[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH v5 20/24] replay: simple auto-snapshot mode for record
From: |
Nicholas Piggin |
Subject: |
[PATCH v5 20/24] replay: simple auto-snapshot mode for record |
Date: |
Tue, 19 Mar 2024 01:46:17 +1000 |
record makes an initial snapshot when the machine is created, to enable
reverse-debugging. Often the issue being debugged appears near the end of
the trace, so it is important for performance to keep snapshots close to
the end.
This implements a periodic snapshot mode that keeps a rolling set of
recent snapshots. This could be done by the debugger or other program
that talks QMP, but for setting up simple scenarios and tests, this is
more convenient.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
docs/system/replay.rst | 5 ++++
include/sysemu/replay.h | 11 ++++++++
replay/replay-snapshot.c | 57 ++++++++++++++++++++++++++++++++++++++++
replay/replay.c | 27 +++++++++++++++++--
system/vl.c | 9 +++++++
qemu-options.hx | 9 +++++--
6 files changed, 114 insertions(+), 4 deletions(-)
diff --git a/docs/system/replay.rst b/docs/system/replay.rst
index ca7c17c63d..1ae8614475 100644
--- a/docs/system/replay.rst
+++ b/docs/system/replay.rst
@@ -156,6 +156,11 @@ for storing VM snapshots. Here is the example of the
command line for this:
``empty.qcow2`` drive does not connected to any virtual block device and used
for VM snapshots only.
+``rrsnapmode`` can be used to select just an initial snapshot or periodic
+snapshots, with ``rrsnapcount`` specifying the number of periodic snapshots
+to maintain, and ``rrsnaptime`` the amount of run time in seconds between
+periodic snapshots.
+
.. _network-label:
Network devices
diff --git a/include/sysemu/replay.h b/include/sysemu/replay.h
index 8102fa54f0..92fa82842b 100644
--- a/include/sysemu/replay.h
+++ b/include/sysemu/replay.h
@@ -48,6 +48,17 @@ typedef enum ReplayCheckpoint ReplayCheckpoint;
typedef struct ReplayNetState ReplayNetState;
+enum ReplaySnapshotMode {
+ REPLAY_SNAPSHOT_MODE_INITIAL,
+ REPLAY_SNAPSHOT_MODE_PERIODIC,
+};
+typedef enum ReplaySnapshotMode ReplaySnapshotMode;
+
+extern ReplaySnapshotMode replay_snapshot_mode;
+
+extern uint64_t replay_snapshot_periodic_delay;
+extern int replay_snapshot_periodic_nr_keep;
+
/* Name of the initial VM snapshot */
extern char *replay_snapshot;
diff --git a/replay/replay-snapshot.c b/replay/replay-snapshot.c
index ccb4d89dda..762555feaa 100644
--- a/replay/replay-snapshot.c
+++ b/replay/replay-snapshot.c
@@ -70,6 +70,53 @@ void replay_vmstate_register(void)
vmstate_register(NULL, 0, &vmstate_replay, &replay_state);
}
+static QEMUTimer *replay_snapshot_timer;
+static int replay_snapshot_count;
+
+static void replay_snapshot_timer_cb(void *opaque)
+{
+ Error *err = NULL;
+ char *name;
+
+ if (!replay_can_snapshot()) {
+ /* Try again soon */
+ timer_mod(replay_snapshot_timer,
+ qemu_clock_get_ms(QEMU_CLOCK_REALTIME) +
+ replay_snapshot_periodic_delay / 10);
+ return;
+ }
+
+ name = g_strdup_printf("%s-%d", replay_snapshot, replay_snapshot_count);
+ if (!save_snapshot(name,
+ true, NULL, false, NULL, &err)) {
+ error_report_err(err);
+ error_report("Could not create periodic snapshot "
+ "for icount record, disabling");
+ g_free(name);
+ return;
+ }
+ g_free(name);
+ replay_snapshot_count++;
+
+ if (replay_snapshot_periodic_nr_keep >= 1 &&
+ replay_snapshot_count > replay_snapshot_periodic_nr_keep) {
+ int del_nr;
+
+ del_nr = replay_snapshot_count - replay_snapshot_periodic_nr_keep - 1;
+ name = g_strdup_printf("%s-%d", replay_snapshot, del_nr);
+ if (!delete_snapshot(name, false, NULL, &err)) {
+ error_report_err(err);
+ error_report("Could not delete periodic snapshot "
+ "for icount record");
+ }
+ g_free(name);
+ }
+
+ timer_mod(replay_snapshot_timer,
+ qemu_clock_get_ms(QEMU_CLOCK_REALTIME) +
+ replay_snapshot_periodic_delay);
+}
+
void replay_vmstate_init(void)
{
Error *err = NULL;
@@ -82,6 +129,16 @@ void replay_vmstate_init(void)
error_report("Could not create snapshot for icount record");
exit(1);
}
+
+ if (replay_snapshot_mode == REPLAY_SNAPSHOT_MODE_PERIODIC) {
+ replay_snapshot_timer = timer_new_ms(QEMU_CLOCK_REALTIME,
+ replay_snapshot_timer_cb,
+ NULL);
+ timer_mod(replay_snapshot_timer,
+ qemu_clock_get_ms(QEMU_CLOCK_REALTIME) +
+ replay_snapshot_periodic_delay);
+ }
+
} else if (replay_mode == REPLAY_MODE_PLAY) {
if (!load_snapshot(replay_snapshot, NULL, false, NULL, &err)) {
error_report_err(err);
diff --git a/replay/replay.c b/replay/replay.c
index 895fa6b67a..c916e71d30 100644
--- a/replay/replay.c
+++ b/replay/replay.c
@@ -29,6 +29,10 @@
ReplayMode replay_mode = REPLAY_MODE_NONE;
char *replay_snapshot;
+ReplaySnapshotMode replay_snapshot_mode;
+uint64_t replay_snapshot_periodic_delay;
+int replay_snapshot_periodic_nr_keep;
+
/* Name of replay file */
static char *replay_filename;
ReplayState replay_state;
@@ -424,6 +428,27 @@ void replay_configure(QemuOpts *opts)
}
replay_snapshot = g_strdup(qemu_opt_get(opts, "rrsnapshot"));
+ if (replay_snapshot && mode == REPLAY_MODE_RECORD) {
+ const char *snapmode;
+
+ snapmode = qemu_opt_get(opts, "rrsnapmode");
+ if (!snapmode || !strcmp(snapmode, "initial")) {
+ replay_snapshot_mode = REPLAY_SNAPSHOT_MODE_INITIAL;
+ } else if (!strcmp(snapmode, "periodic")) {
+ replay_snapshot_mode = REPLAY_SNAPSHOT_MODE_PERIODIC;
+ } else {
+ error_report("Invalid rrsnapmode option: %s", snapmode);
+ exit(1);
+ }
+
+ /* Default 10 host seconds of machine runtime per snapshot. */
+ replay_snapshot_periodic_delay =
+ qemu_opt_get_number(opts, "rrsnaptime", 10) * 1000;
+
+ /* Default 2, to cover at least the last 10 host seconds of runtime. */
+ replay_snapshot_periodic_nr_keep =
+ qemu_opt_get_number(opts, "rrsnapcount", 2);
+ }
replay_vmstate_register();
replay_enable(fname, mode);
@@ -446,8 +471,6 @@ void replay_start(void)
exit(1);
}
- /* Timer for snapshotting will be set up here. */
-
replay_enable_events();
}
diff --git a/system/vl.c b/system/vl.c
index 70f4cece7f..8070cee6da 100644
--- a/system/vl.c
+++ b/system/vl.c
@@ -447,6 +447,15 @@ static QemuOptsList qemu_icount_opts = {
}, {
.name = "rrsnapshot",
.type = QEMU_OPT_STRING,
+ }, {
+ .name = "rrsnapmode",
+ .type = QEMU_OPT_STRING,
+ }, {
+ .name = "rrsnaptime",
+ .type = QEMU_OPT_NUMBER,
+ }, {
+ .name = "rrsnapcount",
+ .type = QEMU_OPT_NUMBER,
},
{ /* end of list */ }
},
diff --git a/qemu-options.hx b/qemu-options.hx
index 7fd1713fa8..51f2498f12 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -4665,13 +4665,13 @@ SRST
ERST
DEF("icount", HAS_ARG, QEMU_OPTION_icount, \
- "-icount
[shift=N|auto][,align=on|off][,sleep=on|off][,rr=record|replay,rrfile=<filename>[,rrsnapshot=<snapshot>]]\n"
\
+ "-icount
[shift=N|auto][,align=on|off][,sleep=on|off][,rr=record|replay,rrfile=<filename>[,rrsnapshot=<snapshot>][,rrsnapmode=initial|periodic][,rrsnaptime=secs][,rrsnapcount=N]\n"
\
" enable virtual instruction counter with 2^N clock ticks
per\n" \
" instruction, enable aligning the host and virtual
clocks\n" \
" or disable real time cpu sleeping, and optionally
enable\n" \
" record-and-replay mode\n", QEMU_ARCH_ALL)
SRST
-``-icount
[shift=N|auto][,align=on|off][,sleep=on|off][,rr=record|replay,rrfile=filename[,rrsnapshot=snapshot]]``
+``-icount
[shift=N|auto][,align=on|off][,sleep=on|off][,rr=record|replay,rrfile=filename[,rrsnapshot=snapshot][,rrsnapmode=initial|periodic][,rrsnaptime=secs][,rrsnapcount=N]]``
Enable virtual instruction counter. The virtual cpu will execute one
instruction every 2^N ns of virtual time. If ``auto`` is specified
then the virtual cpu speed will be automatically adjusted to keep
@@ -4713,6 +4713,11 @@ SRST
name. In record mode, a new VM snapshot with the given name is created
at the start of execution recording. In replay mode this option
specifies the snapshot name used to load the initial VM state.
+ ``rrsnapmode=periodic`` will additionally cause a periodic snapshot to
+ be created after ``rrsnaptime=secs`` seconds of real runtime. The last
+ ``rrsnapcount=N`` periodic snapshots (not including the initial) will
+ be kept (0 for infinite). Periodic snapshots are useful to speed
+ reverse debugging operations near the end of the recorded trace.
ERST
DEF("watchdog-action", HAS_ARG, QEMU_OPTION_watchdog_action, \
--
2.42.0
- [PATCH v5 09/24] replay: Fix migration replay_mutex locking, (continued)
- [PATCH v5 09/24] replay: Fix migration replay_mutex locking, Nicholas Piggin, 2024/03/18
- [PATCH v5 11/24] virtio-net: Use virtual time for RSC timers, Nicholas Piggin, 2024/03/18
- [PATCH v5 12/24] savevm: Fix load_snapshot error path crash, Nicholas Piggin, 2024/03/18
- [PATCH v5 13/24] tests/avocado: replay_linux.py remove the timeout expected guards, Nicholas Piggin, 2024/03/18
- [PATCH v5 15/24] tests/avocado: reverse_debugging.py add test for x86-64 q35 machine, Nicholas Piggin, 2024/03/18
- [PATCH v5 16/24] tests/avocado: reverse_debugging.py verify addresses between record and replay, Nicholas Piggin, 2024/03/18
- [PATCH v5 17/24] tests/avocado: reverse_debugging.py stop VM before sampling icount, Nicholas Piggin, 2024/03/18
- [PATCH v5 14/24] tests/avocado: reverse_debugging.py mark aarch64 and pseries as not flaky, Nicholas Piggin, 2024/03/18
- [PATCH v5 18/24] tests/avocado: reverse_debugging reverse-step at the end of the trace, Nicholas Piggin, 2024/03/18
- [PATCH v5 19/24] tests/avocado: reverse_debugging.py add snapshot testing, Nicholas Piggin, 2024/03/18
- [PATCH v5 20/24] replay: simple auto-snapshot mode for record,
Nicholas Piggin <=
- [PATCH v5 21/24] tests/avocado: reverse_debugging.py test auto-snapshot mode, Nicholas Piggin, 2024/03/18
- [PATCH v5 22/24] target/ppc: fix timebase register reset state, Nicholas Piggin, 2024/03/18
- [PATCH v5 23/24] spapr: Fix vpa dispatch count for record-replay, Nicholas Piggin, 2024/03/18
- [PATCH v5 24/24] tests/avocado: replay_linux.py add ppc64 pseries test, Nicholas Piggin, 2024/03/18