Adds the ability to monitor the nbdkit process so that we can take
action in case the child exits unexpectedly.
When the nbdkit process exits, we pause the vm, restart nbdkit, and then
resume the vm. This allows the vm to continue working in the event of a
nbdkit failure.
Eventually we may want to generalize this functionality since we may
need something similar for e.g. qemu-storage-daemon, etc.
The process is monitored with the pidfd_open() syscall if it exists
(since linux 5.3). Otherwise it resorts to checking whether the process
is alive once a second. The one-second time period was chosen somewhat
arbitrarily.
Signed-off-by: Jonathon Jongsma <jjongsma@xxxxxxxxxx>
---
meson.build | 3 +
src/qemu/qemu_nbdkit.c | 220 ++++++++++++++++++++++++++++++++++++++++
src/qemu/qemu_nbdkit.h | 10 ++
src/qemu/qemu_process.c | 13 +++
4 files changed, 246 insertions(+)
diff --git a/meson.build b/meson.build
index e4581e74dd..b4ed170ca1 100644
--- a/meson.build
+++ b/meson.build
@@ -686,6 +686,9 @@ if host_machine.system() == 'linux'
# Check if we have new enough kernel to support BPF devices for cgroups v2
[ 'linux/bpf.h', 'BPF_PROG_QUERY' ],
[ 'linux/bpf.h', 'BPF_CGROUP_DEVICE' ],
+
+ # process management
+ [ 'sys/syscall.h', 'SYS_pidfd_open' ],
]
endif
diff --git a/src/qemu/qemu_nbdkit.c b/src/qemu/qemu_nbdkit.c
index 0a0dc5d2a4..f17fe022ec 100644
--- a/src/qemu/qemu_nbdkit.c
+++ b/src/qemu/qemu_nbdkit.c
@@ -21,9 +21,11 @@
#include <config.h>
#include <glib.h>
+#include <sys/syscall.h>
#include "vircommand.h"
#include "virerror.h"
+#include "virevent.h"
#include "virlog.h"
#include "virpidfile.h"
#include "virtime.h"
@@ -36,6 +38,7 @@
#include "qemu_nbdkit.h"
#define LIBVIRT_QEMU_NBDKITPRIV_H_ALLOW
#include "qemu_nbdkitpriv.h"
+#include "qemu_process.h"
#include "qemu_security.h"
#include <fcntl.h>
@@ -72,6 +75,13 @@ struct _qemuNbdkitCaps {
G_DEFINE_TYPE(qemuNbdkitCaps, qemu_nbdkit_caps, G_TYPE_OBJECT);
+struct _qemuNbdkitProcessPrivate {
+ int monitor;
+ virQEMUDriver *driver;
+ virDomainObj *vm;
+};
+
+
enum {
PIPE_FD_READ = 0,
PIPE_FD_WRITE = 1
@@ -588,6 +598,168 @@ qemuNbdkitCapsCacheNew(const char *cachedir)
}
+static int
+qemuNbdkitProcessStartMonitor(qemuNbdkitProcess *proc,
+ virDomainObj *vm,
+ virQEMUDriver *driver);
+
+
+static void
+qemuNbdkitProcessHandleExit(qemuNbdkitProcess *proc)
+{
+ qemuNbdkitProcessPrivate *priv = proc->priv;
+ bool was_running = false;
+
+ VIR_DEBUG("nbdkit process %i died", proc->pid);
+
+ /* clean up resources associated with process */
+ qemuNbdkitProcessStop(proc);
+
+ if (!(priv->vm && priv->driver)) {
+ VIR_WARN("Unable to restart nbdkit -- vm and driver not set");
+ return;
+ }
+
+ VIR_DEBUG("restarting nbdkit process");
+
+ virObjectLock(priv->vm);
+ if (virDomainObjBeginJob(priv->vm, VIR_JOB_SUSPEND) < 0) {
+ VIR_WARN("can't begin job");
+ goto cleanup;
+ }
+
+ /* Pause domain */
+ if (virDomainObjGetState(priv->vm, NULL) == VIR_DOMAIN_RUNNING) {
+ was_running = true;
+ if (qemuProcessStopCPUs(priv->driver, priv->vm,
+ VIR_DOMAIN_PAUSED_IOERROR,
+ VIR_ASYNC_JOB_NONE) < 0)
+ goto endjob;
+ VIR_DEBUG("Paused vm while we restart nbdkit backend");
+ }
+
+ if (qemuNbdkitProcessStart(proc, priv->vm, priv->driver) < 0)
+ VIR_WARN("Unable to restart nbkdit process");
+
+ if (was_running && virDomainObjIsActive(priv->vm)) {
+ if (qemuProcessStartCPUs(priv->driver, priv->vm,
+ VIR_DOMAIN_RUNNING_UNPAUSED,
+ VIR_ASYNC_JOB_NONE) < 0) {
+ VIR_WARN("Unable to resume guest CPUs after nbdkit restart");
+ goto endjob;
+ }
+ VIR_DEBUG("Resumed vm");
+ }
+ qemuNbdkitProcessStartMonitor(proc, NULL, NULL);
+
+ endjob:
+ virDomainObjEndJob(priv->vm);
+ cleanup:
+ virObjectUnlock(priv->vm);
+}
+
+
+#if WITH_DECL_SYS_PIDFD_OPEN
+static void
+qemuNbdkitProcessPidfdCb(int watch G_GNUC_UNUSED,
+ int fd,
+ int events G_GNUC_UNUSED,
+ void *opaque)
+{
+ qemuNbdkitProcess *proc = opaque;
+
+ VIR_FORCE_CLOSE(fd);
+ qemuNbdkitProcessHandleExit(proc);
+}
+#else
+static void
+qemuNbdkitProcessTimeoutCb(int timer G_GNUC_UNUSED,
+ void *opaque)
+{
+ qemuNbdkitProcess *proc = opaque;
+
+ if (virProcessKill(proc->pid, 0) < 0)
+ qemuNbdkitProcessHandleExit(proc);
+}
+#endif /* WITH_DECL_SYS_PIDFD_OPEN */
+
+
+static int
+qemuNbdkitProcessStartMonitor(qemuNbdkitProcess *proc,
+ virDomainObj *vm,
+ virQEMUDriver *driver)
+{
+ qemuNbdkitProcessPrivate *priv = proc->priv;
+#if WITH_DECL_SYS_PIDFD_OPEN
+ int pidfd;
+#endif
+
+ if (vm) {
+ virObjectRef(vm);
+
+ if (priv->vm)
+ virObjectUnref(priv->vm);
+
+ priv->vm = vm;
+ }
+
+ if (driver)
+ priv->driver = driver;
+
+ if (!(priv->vm && priv->driver)) {
+ VIR_WARN("set vm and driver before calling %s", G_STRFUNC);
+ return -1;
+ }
+
+#if WITH_DECL_SYS_PIDFD_OPEN
+ pidfd = syscall(SYS_pidfd_open, proc->pid, 0);
+ if (pidfd < 0)
+ return -1;
+
+ priv->monitor = virEventAddHandle(pidfd,
+ VIR_EVENT_HANDLE_READABLE,
+ qemuNbdkitProcessPidfdCb,
+ proc, NULL);
+#else
+ /* fall back to checking once a second */
+ priv->monitor = virEventAddTimeout(1000,
+ qemuNbdkitProcessTimeoutCb,
+ proc, NULL);
+#endif /* WITH_DECL_SYS_PIDFD_OPEN */
+
+ if (priv->monitor < 0)
+ return -1;
+
+ VIR_DEBUG("Monitoring nbdkit process %i for exit", proc->pid);
+
+ return 0;
+}
+
+
+static void
+qemuNbdkitProcessStopMonitor(qemuNbdkitProcess *proc)
+{
+ qemuNbdkitProcessPrivate *priv = proc->priv;
+
+ if (priv->monitor > 0) {
+#if WITH_DECL_SYS_PIDFD_OPEN
+ virEventRemoveHandle(priv->monitor);
+#else
+ virEventRemoveTimeout(priv->monitor);
+#endif /* WITH_DECL_SYS_PIDFD_OPEN */
+ priv->monitor = 0;
+ }
+}
+
+
+static void
+qemuNbdkitProcessPrivateFree(qemuNbdkitProcessPrivate *priv)
+{
+ virObjectUnref(priv->vm);
+ g_free(priv);
+}
+
+
static qemuNbdkitProcess *
qemuNbdkitProcessNew(virStorageSource *source,
const char *pidfile,
@@ -601,6 +773,7 @@ qemuNbdkitProcessNew(virStorageSource *source,
nbdkit->pid = -1;
nbdkit->pidfile = g_strdup(pidfile);
nbdkit->socketfile = g_strdup(socketfile);
+ nbdkit->priv = g_new0(qemuNbdkitProcessPrivate, 1);
return nbdkit;
}
@@ -627,6 +800,45 @@ qemuNbdkitProcessLoad(virStorageSource *source,
}
+static int
+qemuNbdkitStorageSourceManageProcessOne(virStorageSource *src,
+ virDomainObj *vm,
+ virQEMUDriver *driver)
+{
+ qemuDomainStorageSourcePrivate *srcPriv = QEMU_DOMAIN_STORAGE_SOURCE_PRIVATE(src);
+ qemuNbdkitProcess *nbdkit;
+
+ if (!srcPriv)
+ return 0;
+
+ nbdkit = srcPriv->nbdkitProcess;
+ if (nbdkit) {
+ nbdkit->caps = qemuGetNbdkitCaps(nbdkit->priv->driver);
+
+ if (qemuNbdkitProcessStartMonitor(nbdkit, vm, driver) < 0)
+ return -1;
+ }
+
+ return 0;
+}
+
+
+int
+qemuNbdkitStorageSourceManageProcess(virQEMUDriver *driver,
+ virDomainObj *vm,
+ virStorageSource *src)
+{
+ virStorageSource *backing;
+
+ for (backing = src->backingStore; backing != NULL; backing = backing->backingStore) {
+ if (qemuNbdkitStorageSourceManageProcessOne(backing, vm, driver) < 0)
+ return -1;
+ }
+
+ return qemuNbdkitStorageSourceManageProcessOne(src, vm, driver);
+}
+
+
bool
qemuNbdkitInitStorageSource(qemuNbdkitCaps *caps,
virStorageSource *source,
@@ -915,9 +1127,12 @@ qemuNbdkitProcessBuildCommand(qemuNbdkitProcess *proc)
void
qemuNbdkitProcessFree(qemuNbdkitProcess *proc)
{
+ qemuNbdkitProcessStopMonitor(proc);
+
g_clear_pointer(&proc->pidfile, g_free);
g_clear_pointer(&proc->socketfile, g_free);
g_clear_object(&proc->caps);
+ g_clear_pointer(&proc->priv, qemuNbdkitProcessPrivateFree);
g_free(proc);
}
@@ -988,6 +1203,9 @@ qemuNbdkitProcessStart(qemuNbdkitProcess *proc,
goto error;
}
+ if (qemuNbdkitProcessStartMonitor(proc, vm, driver) < 0)
+ goto error;
+
return 0;
error:
@@ -1007,6 +1225,8 @@ qemuNbdkitProcessStop(qemuNbdkitProcess *proc)
{
int ret;
+ qemuNbdkitProcessStopMonitor(proc);
+
if (proc->pid < 0)
return 0;
diff --git a/src/qemu/qemu_nbdkit.h b/src/qemu/qemu_nbdkit.h
index c9af6efcfa..da53138d13 100644
--- a/src/qemu/qemu_nbdkit.h
+++ b/src/qemu/qemu_nbdkit.h
@@ -65,6 +65,11 @@ qemuNbdkitStartStorageSource(virQEMUDriver *driver,
void
qemuNbdkitStopStorageSource(virStorageSource *src);
+int
+qemuNbdkitStorageSourceManageProcess(virQEMUDriver *driver,
+ virDomainObj *vm,
+ virStorageSource *src);
+
bool
qemuNbdkitCapsGet(qemuNbdkitCaps *nbdkitCaps,
qemuNbdkitCapsFlags flag);
@@ -76,6 +81,8 @@ qemuNbdkitCapsSet(qemuNbdkitCaps *nbdkitCaps,
#define QEMU_TYPE_NBDKIT_CAPS qemu_nbdkit_caps_get_type()
G_DECLARE_FINAL_TYPE(qemuNbdkitCaps, qemu_nbdkit_caps, QEMU, NBDKIT_CAPS, GObject);
+typedef struct _qemuNbdkitProcessPrivate qemuNbdkitProcessPrivate;
+
struct _qemuNbdkitProcess {
qemuNbdkitCaps *caps;
virStorageSource *source;
@@ -85,6 +92,8 @@ struct _qemuNbdkitProcess {
uid_t user;
gid_t group;
pid_t pid;
+
+ qemuNbdkitProcessPrivate *priv;
};
int
@@ -107,4 +116,5 @@ qemuNbdkitProcessLoad(virStorageSource *source,
const char *pidfile,
const char *socketfile);
+
G_DEFINE_AUTOPTR_CLEANUP_FUNC(qemuNbdkitProcess, qemuNbdkitProcessFree);
diff --git a/src/qemu/qemu_process.c b/src/qemu/qemu_process.c
index f405326312..43e828d42f 100644
--- a/src/qemu/qemu_process.c
+++ b/src/qemu/qemu_process.c
@@ -9009,6 +9009,19 @@ qemuProcessReconnect(void *opaque)
}
}
+ for (i = 0; i < obj->def->ndisks; i++) {
+ virDomainDiskDef *disk = obj->def->disks[i];
+ if (qemuNbdkitStorageSourceManageProcess(driver, obj, disk->src) < 0)
+ goto error;
+ }
+
+ if (obj->def->os.loader && obj->def->os.loader->nvram) {
+ if (qemuNbdkitStorageSourceManageProcess(driver, obj,
+ obj->def->os.loader->nvram) < 0)
+ goto error;
+ }
+
+
/* update domain state XML with possibly updated state in virDomainObj */
if (virDomainObjSave(obj, driver->xmlopt, cfg->stateDir) < 0)
goto error;
--
2.37.3
