7:29 a.m.
There were couple of reports on the list (e.g. [1]) that guests
with huge amounts of RAM are unable to start because libvirt
kills qemu in the initialization phase. The problem is that if
guest is configured to use hugepages kernel has to zero them all
out before handing over to qemu process. For instance, 402GiB
worth of 1GiB pages took around 105 seconds (~3.8GiB/s). Since we
do not want to make the timeout for connecting to monitor
configurable [2], we have to teach libvirt to count with this
fact. This commit implements "1s per each 1GiB of RAM" approach
as suggested here [3].
1: https://www.redhat.com/archives/libvir-list/2017-March/msg00373.html
3: https://www.redhat.com/archives/libvir-list/2017-March/msg00405.html
2: The reason is that ideally someday it will be Libvirt who
creates the monitor socket and qemu will just use it.
Signed-off-by: Michal Privoznik <mprivozn(a)redhat.com>
---
src/qemu/qemu_capabilities.c | 2 +-
src/qemu/qemu_monitor.c | 36 +++++++++++++++++++++++++++++++-----
src/qemu/qemu_monitor.h | 1 +
src/qemu/qemu_process.c | 8 ++++++++
tests/qemumonitortestutils.c | 1 +
5 files changed, 42 insertions(+), 6 deletions(-)
diff --git a/src/qemu/qemu_capabilities.c b/src/qemu/qemu_capabilities.c
index 5a3b4ac50..54dfd22d8 100644
--- a/src/qemu/qemu_capabilities.c
+++ b/src/qemu/qemu_capabilities.c
@@ -4761,7 +4761,7 @@ virQEMUCapsInitQMPCommandRun(virQEMUCapsInitQMPCommandPtr cmd,
cmd->vm->pid = cmd->pid;
if (!(cmd->mon = qemuMonitorOpen(cmd->vm, &cmd->config, true,
- &callbacks, NULL)))
+ 0, &callbacks, NULL)))
goto ignore;
virObjectLock(cmd->mon);
diff --git a/src/qemu/qemu_monitor.c b/src/qemu/qemu_monitor.c
index d71f84c80..272350bf5 100644
--- a/src/qemu/qemu_monitor.c
+++ b/src/qemu/qemu_monitor.c
@@ -327,11 +327,13 @@ qemuMonitorDispose(void *obj)
static int
-qemuMonitorOpenUnix(const char *monitor, pid_t cpid)
+qemuMonitorOpenUnix(const char *monitor,
+ pid_t cpid,
+ unsigned long long timeout)
{
struct sockaddr_un addr;
int monfd;
- virTimeBackOffVar timeout;
+ virTimeBackOffVar timebackoff;
int ret = -1;
if ((monfd = socket(AF_UNIX, SOCK_STREAM, 0)) < 0) {
@@ -348,9 +350,9 @@ qemuMonitorOpenUnix(const char *monitor, pid_t cpid)
goto error;
}
- if (virTimeBackOffStart(&timeout, 1, 30*1000 /* ms */) < 0)
+ if (virTimeBackOffStart(&timebackoff, 1, timeout * 1000) < 0)
goto error;
- while (virTimeBackOffWait(&timeout)) {
+ while (virTimeBackOffWait(&timebackoff)) {
ret = connect(monfd, (struct sockaddr *) &addr, sizeof(addr));
if (ret == 0)
@@ -871,10 +873,30 @@ qemuMonitorOpenInternal(virDomainObjPtr vm,
}
+#define QEMU_DEFAULT_MONITOR_WAIT 30
+
+/**
+ * qemuMonitorOpen:
+ * @vm: domain object
+ * @config: monitor configuration
+ * @json: enable JSON on the monitor
+ * @timeout: how much seconds add to default timeout
+ * @cb: monitor event handles
+ * @opaque: opaque data for @cb
+ *
+ * Opens the monitor for running qemu. It may happen that it
+ * takes some time for qemu to create the monitor socket (e.g.
+ * because kernel is zeroing configured hugepages), therefore we
+ * wait up to default + timeout seconds for the monitor to show
+ * up after which a failure is claimed.
+ *
+ * Returns monitor object, NULL on error.
+ */
qemuMonitorPtr
qemuMonitorOpen(virDomainObjPtr vm,
virDomainChrSourceDefPtr config,
bool json,
+ unsigned long long timeout,
qemuMonitorCallbacksPtr cb,
void *opaque)
{
@@ -882,10 +904,14 @@ qemuMonitorOpen(virDomainObjPtr vm,
bool hasSendFD = false;
qemuMonitorPtr ret;
+ timeout += QEMU_DEFAULT_MONITOR_WAIT;
+
switch (config->type) {
case VIR_DOMAIN_CHR_TYPE_UNIX:
hasSendFD = true;
- if ((fd = qemuMonitorOpenUnix(config->data.nix.path, vm ? vm->pid : 0))
< 0)
+ if ((fd = qemuMonitorOpenUnix(config->data.nix.path,
+ vm ? vm->pid : 0,
+ timeout)) < 0)
return NULL;
break;
diff --git a/src/qemu/qemu_monitor.h b/src/qemu/qemu_monitor.h
index 847e9458a..3c37a6ffe 100644
--- a/src/qemu/qemu_monitor.h
+++ b/src/qemu/qemu_monitor.h
@@ -246,6 +246,7 @@ char *qemuMonitorUnescapeArg(const char *in);
qemuMonitorPtr qemuMonitorOpen(virDomainObjPtr vm,
virDomainChrSourceDefPtr config,
bool json,
+ unsigned long long timeout,
qemuMonitorCallbacksPtr cb,
void *opaque)
ATTRIBUTE_NONNULL(1) ATTRIBUTE_NONNULL(2) ATTRIBUTE_NONNULL(4);
diff --git a/src/qemu/qemu_process.c b/src/qemu/qemu_process.c
index b9c1847bb..6a9c53aea 100644
--- a/src/qemu/qemu_process.c
+++ b/src/qemu/qemu_process.c
@@ -1658,6 +1658,7 @@ qemuConnectMonitor(virQEMUDriverPtr driver, virDomainObjPtr vm, int
asyncJob,
qemuDomainObjPrivatePtr priv = vm->privateData;
int ret = -1;
qemuMonitorPtr mon = NULL;
+ unsigned long long timeout = 0;
if (qemuSecuritySetDaemonSocketLabel(driver->securityManager, vm->def) < 0)
{
VIR_ERROR(_("Failed to set security context for monitor for %s"),
@@ -1665,6 +1666,12 @@ qemuConnectMonitor(virQEMUDriverPtr driver, virDomainObjPtr vm, int
asyncJob,
return -1;
}
+ /* When using hugepages, kernel zeroes them out before
+ * handing them over to qemu. This can be very time
+ * consuming. Therefore, add a seconds to timeout for each
+ * 1GiB of guest RAM. */
+ timeout = vm->def->mem.total_memory / (1024 * 1024);
+
/* Hold an extra reference because we can't allow 'vm' to be
* deleted until the monitor gets its own reference. */
virObjectRef(vm);
@@ -1675,6 +1682,7 @@ qemuConnectMonitor(virQEMUDriverPtr driver, virDomainObjPtr vm, int
asyncJob,
mon = qemuMonitorOpen(vm,
priv->monConfig,
priv->monJSON,
+ timeout,
&monitorCallbacks,
driver);
diff --git a/tests/qemumonitortestutils.c b/tests/qemumonitortestutils.c
index cfd0a38cb..89857a662 100644
--- a/tests/qemumonitortestutils.c
+++ b/tests/qemumonitortestutils.c
@@ -1175,6 +1175,7 @@ qemuMonitorTestNew(bool json,
if (!(test->mon = qemuMonitorOpen(test->vm,
&src,
json,
+ 0,
&qemuMonitorTestCallbacks,
driver)))
goto error;
--
2.11.0