Add functions for handling exponential backoff loops.

In a few places in libvirt we busy-wait for events, for example qemu
creating a monitor socket.  This is problematic because:

 - We need to choose a sufficiently small polling period so that
   libvirt doesn't add unnecessary delays.

 - We need to choose a sufficiently large polling period so that
   the effect of busy-waiting doesn't affect the system.

The solution to this conflict is to use an exponential backoff.

This patch adds two functions to hide the details, and modifies a few
places where we currently busy-wait.

Signed-off-by: Richard W.M. Jones <rjones@redhat.com>

diff --git a/src/fdstream.c b/src/fdstream.c
index ef118b56ec5031c4ed57e6bb20420f555dd1c2aa..a6a0fbe0a461e97be643ab00b85a4a3b95147281 100644 (file)
--- a/src/fdstream.c
+++ b/src/fdstream.c
@@ -42,6 +42,7 @@
 #include "virfile.h"
 #include "configmake.h"
 #include "virstring.h"
+#include "virtime.h"
 
 #define VIR_FROM_THIS VIR_FROM_STREAMS
 
@@ -520,8 +521,7 @@ int virFDStreamConnectUNIX(virStreamPtr st,
                            bool abstract)
 {
     struct sockaddr_un sa;
-    size_t i = 0;
-    int timeout = 3;
+    virTimeBackOffVar timeout;
     int ret;
 
     int fd = socket(AF_UNIX, SOCK_STREAM, 0);
@@ -541,7 +541,9 @@ int virFDStreamConnectUNIX(virStreamPtr st,
             goto error;
     }
 
-    do {
+    if (virTimeBackOffStart(&timeout, 1, 3*1000 /* ms */) < 0)
+        goto error;
+    while (virTimeBackOffWait(&timeout)) {
         ret = connect(fd, (struct sockaddr *)&sa, sizeof(sa));
         if (ret == 0)
             break;
@@ -553,7 +555,7 @@ int virFDStreamConnectUNIX(virStreamPtr st,
         }
 
         goto error;
-    } while ((++i <= timeout*5) && (usleep(.2 * 1000000) <= 0));
+    }
 
     if (virFDStreamOpenInternal(st, fd, NULL, -1, 0) < 0)
         goto error;

diff --git a/src/libvirt_private.syms b/src/libvirt_private.syms
index b626fd237cb7cc23c8cece1376b326d60b6eb2f1..61fc5004bbb7b96c89eaf1681872e5a04a1ea15b 100644 (file)
--- a/src/libvirt_private.syms
+++ b/src/libvirt_private.syms
@@ -2373,6 +2373,8 @@ virThreadPoolSendJob;
 
 
 # util/virtime.h
+virTimeBackOffStart;
+virTimeBackOffWait;
 virTimeFieldsNow;
 virTimeFieldsNowRaw;
 virTimeFieldsThen;

diff --git a/src/qemu/qemu_agent.c b/src/qemu/qemu_agent.c
index 559d79fc0a52405f7f503920a711aac38a40dfdc..0610f75e52aa1f429bb2a9b195a78f5dbdfd9b9d 100644 (file)
--- a/src/qemu/qemu_agent.c
+++ b/src/qemu/qemu_agent.c
@@ -173,9 +173,8 @@ qemuAgentOpenUnix(const char *monitor, pid_t cpid, bool *inProgress)
 {
     struct sockaddr_un addr;
     int monfd;
-    int timeout = 3; /* In seconds */
-    int ret;
-    size_t i = 0;
+    virTimeBackOffVar timeout;
+    int ret = -1;
 
     *inProgress = false;
 
@@ -207,7 +206,9 @@ qemuAgentOpenUnix(const char *monitor, pid_t cpid, bool *inProgress)
         goto error;
     }
 
-    do {
+    if (virTimeBackOffStart(&timeout, 1, 3*1000 /* ms */) < 0)
+        goto error;
+    while (virTimeBackOffWait(&timeout)) {
         ret = connect(monfd, (struct sockaddr *) &addr, sizeof(addr));
 
         if (ret == 0)
@@ -232,7 +233,7 @@ qemuAgentOpenUnix(const char *monitor, pid_t cpid, bool *inProgress)
                              _("failed to connect to monitor socket"));
         goto error;
 
-    } while ((++i <= timeout*5) && (usleep(.2 * 1000000) <= 0));
+    }
 
     if (ret != 0) {
         virReportSystemError(errno, "%s",

diff --git a/src/qemu/qemu_monitor.c b/src/qemu/qemu_monitor.c
index 83551a83f2e818241f52467bb7e2de6503109539..2847cef9edb410fa39bf3382d7bc248b02ef3247 100644 (file)
--- a/src/qemu/qemu_monitor.c
+++ b/src/qemu/qemu_monitor.c
@@ -42,6 +42,7 @@
 #include "virobject.h"
 #include "virprobe.h"
 #include "virstring.h"
+#include "virtime.h"
 
 #ifdef WITH_DTRACE_PROBES
 # include "libvirt_qemu_probes.h"
@@ -327,9 +328,8 @@ qemuMonitorOpenUnix(const char *monitor, pid_t cpid)
 {
     struct sockaddr_un addr;
     int monfd;
-    int timeout = 30; /* In seconds */
-    int ret;
-    size_t i = 0;
+    virTimeBackOffVar timeout;
+    int ret = -1;
 
     if ((monfd = socket(AF_UNIX, SOCK_STREAM, 0)) < 0) {
         virReportSystemError(errno,
@@ -345,7 +345,9 @@ qemuMonitorOpenUnix(const char *monitor, pid_t cpid)
         goto error;
     }
 
-    do {
+    if (virTimeBackOffStart(&timeout, 1, 30*1000 /* ms */) < 0)
+        goto error;
+    while (virTimeBackOffWait(&timeout)) {
         ret = connect(monfd, (struct sockaddr *) &addr, sizeof(addr));
 
         if (ret == 0)
@@ -362,7 +364,7 @@ qemuMonitorOpenUnix(const char *monitor, pid_t cpid)
                              _("failed to connect to monitor socket"));
         goto error;
 
-    } while ((++i <= timeout*5) && (usleep(.2 * 1000000) <= 0));
+    }
 
     if (ret != 0) {
         virReportSystemError(errno, "%s",

diff --git a/src/util/virtime.c b/src/util/virtime.c
index 9d365d51c8b4f6a11ab6a0a76beaf4d0bd952ca3..aac96918a7606321cc79562fc5853ca09bd251f1 100644 (file)
--- a/src/util/virtime.c
+++ b/src/util/virtime.c
@@ -34,14 +34,18 @@
 #include <config.h>
 
 #include <stdio.h>
+#include <unistd.h>
 #include <sys/time.h>
 
 #include "virtime.h"
 #include "viralloc.h"
 #include "virerror.h"
+#include "virlog.h"
 
 #define VIR_FROM_THIS VIR_FROM_NONE
 
+VIR_LOG_INIT("util.time");
+
 /* We prefer clock_gettime if available because that is officially
  * async signal safe according to POSIX. Many platforms lack it
  * though, so fallback to gettimeofday everywhere else
@@ -363,3 +367,80 @@ virTimeLocalOffsetFromUTC(long *offset)
     *offset = current - utc;
     return 0;
 }
+
+/**
+ * virTimeBackOffStart:
+ * @var: Timeout variable (with type virTimeBackOffVar).
+ * @first: Initial time to wait (milliseconds).
+ * @timeout: Timeout (milliseconds).
+ *
+ * Initialize the timeout variable @var and start the timer running.
+ *
+ * Returns 0 on success, -1 on error and raises a libvirt error.
+ */
+int
+virTimeBackOffStart(virTimeBackOffVar *var,
+                    unsigned long long first, unsigned long long timeout)
+{
+    if (virTimeMillisNow(&var->start_t) < 0)
+        return -1;
+
+    var->next = first;
+    var->limit_t = var->start_t + timeout;
+    return 0;
+}
+
+/**
+ * virTimeBackOffWait
+ * @var: Timeout variable (with type virTimeBackOffVar *).
+ *
+ * You must initialize @var first by calling the following function,
+ * which also starts the timer:
+ *
+ * if (virTimeBackOffStart(&var, first, timeout) < 0) {
+ *   // handle errors
+ * }
+ *
+ * Then you use a while loop:
+ *
+ * while (virTimeBackOffWait(&var)) {
+ *   //...
+ * }
+ *
+ * The while loop that runs the body of the code repeatedly, with an
+ * exponential backoff.  It first waits for first milliseconds, then
+ * runs the body, then waits for 2*first ms, then runs the body again.
+ * Then 4*first ms, and so on.
+ *
+ * When timeout milliseconds is reached, the while loop ends.
+ *
+ * The body should use "break" or "goto" when whatever condition it is
+ * testing for succeeds (or there is an unrecoverable error).
+ */
+bool
+virTimeBackOffWait(virTimeBackOffVar *var)
+{
+    unsigned long long t, next;
+
+    ignore_value(virTimeMillisNowRaw(&t));
+
+    VIR_DEBUG("t=%llu, limit=%llu", t, var->limit_t);
+
+    if (t > var->limit_t)
+        return 0;               /* ends the while loop */
+
+    next = var->next;
+    var->next *= 2;
+
+    /* If sleeping would take us beyond the limit, then shorten the
+     * sleep.  This is so we always run the body just before the final
+     * timeout.
+     */
+    if (t + next > var->limit_t)
+        next = var->limit_t - t;
+
+    VIR_DEBUG("sleeping for %llu ms", next);
+
+    usleep(next * 1000);
+    return 1;
+}

diff --git a/src/util/virtime.h b/src/util/virtime.h
index 8ebad38c7f0c3f9ea8d83e03b3e6f2010cdbd4b2..fbcd3ba667684a47430f82cb710925e09e19f0e2 100644 (file)
--- a/src/util/virtime.h
+++ b/src/util/virtime.h
@@ -64,4 +64,15 @@ char *virTimeStringThen(unsigned long long when);
 int virTimeLocalOffsetFromUTC(long *offset)
     ATTRIBUTE_NONNULL(1) ATTRIBUTE_RETURN_CHECK;
 
+typedef struct {
+    unsigned long long start_t;
+    unsigned long long next;
+    unsigned long long limit_t;
+} virTimeBackOffVar;
+
+int virTimeBackOffStart(virTimeBackOffVar *var,
+                        unsigned long long first, unsigned long long timeout);
+
+bool virTimeBackOffWait(virTimeBackOffVar *var);
+
 #endif