From 7d1eb32b705304a4230726638c5cd5ddd3969f91 Mon Sep 17 00:00:00 2001
From: Jeffrey Cody <jcody@redhat.com>
Date: Wed, 21 Mar 2012 21:55:06 +0100
Subject: [PATCH 39/55] block: add image streaming block job
RH-Author: Jeffrey Cody <jcody@redhat.com>
Message-id: <1b61917a4947dde01736a89b84292b27d9efe66a.1332362400.git.jcody@redhat.com>
Patchwork-id: 38889
O-Subject: [RHEL6.3 qemu-kvm PATCH v8 39/54] block: add image streaming block job
Bugzilla: 582475
RH-Acked-by: Paolo Bonzini <pbonzini@redhat.com>
RH-Acked-by: Marcelo Tosatti <mtosatti@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
From: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 4f1043b4ffdd6f130cab7c1d8d59d833a475adac)
Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Signed-off-by: Jeff Cody <jcody@redhat.com>
---
Makefile.objs | 1 +
block/stream.c | 133 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++
block_int.h | 3 +
trace-events | 4 ++
4 files changed, 141 insertions(+), 0 deletions(-)
create mode 100644 block/stream.c
Signed-off-by: Michal Novotny <minovotn@redhat.com>
---
Makefile.objs | 1 +
block/stream.c | 133 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++
block_int.h | 3 +
trace-events | 4 ++
4 files changed, 141 insertions(+), 0 deletions(-)
create mode 100644 block/stream.c
diff --git a/Makefile.objs b/Makefile.objs
index 716b346..d21d747 100644
--- a/Makefile.objs
+++ b/Makefile.objs
@@ -26,6 +26,7 @@ block-nested-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o qcow
block-nested-y += qed.o qed-gencb.o qed-l2-cache.o qed-table.o qed-cluster.o
block-nested-y += qed-check.o
block-nested-y += parallels.o nbd.o blkdebug.o
+block-nested-y += stream.o
block-nested-$(CONFIG_WIN32) += raw-win32.o
block-nested-$(CONFIG_POSIX) += raw-posix.o
block-nested-$(CONFIG_CURL) += curl.o
diff --git a/block/stream.c b/block/stream.c
new file mode 100644
index 0000000..886f704
--- /dev/null
+++ b/block/stream.c
@@ -0,0 +1,133 @@
+/*
+ * Image streaming
+ *
+ * Copyright IBM, Corp. 2011
+ *
+ * Authors:
+ * Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#include "trace.h"
+#include "block_int.h"
+
+enum {
+ /*
+ * Size of data buffer for populating the image file. This should be large
+ * enough to process multiple clusters in a single call, so that populating
+ * contiguous regions of the image is efficient.
+ */
+ STREAM_BUFFER_SIZE = 512 * 1024, /* in bytes */
+};
+
+typedef struct StreamBlockJob {
+ BlockJob common;
+ BlockDriverState *base;
+} StreamBlockJob;
+
+static int coroutine_fn stream_populate(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors,
+ void *buf)
+{
+ struct iovec iov = {
+ .iov_base = buf,
+ .iov_len = nb_sectors * BDRV_SECTOR_SIZE,
+ };
+ QEMUIOVector qiov;
+
+ qemu_iovec_init_external(&qiov, &iov, 1);
+
+ /* Copy-on-read the unallocated clusters */
+ return bdrv_co_copy_on_readv(bs, sector_num, nb_sectors, &qiov);
+}
+
+static void coroutine_fn stream_run(void *opaque)
+{
+ StreamBlockJob *s = opaque;
+ BlockDriverState *bs = s->common.bs;
+ int64_t sector_num, end;
+ int ret = 0;
+ int n;
+ void *buf;
+
+ s->common.len = bdrv_getlength(bs);
+ if (s->common.len < 0) {
+ block_job_complete(&s->common, s->common.len);
+ return;
+ }
+
+ end = s->common.len >> BDRV_SECTOR_BITS;
+ buf = qemu_blockalign(bs, STREAM_BUFFER_SIZE);
+
+ /* Turn on copy-on-read for the whole block device so that guest read
+ * requests help us make progress. Only do this when copying the entire
+ * backing chain since the copy-on-read operation does not take base into
+ * account.
+ */
+ if (!s->base) {
+ bdrv_enable_copy_on_read(bs);
+ }
+
+ for (sector_num = 0; sector_num < end; sector_num += n) {
+ if (block_job_is_cancelled(&s->common)) {
+ break;
+ }
+
+ /* TODO rate-limit */
+ /* Note that even when no rate limit is applied we need to yield with
+ * no pending I/O here so that qemu_aio_flush() is able to return.
+ */
+ co_sleep(rt_clock, 0);
+
+ ret = bdrv_co_is_allocated(bs, sector_num,
+ STREAM_BUFFER_SIZE / BDRV_SECTOR_SIZE, &n);
+ trace_stream_one_iteration(s, sector_num, n, ret);
+ if (ret == 0) {
+ ret = stream_populate(bs, sector_num, n, buf);
+ }
+ if (ret < 0) {
+ break;
+ }
+
+ /* Publish progress */
+ s->common.offset += n * BDRV_SECTOR_SIZE;
+ }
+
+ if (!s->base) {
+ bdrv_disable_copy_on_read(bs);
+ }
+
+ if (sector_num == end && ret == 0) {
+ ret = bdrv_change_backing_file(bs, NULL, NULL);
+ }
+
+ qemu_vfree(buf);
+ block_job_complete(&s->common, ret);
+}
+
+static BlockJobType stream_job_type = {
+ .instance_size = sizeof(StreamBlockJob),
+ .job_type = "stream",
+};
+
+int stream_start(BlockDriverState *bs, BlockDriverState *base,
+ BlockDriverCompletionFunc *cb, void *opaque)
+{
+ StreamBlockJob *s;
+ Coroutine *co;
+
+ s = block_job_create(&stream_job_type, bs, cb, opaque);
+ if (!s) {
+ return -EBUSY; /* bs must already be in use */
+ }
+
+ s->base = base;
+
+ co = qemu_coroutine_create(stream_run);
+ trace_stream_start(bs, base, s, co, opaque);
+ qemu_coroutine_enter(co, s);
+ return 0;
+}
diff --git a/block_int.h b/block_int.h
index a99ddc2..c61604c 100644
--- a/block_int.h
+++ b/block_int.h
@@ -282,6 +282,9 @@ int block_job_set_speed(BlockJob *job, int64_t value);
void block_job_cancel(BlockJob *job);
bool block_job_is_cancelled(BlockJob *job);
+int stream_start(BlockDriverState *bs, BlockDriverState *base,
+ BlockDriverCompletionFunc *cb, void *opaque);
+
typedef struct BlockConf {
BlockDriverState *bs;
uint16_t physical_block_size;
diff --git a/trace-events b/trace-events
index 6725413..bf83d7a 100644
--- a/trace-events
+++ b/trace-events
@@ -62,6 +62,10 @@ disable bdrv_co_io_em(void *bs, int64_t sector_num, int nb_sectors, int is_write
disable bdrv_co_copy_on_readv(void *bs, int64_t sector_num, int nb_sector) "bs %p sector_num %"PRId64" nb_sectors %d"
disable bdrv_co_do_copy_on_readv(void *bs, int64_t sector_num, int nb_sectors, int64_t cluster_sector_num, int cluster_nb_sectors) "bs %p sector_num %"PRId64" nb_sectors %d cluster_sector_num %"PRId64" cluster_nb_sectors %d"
+# block/stream.c
+disable stream_one_iteration(void *s, int64_t sector_num, int nb_sectors, int is_allocated) "s %p sector_num %"PRId64" nb_sectors %d is_allocated %d"
+disable stream_start(void *bs, void *base, void *s, void *co, void *opaque) "bs %p base %p s %p co %p opaque %p"
+
# hw/virtio-blk.c
disable virtio_blk_req_complete(void *req, int status) "req %p status %d"
disable virtio_blk_rw_complete(void *req, int ret) "req %p ret %d"
--
1.7.7.6