* [Qemu-devel] [patch 2/3] live block copy
2010-12-16 17:44 [Qemu-devel] [patch 0/3] add support for live block copy Marcelo Tosatti
2010-12-16 17:44 ` [Qemu-devel] [patch 1/3] add migration_active function Marcelo Tosatti
@ 2010-12-16 17:44 ` Marcelo Tosatti
2011-01-14 10:46 ` Stefan Hajnoczi
2010-12-16 17:44 ` [Qemu-devel] [patch 3/3] do not allow migration if block copy in progress Marcelo Tosatti
2 siblings, 1 reply; 7+ messages in thread
From: Marcelo Tosatti @ 2010-12-16 17:44 UTC (permalink / raw)
To: qemu-devel; +Cc: Kevin Wolf, Anthony Liguori, Marcelo Tosatti
[-- Attachment #1: block-copy --]
[-- Type: text/plain, Size: 29933 bytes --]
Add support for live block copy.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Index: qemu-kvm/block-copy.c
===================================================================
--- /dev/null
+++ qemu-kvm/block-copy.c
@@ -0,0 +1,728 @@
+/*
+ * QEMU live block copy
+ *
+ * Copyright (C) 2010 Red Hat Inc.
+ *
+ * Authors: Marcelo Tosatti <mtosatti@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu-common.h"
+#include "block_int.h"
+#include "qemu-queue.h"
+#include "qemu-timer.h"
+#include "monitor.h"
+#include "block-copy.h"
+#include "migration.h"
+#include "sysemu.h"
+#include "qjson.h"
+#include <assert.h>
+
+#define BLOCK_SIZE (BDRV_SECTORS_PER_DIRTY_CHUNK << BDRV_SECTOR_BITS)
+#define MAX_IS_ALLOCATED_SEARCH 65536
+
+/*
+ * Stages:
+ *
+ * STAGE_BULK: bulk reads/writes in progress
+ * STAGE_BULK_FINISHED: bulk reads finished, bulk writes in progress
+ * STAGE_DIRTY: bulk writes finished, dirty reads/writes in progress
+ * STAGE_SWITCH_FINISHED: switched to new image.
+ */
+
+enum BdrvCopyStage {
+ STAGE_BULK,
+ STAGE_BULK_FINISHED,
+ STAGE_DIRTY,
+ STAGE_SWITCH_FINISHED,
+};
+
+typedef struct BdrvCopyState {
+ BlockDriverState *src;
+ BlockDriverState *dst;
+ bool shared_base;
+
+ int64_t curr_sector;
+ int64_t completed_sectors;
+ int64_t nr_sectors;
+
+ enum BdrvCopyStage stage;
+ int inflight_reads;
+ int error;
+ int failed;
+ int cancelled;
+ QLIST_HEAD(, BdrvCopyBlock) io_list;
+ unsigned long *aio_bitmap;
+ QEMUTimer *aio_timer;
+ QLIST_ENTRY(BdrvCopyState) list;
+
+ int64_t blocks;
+ int64_t total_time;
+
+ char src_device_name[32];
+ char dst_filename[1024];
+ int commit_fd;
+} BdrvCopyState;
+
+typedef struct BdrvCopyBlock {
+ BdrvCopyState *state;
+ uint8_t *buf;
+ int64_t sector;
+ int64_t nr_sectors;
+ struct iovec iov;
+ QEMUIOVector qiov;
+ BlockDriverAIOCB *aiocb;
+ int64_t time;
+ QLIST_ENTRY(BdrvCopyBlock) list;
+} BdrvCopyBlock;
+
+static QLIST_HEAD(, BdrvCopyState) block_copy_list =
+ QLIST_HEAD_INITIALIZER(block_copy_list);
+
+static void alloc_aio_bitmap(BdrvCopyState *s)
+{
+ BlockDriverState *bs = s->src;
+ int64_t bitmap_size;
+
+ bitmap_size = (bdrv_getlength(bs) >> BDRV_SECTOR_BITS) +
+ BDRV_SECTORS_PER_DIRTY_CHUNK * 8 - 1;
+ bitmap_size /= BDRV_SECTORS_PER_DIRTY_CHUNK * 8;
+
+ s->aio_bitmap = qemu_mallocz(bitmap_size);
+}
+
+static bool aio_inflight(BdrvCopyState *s, int64_t sector)
+{
+ int64_t chunk = sector / (int64_t)BDRV_SECTORS_PER_DIRTY_CHUNK;
+
+ if (s->aio_bitmap &&
+ (sector << BDRV_SECTOR_BITS) < bdrv_getlength(s->src)) {
+ return !!(s->aio_bitmap[chunk / (sizeof(unsigned long) * 8)] &
+ (1UL << (chunk % (sizeof(unsigned long) * 8))));
+ } else {
+ return 0;
+ }
+}
+
+static void set_aio_inflight(BdrvCopyState *s, int64_t sector_num,
+ int nb_sectors, int set)
+{
+ int64_t start, end;
+ unsigned long val, idx, bit;
+
+ start = sector_num / BDRV_SECTORS_PER_DIRTY_CHUNK;
+ end = (sector_num + nb_sectors - 1) / BDRV_SECTORS_PER_DIRTY_CHUNK;
+
+ for (; start <= end; start++) {
+ idx = start / (sizeof(unsigned long) * 8);
+ bit = start % (sizeof(unsigned long) * 8);
+ val = s->aio_bitmap[idx];
+ if (set) {
+ if (!(val & (1UL << bit))) {
+ val |= 1UL << bit;
+ }
+ } else {
+ if (val & (1UL << bit)) {
+ val &= ~(1UL << bit);
+ }
+ }
+ s->aio_bitmap[idx] = val;
+ }
+}
+
+static void blkcopy_set_stage(BdrvCopyState *s, enum BdrvCopyStage stage)
+{
+ s->stage = stage;
+
+ switch (stage) {
+ case STAGE_BULK:
+ BLKDBG_EVENT(s->dst->file, BLKDBG_BLKCOPY_STAGE_BULK);
+ break;
+ case STAGE_BULK_FINISHED:
+ BLKDBG_EVENT(s->dst->file, BLKDBG_BLKCOPY_STAGE_BULK_FINISHED);
+ break;
+ case STAGE_DIRTY:
+ BLKDBG_EVENT(s->dst->file, BLKDBG_BLKCOPY_STAGE_DIRTY);
+ break;
+ case STAGE_SWITCH_FINISHED:
+ BLKDBG_EVENT(s->dst->file, BLKDBG_BLKCOPY_STAGE_SWITCH_FINISHED);
+ break;
+ default:
+ break;
+ }
+}
+
+static void blk_copy_handle_cb_error(BdrvCopyState *s, int ret)
+{
+ s->error = ret;
+ qemu_mod_timer(s->aio_timer, qemu_get_clock(rt_clock));
+}
+
+static inline void add_avg_transfer_time(BdrvCopyState *s, int64_t time)
+{
+ s->blocks++;
+ s->total_time += time;
+}
+
+static void blk_copy_write_cb(void *opaque, int ret)
+{
+ BdrvCopyBlock *blk = opaque;
+ BdrvCopyState *s = blk->state;
+
+ if (ret < 0) {
+ QLIST_REMOVE(blk, list);
+ qemu_free(blk->buf);
+ qemu_free(blk);
+ blk_copy_handle_cb_error(s, ret);
+ return;
+ }
+
+ QLIST_REMOVE(blk, list);
+ add_avg_transfer_time(s, qemu_get_clock_ns(rt_clock) - blk->time);
+
+ /* schedule switch to STAGE_DIRTY on last bulk write completion */
+ if (blk->state->stage == STAGE_BULK_FINISHED) {
+ qemu_mod_timer(s->aio_timer, qemu_get_clock(rt_clock));
+ }
+
+ if (blk->state->stage > STAGE_BULK_FINISHED) {
+ set_aio_inflight(blk->state, blk->sector, blk->nr_sectors, 0);
+ }
+
+ qemu_free(blk->buf);
+ qemu_free(blk);
+}
+
+static void blk_copy_issue_write(BdrvCopyState *s, BdrvCopyBlock *read_blk)
+{
+ BdrvCopyBlock *blk = qemu_mallocz(sizeof(BdrvCopyBlock));
+ blk->state = s;
+ blk->sector = read_blk->sector;
+ blk->nr_sectors = read_blk->nr_sectors;
+ blk->time = read_blk->time;
+ blk->buf = read_blk->buf;
+ QLIST_INSERT_HEAD(&s->io_list, blk, list);
+
+ blk->iov.iov_base = read_blk->buf;
+ blk->iov.iov_len = read_blk->iov.iov_len;
+ qemu_iovec_init_external(&blk->qiov, &blk->iov, 1);
+
+ BLKDBG_EVENT(s->dst->file, BLKDBG_BLKCOPY_AIO_WRITE);
+ blk->aiocb = bdrv_aio_writev(s->dst, blk->sector, &blk->qiov,
+ blk->iov.iov_len / BDRV_SECTOR_SIZE,
+ blk_copy_write_cb, blk);
+ if (!blk->aiocb) {
+ s->error = 1;
+ goto error;
+ }
+
+ return;
+
+error:
+ QLIST_REMOVE(blk, list);
+ qemu_free(read_blk->buf);
+ qemu_free(blk);
+}
+
+static void blk_copy_read_cb(void *opaque, int ret)
+{
+ BdrvCopyBlock *blk = opaque;
+ BdrvCopyState *s = blk->state;
+
+ s->inflight_reads--;
+ if (ret < 0) {
+ QLIST_REMOVE(blk, list);
+ qemu_free(blk->buf);
+ qemu_free(blk);
+ blk_copy_handle_cb_error(s, ret);
+ return;
+ }
+ blk_copy_issue_write(s, blk);
+ QLIST_REMOVE(blk, list);
+ qemu_free(blk);
+ qemu_mod_timer(s->aio_timer, qemu_get_clock(rt_clock));
+}
+
+static void blk_copy_issue_read(BdrvCopyState *s, int64_t sector,
+ int nr_sectors)
+{
+ BdrvCopyBlock *blk = qemu_mallocz(sizeof(BdrvCopyBlock));
+ blk->buf = qemu_mallocz(BLOCK_SIZE);
+ blk->state = s;
+ blk->sector = sector;
+ blk->nr_sectors = nr_sectors;
+ QLIST_INSERT_HEAD(&s->io_list, blk, list);
+
+ blk->iov.iov_base = blk->buf;
+ blk->iov.iov_len = nr_sectors * BDRV_SECTOR_SIZE;
+ qemu_iovec_init_external(&blk->qiov, &blk->iov, 1);
+
+ s->inflight_reads++;
+ blk->time = qemu_get_clock_ns(rt_clock);
+ blk->aiocb = bdrv_aio_readv(s->src, sector, &blk->qiov, nr_sectors,
+ blk_copy_read_cb, blk);
+ if (!blk->aiocb) {
+ s->error = 1;
+ goto error;
+ }
+
+ return;
+
+error:
+ s->inflight_reads--;
+ QLIST_REMOVE(blk, list);
+ qemu_free(blk->buf);
+ qemu_free(blk);
+}
+
+static bool blkcopy_can_switch(BdrvCopyState *s)
+{
+ int64_t remaining_dirty;
+ int64_t avg_transfer_time;
+
+ remaining_dirty = bdrv_get_dirty_count(s->src);
+ if (remaining_dirty == 0 || s->blocks == 0) {
+ return true;
+ }
+
+ avg_transfer_time = s->total_time / s->blocks;
+ if ((remaining_dirty * avg_transfer_time) <= migrate_max_downtime()) {
+ return true;
+ }
+ return false;
+}
+
+static int blk_issue_reads_dirty(BdrvCopyState *s)
+{
+ int64_t sector;
+
+ for (sector = s->curr_sector; sector < s->nr_sectors;) {
+ if (bdrv_get_dirty(s->src, sector) && !aio_inflight(s, sector)) {
+ int nr_sectors = MIN(s->nr_sectors - s->curr_sector,
+ BDRV_SECTORS_PER_DIRTY_CHUNK);
+
+ blk_copy_issue_read(s, sector, nr_sectors);
+ bdrv_reset_dirty(s->src, sector, nr_sectors);
+ set_aio_inflight(s, sector, nr_sectors, 1);
+ break;
+ }
+
+ sector += BDRV_SECTORS_PER_DIRTY_CHUNK;
+ s->curr_sector = sector;
+ }
+
+ if (sector >= s->nr_sectors) {
+ s->curr_sector = 0;
+ }
+ return 0;
+}
+
+static int blk_issue_reads_bulk(BdrvCopyState *s)
+{
+ int nr_sectors;
+ int64_t curr_sector = s->curr_sector;
+
+ if (s->shared_base) {
+ while (curr_sector < s->nr_sectors &&
+ !bdrv_is_allocated(s->src, curr_sector,
+ MAX_IS_ALLOCATED_SEARCH, &nr_sectors)) {
+ curr_sector += nr_sectors;
+ }
+ }
+
+ if (curr_sector >= s->nr_sectors) {
+ s->curr_sector = 0;
+ return 1;
+ }
+
+ curr_sector &= ~((int64_t)BDRV_SECTORS_PER_DIRTY_CHUNK - 1);
+ nr_sectors = BDRV_SECTORS_PER_DIRTY_CHUNK;
+
+ blk_copy_issue_read(s, s->curr_sector, nr_sectors);
+ s->curr_sector += nr_sectors;
+ s->completed_sectors = curr_sector;
+ return 0;
+}
+
+static void blkcopy_finish(BdrvCopyState *s)
+{
+ int64_t sector;
+ uint8_t *buf;
+
+ buf = qemu_malloc(BLOCK_SIZE);
+
+ /* FIXME: speed up loop, get_next_dirty_block? */
+ for (sector = 0; sector < s->nr_sectors;
+ sector += BDRV_SECTORS_PER_DIRTY_CHUNK) {
+ if (bdrv_get_dirty(s->src, sector)) {
+ int nr_sectors = MIN(s->nr_sectors - sector,
+ BDRV_SECTORS_PER_DIRTY_CHUNK);
+
+ memset(buf, 0, BLOCK_SIZE);
+ if (bdrv_read(s->src, sector, buf, nr_sectors) < 0) {
+ goto error;
+ }
+ if (bdrv_write(s->dst, sector, buf, nr_sectors) < 0) {
+ goto error;
+ }
+ bdrv_reset_dirty(s->src, sector, nr_sectors);
+ }
+
+ if (bdrv_get_dirty_count(s->src) == 0)
+ break;
+ }
+ qemu_free(buf);
+ return;
+
+error:
+ qemu_free(buf);
+ s->error = 1;
+}
+
+static int write_commit_file(BdrvCopyState *s)
+{
+ char commit_msg[1400];
+ const char *buf = commit_msg;
+ int len, ret;
+
+ sprintf(commit_msg, "commit QEMU block_copy %s -> %s\n", s->src_device_name,
+ s->dst_filename);
+
+ len = strlen(commit_msg);
+ while (len > 0) {
+ ret = write(s->commit_fd, buf, len);
+ if (ret == -1 && errno == EINTR) {
+ continue;
+ }
+ if (ret <= 0) {
+ return -errno;
+ }
+ buf += ret;
+ len -= ret;
+ }
+
+ if (fsync(s->commit_fd) == -1) {
+ return -errno;
+ }
+
+ return 0;
+}
+
+static void blkcopy_cleanup(BdrvCopyState *s)
+{
+ assert(s->inflight_reads == 0);
+ assert(QLIST_EMPTY(&s->io_list));
+ bdrv_set_dirty_tracking(s->src, 0);
+ if (s->stage >= STAGE_DIRTY)
+ qemu_free(s->aio_bitmap);
+ qemu_del_timer(s->aio_timer);
+ if (s->commit_fd)
+ close(s->commit_fd);
+}
+
+static void blkcopy_free(BdrvCopyState *s)
+{
+ QLIST_REMOVE(s, list);
+ qemu_free(s);
+}
+
+static void handle_error(BdrvCopyState *s)
+{
+ if (!QLIST_EMPTY(&s->io_list))
+ return;
+ s->failed = 1;
+ blkcopy_cleanup(s);
+}
+
+static void blkcopy_switch(BdrvCopyState *s)
+{
+ char src_filename[1024];
+ int open_flags;
+
+ strncpy(src_filename, s->src->filename, sizeof(src_filename));
+ open_flags = s->src->open_flags;
+
+ assert(s->stage == STAGE_DIRTY);
+
+ vm_stop(0);
+ /* flush any guest writes, dirty bitmap uptodate after this.
+ * copy AIO also finished.
+ */
+ qemu_aio_flush();
+ assert(QLIST_EMPTY(&s->io_list));
+ if (s->error) {
+ handle_error(s);
+ goto vm_start;
+ }
+ blkcopy_finish(s);
+ if (s->error) {
+ handle_error(s);
+ goto vm_start;
+ }
+ assert(bdrv_get_dirty_count(s->src) == 0);
+ bdrv_flush_all();
+ bdrv_close(s->src);
+ bdrv_close(s->dst);
+ if (bdrv_open(s->src, s->dst->filename, s->src->open_flags, NULL) < 0) {
+ s->failed = 1;
+ goto err;
+ }
+ if (s->commit_fd && write_commit_file(s)) {
+ s->failed = 1;
+ bdrv_close(s->src);
+ goto err;
+ }
+
+ blkcopy_set_stage(s, STAGE_SWITCH_FINISHED);
+ blkcopy_cleanup(s);
+vm_start:
+ vm_start();
+ return;
+
+err:
+ if (bdrv_open(s->src, src_filename, open_flags, NULL) < 0) {
+ error_report("%s: %s: cannot fallback to source image\n", __func__,
+ s->dst_filename);
+ abort();
+ }
+ blkcopy_cleanup(s);
+ goto vm_start;
+}
+
+#define BLKCOPY_INFLIGHT 2
+
+static void aio_timer(void *opaque)
+{
+ BdrvCopyState *s = opaque;
+
+ assert(s->cancelled == 0);
+
+ if (s->error) {
+ handle_error(s);
+ return;
+ }
+
+ while (s->stage == STAGE_BULK) {
+ if (s->inflight_reads >= BLKCOPY_INFLIGHT) {
+ break;
+ }
+ if (blk_issue_reads_bulk(s)) {
+ blkcopy_set_stage(s, STAGE_BULK_FINISHED);
+ }
+ }
+
+ if (s->stage == STAGE_BULK_FINISHED) {
+ if (QLIST_EMPTY(&s->io_list)) {
+ blkcopy_set_stage(s, STAGE_DIRTY);
+ alloc_aio_bitmap(s);
+ }
+ }
+
+ while (s->stage == STAGE_DIRTY) {
+ if (s->inflight_reads >= BLKCOPY_INFLIGHT) {
+ break;
+ }
+ blk_issue_reads_dirty(s);
+ if (blkcopy_can_switch(s)) {
+ BLKDBG_EVENT(s->dst->file, BLKDBG_BLKCOPY_SWITCH_START);
+ blkcopy_switch(s);
+ return;
+ }
+ }
+}
+
+static int bdrv_copy(Monitor *mon, const char * device, BlockDriverState *src,
+ BlockDriverState *dst, const char *commit_file,
+ bool shared_base)
+{
+ int64_t sectors;
+ BdrvCopyState *blkcopy, *safe;
+ int f;
+
+ QLIST_FOREACH_SAFE(blkcopy, &block_copy_list, list, safe) {
+ if (!strcmp(blkcopy->src_device_name, src->device_name)) {
+ if (blkcopy->stage == STAGE_SWITCH_FINISHED || blkcopy->failed) {
+ blkcopy_free(blkcopy);
+ } else {
+ qerror_report(QERR_BLOCKCOPY_IN_PROGRESS, src->device_name);
+ return -1;
+ }
+ }
+ }
+
+ sectors = bdrv_getlength(src) >> BDRV_SECTOR_BITS;
+ if (sectors != bdrv_getlength(dst) >> BDRV_SECTOR_BITS) {
+ qerror_report(QERR_BLOCKCOPY_IMAGE_SIZE_DIFFERS);
+ return -1;
+ }
+
+ if (commit_file) {
+ f = open(commit_file, O_CREAT|O_WRONLY, S_IRUSR);
+ if (f == -1) {
+ qerror_report(QERR_OPEN_FILE_FAILED, commit_file);
+ return -1;
+ }
+ }
+
+ blkcopy = qemu_mallocz(sizeof(BdrvCopyState));
+ blkcopy->src = src;
+ blkcopy->dst = dst;
+ blkcopy->curr_sector = 0;
+ blkcopy->nr_sectors = sectors;
+ blkcopy_set_stage(blkcopy, STAGE_BULK);
+ blkcopy->aio_timer = qemu_new_timer(rt_clock, aio_timer, blkcopy);
+ blkcopy->shared_base = shared_base;
+ blkcopy->commit_fd = f;
+ strncpy(blkcopy->src_device_name, blkcopy->src->device_name,
+ sizeof(blkcopy->src_device_name) - 1);
+ strncpy(blkcopy->dst_filename, blkcopy->dst->filename,
+ sizeof(blkcopy->dst_filename) - 1);
+
+ bdrv_set_dirty_tracking(src, 1);
+ qemu_mod_timer(blkcopy->aio_timer, qemu_get_clock(rt_clock));
+
+ QLIST_INSERT_HEAD(&block_copy_list, blkcopy, list);
+ return 0;
+}
+
+int do_bdrv_copy(Monitor *mon, const QDict *qdict, QObject **ret_data)
+{
+ const char *device = qdict_get_str(qdict, "device");
+ const char *filename = qdict_get_str(qdict, "filename");
+ const char *commit_file = qdict_get_try_str(qdict, "commit_filename");
+ bool shared_base = qdict_get_try_bool(qdict, "inc", 0);
+ BlockDriverState *new_bs, *bs;
+ int ret;
+
+ if (migration_active()) {
+ qerror_report(QERR_MIGRATION_IN_PROGRESS);
+ return -1;
+ }
+
+ bs = bdrv_find(device);
+ if (!bs) {
+ qerror_report(QERR_DEVICE_NOT_FOUND, device);
+ return -1;
+ }
+
+ new_bs = bdrv_new("");
+ if (bdrv_open(new_bs, filename, bs->open_flags, NULL) < 0) {
+ bdrv_delete(new_bs);
+ qerror_report(QERR_OPEN_FILE_FAILED, filename);
+ return -1;
+ }
+
+ ret = bdrv_copy(mon, device, bs, new_bs, commit_file, shared_base);
+ return ret;
+}
+
+int do_bdrv_copy_cancel(Monitor *mon, const QDict *qdict, QObject **ret_data)
+{
+ BdrvCopyState *blkcopy, *s = NULL;
+ const char *device = qdict_get_str(qdict, "device");
+
+ QLIST_FOREACH(blkcopy, &block_copy_list, list) {
+ if (!strcmp(blkcopy->src_device_name, device)) {
+ s = blkcopy;
+ break;
+ }
+ }
+
+ if (!s) {
+ qerror_report(QERR_DEVICE_NOT_FOUND, device);
+ return -1;
+ }
+
+ s->cancelled = 1;
+ do {
+ qemu_aio_flush();
+ } while (!QLIST_EMPTY(&s->io_list));
+ blkcopy_cleanup(s);
+ blkcopy_free(s);
+
+ return 0;
+}
+
+static void blockcopy_print_dict(QObject *obj, void *opaque)
+{
+ QDict *c_dict;
+ Monitor *mon = opaque;
+
+ c_dict = qobject_to_qdict(obj);
+
+ monitor_printf(mon, "%s: status=%s ",
+ qdict_get_str(c_dict, "device"),
+ qdict_get_str(c_dict, "status"));
+
+ if (qdict_haskey(c_dict, "info")) {
+ QDict *qdict = qobject_to_qdict(qdict_get(c_dict, "info"));
+
+ monitor_printf(mon, "percentage=%ld %%",
+ qdict_get_int(qdict, "percentage"));
+ }
+
+ monitor_printf(mon, "\n");
+}
+
+void do_info_blockcopy_print(Monitor *mon, const QObject *data)
+{
+ qlist_iter(qobject_to_qlist(data), blockcopy_print_dict, mon);
+}
+
+void do_info_blockcopy(Monitor *mon, QObject **ret_data)
+{
+ QList *c_list;
+ BdrvCopyState *s;
+
+ c_list = qlist_new();
+
+ QLIST_FOREACH(s, &block_copy_list, list) {
+ QObject *c_obj;
+ static const char *status[] = { "failed", "active", "completed" };
+ int i;
+
+ if (s->failed) {
+ i = 0;
+ } else if (s->stage < STAGE_SWITCH_FINISHED) {
+ i = 1;
+ } else {
+ i = 2;
+ }
+
+ c_obj = qobject_from_jsonf("{ 'device': %s, 'status': %s }",
+ s->src_device_name, status[i]);
+
+ if (i == 1) {
+ QDict *dict = qobject_to_qdict(c_obj);
+ QObject *obj;
+
+ /* FIXME: add dirty stage progress? */
+ obj = qobject_from_jsonf("{ 'percentage': %" PRId64 "}",
+ s->completed_sectors * 100 / s->nr_sectors);
+ qdict_put_obj(dict, "info", obj);
+ }
+ qlist_append_obj(c_list, c_obj);
+ }
+
+ *ret_data = QOBJECT(c_list);
+}
+
+bool block_copy_active(void)
+{
+ BdrvCopyState *s;
+
+ QLIST_FOREACH(s, &block_copy_list, list) {
+ if (s->failed) {
+ continue;
+ }
+ if (s->stage < STAGE_SWITCH_FINISHED) {
+ return true;
+ }
+ }
+
+ return false;
+}
+
Index: qemu-kvm/block-copy.h
===================================================================
--- /dev/null
+++ qemu-kvm/block-copy.h
@@ -0,0 +1,25 @@
+/*
+ * QEMU live block copy
+ *
+ * Copyright (C) 2010 Red Hat Inc.
+ *
+ * Authors: Marcelo Tosatti <mtosatti@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef BLOCK_COPY_H
+#define BLOCK_COPY_H
+
+int do_bdrv_copy(Monitor *mon, const QDict *qdict, QObject **ret_data);
+int do_bdrv_copy_cancel(Monitor *mon, const QDict *qdict, QObject **ret_data);
+
+void do_info_blockcopy_print(Monitor *mon, const QObject *data);
+void do_info_blockcopy(Monitor *mon, QObject **ret_data);
+
+bool block_copy_active(void);
+
+#endif /* BLOCK_COPY_H */
+
Index: qemu-kvm/hmp-commands.hx
===================================================================
--- qemu-kvm.orig/hmp-commands.hx
+++ qemu-kvm/hmp-commands.hx
@@ -769,6 +769,43 @@ Set maximum speed to @var{value} (in byt
ETEXI
{
+ .name = "block_copy",
+ .args_type = "device:s,filename:s,commit_filename:s?,inc:-i",
+ .params = "device filename [commit_filename] [-i]",
+ .help = "live block copy device to image"
+ "\n\t\t\t optional commit filename "
+ "\n\t\t\t -i for incremental copy "
+ "(base image shared between src and destination)",
+ .user_print = monitor_user_noop,
+ .mhandler.cmd_new = do_bdrv_copy,
+ },
+
+STEXI
+@item block_copy @var{device} @var{filename} [@var{commit_filename}] [-i]
+@findex block_copy
+Live copy block device @var{device} to image @var{filename}.
+ -i for incremental copy (base image is shared)
+
+Optionally a commit message is written to @var{commit_filename}
+once the switch to the new image is performed.
+ETEXI
+
+ {
+ .name = "block_copy_cancel",
+ .args_type = "device:s",
+ .params = "device",
+ .help = "cancel live block copy",
+ .user_print = monitor_user_noop,
+ .mhandler.cmd_new = do_bdrv_copy_cancel,
+ },
+
+STEXI
+@item block_copy_cancel @var{device}
+@findex block_copy_cancel
+Cancel live block copy on @var{device}.
+ETEXI
+
+ {
.name = "migrate_set_downtime",
.args_type = "value:T",
.params = "value",
@@ -1213,6 +1250,8 @@ show device tree
show qdev device model list
@item info roms
show roms
+@item info block-copy
+show block copy status
@end table
ETEXI
Index: qemu-kvm/monitor.c
===================================================================
--- qemu-kvm.orig/monitor.c
+++ qemu-kvm/monitor.c
@@ -44,6 +44,7 @@
#include "balloon.h"
#include "qemu-timer.h"
#include "migration.h"
+#include "block-copy.h"
#include "kvm.h"
#include "acl.h"
#include "qint.h"
@@ -2651,6 +2652,14 @@ static const mon_cmd_t info_cmds[] = {
},
#endif
{
+ .name = "block-copy",
+ .args_type = "",
+ .params = "",
+ .help = "show block copy status",
+ .user_print = do_info_blockcopy_print,
+ .mhandler.info_new = do_info_blockcopy,
+ },
+ {
.name = NULL,
},
};
@@ -2782,6 +2791,14 @@ static const mon_cmd_t qmp_query_cmds[]
.mhandler.info_async = do_info_balloon,
.flags = MONITOR_CMD_ASYNC,
},
+ {
+ .name = "block-copy",
+ .args_type = "",
+ .params = "",
+ .help = "show block copy status",
+ .user_print = do_info_blockcopy_print,
+ .mhandler.info_new = do_info_blockcopy,
+ },
{ /* NULL */ },
};
Index: qemu-kvm/block.h
===================================================================
--- qemu-kvm.orig/block.h
+++ qemu-kvm/block.h
@@ -281,6 +281,13 @@ typedef enum {
BLKDBG_CLUSTER_ALLOC_BYTES,
BLKDBG_CLUSTER_FREE,
+ BLKDBG_BLKCOPY_STAGE_BULK,
+ BLKDBG_BLKCOPY_STAGE_BULK_FINISHED,
+ BLKDBG_BLKCOPY_STAGE_DIRTY,
+ BLKDBG_BLKCOPY_STAGE_SWITCH_FINISHED,
+ BLKDBG_BLKCOPY_SWITCH_START,
+ BLKDBG_BLKCOPY_AIO_WRITE,
+
BLKDBG_EVENT_MAX,
} BlkDebugEvent;
Index: qemu-kvm/block/blkdebug.c
===================================================================
--- qemu-kvm.orig/block/blkdebug.c
+++ qemu-kvm/block/blkdebug.c
@@ -178,6 +178,14 @@ static const char *event_names[BLKDBG_EV
[BLKDBG_CLUSTER_ALLOC] = "cluster_alloc",
[BLKDBG_CLUSTER_ALLOC_BYTES] = "cluster_alloc_bytes",
[BLKDBG_CLUSTER_FREE] = "cluster_free",
+
+
+ [BLKDBG_BLKCOPY_STAGE_BULK] = "blkcopy_stage_bulk",
+ [BLKDBG_BLKCOPY_STAGE_BULK_FINISHED] = "blkcopy_stage_bulk_finished",
+ [BLKDBG_BLKCOPY_STAGE_DIRTY] = "blkcopy_stage_dirty",
+ [BLKDBG_BLKCOPY_STAGE_SWITCH_FINISHED] = "blkcopy_stage_switch_finished",
+ [BLKDBG_BLKCOPY_SWITCH_START] = "blkcopy_switch_start",
+ [BLKDBG_BLKCOPY_AIO_WRITE] = "blkcopy_aio_write",
};
static int get_event_by_name(const char *name, BlkDebugEvent *event)
Index: qemu-kvm/qerror.c
===================================================================
--- qemu-kvm.orig/qerror.c
+++ qemu-kvm/qerror.c
@@ -200,6 +200,18 @@ static const QErrorStringTable qerror_ta
.error_fmt = QERR_VNC_SERVER_FAILED,
.desc = "Could not start VNC server on %(target)",
},
+ {
+ .error_fmt = QERR_BLOCKCOPY_IN_PROGRESS,
+ .desc = "Block copy for %(device) in progress",
+ },
+ {
+ .error_fmt = QERR_BLOCKCOPY_IMAGE_SIZE_DIFFERS,
+ .desc = "Length of destination image differs from source image",
+ },
+ {
+ .error_fmt = QERR_MIGRATION_IN_PROGRESS,
+ .desc = "Migration in progress",
+ },
{}
};
Index: qemu-kvm/qerror.h
===================================================================
--- qemu-kvm.orig/qerror.h
+++ qemu-kvm/qerror.h
@@ -165,4 +165,13 @@ QError *qobject_to_qerror(const QObject
#define QERR_VNC_SERVER_FAILED \
"{ 'class': 'VNCServerFailed', 'data': { 'target': %s } }"
+#define QERR_BLOCKCOPY_IN_PROGRESS \
+ "{ 'class': 'BlockCopyInProgress', 'data': { 'device': %s } }"
+
+#define QERR_BLOCKCOPY_IMAGE_SIZE_DIFFERS \
+ "{ 'class': 'BlockCopyImageSizeDiffers', 'data': {} }"
+
+#define QERR_MIGRATION_IN_PROGRESS \
+ "{ 'class': 'MigrationInProgress', 'data': {} }"
+
#endif /* QERROR_H */
Index: qemu-kvm/qmp-commands.hx
===================================================================
--- qemu-kvm.orig/qmp-commands.hx
+++ qemu-kvm/qmp-commands.hx
@@ -546,6 +546,75 @@ Example:
EQMP
{
+ .name = "block_copy",
+ .args_type = "device:s,filename:s,commit_filename:s?,inc:-i",
+ .params = "device filename [commit_filename] [-i]",
+ .help = "live block copy device to image"
+ "\n\t\t\t optional commit filename "
+ "\n\t\t\t -i for incremental copy "
+ "(base image shared between src and destination)",
+ .user_print = monitor_user_noop,
+ .mhandler.cmd_new = do_bdrv_copy,
+ },
+
+SQMP
+block-copy
+-------
+
+Live block copy.
+
+Arguments:
+
+- "device": device name (json-string)
+- "filename": target image filename (json-string)
+- "commit_filename": target commit filename (json-string, optional)
+- "inc": incremental disk copy (json-bool, optional)
+
+Example:
+
+-> { "execute": "block_copy",
+ "arguments": { "device": "ide0-hd1",
+ "filename": "/mnt/new-disk.img",
+ "commit_filename: "/mnt/commit-new-disk.img"
+ } }
+
+<- { "return": {} }
+
+Notes:
+
+(1) The 'query-block-copy' command should be used to check block copy progress
+ and final result (this information is provided by the 'status' member)
+(2) Boolean argument "inc" defaults to false
+
+EQMP
+
+ {
+ .name = "block_copy_cancel",
+ .args_type = "device:s",
+ .params = "device",
+ .help = "cancel live block copy",
+ .user_print = monitor_user_noop,
+ .mhandler.cmd_new = do_bdrv_copy_cancel,
+ },
+
+SQMP
+block_copy_cancel
+--------------
+
+Cancel live block copy.
+
+Arguments:
+
+- device: device name (json-string)
+
+Example:
+
+-> { "execute": "block_copy_cancel", "arguments": { "device": "ide0-hd1" } }
+<- { "return": {} }
+
+EQMP
+
+ {
.name = "netdev_add",
.args_type = "netdev:O",
.params = "[user|tap|socket],id=str[,prop=value][,...]",
@@ -1505,6 +1574,44 @@ Examples:
EQMP
SQMP
+query-block-copy
+-------------
+
+Live block copy status.
+
+Each block copy instance information is stored in a json-object and the returned
+value is a json-array of all instances.
+
+Each json-object contains the following:
+
+- "device": device name (json-string)
+- "status": block copy status (json-string)
+ - Possible values: "active", "failed", "completed"
+- "info": A json-object with the statistics information, if status is "active":
+ - "percentage": percentage completed (json-int)
+
+Example:
+
+Block copy for "ide1-hd0" active and block copy for "ide1-hd1" failed:
+
+-> { "execute": "query-block-copy" }
+<- {
+ "return":[
+ {"device":"ide1-hd0",
+ "status":"active",
+ "info":{
+ "percentage":23,
+ }
+ },
+ {"device":"ide1-hd1",
+ "status":"failed"
+ }
+ ]
+ }
+
+EQMP
+
+SQMP
query-balloon
-------------
Index: qemu-kvm/Makefile.objs
===================================================================
--- qemu-kvm.orig/Makefile.objs
+++ qemu-kvm/Makefile.objs
@@ -91,7 +91,7 @@ common-obj-y += buffered_file.o migratio
common-obj-y += qemu-char.o savevm.o #aio.o
common-obj-y += msmouse.o ps2.o
common-obj-y += qdev.o qdev-properties.o
-common-obj-y += block-migration.o
+common-obj-y += block-migration.o block-copy.o
common-obj-y += pflib.o
common-obj-$(CONFIG_BRLAPI) += baum.o
^ permalink raw reply [flat|nested] 7+ messages in thread