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 a macro VIR_WHILE_EXPONENTIAL_BACKOFF to hide the details, and modifies a few places where we currently busy-wait. --- src/fdstream.c | 8 ++++---- src/libvirt_private.syms | 2 ++ src/qemu/qemu_agent.c | 8 ++++---- src/qemu/qemu_monitor.c | 8 ++++---- src/util/virtime.c | 42 ++++++++++++++++++++++++++++++++++++++++++ src/util/virtime.h | 39 +++++++++++++++++++++++++++++++++++++++ 6 files changed, 95 insertions(+), 12 deletions(-) diff --git a/src/fdstream.c b/src/fdstream.c index a85cf9d..7a311f5 100644 --- 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 @@ -516,8 +517,7 @@ 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); @@ -537,7 +537,7 @@ int virFDStreamConnectUNIX(virStreamPtr st, goto error; } - do { + VIR_WHILE_EXPONENTIAL_BACKOFF(timeout, 1, 3*1000 /* ms */) { ret = connect(fd, (struct sockaddr *)&sa, sizeof(sa)); if (ret == 0) break; @@ -549,7 +549,7 @@ 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 068bc00..b69d2e0 100644 --- a/src/libvirt_private.syms +++ b/src/libvirt_private.syms @@ -2360,6 +2360,8 @@ virThreadPoolSendJob; # util/virtime.h +virTimeBackOffCondition; +virTimeBackOffInit; virTimeFieldsNow; virTimeFieldsNowRaw; virTimeFieldsThen; diff --git a/src/qemu/qemu_agent.c b/src/qemu/qemu_agent.c index bee8d4c..adf38c5 100644 --- a/src/qemu/qemu_agent.c +++ b/src/qemu/qemu_agent.c @@ -42,6 +42,7 @@ #include "virtime.h" #include "virobject.h" #include "virstring.h" +#include "virtime.h" #include "base64.h" #define VIR_FROM_THIS VIR_FROM_QEMU @@ -173,9 +174,8 @@ qemuAgentOpenUnix(const char *monitor, pid_t cpid, bool *inProgress) { struct sockaddr_un addr; int monfd; - int timeout = 3; /* In seconds */ + virTimeBackOffVar timeout; int ret; - size_t i = 0; *inProgress = false; @@ -207,7 +207,7 @@ qemuAgentOpenUnix(const char *monitor, pid_t cpid, bool *inProgress) goto error; } - do { + VIR_WHILE_EXPONENTIAL_BACKOFF(timeout, 1, 3*1000 /* ms */) { ret = connect(monfd, (struct sockaddr *) &addr, sizeof(addr)); if (ret == 0) @@ -232,7 +232,7 @@ 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 10a6713..52f0d20 100644 --- 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 */ + virTimeBackOffVar timeout; int ret; - size_t i = 0; if ((monfd = socket(AF_UNIX, SOCK_STREAM, 0)) < 0) { virReportSystemError(errno, @@ -345,7 +345,7 @@ qemuMonitorOpenUnix(const char *monitor, pid_t cpid) goto error; } - do { + VIR_WHILE_EXPONENTIAL_BACKOFF(timeout, 1, 30*1000 /* ms */) { ret = connect(monfd, (struct sockaddr *) &addr, sizeof(addr)); if (ret == 0) @@ -362,7 +362,7 @@ 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 9d365d5..78622e7 100644 --- 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 +367,41 @@ virTimeLocalOffsetFromUTC(long *offset) *offset = current - utc; return 0; } + +void +virTimeBackOffInit(virTimeBackOffVar *var, + unsigned long long first, unsigned long long limit) +{ + ignore_value(virTimeMillisNowRaw(&var->start_t)); + var->next = first; + var->limit = var->start_t + limit; +} + +int +virTimeBackOffCondition(virTimeBackOffVar *var) +{ + unsigned long long t, next; + + ignore_value(virTimeMillisNowRaw(&t)); + + VIR_DEBUG("t=%llu, limit=%llu", t, var->limit); + + if (t > var->limit) + 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) { + next = var->limit - t - 2; + } + + 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 8ebad38..723a93a 100644 --- a/src/util/virtime.h +++ b/src/util/virtime.h @@ -64,4 +64,43 @@ char *virTimeStringThen(unsigned long long when); int virTimeLocalOffsetFromUTC(long *offset) ATTRIBUTE_NONNULL(1) ATTRIBUTE_RETURN_CHECK; +/** + * VIR_WHILE_EXPONENTIAL_BACKOFF: + * @var: A scratch variable used by the loop (with type virTimeBackOffVar). + * @first: First time period to wait, in milliseconds. + * @limit: Total time we run before the loop times out, in milliseconds. + * + * This macro is a while loop that runs the body of the code + * repeatedly, with an exponential backoff. It first waits for @first + * ms, then runs the body, then waits for 2*@first ms, then runs the + * body again. Then 4*@first ms, and so on. + * + * When @limit ms (total running time) 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). + * + * NOTE: VIR_WHILE_EXPONENTIAL_BACKOFF is not a single atomic C + * statement (unfortunately), so you will get incorrect code if you + * write something like: + * + * if (foo) + * VIR_WHILE_EXPONENTIAL_BACKOFF(...) { + * } + */ +#define VIR_WHILE_EXPONENTIAL_BACKOFF(var, first, limit) \ + virTimeBackOffInit(&(var), (first), (limit)); \ + while (virTimeBackOffCondition(&(var))) + +typedef struct { + unsigned long long start_t; + unsigned long long next; + unsigned long long limit; +} virTimeBackOffVar; + +void virTimeBackOffInit(virTimeBackOffVar *var, + unsigned long long first, unsigned long long limit); +int virTimeBackOffCondition(virTimeBackOffVar *var); + #endif -- 2.7.4