block: add event when disk usage exceeds threshold

Managing applications, like oVirt (http://www.ovirt.org), make extensive
use of thin-provisioned disk images.
To let the guest run smoothly and be not unnecessarily paused, oVirt sets
a disk usage threshold (so called 'high water mark') based on the occupation
of the device,  and automatically extends the image once the threshold
is reached or exceeded.

In order to detect the crossing of the threshold, oVirt has no choice but
aggressively polling the QEMU monitor using the query-blockstats command.
This lead to unnecessary system load, and is made even worse under scale:
deployments with hundreds of VMs are no longer rare.

To fix this, this patch adds:
* A new monitor command `block-set-write-threshold', to set a mark for
  a given block device.
* A new event `BLOCK_WRITE_THRESHOLD', to report if a block device
  usage exceeds the threshold.
* A new `write_threshold' field into the `BlockDeviceInfo' structure,
  to report the configured threshold.

This will allow the managing application to use smarter and more
efficient monitoring, greatly reducing the need of polling.

[Updated qemu-iotests 067 output to add the new 'write_threshold'
property. --Stefan]
[Changed g_assert_false() to !g_assert() to fix the build on older glib
versions. --Kevin]

Signed-off-by: Francesco Romani <fromani@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-id: 1421068273-692-1-git-send-email-fromani@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

3 files changed, 127 insertions, 0 deletions

diff --git a/tests/Makefile b/tests/Makefile
index 5caccf7..d5df168 100644
--- a/tests/Makefile
+++ b/tests/Makefile
@@ -68,6 +68,8 @@ check-unit-y += tests/check-qom-interface$(EXESUF)
 gcov-files-check-qom-interface-y = qom/object.c
 check-unit-y += tests/test-qemu-opts$(EXESUF)
 gcov-files-test-qemu-opts-y = qom/test-qemu-opts.c
+check-unit-y += tests/test-write-threshold$(EXESUF)
+gcov-files-test-write-threshold-y = block/write-threshold.c
 
 check-block-$(CONFIG_POSIX) += tests/qemu-iotests-quick.sh
 
@@ -360,6 +362,7 @@ tests/usb-hcd-xhci-test$(EXESUF): tests/usb-hcd-xhci-test.o $(libqos-usb-obj-y)
 tests/vhost-user-test$(EXESUF): tests/vhost-user-test.o qemu-char.o qemu-timer.o $(qtest-obj-y)
 tests/qemu-iotests/socket_scm_helper$(EXESUF): tests/qemu-iotests/socket_scm_helper.o
 tests/test-qemu-opts$(EXESUF): tests/test-qemu-opts.o libqemuutil.a libqemustub.a
+tests/test-write-threshold$(EXESUF): tests/test-write-threshold.o $(block-obj-y) libqemuutil.a libqemustub.a
 
 ifeq ($(CONFIG_POSIX),y)
 LIBS += -lutil
diff --git a/tests/qemu-iotests/067.out b/tests/qemu-iotests/067.out
index 13ff3cd..00b3eae 100644
--- a/tests/qemu-iotests/067.out
+++ b/tests/qemu-iotests/067.out
@@ -43,6 +43,7 @@ Testing: -drive file=TEST_DIR/t.qcow2,format=qcow2,if=none,id=disk -device virti
                 "drv": "qcow2",
                 "iops": 0,
                 "bps_wr": 0,
+                "write_threshold": 0,
                 "encrypted": false,
                 "bps": 0,
                 "bps_rd": 0,
@@ -218,6 +219,7 @@ Testing: -drive file=TEST_DIR/t.qcow2,format=qcow2,if=none,id=disk
                 "drv": "qcow2",
                 "iops": 0,
                 "bps_wr": 0,
+                "write_threshold": 0,
                 "encrypted": false,
                 "bps": 0,
                 "bps_rd": 0,
@@ -423,6 +425,7 @@ Testing:
                 "drv": "qcow2",
                 "iops": 0,
                 "bps_wr": 0,
+                "write_threshold": 0,
                 "encrypted": false,
                 "bps": 0,
                 "bps_rd": 0,
@@ -607,6 +610,7 @@ Testing:
                 "drv": "qcow2",
                 "iops": 0,
                 "bps_wr": 0,
+                "write_threshold": 0,
                 "encrypted": false,
                 "bps": 0,
                 "bps_rd": 0,
@@ -717,6 +721,7 @@ Testing:
                 "drv": "qcow2",
                 "iops": 0,
                 "bps_wr": 0,
+                "write_threshold": 0,
                 "encrypted": false,
                 "bps": 0,
                 "bps_rd": 0,
diff --git a/tests/test-write-threshold.c b/tests/test-write-threshold.c
new file mode 100644
index 0000000..faffa7b
--- /dev/null
+++ b/tests/test-write-threshold.c
@@ -0,0 +1,119 @@
+/*
+ * Test block device write threshold
+ *
+ * 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 <glib.h>
+#include <stdint.h>
+#include "block/block_int.h"
+#include "block/write-threshold.h"
+
+
+static void test_threshold_not_set_on_init(void)
+{
+    uint64_t res;
+    BlockDriverState bs;
+    memset(&bs, 0, sizeof(bs));
+
+    g_assert(!bdrv_write_threshold_is_set(&bs));
+
+    res = bdrv_write_threshold_get(&bs);
+    g_assert_cmpint(res, ==, 0);
+}
+
+static void test_threshold_set_get(void)
+{
+    uint64_t threshold = 4 * 1024 * 1024;
+    uint64_t res;
+    BlockDriverState bs;
+    memset(&bs, 0, sizeof(bs));
+
+    bdrv_write_threshold_set(&bs, threshold);
+
+    g_assert(bdrv_write_threshold_is_set(&bs));
+
+    res = bdrv_write_threshold_get(&bs);
+    g_assert_cmpint(res, ==, threshold);
+}
+
+static void test_threshold_multi_set_get(void)
+{
+    uint64_t threshold1 = 4 * 1024 * 1024;
+    uint64_t threshold2 = 15 * 1024 * 1024;
+    uint64_t res;
+    BlockDriverState bs;
+    memset(&bs, 0, sizeof(bs));
+
+    bdrv_write_threshold_set(&bs, threshold1);
+    bdrv_write_threshold_set(&bs, threshold2);
+    res = bdrv_write_threshold_get(&bs);
+    g_assert_cmpint(res, ==, threshold2);
+}
+
+static void test_threshold_not_trigger(void)
+{
+    uint64_t amount = 0;
+    uint64_t threshold = 4 * 1024 * 1024;
+    BlockDriverState bs;
+    BdrvTrackedRequest req;
+
+    memset(&bs, 0, sizeof(bs));
+    memset(&req, 0, sizeof(req));
+    req.offset = 1024;
+    req.bytes = 1024;
+
+    bdrv_write_threshold_set(&bs, threshold);
+    amount = bdrv_write_threshold_exceeded(&bs, &req);
+    g_assert_cmpuint(amount, ==, 0);
+}
+
+
+static void test_threshold_trigger(void)
+{
+    uint64_t amount = 0;
+    uint64_t threshold = 4 * 1024 * 1024;
+    BlockDriverState bs;
+    BdrvTrackedRequest req;
+
+    memset(&bs, 0, sizeof(bs));
+    memset(&req, 0, sizeof(req));
+    req.offset = (4 * 1024 * 1024) - 1024;
+    req.bytes = 2 * 1024;
+
+    bdrv_write_threshold_set(&bs, threshold);
+    amount = bdrv_write_threshold_exceeded(&bs, &req);
+    g_assert_cmpuint(amount, >=, 1024);
+}
+
+typedef struct TestStruct {
+    const char *name;
+    void (*func)(void);
+} TestStruct;
+
+
+int main(int argc, char **argv)
+{
+    size_t i;
+    TestStruct tests[] = {
+        { "/write-threshold/not-set-on-init",
+          test_threshold_not_set_on_init },
+        { "/write-threshold/set-get",
+          test_threshold_set_get },
+        { "/write-threshold/multi-set-get",
+          test_threshold_multi_set_get },
+        { "/write-threshold/not-trigger",
+          test_threshold_not_trigger },
+        { "/write-threshold/trigger",
+          test_threshold_trigger },
+        { NULL, NULL }
+    };
+
+    g_test_init(&argc, &argv, NULL);
+    for (i = 0; tests[i].name != NULL; i++) {
+        g_test_add_func(tests[i].name, tests[i].func);
+    }
+    return g_test_run();
+}