration/savevm.c +++ b/migration/savevm.c @@ -1003,6 +1003,10 @@ void qemu_savevm_state_begin(QEMUFile *f, break; } } + if (migration_in_colo_state()) { + qemu_put_byte(f, QEMU_VM_EOF); + qemu_fflush(f); + } } /* -- 1.8.3.1