Fix QEMU startup timeout/race (rhbz #484649)

Setup DBus threading. Don't allow dbus to call _exit / change SIGPIPE (rhbz #484553)
Fix timeout when autostarting session daemon

.cvsignore

@@ -3,12 +3,4 @@
 i686
 x86_64
 libvirt-*.tar.gz
-libvirt-0.6.0.tar.gz
-libvirt-0.6.1.tar.gz
-libvirt-0.6.2.tar.gz
-libvirt-0.6.3.tar.gz
-libvirt-0.6.4.tar.gz
-libvirt-0.6.5.tar.gz
-libvirt-0.7.0.tar.gz
-libvirt-0.7.1.tar.gz
-libvirt-0.7.2.tar.gz
+libvirt-0.4.6.tar.gz

branch

@@ -0,0 +1 @@
+F-10

libvirt-0.6.0-autostart-timeout.patch

@@ -0,0 +1,21 @@
+diff -rup libvirt-0.6.0.orig/src/remote_internal.c libvirt-0.6.0.new/src/remote_internal.c
+--- libvirt-0.6.0.orig/src/remote_internal.c	2009-02-18 10:56:34.000000000 +0000
++++ libvirt-0.6.0.new/src/remote_internal.c	2009-02-18 13:35:26.000000000 +0000
+@@ -654,12 +654,13 @@ doRemoteOpen (virConnectPtr conn,
+              */
+             if (errno == ECONNREFUSED &&
+                 flags & VIR_DRV_OPEN_REMOTE_AUTOSTART &&
+-                trials < 5) {
++                trials < 20) {
+                 close(priv->sock);
+                 priv->sock = -1;
+-                if (remoteForkDaemon(conn) == 0) {
++                if (trials > 0 ||
++                    remoteForkDaemon(conn) == 0) {
+                     trials++;
+-                    usleep(5000 * trials * trials);
++                    usleep(1000 * 100 * trials);
+                     goto autostart_retry;
+                 }
+             }
+Only in libvirt-0.6.0.new/src: remote_internal.c~

libvirt-0.6.0-dbus-threads.patch

@@ -0,0 +1,44 @@
+diff -rup libvirt-0.6.0.orig/qemud/qemud.c libvirt-0.6.0.new/qemud/qemud.c
+--- libvirt-0.6.0.orig/qemud/qemud.c	2009-02-18 10:56:34.000000000 +0000
++++ libvirt-0.6.0.new/qemud/qemud.c	2009-02-18 12:52:18.000000000 +0000
+@@ -860,6 +860,10 @@ static struct qemud_server *qemudNetwork
+     if (auth_unix_rw == REMOTE_AUTH_POLKIT ||
+         auth_unix_ro == REMOTE_AUTH_POLKIT) {
+         DBusError derr;
++
++        dbus_connection_set_change_sigpipe(FALSE);
++        dbus_threads_init_default();
++
+         dbus_error_init(&derr);
+         server->sysbus = dbus_bus_get(DBUS_BUS_SYSTEM, &derr);
+         if (!(server->sysbus)) {
+@@ -868,6 +872,7 @@ static struct qemud_server *qemudNetwork
+             dbus_error_free(&derr);
+             goto cleanup;
+         }
++        dbus_connection_set_exit_on_disconnect(server->sysbus, FALSE);
+     }
+ #endif
+ 
+diff -rup libvirt-0.6.0.orig/src/node_device_hal.c libvirt-0.6.0.new/src/node_device_hal.c
+--- libvirt-0.6.0.orig/src/node_device_hal.c	2009-01-16 12:44:22.000000000 +0000
++++ libvirt-0.6.0.new/src/node_device_hal.c	2009-02-18 12:52:48.000000000 +0000
+@@ -685,6 +685,9 @@ static int halDeviceMonitorStartup(void)
+     nodeDeviceLock(driverState);
+ 
+     /* Allocate and initialize a new HAL context */
++    dbus_connection_set_change_sigpipe(FALSE);
++    dbus_threads_init_default();
++
+     dbus_error_init(&err);
+     hal_ctx = libhal_ctx_new();
+     if (hal_ctx == NULL) {
+@@ -696,6 +699,8 @@ static int halDeviceMonitorStartup(void)
+         fprintf(stderr, "%s: dbus_bus_get failed\n", __FUNCTION__);
+         goto failure;
+     }
++    dbus_connection_set_exit_on_disconnect(dbus_conn, FALSE);
++
+     if (!libhal_ctx_set_dbus_connection(hal_ctx, dbus_conn)) {
+         fprintf(stderr, "%s: libhal_ctx_set_dbus_connection failed\n",
+                 __FUNCTION__);

libvirt-0.6.0-qemu-startup.patch

@@ -0,0 +1,109 @@
+diff -rup libvirt-0.6.0.orig/src/qemu_driver.c libvirt-0.6.0.new/src/qemu_driver.c
+--- libvirt-0.6.0.orig/src/qemu_driver.c	2009-01-31 09:04:18.000000000 +0000
++++ libvirt-0.6.0.new/src/qemu_driver.c	2009-02-18 11:15:37.000000000 +0000
+@@ -633,6 +633,7 @@ qemudReadMonitorOutput(virConnectPtr con
+ {
+     int got = 0;
+     buf[0] = '\0';
++    timeout *= 1000; /* poll wants milli seconds */
+ 
+     /* Consume & discard the initial greeting */
+     while (got < (buflen-1)) {
+@@ -694,6 +695,56 @@ qemudReadMonitorOutput(virConnectPtr con
+ 
+ }
+ 
++
++/*
++ * Returns -1 for error, 0 on success
++ */
++static int
++qemudReadLogOutput(virConnectPtr conn,
++                   virDomainObjPtr vm,
++                   int fd,
++                   char *buf,
++                   int buflen,
++                   qemudHandlerMonitorOutput func,
++                   const char *what,
++                   int timeout)
++{
++    int got = 0;
++    int ret;
++    int retries = timeout*10;
++    buf[0] = '\0';
++
++    while (retries) {
++        while((ret = read(fd, buf+got, buflen-got-1)) > 0) {
++            got += ret;
++            buf[got] = '\0';
++            if ((buflen-got-1) == 0) {
++                qemudReportError(conn, NULL, NULL, VIR_ERR_INTERNAL_ERROR,
++                                 _("Out of space while reading %s log output"), what);
++                return -1;
++            }
++        }
++
++        if (ret < 0 && errno != EINTR) {
++            virReportSystemError(conn, errno,
++                                 _("Failure while reading %s log output"),
++                                 what);
++            return -1;
++        }
++
++        ret = func(conn, vm, buf, fd);
++        if (ret <= 0)
++            return ret;
++
++        usleep(100*1000);
++        retries--;
++    }
++    if (retries == 0)
++        qemudReportError(conn, NULL, NULL, VIR_ERR_INTERNAL_ERROR,
++                         _("Timed out while reading %s log output"), what);
++    return -1;
++}
++
+ static int
+ qemudCheckMonitorPrompt(virConnectPtr conn ATTRIBUTE_UNUSED,
+                         virDomainObjPtr vm,
+@@ -738,7 +789,7 @@ static int qemudOpenMonitor(virConnectPt
+                                    vm, monfd,
+                                    buf, sizeof(buf),
+                                    qemudCheckMonitorPrompt,
+-                                   "monitor", 10000) <= 0)
++                                   "monitor", 10) <= 0)
+             ret = -1;
+         else
+             ret = 0;
+@@ -770,6 +821,7 @@ static int qemudOpenMonitor(virConnectPt
+     return ret;
+ }
+ 
++/* Returns -1 for error, 0 success, 1 continue reading */
+ static int qemudExtractMonitorPath(virConnectPtr conn,
+                                    const char *haystack,
+                                    size_t *offset,
+@@ -873,19 +925,16 @@ static int qemudWaitForMonitor(virConnec
+         < 0)
+         return -1;
+ 
+-    ret = qemudReadMonitorOutput(conn, vm, logfd, buf, sizeof(buf),
+-                                 qemudFindCharDevicePTYs,
+-                                 "console", 3000);
++    ret = qemudReadLogOutput(conn, vm, logfd, buf, sizeof(buf),
++                             qemudFindCharDevicePTYs,
++                             "console", 3);
+     if (close(logfd) < 0)
+         qemudLog(QEMUD_WARN, _("Unable to close logfile: %s\n"),
+                  strerror(errno));
+ 
+-    if (ret == 1) /* Success */
++    if (ret == 0) /* success */
+         return 0;
+ 
+-    if (ret == -1)
+-        return -1;
+-
+     /* Unexpected end of file - inform user of QEMU log data */
+     qemudReportError(conn, NULL, NULL, VIR_ERR_INTERNAL_ERROR,
+                      _("unable to start guest: %s"), buf);

libvirt-0.6.0-timeout.patch

@@ -0,0 +1,124 @@
+diff -rup libvirt-0.6.0.orig/qemud/event.c libvirt-0.6.0.new/qemud/event.c
+--- libvirt-0.6.0.orig/qemud/event.c	2008-12-22 13:02:54.000000000 +0000
++++ libvirt-0.6.0.new/qemud/event.c	2009-02-06 19:29:28.000000000 +0000
+@@ -68,6 +68,7 @@ struct virEventTimeout {
+ /* State for the main event loop */
+ struct virEventLoop {
+     pthread_mutex_t lock;
++    int running;
+     pthread_t leader;
+     int wakeupfd[2];
+     int handlesCount;
+@@ -521,6 +522,7 @@ int virEventRunOnce(void) {
+     int ret, timeout, nfds;
+ 
+     virEventLock();
++    eventLoop.running = 1;
+     eventLoop.leader = pthread_self();
+     if ((nfds = virEventMakePollFDs(&fds)) < 0) {
+         virEventUnlock();
+@@ -572,7 +574,7 @@ int virEventRunOnce(void) {
+         return -1;
+     }
+ 
+-    eventLoop.leader = 0;
++    eventLoop.running = 0;
+     virEventUnlock();
+     return 0;
+ }
+@@ -611,7 +613,9 @@ int virEventInit(void)
+ static int virEventInterruptLocked(void)
+ {
+     char c = '\0';
+-    if (pthread_self() == eventLoop.leader)
++
++    if (!eventLoop.running ||
++        pthread_self() == eventLoop.leader)
+         return 0;
+ 
+     if (safewrite(eventLoop.wakeupfd[1], &c, sizeof(c)) != sizeof(c))
+diff -rup libvirt-0.6.0.orig/qemud/qemud.c libvirt-0.6.0.new/qemud/qemud.c
+--- libvirt-0.6.0.orig/qemud/qemud.c	2009-01-31 09:04:17.000000000 +0000
++++ libvirt-0.6.0.new/qemud/qemud.c	2009-02-06 19:29:28.000000000 +0000
+@@ -2013,11 +2013,15 @@ static int qemudOneLoop(void) {
+     return 0;
+ }
+ 
+-static void qemudInactiveTimer(int timer ATTRIBUTE_UNUSED, void *data) {
++static void qemudInactiveTimer(int timerid, void *data) {
+     struct qemud_server *server = (struct qemud_server *)data;
+-    DEBUG0("Got inactive timer expiry");
+-    if (!virStateActive()) {
+-        DEBUG0("No state active, shutting down");
++
++    if (virStateActive() ||
++        server->clients) {
++        DEBUG0("Timer expired but still active, not shutting down");
++        virEventUpdateTimeoutImpl(timerid, -1);
++    } else {
++        DEBUG0("Timer expired and inactive, shutting down");
+         server->shutdown = 1;
+     }
+ }
+@@ -2048,9 +2052,18 @@ static void qemudFreeClient(struct qemud
+ static int qemudRunLoop(struct qemud_server *server) {
+     int timerid = -1;
+     int ret = -1, i;
++    int timerActive = 0;
+ 
+     virMutexLock(&server->lock);
+ 
++    if (timeout > 0 &&
++        (timerid = virEventAddTimeoutImpl(-1,
++                                          qemudInactiveTimer,
++                                          server, NULL)) < 0) {
++        VIR_ERROR0(_("Failed to register shutdown timeout"));
++        return -1;
++    }
++
+     if (min_workers > max_workers)
+         max_workers = min_workers;
+ 
+@@ -2071,11 +2084,21 @@ static int qemudRunLoop(struct qemud_ser
+          * if any drivers have active state, if not
+          * shutdown after timeout seconds
+          */
+-        if (timeout > 0 && !virStateActive() && !server->clients) {
+-            timerid = virEventAddTimeoutImpl(timeout*1000,
+-                                             qemudInactiveTimer,
+-                                             server, NULL);
+-            DEBUG("Scheduling shutdown timer %d", timerid);
++        if (timeout > 0) {
++            if (timerActive) {
++                if (server->clients) {
++                    DEBUG("Deactivating shutdown timer %d", timerid);
++                    virEventUpdateTimeoutImpl(timerid, -1);
++                    timerActive = 0;
++                }
++            } else {
++                if (!virStateActive() &&
++                    !server->clients) {
++                    DEBUG("Activating shutdown timer %d", timerid);
++                    virEventUpdateTimeoutImpl(timerid, timeout * 1000);
++                    timerActive = 1;
++                }
++            }
+         }
+ 
+         virMutexUnlock(&server->lock);
+@@ -2129,15 +2152,6 @@ static int qemudRunLoop(struct qemud_ser
+             }
+         }
+ 
+-        /* Unregister any timeout that's active, since we
+-         * just had an event processed
+-         */
+-        if (timerid != -1) {
+-            DEBUG("Removing shutdown timer %d", timerid);
+-            virEventRemoveTimeoutImpl(timerid);
+-            timerid = -1;
+-        }
+-
+         if (server->shutdown) {
+             ret = 0;
+             break;

libvirt-qemu-machine-type-fixes2.patch

@@ -1,42 +0,0 @@
-From b7b6a28eb9eae641762de9408a90971d849ce92e Mon Sep 17 00:00:00 2001
-From: Mark McLoughlin <markmc@redhat.com>
-Date: Thu, 15 Oct 2009 12:09:17 +0100
-Subject: [PATCH] Don't copy old machines from a domain which has none
-
-If the the qemu and kvm binaries are the same, we don't include machine
-types in the kvm domain info.
-
-However, the code which refreshes the machine types info from the
-previous capabilities structure first looks at the kvm domain's info,
-finds it matches and then copies the empty machine types list over
-for the top-level qemu domain.
-
-That doesn't make sense, we shouldn't copy an empty machin types list.
-
-* src/qemu/qemu_conf.c: qemudGetOldMachinesFromInfo(): don't copy an
-  empty machine types list.
-
-(cherry picked from commit 2210f8a3a8e2774ca4fb8b42e21899e5b85ca913)
-
-Fedora-patch: libvirt-qemu-machine-type-fixes2.patch
----
- src/qemu/qemu_conf.c |    3 +++
- 1 files changed, 3 insertions(+), 0 deletions(-)
-
-diff --git a/src/qemu/qemu_conf.c b/src/qemu/qemu_conf.c
-index ac63570..b881f1e 100644
---- a/src/qemu/qemu_conf.c
-+++ b/src/qemu/qemu_conf.c
-@@ -505,6 +505,9 @@ qemudGetOldMachinesFromInfo(virCapsGuestDomainInfoPtr info,
-     virCapsGuestMachinePtr *list;
-     int i;
- 
-+    if (!info->nmachines)
-+        return 0;
-+
-     if (!info->emulator || !STREQ(emulator, info->emulator))
-         return 0;
- 
--- 
-1.6.2.5
-

sources

@@ -1 +1 @@
-133aead8c46c0601b6b37e024c6aa86a  libvirt-0.7.2.tar.gz
+8e0120d5452b37179f682031bf0895ea  libvirt-0.6.0.tar.gz