* [PATCH v3 2/3] aio-poll: refine iothread polling using weighted handler intervals
2026-04-05 20:07 [PATCH v3 0/3] improve aio-polling efficiency Jaehoon Kim
2026-04-05 20:07 ` [PATCH v3 1/3] aio-poll: avoid unnecessary polling time computation Jaehoon Kim
@ 2026-04-05 20:07 ` Jaehoon Kim
2026-04-05 20:07 ` [PATCH v3 3/3] qapi/iothread: introduce poll-weight parameter for aio-poll Jaehoon Kim
2 siblings, 0 replies; 6+ messages in thread
From: Jaehoon Kim @ 2026-04-05 20:07 UTC (permalink / raw)
To: qemu-devel, qemu-block
Cc: pbonzini, stefanha, fam, armbru, eblake, berrange, eduardo, dave,
sw, mjrosato, farman, Jaehoon Kim
Improve adaptive polling by updating each AioHandler's poll.ns
every loop iteration using weighted averages. This reduces CPU
consumption while minimizing performance impact.
Background:
Starting from QEMU 10.0, poll.ns was introduced per event handler
to mitigate excessive fluctuations in IOThread polling times
observed in earlier versions (QEMU 9.x). However, the current
design has limitations:
1. poll.ns is updated only when an event occurs, making it
difficult to treat block_ns as a reliable event interval.
2. The IOThread's next polling time is determined by the maximum
poll.ns among all AioHandlers, meaning idle AioHandlers with
high poll.ns can have an outsized impact on polling duration.
3. For io_uring, idle AioHandlers are cleared after
POLL_IDLE_INTERVAL_NS (7s), but for ppoll/epoll there is no
such mechanism, leading to increased CPU consumption from idle
nodes.
Implementation:
This patch treats block_ns as an event interval and updates each
AioHandler's poll.ns in every loop iteration:
- Active handlers (with events): poll.ns is updated using a
weighted average of the current block_ns and previous poll.ns,
smoothing out adjustments and preventing excessive fluctuations.
- Inactive handlers (no events): poll.ns accumulates block_ns
without weighting, allowing rapid isolation of idle nodes. When
poll.ns exceeds poll_max_ns, it resets to 0, preventing
sporadically active handlers from unnecessarily prolonging
iothread polling.
- The iothread polling duration is set based on the largest poll.ns
among active handlers. The shrink divider defaults to 2, matching
the grow rate, to reduce frequent poll_ns resets for slow devices.
The implementation renames poll_idle_timeout to last_dispatch_timestamp
for use as an active handler identifier.
Testing:
POLL_WEIGHT_SHIFT=3 (12.5% weight) was selected based on testing
comparing baseline vs weight=2/3 across various workloads:
The table below shows a comparison between:
-Host: RHEL 10.1 GA + qemu-10.0.0-14.el10_1, Guest: RHEL 9.6GA vs.
-Host: RHEL 10.1 GA + qemu-10.0.0-14.el10_1 (w=2/w=3), Guest: RHEL 9.6GA
for FIO FCP and FICON with 1 iothread and 8 iothreads.
The values shown are the averages for numjobs 1, 4, and 8.
Summary of results (% change vs baseline):
| poll-weight=2 | poll-weight=3
--------------------|--------------------|-----------------
Throughput avg | -2.4% (all tests) | -2.2% (all tests)
CPU consumption avg | -10.9% (all tests) | -9.4% (all tests)
Both configurations achieve ~10% CPU reduction with minimal
throughput impact (~2%), addressing the QEMU 10.0.0 CPU regression.
Weight=3 is chosen as default for its slightly better throughput
while maintaining substantial CPU savings.
Signed-off-by: Jaehoon Kim <jhkim@linux.ibm.com>
---
include/qemu/aio.h | 3 +-
util/aio-posix.c | 130 ++++++++++++++++++++++++++++++---------------
util/aio-posix.h | 2 +-
util/async.c | 1 +
4 files changed, 90 insertions(+), 46 deletions(-)
diff --git a/include/qemu/aio.h b/include/qemu/aio.h
index 8cca2360d1..6c22064a28 100644
--- a/include/qemu/aio.h
+++ b/include/qemu/aio.h
@@ -195,7 +195,7 @@ struct BHListSlice {
typedef QSLIST_HEAD(, AioHandler) AioHandlerSList;
typedef struct AioPolledEvent {
- int64_t ns; /* current polling time in nanoseconds */
+ int64_t ns; /* estimated block time in nanoseconds */
} AioPolledEvent;
struct AioContext {
@@ -306,6 +306,7 @@ struct AioContext {
int poll_disable_cnt;
/* Polling mode parameters */
+ int64_t poll_ns; /* current polling time in nanoseconds */
int64_t poll_max_ns; /* maximum polling time in nanoseconds */
int64_t poll_grow; /* polling time growth factor */
int64_t poll_shrink; /* polling time shrink factor */
diff --git a/util/aio-posix.c b/util/aio-posix.c
index 351847c6fb..8e9e9e5d8f 100644
--- a/util/aio-posix.c
+++ b/util/aio-posix.c
@@ -29,9 +29,11 @@
/* Stop userspace polling on a handler if it isn't active for some time */
#define POLL_IDLE_INTERVAL_NS (7 * NANOSECONDS_PER_SECOND)
+#define POLL_WEIGHT_SHIFT (3)
-static void adjust_polling_time(AioContext *ctx, AioPolledEvent *poll,
- int64_t block_ns);
+static void update_handler_poll_times(AioContext *ctx, int64_t block_ns,
+ int64_t dispatch_time);
+static void adjust_polling_time(AioContext *ctx, int64_t block_ns);
bool aio_poll_disabled(AioContext *ctx)
{
@@ -359,7 +361,7 @@ static bool aio_dispatch_handler(AioContext *ctx, AioHandler *node)
static bool aio_dispatch_ready_handlers(AioContext *ctx,
AioHandlerList *ready_list,
- int64_t block_ns)
+ int64_t dispatch_time)
{
bool progress = false;
AioHandler *node;
@@ -369,11 +371,11 @@ static bool aio_dispatch_ready_handlers(AioContext *ctx,
progress = aio_dispatch_handler(ctx, node) || progress;
/*
- * Adjust polling time only after aio_dispatch_handler(), which can
- * add the handler to ctx->poll_aio_handlers.
+ * Update last_dispatch_timestamp to mark this as an active
+ * handler for polling time adjustment and prevent idle removal.
*/
if (ctx->poll_max_ns && QLIST_IS_INSERTED(node, node_poll)) {
- adjust_polling_time(ctx, &node->poll, block_ns);
+ node->last_dispatch_timestamp = dispatch_time;
}
}
@@ -394,7 +396,7 @@ void aio_dispatch(AioContext *ctx)
ctx->fdmon_ops->dispatch(ctx);
}
- /* block_ns is 0 because polling is disabled in the glib event loop */
+ /* Set now to 0 as polling is disabled in the glib event loop */
aio_dispatch_ready_handlers(ctx, &ready_list, 0);
aio_free_deleted_handlers(ctx);
@@ -415,9 +417,6 @@ static bool run_poll_handlers_once(AioContext *ctx,
QLIST_FOREACH_SAFE(node, &ctx->poll_aio_handlers, node_poll, tmp) {
if (node->io_poll(node->opaque)) {
aio_add_poll_ready_handler(ready_list, node);
-
- node->poll_idle_timeout = now + POLL_IDLE_INTERVAL_NS;
-
/*
* Polling was successful, exit try_poll_mode immediately
* to adjust the next polling time.
@@ -458,11 +457,10 @@ static bool remove_idle_poll_handlers(AioContext *ctx,
}
QLIST_FOREACH_SAFE(node, &ctx->poll_aio_handlers, node_poll, tmp) {
- if (node->poll_idle_timeout == 0LL) {
- node->poll_idle_timeout = now + POLL_IDLE_INTERVAL_NS;
- } else if (now >= node->poll_idle_timeout) {
+ if (node->poll_ready == false &&
+ now >= node->last_dispatch_timestamp + POLL_IDLE_INTERVAL_NS) {
trace_poll_remove(ctx, node, node->pfd.fd);
- node->poll_idle_timeout = 0LL;
+ node->last_dispatch_timestamp = 0LL;
QLIST_SAFE_REMOVE(node, node_poll);
if (ctx->poll_started && node->io_poll_end) {
node->io_poll_end(node->opaque);
@@ -560,18 +558,13 @@ static bool run_poll_handlers(AioContext *ctx, AioHandlerList *ready_list,
static bool try_poll_mode(AioContext *ctx, AioHandlerList *ready_list,
int64_t *timeout)
{
- AioHandler *node;
int64_t max_ns;
if (QLIST_EMPTY_RCU(&ctx->poll_aio_handlers)) {
return false;
}
- max_ns = 0;
- QLIST_FOREACH(node, &ctx->poll_aio_handlers, node_poll) {
- max_ns = MAX(max_ns, node->poll.ns);
- }
- max_ns = qemu_soonest_timeout(*timeout, max_ns);
+ max_ns = qemu_soonest_timeout(*timeout, ctx->poll_ns);
if (max_ns && !ctx->fdmon_ops->need_wait(ctx)) {
/*
@@ -587,43 +580,85 @@ static bool try_poll_mode(AioContext *ctx, AioHandlerList *ready_list,
return false;
}
-static void adjust_polling_time(AioContext *ctx, AioPolledEvent *poll,
- int64_t block_ns)
+static void adjust_polling_time(AioContext *ctx, int64_t block_ns)
{
- if (block_ns <= poll->ns) {
- /* This is the sweet spot, no adjustment needed */
- } else if (block_ns > ctx->poll_max_ns) {
- /* We'd have to poll for too long, poll less */
- int64_t old = poll->ns;
-
- if (ctx->poll_shrink) {
- poll->ns /= ctx->poll_shrink;
- } else {
- poll->ns = 0;
+ if (block_ns < ctx->poll_ns) {
+ int64_t old = ctx->poll_ns;
+ int64_t shrink = ctx->poll_shrink;
+
+ if (shrink == 0) {
+ shrink = 2;
+ }
+
+ if (block_ns < (ctx->poll_ns / shrink)) {
+ ctx->poll_ns /= shrink;
}
- trace_poll_shrink(ctx, old, poll->ns);
- } else if (poll->ns < ctx->poll_max_ns &&
- block_ns < ctx->poll_max_ns) {
+ trace_poll_shrink(ctx, old, ctx->poll_ns);
+ } else if (block_ns > ctx->poll_ns) {
/* There is room to grow, poll longer */
- int64_t old = poll->ns;
+ int64_t old = ctx->poll_ns;
int64_t grow = ctx->poll_grow;
if (grow == 0) {
grow = 2;
}
- if (poll->ns) {
- poll->ns *= grow;
+ if (block_ns > ctx->poll_ns * grow) {
+ ctx->poll_ns = block_ns;
} else {
- poll->ns = 4000; /* start polling at 4 microseconds */
+ ctx->poll_ns *= grow;
}
- if (poll->ns > ctx->poll_max_ns) {
- poll->ns = ctx->poll_max_ns;
+ if (ctx->poll_ns > ctx->poll_max_ns) {
+ ctx->poll_ns = ctx->poll_max_ns;
}
- trace_poll_grow(ctx, old, poll->ns);
+ trace_poll_grow(ctx, old, ctx->poll_ns);
+ }
+}
+
+static void update_handler_poll_times(AioContext *ctx, int64_t block_ns,
+ int64_t dispatch_time)
+{
+ AioHandler *node;
+ int64_t max_poll_ns = -1;
+
+ QLIST_FOREACH(node, &ctx->poll_aio_handlers, node_poll) {
+ if (node->last_dispatch_timestamp == dispatch_time) {
+ /*
+ * Active handler: had an event in this aio_poll() call.
+ * Update poll.ns using a weighted average of the current
+ * block_ns and previous poll.ns to smooth adjustments.
+ */
+ node->poll.ns = node->poll.ns
+ ? (node->poll.ns - (node->poll.ns >> POLL_WEIGHT_SHIFT))
+ + (block_ns >> POLL_WEIGHT_SHIFT) : block_ns;
+
+ if (node->poll.ns > ctx->poll_max_ns) {
+ node->poll.ns = 0;
+ }
+ /*
+ * Track the maximum poll.ns among active handlers to
+ * calculate the next polling time.
+ */
+ max_poll_ns = MAX(max_poll_ns, node->poll.ns);
+ } else {
+ /*
+ * Inactive handler: no event in this aio_poll() call but
+ * was active before. Increase poll.ns by block_ns. If it
+ * exceeds poll_max_ns, reset to 0 until next event.
+ */
+ if (node->poll.ns != 0) {
+ node->poll.ns += block_ns;
+ if (node->poll.ns > ctx->poll_max_ns) {
+ node->poll.ns = 0;
+ }
+ }
+ }
+ }
+ if (max_poll_ns >= 0) {
+ adjust_polling_time(ctx, max_poll_ns);
}
}
@@ -635,6 +670,7 @@ bool aio_poll(AioContext *ctx, bool blocking)
int64_t timeout;
int64_t start = 0;
int64_t block_ns = 0;
+ int64_t dispatch_ns = 0;
/*
* There cannot be two concurrent aio_poll calls for the same AioContext (or
@@ -711,7 +747,8 @@ bool aio_poll(AioContext *ctx, bool blocking)
/* Calculate blocked time for adaptive polling */
if (ctx->poll_max_ns) {
- block_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - start;
+ dispatch_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
+ block_ns = dispatch_ns - start;
}
if (ctx->fdmon_ops->dispatch) {
@@ -719,10 +756,14 @@ bool aio_poll(AioContext *ctx, bool blocking)
}
progress |= aio_bh_poll(ctx);
- progress |= aio_dispatch_ready_handlers(ctx, &ready_list, block_ns);
+ progress |= aio_dispatch_ready_handlers(ctx, &ready_list, dispatch_ns);
aio_free_deleted_handlers(ctx);
+ if (ctx->poll_max_ns) {
+ update_handler_poll_times(ctx, block_ns, dispatch_ns);
+ }
+
qemu_lockcnt_dec(&ctx->list_lock);
progress |= timerlistgroup_run_timers(&ctx->tlg);
@@ -794,6 +835,7 @@ void aio_context_set_poll_params(AioContext *ctx, int64_t max_ns,
ctx->poll_max_ns = max_ns;
ctx->poll_grow = grow;
ctx->poll_shrink = shrink;
+ ctx->poll_ns = 0;
aio_notify(ctx);
}
diff --git a/util/aio-posix.h b/util/aio-posix.h
index ab894a3c0f..cd459bbbae 100644
--- a/util/aio-posix.h
+++ b/util/aio-posix.h
@@ -38,7 +38,7 @@ struct AioHandler {
unsigned flags; /* see fdmon-io_uring.c */
CqeHandler internal_cqe_handler; /* used for POLL_ADD/POLL_REMOVE */
#endif
- int64_t poll_idle_timeout; /* when to stop userspace polling */
+ int64_t last_dispatch_timestamp; /* when last handler was dispatched */
bool poll_ready; /* has polling detected an event? */
AioPolledEvent poll;
};
diff --git a/util/async.c b/util/async.c
index 80d6b01a8a..9d3627566f 100644
--- a/util/async.c
+++ b/util/async.c
@@ -606,6 +606,7 @@ AioContext *aio_context_new(Error **errp)
timerlistgroup_init(&ctx->tlg, aio_timerlist_notify, ctx);
ctx->poll_max_ns = 0;
+ ctx->poll_ns = 0;
ctx->poll_grow = 0;
ctx->poll_shrink = 0;
--
2.43.0
^ permalink raw reply related [flat|nested] 6+ messages in thread* [PATCH v3 3/3] qapi/iothread: introduce poll-weight parameter for aio-poll
2026-04-05 20:07 [PATCH v3 0/3] improve aio-polling efficiency Jaehoon Kim
2026-04-05 20:07 ` [PATCH v3 1/3] aio-poll: avoid unnecessary polling time computation Jaehoon Kim
2026-04-05 20:07 ` [PATCH v3 2/3] aio-poll: refine iothread polling using weighted handler intervals Jaehoon Kim
@ 2026-04-05 20:07 ` Jaehoon Kim
2026-04-16 14:54 ` Markus Armbruster
2 siblings, 1 reply; 6+ messages in thread
From: Jaehoon Kim @ 2026-04-05 20:07 UTC (permalink / raw)
To: qemu-devel, qemu-block
Cc: pbonzini, stefanha, fam, armbru, eblake, berrange, eduardo, dave,
sw, mjrosato, farman, Jaehoon Kim
Introduce a configurable poll-weight parameter for adaptive polling
in IOThread. This parameter replaces the hardcoded POLL_WEIGHT_SHIFT
constant, allowing runtime control over how much the most recent
event interval affects the next polling duration calculation.
The poll-weight parameter uses a shift value where larger values
decrease the weight of the current interval, enabling more gradual
adjustments. When set to 0, a default value of 3 is used (meaning
the current interval contributes approximately 1/8 to the weighted
average).
This patch also removes the hardcoded default values for poll-grow
and poll-shrink parameters from the grow_polling_time() and
shrink_polling_time() functions, as these defaults are now properly
initialized in iothread.c during IOThread creation.
Signed-off-by: Jaehoon Kim <jhkim@linux.ibm.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
---
include/qemu/aio.h | 4 ++-
include/system/iothread.h | 18 ++++++++++++
iothread.c | 47 ++++++++++++++++++++++---------
monitor/hmp-cmds.c | 1 +
qapi/misc.json | 7 +++++
qapi/qom.json | 10 ++++++-
qemu-options.hx | 7 ++++-
tests/unit/test-nested-aio-poll.c | 2 +-
util/aio-posix.c | 37 +++++++++---------------
util/aio-win32.c | 3 +-
util/async.c | 1 +
11 files changed, 95 insertions(+), 42 deletions(-)
diff --git a/include/qemu/aio.h b/include/qemu/aio.h
index 6c22064a28..e65e90093a 100644
--- a/include/qemu/aio.h
+++ b/include/qemu/aio.h
@@ -310,6 +310,7 @@ struct AioContext {
int64_t poll_max_ns; /* maximum polling time in nanoseconds */
int64_t poll_grow; /* polling time growth factor */
int64_t poll_shrink; /* polling time shrink factor */
+ int64_t poll_weight; /* weight of current interval in calculation */
/* AIO engine parameters */
int64_t aio_max_batch; /* maximum number of requests in a batch */
@@ -791,12 +792,13 @@ void aio_context_destroy(AioContext *ctx);
* @max_ns: how long to busy poll for, in nanoseconds
* @grow: polling time growth factor
* @shrink: polling time shrink factor
+ * @weight: weight factor applied to the current polling interval
*
* Poll mode can be disabled by setting poll_max_ns to 0.
*/
void aio_context_set_poll_params(AioContext *ctx, int64_t max_ns,
int64_t grow, int64_t shrink,
- Error **errp);
+ int64_t weight, Error **errp);
/**
* aio_context_set_aio_params:
diff --git a/include/system/iothread.h b/include/system/iothread.h
index e26d13c6c7..a1ef7696cb 100644
--- a/include/system/iothread.h
+++ b/include/system/iothread.h
@@ -21,6 +21,23 @@
#define TYPE_IOTHREAD "iothread"
+#ifdef CONFIG_POSIX
+/*
+ * Benchmark results from 2016 on NVMe SSD drives show max polling times around
+ * 16-32 microseconds yield IOPS improvements for both iodepth=1 and iodepth=32
+ * workloads.
+ */
+#define IOTHREAD_POLL_MAX_NS_DEFAULT 32768ULL
+#define IOTHREAD_POLL_GROW_DEFAULT 2ULL
+#define IOTHREAD_POLL_SHRINK_DEFAULT 2ULL
+#define IOTHREAD_POLL_WEIGHT_DEFAULT 3ULL
+#else
+#define IOTHREAD_POLL_MAX_NS_DEFAULT 0ULL
+#define IOTHREAD_POLL_GROW_DEFAULT 0ULL
+#define IOTHREAD_POLL_SHRINK_DEFAULT 0ULL
+#define IOTHREAD_POLL_WEIGHT_DEFAULT 0ULL
+#endif
+
struct IOThread {
EventLoopBase parent_obj;
@@ -38,6 +55,7 @@ struct IOThread {
int64_t poll_max_ns;
int64_t poll_grow;
int64_t poll_shrink;
+ int64_t poll_weight;
};
typedef struct IOThread IOThread;
diff --git a/iothread.c b/iothread.c
index caf68e0764..3558535b40 100644
--- a/iothread.c
+++ b/iothread.c
@@ -25,17 +25,6 @@
#include "qemu/rcu.h"
#include "qemu/main-loop.h"
-
-#ifdef CONFIG_POSIX
-/* Benchmark results from 2016 on NVMe SSD drives show max polling times around
- * 16-32 microseconds yield IOPS improvements for both iodepth=1 and iodepth=32
- * workloads.
- */
-#define IOTHREAD_POLL_MAX_NS_DEFAULT 32768ULL
-#else
-#define IOTHREAD_POLL_MAX_NS_DEFAULT 0ULL
-#endif
-
static void *iothread_run(void *opaque)
{
IOThread *iothread = opaque;
@@ -103,6 +92,10 @@ static void iothread_instance_init(Object *obj)
IOThread *iothread = IOTHREAD(obj);
iothread->poll_max_ns = IOTHREAD_POLL_MAX_NS_DEFAULT;
+ iothread->poll_grow = IOTHREAD_POLL_GROW_DEFAULT;
+ iothread->poll_shrink = IOTHREAD_POLL_SHRINK_DEFAULT;
+ iothread->poll_weight = IOTHREAD_POLL_WEIGHT_DEFAULT;
+
iothread->thread_id = -1;
qemu_sem_init(&iothread->init_done_sem, 0);
/* By default, we don't run gcontext */
@@ -164,6 +157,7 @@ static void iothread_set_aio_context_params(EventLoopBase *base, Error **errp)
iothread->poll_max_ns,
iothread->poll_grow,
iothread->poll_shrink,
+ iothread->poll_weight,
errp);
if (*errp) {
return;
@@ -233,6 +227,9 @@ static IOThreadParamInfo poll_grow_info = {
static IOThreadParamInfo poll_shrink_info = {
"poll-shrink", offsetof(IOThread, poll_shrink),
};
+static IOThreadParamInfo poll_weight_info = {
+ "poll-weight", offsetof(IOThread, poll_weight),
+};
static void iothread_get_param(Object *obj, Visitor *v,
const char *name, IOThreadParamInfo *info, Error **errp)
@@ -254,13 +251,31 @@ static bool iothread_set_param(Object *obj, Visitor *v,
return false;
}
- if (value < 0) {
+ if (info->offset == offsetof(IOThread, poll_weight)) {
+ if (value < 0 || value > 63) {
+ error_setg(errp, "%s value must be in range [0, 63]",
+ info->name);
+ return false;
+ }
+ } else if (value < 0) {
error_setg(errp, "%s value must be in range [0, %" PRId64 "]",
info->name, INT64_MAX);
return false;
}
- *field = value;
+ if (value == 0) {
+ if (info->offset == offsetof(IOThread, poll_grow)) {
+ *field = IOTHREAD_POLL_GROW_DEFAULT;
+ } else if (info->offset == offsetof(IOThread, poll_shrink)) {
+ *field = IOTHREAD_POLL_SHRINK_DEFAULT;
+ } else if (info->offset == offsetof(IOThread, poll_weight)) {
+ *field = IOTHREAD_POLL_WEIGHT_DEFAULT;
+ } else {
+ *field = value;
+ }
+ } else {
+ *field = value;
+ }
return true;
}
@@ -288,6 +303,7 @@ static void iothread_set_poll_param(Object *obj, Visitor *v,
iothread->poll_max_ns,
iothread->poll_grow,
iothread->poll_shrink,
+ iothread->poll_weight,
errp);
}
}
@@ -311,6 +327,10 @@ static void iothread_class_init(ObjectClass *klass, const void *class_data)
iothread_get_poll_param,
iothread_set_poll_param,
NULL, &poll_shrink_info);
+ object_class_property_add(klass, "poll-weight", "int",
+ iothread_get_poll_param,
+ iothread_set_poll_param,
+ NULL, &poll_weight_info);
}
static const TypeInfo iothread_info = {
@@ -356,6 +376,7 @@ static int query_one_iothread(Object *object, void *opaque)
info->poll_max_ns = iothread->poll_max_ns;
info->poll_grow = iothread->poll_grow;
info->poll_shrink = iothread->poll_shrink;
+ info->poll_weight = iothread->poll_weight;
info->aio_max_batch = iothread->parent_obj.aio_max_batch;
QAPI_LIST_APPEND(*tail, info);
diff --git a/monitor/hmp-cmds.c b/monitor/hmp-cmds.c
index bad034937a..75b6e7fa65 100644
--- a/monitor/hmp-cmds.c
+++ b/monitor/hmp-cmds.c
@@ -206,6 +206,7 @@ void hmp_info_iothreads(Monitor *mon, const QDict *qdict)
monitor_printf(mon, " poll-max-ns=%" PRId64 "\n", value->poll_max_ns);
monitor_printf(mon, " poll-grow=%" PRId64 "\n", value->poll_grow);
monitor_printf(mon, " poll-shrink=%" PRId64 "\n", value->poll_shrink);
+ monitor_printf(mon, " poll-weight=%" PRId64 "\n", value->poll_weight);
monitor_printf(mon, " aio-max-batch=%" PRId64 "\n",
value->aio_max_batch);
}
diff --git a/qapi/misc.json b/qapi/misc.json
index 28c641fe2f..554b0c5717 100644
--- a/qapi/misc.json
+++ b/qapi/misc.json
@@ -85,6 +85,12 @@
# @poll-shrink: how many ns will be removed from polling time, 0 means
# that it's not configured (since 2.9)
#
+# @poll-weight: the weight factor for adaptive polling.
+# Determines how much the current event interval contributes to
+# the next polling time calculation. Valid values are 1 or
+# greater. 0 selects the system default value which is currently
+# 3 (since 11.1)
+#
# @aio-max-batch: maximum number of requests in a batch for the AIO
# engine, 0 means that the engine will use its default (since 6.1)
#
@@ -96,6 +102,7 @@
'poll-max-ns': 'int',
'poll-grow': 'int',
'poll-shrink': 'int',
+ 'poll-weight': 'int',
'aio-max-batch': 'int' } }
##
diff --git a/qapi/qom.json b/qapi/qom.json
index c653248f85..dd45ac1087 100644
--- a/qapi/qom.json
+++ b/qapi/qom.json
@@ -606,6 +606,13 @@
# algorithm detects it is spending too long polling without
# encountering events. 0 selects a default behaviour (default: 0)
#
+# @poll-weight: the weight factor for adaptive polling. Determines
+# how much the most recent event interval affects the next
+# polling duration calculation. If set to 0, the system default
+# value of 3 is used. Typical values: 1 (high weight on recent
+# interval), 2-4 (moderate weight on recent interval).
+# (default: 0) (since 11.1)
+#
# The @aio-max-batch option is available since 6.1.
#
# Since: 2.0
@@ -614,7 +621,8 @@
'base': 'EventLoopBaseProperties',
'data': { '*poll-max-ns': 'int',
'*poll-grow': 'int',
- '*poll-shrink': 'int' } }
+ '*poll-shrink': 'int',
+ '*poll-weight': 'int' } }
##
# @MainLoopProperties:
diff --git a/qemu-options.hx b/qemu-options.hx
index 69e5a874c1..8ddf6c8d36 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -6413,7 +6413,7 @@ SRST
CN=laptop.example.com,O=Example Home,L=London,ST=London,C=GB
- ``-object iothread,id=id,poll-max-ns=poll-max-ns,poll-grow=poll-grow,poll-shrink=poll-shrink,aio-max-batch=aio-max-batch``
+ ``-object iothread,id=id,poll-max-ns=poll-max-ns,poll-grow=poll-grow,poll-shrink=poll-shrink,poll-weight=poll-weight,aio-max-batch=aio-max-batch``
Creates a dedicated event loop thread that devices can be
assigned to. This is known as an IOThread. By default device
emulation happens in vCPU threads or the main event loop thread.
@@ -6449,6 +6449,11 @@ SRST
the polling time when the algorithm detects it is spending too
long polling without encountering events.
+ The ``poll-weight`` parameter is the weight factor used in the
+ adaptive polling algorithm. It determines how much the most
+ recent event interval affects the calculation of the next
+ polling duration.
+
The ``aio-max-batch`` parameter is the maximum number of requests
in a batch for the AIO engine, 0 means that the engine will use
its default.
diff --git a/tests/unit/test-nested-aio-poll.c b/tests/unit/test-nested-aio-poll.c
index 9ab1ad08a7..4c38f36fd4 100644
--- a/tests/unit/test-nested-aio-poll.c
+++ b/tests/unit/test-nested-aio-poll.c
@@ -81,7 +81,7 @@ static void test(void)
qemu_set_current_aio_context(td.ctx);
/* Enable polling */
- aio_context_set_poll_params(td.ctx, 1000000, 2, 2, &error_abort);
+ aio_context_set_poll_params(td.ctx, 1000000, 2, 2, 3, &error_abort);
/* Make the event notifier active (set) right away */
event_notifier_init(&td.poll_notifier, 1);
diff --git a/util/aio-posix.c b/util/aio-posix.c
index 8e9e9e5d8f..df1c213ce5 100644
--- a/util/aio-posix.c
+++ b/util/aio-posix.c
@@ -29,7 +29,6 @@
/* Stop userspace polling on a handler if it isn't active for some time */
#define POLL_IDLE_INTERVAL_NS (7 * NANOSECONDS_PER_SECOND)
-#define POLL_WEIGHT_SHIFT (3)
static void update_handler_poll_times(AioContext *ctx, int64_t block_ns,
int64_t dispatch_time);
@@ -582,28 +581,11 @@ static bool try_poll_mode(AioContext *ctx, AioHandlerList *ready_list,
static void adjust_polling_time(AioContext *ctx, int64_t block_ns)
{
- if (block_ns < ctx->poll_ns) {
- int64_t old = ctx->poll_ns;
- int64_t shrink = ctx->poll_shrink;
-
- if (shrink == 0) {
- shrink = 2;
- }
-
- if (block_ns < (ctx->poll_ns / shrink)) {
- ctx->poll_ns /= shrink;
- }
-
- trace_poll_shrink(ctx, old, ctx->poll_ns);
- } else if (block_ns > ctx->poll_ns) {
+ if (block_ns > ctx->poll_ns) {
/* There is room to grow, poll longer */
int64_t old = ctx->poll_ns;
int64_t grow = ctx->poll_grow;
- if (grow == 0) {
- grow = 2;
- }
-
if (block_ns > ctx->poll_ns * grow) {
ctx->poll_ns = block_ns;
} else {
@@ -615,6 +597,11 @@ static void adjust_polling_time(AioContext *ctx, int64_t block_ns)
}
trace_poll_grow(ctx, old, ctx->poll_ns);
+ } else if (block_ns < (ctx->poll_ns / ctx->poll_shrink)) {
+ int64_t old = ctx->poll_ns;
+ ctx->poll_ns /= ctx->poll_shrink;
+
+ trace_poll_shrink(ctx, old, ctx->poll_ns);
}
}
@@ -632,8 +619,8 @@ static void update_handler_poll_times(AioContext *ctx, int64_t block_ns,
* block_ns and previous poll.ns to smooth adjustments.
*/
node->poll.ns = node->poll.ns
- ? (node->poll.ns - (node->poll.ns >> POLL_WEIGHT_SHIFT))
- + (block_ns >> POLL_WEIGHT_SHIFT) : block_ns;
+ ? (node->poll.ns - (node->poll.ns >> ctx->poll_weight))
+ + (block_ns >> ctx->poll_weight) : block_ns;
if (node->poll.ns > ctx->poll_max_ns) {
node->poll.ns = 0;
@@ -819,7 +806,8 @@ void aio_context_destroy(AioContext *ctx)
}
void aio_context_set_poll_params(AioContext *ctx, int64_t max_ns,
- int64_t grow, int64_t shrink, Error **errp)
+ int64_t grow, int64_t shrink,
+ int64_t weight, Error **errp)
{
AioHandler *node;
@@ -833,8 +821,9 @@ void aio_context_set_poll_params(AioContext *ctx, int64_t max_ns,
* is used once.
*/
ctx->poll_max_ns = max_ns;
- ctx->poll_grow = grow;
- ctx->poll_shrink = shrink;
+ ctx->poll_grow = (grow ? grow : IOTHREAD_POLL_GROW_DEFAULT);
+ ctx->poll_shrink = (shrink ? shrink : IOTHREAD_POLL_SHRINK_DEFAULT);
+ ctx->poll_weight = (weight ? weight : IOTHREAD_POLL_WEIGHT_DEFAULT);
ctx->poll_ns = 0;
aio_notify(ctx);
diff --git a/util/aio-win32.c b/util/aio-win32.c
index 6e6f699e4b..1985843233 100644
--- a/util/aio-win32.c
+++ b/util/aio-win32.c
@@ -429,7 +429,8 @@ void aio_context_destroy(AioContext *ctx)
}
void aio_context_set_poll_params(AioContext *ctx, int64_t max_ns,
- int64_t grow, int64_t shrink, Error **errp)
+ int64_t grow, int64_t shrink,
+ int64_t weight, Error **errp)
{
if (max_ns) {
error_setg(errp, "AioContext polling is not implemented on Windows");
diff --git a/util/async.c b/util/async.c
index 9d3627566f..741fcfd6a7 100644
--- a/util/async.c
+++ b/util/async.c
@@ -609,6 +609,7 @@ AioContext *aio_context_new(Error **errp)
ctx->poll_ns = 0;
ctx->poll_grow = 0;
ctx->poll_shrink = 0;
+ ctx->poll_weight = 0;
ctx->aio_max_batch = 0;
--
2.43.0
^ permalink raw reply related [flat|nested] 6+ messages in thread