libvirt/src/qemu/qemu_monitor.h

940 lines
39 KiB
C
Raw Normal View History

/*
* qemu_monitor.h: interaction with QEMU monitor console
*
qemu: read backing chain names from qemu https://bugzilla.redhat.com/show_bug.cgi?id=1199182 documents that after a series of disk snapshots into existing destination images, followed by active commits of the top image, it is possible for qemu 2.2 and earlier to end up tracking a different name for the image than what it would have had when opening the chain afresh. That is, when starting with the chain 'a <- b <- c', the name associated with 'b' is how it was spelled in the metadata of 'c', but when starting with 'a', taking two snapshots into 'a <- b <- c', then committing 'c' back into 'b', the name associated with 'b' is now the name used when taking the first snapshot. Sadly, older qemu doesn't know how to treat different spellings of the same filename as identical files (it uses strcmp() instead of checking for the same inode), which means libvirt's attempt to commit an image using solely the names learned from qcow2 metadata fails with a cryptic: error: internal error: unable to execute QEMU command 'block-commit': Top image file /tmp/images/c/../b/b not found even though the file exists. Trying to teach libvirt the rules on which name qemu will expect is not worth the effort (besides, we'd have to remember it across libvirtd restarts, and track whether a file was opened via metadata or via snapshot creation for a given qemu process); it is easier to just always directly ask qemu what string it expects to see in the first place. As a safety valve, we validate that any name returned by qemu still maps to the same local file as we have tracked it, so that a compromised qemu cannot accidentally cause us to act on an incorrect file. * src/qemu/qemu_monitor.h (qemuMonitorDiskNameLookup): New prototype. * src/qemu/qemu_monitor_json.h (qemuMonitorJSONDiskNameLookup): Likewise. * src/qemu/qemu_monitor.c (qemuMonitorDiskNameLookup): New function. * src/qemu/qemu_monitor_json.c (qemuMonitorJSONDiskNameLookup) (qemuMonitorJSONDiskNameLookupOne): Likewise. * src/qemu/qemu_driver.c (qemuDomainBlockCommit) (qemuDomainBlockJobImpl): Use it. Signed-off-by: Eric Blake <eblake@redhat.com>
2015-03-11 20:37:04 +00:00
* Copyright (C) 2006-2015 Red Hat, Inc.
* Copyright (C) 2006 Daniel P. Berrange
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this library. If not, see
* <http://www.gnu.org/licenses/>.
*
* Author: Daniel P. Berrange <berrange@redhat.com>
*/
#ifndef QEMU_MONITOR_H
# define QEMU_MONITOR_H
# include "internal.h"
# include "domain_conf.h"
# include "virbitmap.h"
# include "virhash.h"
2012-12-12 17:53:50 +00:00
# include "virjson.h"
qemu: qemuMonitorQueryRxFilter - retrieve guest netdev rx-filter This function can be called at any time to get the current status of a guest's network device rx-filter. In particular it is useful to call after libvirt recieves a NIC_RX_FILTER_CHANGED event - this event only tells you that something has changed in the rx-filter, the details are retrieved with the query-rx-filter monitor command (only available in the json monitor). The command sent to the qemu monitor looks like this: {"execute":"query-rx-filter", "arguments": {"name":"net2"} }' and the results will look something like this: { "return": [ { "promiscuous": false, "name": "net2", "main-mac": "52:54:00:98:2d:e3", "unicast": "normal", "vlan": "normal", "vlan-table": [ 42, 0 ], "unicast-table": [ ], "multicast": "normal", "multicast-overflow": false, "unicast-overflow": false, "multicast-table": [ "33:33:ff:98:2d:e3", "01:80:c2:00:00:21", "01:00:5e:00:00:fb", "33:33:ff:98:2d:e2", "01:00:5e:00:00:01", "33:33:00:00:00:01" ], "broadcast-allowed": false } ], "id": "libvirt-14" } This is all parsed from JSON into a virNetDevRxFilter object for easier consumption. (unicast-table is usually empty, but is also an array of mac addresses similar to multicast-table). (NB: LIBNL_CFLAGS was added to tests/Makefile.am because virnetdev.h now includes util/virnetlink.h, which includes netlink/msg.h when appropriate. Without LIBNL_CFLAGS, gcc can't find that file (if libnl/netlink isn't available, LIBNL_CFLAGS will be empty and virnetlink.h won't try to include netlink/msg.h anyway).)
2014-09-22 16:19:41 +00:00
# include "virnetdev.h"
# include "device_conf.h"
# include "cpu/cpu.h"
# include "util/virgic.h"
typedef struct _qemuMonitor qemuMonitor;
typedef qemuMonitor *qemuMonitorPtr;
typedef struct _qemuMonitorMessage qemuMonitorMessage;
typedef qemuMonitorMessage *qemuMonitorMessagePtr;
typedef int (*qemuMonitorPasswordHandler)(qemuMonitorPtr mon,
qemuMonitorMessagePtr msg,
const char *data,
size_t len,
void *opaque);
struct _qemuMonitorMessage {
int txFD;
char *txBuffer;
int txOffset;
int txLength;
/* Used by the text monitor reply / error */
char *rxBuffer;
int rxLength;
/* Used by the JSON monitor to hold reply / error */
void *rxObject;
/* True if rxBuffer / rxObject are ready, or a
* fatal error occurred on the monitor channel
*/
bool finished;
qemuMonitorPasswordHandler passwordHandler;
void *passwordOpaque;
};
typedef void (*qemuMonitorDestroyCallback)(qemuMonitorPtr mon,
virDomainObjPtr vm,
void *opaque);
typedef void (*qemuMonitorEofNotifyCallback)(qemuMonitorPtr mon,
virDomainObjPtr vm,
void *opaque);
typedef void (*qemuMonitorErrorNotifyCallback)(qemuMonitorPtr mon,
virDomainObjPtr vm,
void *opaque);
/* XXX we'd really like to avoid virConnectPtr here
* It is required so the callback can find the active
* secret driver. Need to change this to work like the
* security drivers do, to avoid this
*/
typedef int (*qemuMonitorDiskSecretLookupCallback)(qemuMonitorPtr mon,
virConnectPtr conn,
virDomainObjPtr vm,
const char *path,
char **secret,
size_t *secretLen,
void *opaque);
typedef int (*qemuMonitorDomainEventCallback)(qemuMonitorPtr mon,
virDomainObjPtr vm,
const char *event,
long long seconds,
unsigned int micros,
const char *details,
void *opaque);
typedef int (*qemuMonitorDomainShutdownCallback)(qemuMonitorPtr mon,
virDomainObjPtr vm,
void *opaque);
typedef int (*qemuMonitorDomainResetCallback)(qemuMonitorPtr mon,
virDomainObjPtr vm,
void *opaque);
typedef int (*qemuMonitorDomainPowerdownCallback)(qemuMonitorPtr mon,
virDomainObjPtr vm,
void *opaque);
typedef int (*qemuMonitorDomainStopCallback)(qemuMonitorPtr mon,
virDomainObjPtr vm,
void *opaque);
typedef int (*qemuMonitorDomainResumeCallback)(qemuMonitorPtr mon,
virDomainObjPtr vm,
void *opaque);
typedef int (*qemuMonitorDomainRTCChangeCallback)(qemuMonitorPtr mon,
virDomainObjPtr vm,
long long offset,
void *opaque);
typedef int (*qemuMonitorDomainWatchdogCallback)(qemuMonitorPtr mon,
virDomainObjPtr vm,
int action,
void *opaque);
typedef int (*qemuMonitorDomainIOErrorCallback)(qemuMonitorPtr mon,
virDomainObjPtr vm,
const char *diskAlias,
int action,
const char *reason,
void *opaque);
typedef int (*qemuMonitorDomainGraphicsCallback)(qemuMonitorPtr mon,
virDomainObjPtr vm,
int phase,
int localFamily,
const char *localNode,
const char *localService,
int remoteFamily,
const char *remoteNode,
const char *remoteService,
const char *authScheme,
const char *x509dname,
const char *saslUsername,
void *opaque);
typedef int (*qemuMonitorDomainBlockJobCallback)(qemuMonitorPtr mon,
virDomainObjPtr vm,
const char *diskAlias,
int type,
int status,
void *opaque);
typedef int (*qemuMonitorDomainTrayChangeCallback)(qemuMonitorPtr mon,
virDomainObjPtr vm,
const char *devAlias,
int reason,
void *opaque);
typedef int (*qemuMonitorDomainPMWakeupCallback)(qemuMonitorPtr mon,
virDomainObjPtr vm,
void *opaque);
typedef int (*qemuMonitorDomainPMSuspendCallback)(qemuMonitorPtr mon,
virDomainObjPtr vm,
void *opaque);
typedef int (*qemuMonitorDomainBalloonChangeCallback)(qemuMonitorPtr mon,
virDomainObjPtr vm,
unsigned long long actual,
void *opaque);
typedef int (*qemuMonitorDomainPMSuspendDiskCallback)(qemuMonitorPtr mon,
virDomainObjPtr vm,
void *opaque);
typedef int (*qemuMonitorDomainGuestPanicCallback)(qemuMonitorPtr mon,
virDomainObjPtr vm,
void *opaque);
typedef int (*qemuMonitorDomainDeviceDeletedCallback)(qemuMonitorPtr mon,
virDomainObjPtr vm,
const char *devAlias,
void *opaque);
typedef int (*qemuMonitorDomainNicRxFilterChangedCallback)(qemuMonitorPtr mon,
virDomainObjPtr vm,
const char *devAlias,
void *opaque);
typedef int (*qemuMonitorDomainSerialChangeCallback)(qemuMonitorPtr mon,
virDomainObjPtr vm,
const char *devAlias,
bool connected,
void *opaque);
typedef int (*qemuMonitorDomainSpiceMigratedCallback)(qemuMonitorPtr mon,
virDomainObjPtr vm,
void *opaque);
typedef int (*qemuMonitorDomainMigrationStatusCallback)(qemuMonitorPtr mon,
virDomainObjPtr vm,
int status,
void *opaque);
typedef int (*qemuMonitorDomainMigrationPassCallback)(qemuMonitorPtr mon,
virDomainObjPtr vm,
int pass,
void *opaque);
typedef int (*qemuMonitorDomainAcpiOstInfoCallback)(qemuMonitorPtr mon,
virDomainObjPtr vm,
const char *alias,
const char *slotType,
const char *slot,
unsigned int source,
unsigned int status,
void *opaque);
typedef struct _qemuMonitorCallbacks qemuMonitorCallbacks;
typedef qemuMonitorCallbacks *qemuMonitorCallbacksPtr;
struct _qemuMonitorCallbacks {
qemuMonitorDestroyCallback destroy;
qemuMonitorEofNotifyCallback eofNotify;
qemuMonitorErrorNotifyCallback errorNotify;
qemuMonitorDiskSecretLookupCallback diskSecretLookup;
qemuMonitorDomainEventCallback domainEvent;
qemuMonitorDomainShutdownCallback domainShutdown;
qemuMonitorDomainResetCallback domainReset;
qemuMonitorDomainPowerdownCallback domainPowerdown;
qemuMonitorDomainStopCallback domainStop;
qemuMonitorDomainResumeCallback domainResume;
qemuMonitorDomainRTCChangeCallback domainRTCChange;
qemuMonitorDomainWatchdogCallback domainWatchdog;
qemuMonitorDomainIOErrorCallback domainIOError;
qemuMonitorDomainGraphicsCallback domainGraphics;
qemuMonitorDomainBlockJobCallback domainBlockJob;
qemuMonitorDomainTrayChangeCallback domainTrayChange;
qemuMonitorDomainPMWakeupCallback domainPMWakeup;
qemuMonitorDomainPMSuspendCallback domainPMSuspend;
qemuMonitorDomainBalloonChangeCallback domainBalloonChange;
qemuMonitorDomainPMSuspendDiskCallback domainPMSuspendDisk;
qemuMonitorDomainGuestPanicCallback domainGuestPanic;
qemuMonitorDomainDeviceDeletedCallback domainDeviceDeleted;
qemuMonitorDomainNicRxFilterChangedCallback domainNicRxFilterChanged;
qemuMonitorDomainSerialChangeCallback domainSerialChange;
qemuMonitorDomainSpiceMigratedCallback domainSpiceMigrated;
qemuMonitorDomainMigrationStatusCallback domainMigrationStatus;
qemuMonitorDomainMigrationPassCallback domainMigrationPass;
qemuMonitorDomainAcpiOstInfoCallback domainAcpiOstInfo;
};
char *qemuMonitorEscapeArg(const char *in);
char *qemuMonitorUnescapeArg(const char *in);
qemuMonitorPtr qemuMonitorOpen(virDomainObjPtr vm,
virDomainChrSourceDefPtr config,
bool json,
qemuMonitorCallbacksPtr cb,
void *opaque)
ATTRIBUTE_NONNULL(1) ATTRIBUTE_NONNULL(2) ATTRIBUTE_NONNULL(4);
qemuMonitorPtr qemuMonitorOpenFD(virDomainObjPtr vm,
int sockfd,
bool json,
qemuMonitorCallbacksPtr cb,
void *opaque)
ATTRIBUTE_NONNULL(1) ATTRIBUTE_NONNULL(4);
void qemuMonitorUnregister(qemuMonitorPtr mon)
ATTRIBUTE_NONNULL(1);
void qemuMonitorClose(qemuMonitorPtr mon);
virErrorPtr qemuMonitorLastError(qemuMonitorPtr mon);
int qemuMonitorSetCapabilities(qemuMonitorPtr mon);
int qemuMonitorSetLink(qemuMonitorPtr mon,
const char *name,
virDomainNetInterfaceLinkState state)
ATTRIBUTE_NONNULL(2);
/* These APIs are for use by the internal Text/JSON monitor impl code only */
char *qemuMonitorNextCommandID(qemuMonitorPtr mon);
int qemuMonitorSend(qemuMonitorPtr mon,
qemuMonitorMessagePtr msg);
virJSONValuePtr qemuMonitorGetOptions(qemuMonitorPtr mon)
ATTRIBUTE_NONNULL(1);
void qemuMonitorSetOptions(qemuMonitorPtr mon, virJSONValuePtr options)
ATTRIBUTE_NONNULL(1);
int qemuMonitorUpdateVideoMemorySize(qemuMonitorPtr mon,
virDomainVideoDefPtr video,
const char *videoName)
ATTRIBUTE_NONNULL(1) ATTRIBUTE_NONNULL(2) ATTRIBUTE_NONNULL(3);
int qemuMonitorUpdateVideoVram64Size(qemuMonitorPtr mon,
virDomainVideoDefPtr video,
const char *videoName)
ATTRIBUTE_NONNULL(1) ATTRIBUTE_NONNULL(2) ATTRIBUTE_NONNULL(3);
int qemuMonitorHMPCommandWithFd(qemuMonitorPtr mon,
const char *cmd,
int scm_fd,
char **reply);
# define qemuMonitorHMPCommand(mon, cmd, reply) \
qemuMonitorHMPCommandWithFd(mon, cmd, -1, reply)
/* XXX same comment about virConnectPtr as above */
int qemuMonitorGetDiskSecret(qemuMonitorPtr mon,
virConnectPtr conn,
const char *path,
char **secret,
size_t *secretLen);
int qemuMonitorEmitEvent(qemuMonitorPtr mon, const char *event,
long long seconds, unsigned int micros,
const char *details);
int qemuMonitorEmitShutdown(qemuMonitorPtr mon);
int qemuMonitorEmitReset(qemuMonitorPtr mon);
int qemuMonitorEmitPowerdown(qemuMonitorPtr mon);
int qemuMonitorEmitStop(qemuMonitorPtr mon);
int qemuMonitorEmitResume(qemuMonitorPtr mon);
int qemuMonitorEmitRTCChange(qemuMonitorPtr mon, long long offset);
int qemuMonitorEmitWatchdog(qemuMonitorPtr mon, int action);
Add support for an explicit IO error event This introduces a new event type VIR_DOMAIN_EVENT_ID_IO_ERROR This event includes the action that is about to be taken as a result of the watchdog triggering typedef enum { VIR_DOMAIN_EVENT_IO_ERROR_NONE = 0, VIR_DOMAIN_EVENT_IO_ERROR_PAUSE, VIR_DOMAIN_EVENT_IO_ERROR_REPORT, } virDomainEventIOErrorAction; In addition it has the source path of the disk that had the error and its unique device alias. It does not include the target device name (/dev/sda), since this would preclude triggering IO errors from other file backed devices (eg serial ports connected to a file) Thus there is a new callback definition for this event type typedef void (*virConnectDomainEventIOErrorCallback)(virConnectPtr conn, virDomainPtr dom, const char *srcPath, const char *devAlias, int action, void *opaque); This is currently wired up to the QEMU block IO error events * daemon/remote.c: Dispatch IO error events to client * examples/domain-events/events-c/event-test.c: Watch for IO error events * include/libvirt/libvirt.h.in: Define new IO error event ID and callback signature * src/conf/domain_event.c, src/conf/domain_event.h, src/libvirt_private.syms: Extend API to handle IO error events * src/qemu/qemu_driver.c: Connect to the QEMU monitor event for block IO errors and emit a libvirt IO error event * src/remote/remote_driver.c: Receive and dispatch IO error events to application * src/remote/remote_protocol.x: Wire protocol definition for IO error events * src/qemu/qemu_monitor.c, src/qemu/qemu_monitor.h, src/qemu/qemu_monitor_json.c: Watch for BLOCK_IO_ERROR event from QEMU monitor
2010-03-18 19:37:44 +00:00
int qemuMonitorEmitIOError(qemuMonitorPtr mon,
const char *diskAlias,
int action,
const char *reason);
Add domain events for graphics network clients This introduces a new event type VIR_DOMAIN_EVENT_ID_GRAPHICS The same event can be emitted in 3 scenarios typedef enum { VIR_DOMAIN_EVENT_GRAPHICS_CONNECT = 0, VIR_DOMAIN_EVENT_GRAPHICS_INITIALIZE, VIR_DOMAIN_EVENT_GRAPHICS_DISCONNECT, } virDomainEventGraphicsPhase; Connect/disconnect are triggered at socket accept/close. The initialize phase is immediately after the protocol setup and authentication has completed. ie when the client is authorized and about to start interacting with the graphical desktop This event comes with *a lot* of potential information - IP address, port & address family of client - IP address, port & address family of server - Authentication scheme (arbitrary string) - Authenticated subject identity. A subject may have multiple identities with some authentication schemes. For example, vencrypt+sasl results in a x509dname and saslUsername identities. This results in a very complicated callback :-( typedef enum { VIR_DOMAIN_EVENT_GRAPHICS_ADDRESS_IPV4, VIR_DOMAIN_EVENT_GRAPHICS_ADDRESS_IPV6, } virDomainEventGraphicsAddressType; struct _virDomainEventGraphicsAddress { int family; const char *node; const char *service; }; typedef struct _virDomainEventGraphicsAddress virDomainEventGraphicsAddress; typedef virDomainEventGraphicsAddress *virDomainEventGraphicsAddressPtr; struct _virDomainEventGraphicsSubject { int nidentity; struct { const char *type; const char *name; } *identities; }; typedef struct _virDomainEventGraphicsSubject virDomainEventGraphicsSubject; typedef virDomainEventGraphicsSubject *virDomainEventGraphicsSubjectPtr; typedef void (*virConnectDomainEventGraphicsCallback)(virConnectPtr conn, virDomainPtr dom, int phase, virDomainEventGraphicsAddressPtr local, virDomainEventGraphicsAddressPtr remote, const char *authScheme, virDomainEventGraphicsSubjectPtr subject, void *opaque); The wire protocol is similarly complex struct remote_domain_event_graphics_address { int family; remote_nonnull_string node; remote_nonnull_string service; }; const REMOTE_DOMAIN_EVENT_GRAPHICS_IDENTITY_MAX = 20; struct remote_domain_event_graphics_identity { remote_nonnull_string type; remote_nonnull_string name; }; struct remote_domain_event_graphics_msg { remote_nonnull_domain dom; int phase; remote_domain_event_graphics_address local; remote_domain_event_graphics_address remote; remote_nonnull_string authScheme; remote_domain_event_graphics_identity subject<REMOTE_DOMAIN_EVENT_GRAPHICS_IDENTITY_MAX>; }; This is currently implemented in QEMU for the VNC graphics protocol, but designed to be usable with SPICE graphics in the future too. * daemon/remote.c: Dispatch graphics events to client * examples/domain-events/events-c/event-test.c: Watch for graphics events * include/libvirt/libvirt.h.in: Define new graphics event ID and callback signature * src/conf/domain_event.c, src/conf/domain_event.h, src/libvirt_private.syms: Extend API to handle graphics events * src/qemu/qemu_driver.c: Connect to the QEMU monitor event for VNC events and emit a libvirt graphics event * src/remote/remote_driver.c: Receive and dispatch graphics events to application * src/remote/remote_protocol.x: Wire protocol definition for graphics events * src/qemu/qemu_monitor.c, src/qemu/qemu_monitor.h, src/qemu/qemu_monitor_json.c: Watch for VNC_CONNECTED, VNC_INITIALIZED & VNC_DISCONNETED events from QEMU monitor
2010-03-19 13:27:45 +00:00
int qemuMonitorEmitGraphics(qemuMonitorPtr mon,
int phase,
int localFamily,
const char *localNode,
const char *localService,
int remoteFamily,
const char *remoteNode,
const char *remoteService,
const char *authScheme,
const char *x509dname,
const char *saslUsername);
int qemuMonitorEmitTrayChange(qemuMonitorPtr mon,
const char *devAlias,
int reason);
int qemuMonitorEmitPMWakeup(qemuMonitorPtr mon);
int qemuMonitorEmitPMSuspend(qemuMonitorPtr mon);
int qemuMonitorEmitBlockJob(qemuMonitorPtr mon,
const char *diskAlias,
int type,
int status);
int qemuMonitorEmitBalloonChange(qemuMonitorPtr mon,
unsigned long long actual);
int qemuMonitorEmitPMSuspendDisk(qemuMonitorPtr mon);
int qemuMonitorEmitGuestPanic(qemuMonitorPtr mon);
int qemuMonitorEmitDeviceDeleted(qemuMonitorPtr mon,
const char *devAlias);
int qemuMonitorEmitNicRxFilterChanged(qemuMonitorPtr mon,
const char *devAlias);
int qemuMonitorEmitSerialChange(qemuMonitorPtr mon,
const char *devAlias,
bool connected);
int qemuMonitorEmitSpiceMigrated(qemuMonitorPtr mon);
int qemuMonitorEmitMigrationStatus(qemuMonitorPtr mon,
int status);
int qemuMonitorEmitMigrationPass(qemuMonitorPtr mon,
int pass);
int qemuMonitorEmitAcpiOstInfo(qemuMonitorPtr mon,
const char *alias,
const char *slotType,
const char *slot,
unsigned int source,
unsigned int status);
int qemuMonitorStartCPUs(qemuMonitorPtr mon,
virConnectPtr conn);
int qemuMonitorStopCPUs(qemuMonitorPtr mon);
typedef enum {
QEMU_MONITOR_VM_STATUS_DEBUG,
QEMU_MONITOR_VM_STATUS_INMIGRATE,
QEMU_MONITOR_VM_STATUS_INTERNAL_ERROR,
QEMU_MONITOR_VM_STATUS_IO_ERROR,
QEMU_MONITOR_VM_STATUS_PAUSED,
QEMU_MONITOR_VM_STATUS_POSTMIGRATE,
QEMU_MONITOR_VM_STATUS_PRELAUNCH,
QEMU_MONITOR_VM_STATUS_FINISH_MIGRATE,
QEMU_MONITOR_VM_STATUS_RESTORE_VM,
QEMU_MONITOR_VM_STATUS_RUNNING,
QEMU_MONITOR_VM_STATUS_SAVE_VM,
QEMU_MONITOR_VM_STATUS_SHUTDOWN,
QEMU_MONITOR_VM_STATUS_WATCHDOG,
QEMU_MONITOR_VM_STATUS_GUEST_PANICKED,
QEMU_MONITOR_VM_STATUS_LAST
} qemuMonitorVMStatus;
VIR_ENUM_DECL(qemuMonitorVMStatus)
int qemuMonitorVMStatusToPausedReason(const char *status);
int qemuMonitorGetStatus(qemuMonitorPtr mon,
bool *running,
virDomainPausedReason *reason)
ATTRIBUTE_NONNULL(2);
int qemuMonitorSystemReset(qemuMonitorPtr mon);
int qemuMonitorSystemPowerdown(qemuMonitorPtr mon);
int qemuMonitorGetCPUInfo(qemuMonitorPtr mon,
int **pids);
int qemuMonitorGetVirtType(qemuMonitorPtr mon,
virDomainVirtType *virtType);
int qemuMonitorGetBalloonInfo(qemuMonitorPtr mon,
xml: use better types for memory values Using 'unsigned long' for memory values is risky on 32-bit platforms, as a PAE guest can have more than 4GiB memory. Our API is (unfortunately) locked at 'unsigned long' and a scale of 1024, but the rest of our system should consistently use 64-bit values, especially since the previous patch centralized overflow checking. * src/conf/domain_conf.h (_virDomainDef): Always use 64-bit values for memory. Change hugepage_backed to a bool. * src/conf/domain_conf.c (virDomainDefParseXML) (virDomainDefCheckABIStability, virDomainDefFormatInternal): Fix clients. * src/vmx/vmx.c (virVMXFormatConfig): Likewise. * src/xenxs/xen_sxpr.c (xenParseSxpr, xenFormatSxpr): Likewise. * src/xenxs/xen_xm.c (xenXMConfigGetULongLong): New function. (xenXMConfigGetULong, xenXMConfigSetInt): Avoid truncation. (xenParseXM, xenFormatXM): Fix clients. * src/phyp/phyp_driver.c (phypBuildLpar): Likewise. * src/openvz/openvz_driver.c (openvzDomainSetMemoryInternal): Likewise. * src/vbox/vbox_tmpl.c (vboxDomainDefineXML): Likewise. * src/qemu/qemu_command.c (qemuBuildCommandLine): Likewise. * src/qemu/qemu_process.c (qemuProcessStart): Likewise. * src/qemu/qemu_monitor.h (qemuMonitorGetBalloonInfo): Likewise. * src/qemu/qemu_monitor_text.h (qemuMonitorTextGetBalloonInfo): Likewise. * src/qemu/qemu_monitor_text.c (qemuMonitorTextGetBalloonInfo): Likewise. * src/qemu/qemu_monitor_json.h (qemuMonitorJSONGetBalloonInfo): Likewise. * src/qemu/qemu_monitor_json.c (qemuMonitorJSONGetBalloonInfo): Likewise. * src/qemu/qemu_driver.c (qemudDomainGetInfo) (qemuDomainGetXMLDesc): Likewise. * src/uml/uml_conf.c (umlBuildCommandLine): Likewise.
2012-03-02 20:27:39 +00:00
unsigned long long *currmem);
int qemuMonitorGetMemoryStats(qemuMonitorPtr mon,
virDomainMemoryStatPtr stats,
unsigned int nr_stats);
int qemuMonitorSetMemoryStatsPeriod(qemuMonitorPtr mon,
int period);
2012-01-19 16:58:58 +00:00
int qemuMonitorBlockIOStatusToError(const char *status);
virHashTablePtr qemuMonitorGetBlockInfo(qemuMonitorPtr mon);
struct qemuDomainDiskInfo *
qemuMonitorBlockInfoLookup(virHashTablePtr blockInfo,
const char *dev_name);
typedef struct _qemuBlockStats qemuBlockStats;
typedef qemuBlockStats *qemuBlockStatsPtr;
struct _qemuBlockStats {
long long rd_req;
long long rd_bytes;
long long wr_req;
long long wr_bytes;
long long rd_total_times;
long long wr_total_times;
long long flush_req;
long long flush_total_times;
unsigned long long capacity;
unsigned long long physical;
/* value of wr_highest_offset is valid if it's non 0 or
* if wr_highest_offset_valid is true */
unsigned long long wr_highest_offset;
bool wr_highest_offset_valid;
};
int qemuMonitorGetAllBlockStatsInfo(qemuMonitorPtr mon,
virHashTablePtr *ret_stats,
bool backingChain)
ATTRIBUTE_NONNULL(1) ATTRIBUTE_NONNULL(2);
int qemuMonitorBlockStatsUpdateCapacity(qemuMonitorPtr mon,
virHashTablePtr stats,
bool backingChain)
ATTRIBUTE_NONNULL(1) ATTRIBUTE_NONNULL(2);
int qemuMonitorBlockResize(qemuMonitorPtr mon,
const char *dev_name,
unsigned long long size);
int qemuMonitorSetVNCPassword(qemuMonitorPtr mon,
const char *password);
int qemuMonitorSetPassword(qemuMonitorPtr mon,
int type,
const char *password,
const char *action_if_connected);
int qemuMonitorExpirePassword(qemuMonitorPtr mon,
int type,
const char *expire_time);
int qemuMonitorSetBalloon(qemuMonitorPtr mon,
unsigned long long newmem);
int qemuMonitorSetCPU(qemuMonitorPtr mon, int cpu, bool online);
/* XXX should we pass the virDomainDiskDefPtr instead
* and hide dev_name details inside monitor. Reconsider
* this when doing the QMP implementation
*/
int qemuMonitorEjectMedia(qemuMonitorPtr mon,
const char *dev_name,
bool force);
int qemuMonitorChangeMedia(qemuMonitorPtr mon,
const char *dev_name,
const char *newmedia,
const char *format);
int qemuMonitorSaveVirtualMemory(qemuMonitorPtr mon,
unsigned long long offset,
size_t length,
const char *path);
int qemuMonitorSavePhysicalMemory(qemuMonitorPtr mon,
unsigned long long offset,
size_t length,
const char *path);
int qemuMonitorSetMigrationSpeed(qemuMonitorPtr mon,
unsigned long bandwidth);
int qemuMonitorSetMigrationDowntime(qemuMonitorPtr mon,
unsigned long long downtime);
int qemuMonitorGetMigrationCacheSize(qemuMonitorPtr mon,
unsigned long long *cacheSize);
int qemuMonitorSetMigrationCacheSize(qemuMonitorPtr mon,
unsigned long long cacheSize);
typedef struct _qemuMonitorMigrationCompression qemuMonitorMigrationCompression;
typedef qemuMonitorMigrationCompression *qemuMonitorMigrationCompressionPtr;
struct _qemuMonitorMigrationCompression {
bool level_set;
bool threads_set;
bool dthreads_set;
int level;
int threads;
int dthreads;
};
int qemuMonitorGetMigrationCompression(qemuMonitorPtr mon,
qemuMonitorMigrationCompressionPtr compress);
int qemuMonitorSetMigrationCompression(qemuMonitorPtr mon,
qemuMonitorMigrationCompressionPtr compress);
typedef enum {
QEMU_MONITOR_MIGRATION_STATUS_INACTIVE,
QEMU_MONITOR_MIGRATION_STATUS_SETUP,
QEMU_MONITOR_MIGRATION_STATUS_ACTIVE,
QEMU_MONITOR_MIGRATION_STATUS_POSTCOPY,
QEMU_MONITOR_MIGRATION_STATUS_COMPLETED,
QEMU_MONITOR_MIGRATION_STATUS_ERROR,
QEMU_MONITOR_MIGRATION_STATUS_CANCELLING,
QEMU_MONITOR_MIGRATION_STATUS_CANCELLED,
QEMU_MONITOR_MIGRATION_STATUS_LAST
} qemuMonitorMigrationStatus;
VIR_ENUM_DECL(qemuMonitorMigrationStatus)
typedef struct _qemuMonitorMigrationStats qemuMonitorMigrationStats;
typedef qemuMonitorMigrationStats *qemuMonitorMigrationStatsPtr;
struct _qemuMonitorMigrationStats {
int status; /* qemuMonitorMigrationStatus */
unsigned long long total_time;
/* total or expected depending on status */
bool downtime_set;
unsigned long long downtime;
/*
* Duration of the QEMU 'setup' state.
* for RDMA, this may be on the order of several seconds
* if pinning support is requested before the migration begins.
*/
bool setup_time_set;
unsigned long long setup_time;
unsigned long long ram_transferred;
unsigned long long ram_remaining;
unsigned long long ram_total;
unsigned long long ram_bps;
bool ram_duplicate_set;
unsigned long long ram_duplicate;
unsigned long long ram_normal;
unsigned long long ram_normal_bytes;
unsigned long long ram_dirty_rate;
unsigned long long ram_iteration;
unsigned long long disk_transferred;
unsigned long long disk_remaining;
unsigned long long disk_total;
unsigned long long disk_bps;
bool xbzrle_set;
unsigned long long xbzrle_cache_size;
unsigned long long xbzrle_bytes;
unsigned long long xbzrle_pages;
unsigned long long xbzrle_cache_miss;
unsigned long long xbzrle_overflow;
};
int qemuMonitorGetMigrationStats(qemuMonitorPtr mon,
qemuMonitorMigrationStatsPtr stats);
typedef enum {
QEMU_MONITOR_MIGRATION_CAPS_XBZRLE,
QEMU_MONITOR_MIGRATION_CAPS_AUTO_CONVERGE,
2014-09-11 12:11:54 +00:00
QEMU_MONITOR_MIGRATION_CAPS_RDMA_PIN_ALL,
QEMU_MONITOR_MIGRATION_CAPS_EVENTS,
QEMU_MONITOR_MIGRATION_CAPS_POSTCOPY,
QEMU_MONITOR_MIGRATION_CAPS_COMPRESS,
QEMU_MONITOR_MIGRATION_CAPS_LAST
} qemuMonitorMigrationCaps;
VIR_ENUM_DECL(qemuMonitorMigrationCaps);
2014-09-11 12:11:54 +00:00
int qemuMonitorGetMigrationCapabilities(qemuMonitorPtr mon,
char ***capabilities);
int qemuMonitorGetMigrationCapability(qemuMonitorPtr mon,
qemuMonitorMigrationCaps capability);
int qemuMonitorSetMigrationCapability(qemuMonitorPtr mon,
qemuMonitorMigrationCaps capability,
bool state);
int qemuMonitorGetGICCapabilities(qemuMonitorPtr mon,
virGICCapability **capabilities);
typedef enum {
QEMU_MONITOR_MIGRATE_BACKGROUND = 1 << 0,
QEMU_MONITOR_MIGRATE_NON_SHARED_DISK = 1 << 1, /* migration with non-shared storage with full disk copy */
QEMU_MONITOR_MIGRATE_NON_SHARED_INC = 1 << 2, /* migration with non-shared storage with incremental copy */
QEMU_MONITOR_MIGRATION_FLAGS_LAST
} QEMU_MONITOR_MIGRATE;
int qemuMonitorMigrateToFd(qemuMonitorPtr mon,
unsigned int flags,
int fd);
int qemuMonitorMigrateToHost(qemuMonitorPtr mon,
unsigned int flags,
const char *protocol,
const char *hostname,
int port);
int qemuMonitorMigrateToCommand(qemuMonitorPtr mon,
unsigned int flags,
const char * const *argv);
int qemuMonitorMigrateToUnix(qemuMonitorPtr mon,
unsigned int flags,
const char *unixfile);
int qemuMonitorMigrateCancel(qemuMonitorPtr mon);
int qemuMonitorGetDumpGuestMemoryCapability(qemuMonitorPtr mon,
const char *capability);
int qemuMonitorDumpToFd(qemuMonitorPtr mon,
int fd,
const char *dumpformat);
int qemuMonitorGraphicsRelocate(qemuMonitorPtr mon,
int type,
const char *hostname,
int port,
int tlsPort,
const char *tlsSubject);
int qemuMonitorSendFileHandle(qemuMonitorPtr mon,
const char *fdname,
int fd);
int qemuMonitorAddFd(qemuMonitorPtr mon, int fdset, int fd, const char *name);
/* These two functions preserve previous error and only set their own
* error if no error was set before.
*/
int qemuMonitorCloseFileHandle(qemuMonitorPtr mon,
const char *fdname);
int qemuMonitorRemoveFd(qemuMonitorPtr mon, int fdset, int fd);
/* XXX do we really want to hardcode 'netstr' as the
* sendable item here
*/
int qemuMonitorAddHostNetwork(qemuMonitorPtr mon,
const char *netstr,
int *tapfd, char **tapfdName, int tapfdSize,
int *vhostfd, char **vhostfdName, int vhostfdSize);
int qemuMonitorRemoveHostNetwork(qemuMonitorPtr mon,
int vlan,
const char *netname);
int qemuMonitorAddNetdev(qemuMonitorPtr mon,
const char *netdevstr,
int *tapfd, char **tapfdName, int tapfdSize,
int *vhostfd, char **vhostfdName, int vhostfdSize);
int qemuMonitorRemoveNetdev(qemuMonitorPtr mon,
const char *alias);
qemu: qemuMonitorQueryRxFilter - retrieve guest netdev rx-filter This function can be called at any time to get the current status of a guest's network device rx-filter. In particular it is useful to call after libvirt recieves a NIC_RX_FILTER_CHANGED event - this event only tells you that something has changed in the rx-filter, the details are retrieved with the query-rx-filter monitor command (only available in the json monitor). The command sent to the qemu monitor looks like this: {"execute":"query-rx-filter", "arguments": {"name":"net2"} }' and the results will look something like this: { "return": [ { "promiscuous": false, "name": "net2", "main-mac": "52:54:00:98:2d:e3", "unicast": "normal", "vlan": "normal", "vlan-table": [ 42, 0 ], "unicast-table": [ ], "multicast": "normal", "multicast-overflow": false, "unicast-overflow": false, "multicast-table": [ "33:33:ff:98:2d:e3", "01:80:c2:00:00:21", "01:00:5e:00:00:fb", "33:33:ff:98:2d:e2", "01:00:5e:00:00:01", "33:33:00:00:00:01" ], "broadcast-allowed": false } ], "id": "libvirt-14" } This is all parsed from JSON into a virNetDevRxFilter object for easier consumption. (unicast-table is usually empty, but is also an array of mac addresses similar to multicast-table). (NB: LIBNL_CFLAGS was added to tests/Makefile.am because virnetdev.h now includes util/virnetlink.h, which includes netlink/msg.h when appropriate. Without LIBNL_CFLAGS, gcc can't find that file (if libnl/netlink isn't available, LIBNL_CFLAGS will be empty and virnetlink.h won't try to include netlink/msg.h anyway).)
2014-09-22 16:19:41 +00:00
int qemuMonitorQueryRxFilter(qemuMonitorPtr mon, const char *alias,
virNetDevRxFilterPtr *filter);
typedef struct _qemuMonitorChardevInfo qemuMonitorChardevInfo;
typedef qemuMonitorChardevInfo *qemuMonitorChardevInfoPtr;
struct _qemuMonitorChardevInfo {
char *ptyPath;
virDomainChrDeviceState state;
};
void qemuMonitorChardevInfoFree(void *data, const void *name);
int qemuMonitorGetChardevInfo(qemuMonitorPtr mon,
virHashTablePtr *retinfo);
int qemuMonitorAttachPCIDiskController(qemuMonitorPtr mon,
const char *bus,
virPCIDeviceAddress *guestAddr);
typedef struct _qemuMonitorPCIAddress qemuMonitorPCIAddress;
struct _qemuMonitorPCIAddress {
unsigned int vendor;
unsigned int product;
virPCIDeviceAddress addr;
};
int qemuMonitorGetAllPCIAddresses(qemuMonitorPtr mon,
qemuMonitorPCIAddress **addrs);
int qemuMonitorAddDevice(qemuMonitorPtr mon,
const char *devicestr);
int qemuMonitorAddDeviceWithFd(qemuMonitorPtr mon,
const char *devicestr,
int fd,
const char *fdname);
int qemuMonitorDelDevice(qemuMonitorPtr mon,
const char *devalias);
int qemuMonitorAddObject(qemuMonitorPtr mon,
const char *type,
const char *objalias,
virJSONValuePtr props);
int qemuMonitorDelObject(qemuMonitorPtr mon,
const char *objalias);
int qemuMonitorAddDrive(qemuMonitorPtr mon,
const char *drivestr);
int qemuMonitorDriveDel(qemuMonitorPtr mon,
const char *drivestr);
int qemuMonitorSetDrivePassphrase(qemuMonitorPtr mon,
const char *alias,
const char *passphrase);
int qemuMonitorCreateSnapshot(qemuMonitorPtr mon, const char *name);
int qemuMonitorLoadSnapshot(qemuMonitorPtr mon, const char *name);
int qemuMonitorDeleteSnapshot(qemuMonitorPtr mon, const char *name);
int qemuMonitorDiskSnapshot(qemuMonitorPtr mon,
snapshot: add support for qemu transaction command QEmu 1.1 is adding a 'transaction' command to the JSON monitor. Each element of a transaction corresponds to a top-level command, with the additional guarantee that the transaction flushes all pending I/O, then guarantees that all actions will be successful as a group or that failure will roll back the state to what it was before the monitor command. The difference between a top-level command: { "execute": "blockdev-snapshot-sync", "arguments": { "device": "virtio0", ... } } and a transaction: { "execute": "transaction", "arguments": { "actions": [ { "type": "blockdev-snapshot-sync", "data": { "device": "virtio0", ... } } ] } } is just a couple of changed key names and nesting the shorter command inside a JSON array to the longer command. This patch just adds the framework; the next patch will actually use a transaction. * src/qemu/qemu_monitor_json.c (qemuMonitorJSONMakeCommand): Move guts... (qemuMonitorJSONMakeCommandRaw): ...into new helper. Add support for array element. (qemuMonitorJSONTransaction): New command. (qemuMonitorJSONDiskSnapshot): Support use in a transaction. * src/qemu/qemu_monitor_json.h (qemuMonitorJSONDiskSnapshot): Add argument. (qemuMonitorJSONTransaction): New declaration. * src/qemu/qemu_monitor.h (qemuMonitorTransaction): Likewise. (qemuMonitorDiskSnapshot): Add argument. * src/qemu/qemu_monitor.c (qemuMonitorTransaction): New wrapper. (qemuMonitorDiskSnapshot): Pass argument on. * src/qemu/qemu_driver.c (qemuDomainSnapshotCreateSingleDiskActive): Update caller.
2012-03-17 04:17:28 +00:00
virJSONValuePtr actions,
const char *device,
snapshot: improve qemu handling of reused snapshot targets The oVirt developers have stated that the real reasons they want to have qemu reuse existing volumes when creating a snapshot are: 1. the management framework is set up so that creation has to be done from a central node for proper resource tracking, and having libvirt and/or qemu create things violates the framework, and 2. qemu defaults to creating snapshots with an absolute path to the backing file, but oVirt wants to manage a backing chain that uses just relative names, to allow for easier migration of a chain across storage locations. When 0.9.10 added VIR_DOMAIN_SNAPSHOT_CREATE_REUSE_EXT (commit 4e9953a4), it only addressed point 1, but libvirt was still using O_TRUNC which violates point 2. Meanwhile, the new qemu 'transaction' monitor command includes a new optional mode argument that will force qemu to reuse the metadata of the file it just opened (with the burden on the caller to have valid metadata there in the first place). So, this tweaks the meaning of the flag to cover both points as intended for use by oVirt. It is not strictly backward-compatible to 0.9.10 behavior, but it can be argued that the O_TRUNC of 0.9.10 was a bug. Note that this flag is all-or-nothing, and only selects between 'existing' and the default 'absolute-paths'. A more flexible approach that would allow per-disk selections, as well as adding support for the 'no-backing-file' mode, would be possible by extending the <domainsnapshot> xml to have a per-disk mode, but until we have a management application expressing a need for that additional complexity, it is not worth doing. * src/libvirt.c (virDomainSnapshotCreateXML): Tweak documentation. * src/qemu/qemu_monitor.h (qemuMonitorDiskSnapshot): Add parameters. * src/qemu/qemu_monitor_json.h (qemuMonitorJSONDiskSnapshot): Likewise. * src/qemu/qemu_monitor.c (qemuMonitorDiskSnapshot): Pass them through. * src/qemu/qemu_monitor_json.c (qemuMonitorJSONDiskSnapshot): Use new monitor command arguments. * src/qemu/qemu_driver.c (qemuDomainSnapshotCreateDiskActive) (qemuDomainSnapshotCreateSingleDiskActive): Adjust callers. (qemuDomainSnapshotDiskPrepare): Allow qed, modify rules on reuse.
2012-03-20 21:03:45 +00:00
const char *file,
const char *format,
bool reuse);
snapshot: add support for qemu transaction command QEmu 1.1 is adding a 'transaction' command to the JSON monitor. Each element of a transaction corresponds to a top-level command, with the additional guarantee that the transaction flushes all pending I/O, then guarantees that all actions will be successful as a group or that failure will roll back the state to what it was before the monitor command. The difference between a top-level command: { "execute": "blockdev-snapshot-sync", "arguments": { "device": "virtio0", ... } } and a transaction: { "execute": "transaction", "arguments": { "actions": [ { "type": "blockdev-snapshot-sync", "data": { "device": "virtio0", ... } } ] } } is just a couple of changed key names and nesting the shorter command inside a JSON array to the longer command. This patch just adds the framework; the next patch will actually use a transaction. * src/qemu/qemu_monitor_json.c (qemuMonitorJSONMakeCommand): Move guts... (qemuMonitorJSONMakeCommandRaw): ...into new helper. Add support for array element. (qemuMonitorJSONTransaction): New command. (qemuMonitorJSONDiskSnapshot): Support use in a transaction. * src/qemu/qemu_monitor_json.h (qemuMonitorJSONDiskSnapshot): Add argument. (qemuMonitorJSONTransaction): New declaration. * src/qemu/qemu_monitor.h (qemuMonitorTransaction): Likewise. (qemuMonitorDiskSnapshot): Add argument. * src/qemu/qemu_monitor.c (qemuMonitorTransaction): New wrapper. (qemuMonitorDiskSnapshot): Pass argument on. * src/qemu/qemu_driver.c (qemuDomainSnapshotCreateSingleDiskActive): Update caller.
2012-03-17 04:17:28 +00:00
int qemuMonitorTransaction(qemuMonitorPtr mon, virJSONValuePtr actions)
ATTRIBUTE_NONNULL(2);
blockjob: add qemu capabilities related to block jobs Upstream qemu 1.3 is adding two new monitor commands, 'drive-mirror' and 'block-job-complete'[1], which can drive live block copy and storage migration. [Additionally, RHEL 6.3 had backported an earlier version of most of the same functionality, but under the names '__com.redhat_drive-mirror' and '__com.redhat_drive-reopen' and with slightly different JSON arguments, and has been using patches similar to these upstream patches for several months now.] The libvirt API virDomainBlockRebase as already committed for 0.9.12 is flexible enough to expose the basics of block copy, but some additional features in the 'drive-mirror' qemu command, such as setting error policy, setting granularity, or using a persistent bitmap, may later require a new libvirt API virDomainBlockCopy. I will wait to add that API until we know more about what qemu 1.3 will finally provide. This patch caters only to the upstream qemu 1.3 interface, although I have proven that the changes for RHEL 6.3 can be isolated to just qemu_monitor_json.c, and the rest of this series will gracefully handle either interface once the JSON differences are papered over in a downstream patch. For consistency with other block job commands, libvirt must handle the bandwidth argument as MiB/sec from the user, even though qemu exposes the speed argument as bytes/sec; then again, qemu rounds up to cluster size internally, so using MiB hides the worst effects of that rounding if you pass small numbers. [1]https://lists.gnu.org/archive/html/qemu-devel/2012-10/msg04123.html * src/qemu/qemu_capabilities.h (QEMU_CAPS_DRIVE_MIRROR) (QEMU_CAPS_DRIVE_REOPEN): New bits. * src/qemu/qemu_capabilities.c (qemuCaps): Name them. * src/qemu/qemu_monitor_json.c (qemuMonitorJSONCheckCommands): Set them. (qemuMonitorJSONDriveMirror, qemuMonitorDrivePivot): New functions. * src/qemu/qemu_monitor_json.h (qemuMonitorJSONDriveMirror) (qemuMonitorDrivePivot): Declare them. * src/qemu/qemu_monitor.c (qemuMonitorDriveMirror) (qemuMonitorDrivePivot): New passthroughs. * src/qemu/qemu_monitor.h (qemuMonitorDriveMirror) (qemuMonitorDrivePivot): Declare them.
2012-09-28 23:29:53 +00:00
int qemuMonitorDriveMirror(qemuMonitorPtr mon,
const char *device,
const char *file,
const char *format,
blockjob: hoist bandwidth scaling out of monitor code qemu treats blockjob bandwidth as a 64-bit number, in the units of bytes/second. But we stupidly modeled block job bandwidth after migration bandwidth, which in turn was an 'unsigned long' and therefore subject to 32-bit vs. 64-bit interpretations, and with a scale of MiB/s. Our code already has to convert between the two scales, and report overflow as appropriate; although this conversion currently lives in the monitor code. In fact, our conversion code limited things to 63 bits, because we checked against LLONG_MAX and reject what would be negative bandwidth if treated as signed. On the bright side, our use of MiB/s means that even with a 32-bit unsigned long, we still have no problem representing a bandwidth of 2GiB/s, which is starting to be more feasible as 10-gigabit or even faster interfaces are used. And once you get past the physical speeds of existing interfaces, any larger bandwidth number behaves the same - effectively unlimited. But on the low side, the granularity of 1MiB/s tuning is rather coarse. So the new virDomainBlockJob API decided to go with a direct 64-bit bytes/sec number instead of the scaled number that prior blockjob APIs had used. But there is no point in rounding this number to MiB/s just to scale it back to bytes/s for handing to qemu. In order to make future code sharing possible between the old virDomainBlockRebase and the new virDomainBlockCopy, this patch moves the scaling and overflow detection into the driver code. Several of the block job calls that can set speed are fed through a common interface, so it was easier to adjust all block jobs at once, for consistency. This patch is just code motion; there should be no user-visible change in behavior. * src/qemu/qemu_monitor.h (qemuMonitorBlockJob) (qemuMonitorBlockCommit, qemuMonitorDriveMirror): Change parameter type and scale. * src/qemu/qemu_monitor.c (qemuMonitorBlockJob) (qemuMonitorBlockCommit, qemuMonitorDriveMirror): Move scaling and overflow detection... * src/qemu/qemu_driver.c (qemuDomainBlockJobImpl) (qemuDomainBlockRebase, qemuDomainBlockCommit): ...here. (qemuDomainBlockCopy): Use bytes/sec. Signed-off-by: Eric Blake <eblake@redhat.com>
2014-08-29 19:58:45 +00:00
unsigned long long bandwidth,
blockcopy: add qemu implementation of new tunables Upstream qemu 1.4 added some drive-mirror tunables not present when it was first introduced in 1.3. Management apps may want to set these in some cases (for example, without tuning granularity down to sector size, a copy may end up occupying more bytes than the original because an entire cluster is copied even when only a sector within the cluster is dirty, although tuning it down results in more CPU time to do the copy). I haven't personally needed to use the parameters, but since they exist, and since the new API supports virTypedParams, we might as well expose them. Since the tuning parameters aren't often used, and omitted from the QMP command when unspecified, I think it is safe to rely on qemu 1.3 to issue an error about them being unsupported, rather than trying to create a new capability bit in libvirt. Meanwhile, all versions of qemu from 1.4 to 2.1 have a bug where a bad granularity (such as non-power-of-2) gives a poor message: error: internal error: unable to execute QEMU command 'drive-mirror': Invalid parameter 'drive-virtio-disk0' because of abuse of QERR_INVALID_PARAMETER (which is supposed to name the parameter that was given a bad value, rather than the value passed to some other parameter). I don't see that a capability check will help, so we'll just live with it (and it has since been improved in upstream qemu). * src/qemu/qemu_monitor.h (qemuMonitorDriveMirror): Add parameters. * src/qemu/qemu_monitor.c (qemuMonitorDriveMirror): Likewise. * src/qemu/qemu_monitor_json.h (qemuMonitorJSONDriveMirror): Likewise. * src/qemu/qemu_monitor_json.c (qemuMonitorJSONDriveMirror): Likewise. * src/qemu/qemu_driver.c (qemuDomainBlockCopyCommon): Likewise. (qemuDomainBlockRebase, qemuDomainBlockCopy): Adjust callers. * src/qemu/qemu_migration.c (qemuMigrationDriveMirror): Likewise. * tests/qemumonitorjsontest.c (qemuMonitorJSONDriveMirror): Likewise. Signed-off-by: Eric Blake <eblake@redhat.com>
2014-09-08 20:53:12 +00:00
unsigned int granularity,
unsigned long long buf_size,
blockjob: add qemu capabilities related to block jobs Upstream qemu 1.3 is adding two new monitor commands, 'drive-mirror' and 'block-job-complete'[1], which can drive live block copy and storage migration. [Additionally, RHEL 6.3 had backported an earlier version of most of the same functionality, but under the names '__com.redhat_drive-mirror' and '__com.redhat_drive-reopen' and with slightly different JSON arguments, and has been using patches similar to these upstream patches for several months now.] The libvirt API virDomainBlockRebase as already committed for 0.9.12 is flexible enough to expose the basics of block copy, but some additional features in the 'drive-mirror' qemu command, such as setting error policy, setting granularity, or using a persistent bitmap, may later require a new libvirt API virDomainBlockCopy. I will wait to add that API until we know more about what qemu 1.3 will finally provide. This patch caters only to the upstream qemu 1.3 interface, although I have proven that the changes for RHEL 6.3 can be isolated to just qemu_monitor_json.c, and the rest of this series will gracefully handle either interface once the JSON differences are papered over in a downstream patch. For consistency with other block job commands, libvirt must handle the bandwidth argument as MiB/sec from the user, even though qemu exposes the speed argument as bytes/sec; then again, qemu rounds up to cluster size internally, so using MiB hides the worst effects of that rounding if you pass small numbers. [1]https://lists.gnu.org/archive/html/qemu-devel/2012-10/msg04123.html * src/qemu/qemu_capabilities.h (QEMU_CAPS_DRIVE_MIRROR) (QEMU_CAPS_DRIVE_REOPEN): New bits. * src/qemu/qemu_capabilities.c (qemuCaps): Name them. * src/qemu/qemu_monitor_json.c (qemuMonitorJSONCheckCommands): Set them. (qemuMonitorJSONDriveMirror, qemuMonitorDrivePivot): New functions. * src/qemu/qemu_monitor_json.h (qemuMonitorJSONDriveMirror) (qemuMonitorDrivePivot): Declare them. * src/qemu/qemu_monitor.c (qemuMonitorDriveMirror) (qemuMonitorDrivePivot): New passthroughs. * src/qemu/qemu_monitor.h (qemuMonitorDriveMirror) (qemuMonitorDrivePivot): Declare them.
2012-09-28 23:29:53 +00:00
unsigned int flags)
ATTRIBUTE_NONNULL(2) ATTRIBUTE_NONNULL(3);
blockjob: add qemu capabilities related to block jobs Upstream qemu 1.3 is adding two new monitor commands, 'drive-mirror' and 'block-job-complete'[1], which can drive live block copy and storage migration. [Additionally, RHEL 6.3 had backported an earlier version of most of the same functionality, but under the names '__com.redhat_drive-mirror' and '__com.redhat_drive-reopen' and with slightly different JSON arguments, and has been using patches similar to these upstream patches for several months now.] The libvirt API virDomainBlockRebase as already committed for 0.9.12 is flexible enough to expose the basics of block copy, but some additional features in the 'drive-mirror' qemu command, such as setting error policy, setting granularity, or using a persistent bitmap, may later require a new libvirt API virDomainBlockCopy. I will wait to add that API until we know more about what qemu 1.3 will finally provide. This patch caters only to the upstream qemu 1.3 interface, although I have proven that the changes for RHEL 6.3 can be isolated to just qemu_monitor_json.c, and the rest of this series will gracefully handle either interface once the JSON differences are papered over in a downstream patch. For consistency with other block job commands, libvirt must handle the bandwidth argument as MiB/sec from the user, even though qemu exposes the speed argument as bytes/sec; then again, qemu rounds up to cluster size internally, so using MiB hides the worst effects of that rounding if you pass small numbers. [1]https://lists.gnu.org/archive/html/qemu-devel/2012-10/msg04123.html * src/qemu/qemu_capabilities.h (QEMU_CAPS_DRIVE_MIRROR) (QEMU_CAPS_DRIVE_REOPEN): New bits. * src/qemu/qemu_capabilities.c (qemuCaps): Name them. * src/qemu/qemu_monitor_json.c (qemuMonitorJSONCheckCommands): Set them. (qemuMonitorJSONDriveMirror, qemuMonitorDrivePivot): New functions. * src/qemu/qemu_monitor_json.h (qemuMonitorJSONDriveMirror) (qemuMonitorDrivePivot): Declare them. * src/qemu/qemu_monitor.c (qemuMonitorDriveMirror) (qemuMonitorDrivePivot): New passthroughs. * src/qemu/qemu_monitor.h (qemuMonitorDriveMirror) (qemuMonitorDrivePivot): Declare them.
2012-09-28 23:29:53 +00:00
int qemuMonitorDrivePivot(qemuMonitorPtr mon,
const char *device)
ATTRIBUTE_NONNULL(2);
int qemuMonitorBlockCommit(qemuMonitorPtr mon,
const char *device,
const char *top,
const char *base,
const char *backingName,
blockjob: hoist bandwidth scaling out of monitor code qemu treats blockjob bandwidth as a 64-bit number, in the units of bytes/second. But we stupidly modeled block job bandwidth after migration bandwidth, which in turn was an 'unsigned long' and therefore subject to 32-bit vs. 64-bit interpretations, and with a scale of MiB/s. Our code already has to convert between the two scales, and report overflow as appropriate; although this conversion currently lives in the monitor code. In fact, our conversion code limited things to 63 bits, because we checked against LLONG_MAX and reject what would be negative bandwidth if treated as signed. On the bright side, our use of MiB/s means that even with a 32-bit unsigned long, we still have no problem representing a bandwidth of 2GiB/s, which is starting to be more feasible as 10-gigabit or even faster interfaces are used. And once you get past the physical speeds of existing interfaces, any larger bandwidth number behaves the same - effectively unlimited. But on the low side, the granularity of 1MiB/s tuning is rather coarse. So the new virDomainBlockJob API decided to go with a direct 64-bit bytes/sec number instead of the scaled number that prior blockjob APIs had used. But there is no point in rounding this number to MiB/s just to scale it back to bytes/s for handing to qemu. In order to make future code sharing possible between the old virDomainBlockRebase and the new virDomainBlockCopy, this patch moves the scaling and overflow detection into the driver code. Several of the block job calls that can set speed are fed through a common interface, so it was easier to adjust all block jobs at once, for consistency. This patch is just code motion; there should be no user-visible change in behavior. * src/qemu/qemu_monitor.h (qemuMonitorBlockJob) (qemuMonitorBlockCommit, qemuMonitorDriveMirror): Change parameter type and scale. * src/qemu/qemu_monitor.c (qemuMonitorBlockJob) (qemuMonitorBlockCommit, qemuMonitorDriveMirror): Move scaling and overflow detection... * src/qemu/qemu_driver.c (qemuDomainBlockJobImpl) (qemuDomainBlockRebase, qemuDomainBlockCommit): ...here. (qemuDomainBlockCopy): Use bytes/sec. Signed-off-by: Eric Blake <eblake@redhat.com>
2014-08-29 19:58:45 +00:00
unsigned long long bandwidth)
ATTRIBUTE_NONNULL(2) ATTRIBUTE_NONNULL(3) ATTRIBUTE_NONNULL(4);
blockjob: allow omitted arguments to QMP block-commit We are about to turn on support for active block commit. Although qemu 2.0 was the first version to mostly support it, that version mis-handles 0-length files, and doesn't have anything available for easy probing. But qemu 2.1 fixed bugs, and made life simpler by letting the 'top' argument be optional. Unless someone begs for active commit with qemu 2.0, for now we are just going to enable it only by probing for qemu 2.1 behavior (anyone backporting active commit can also backport the optional argument behavior). This requires qemu.git commit 7676e2c597000eff3a7233b40cca768b358f9bc9. Although all our actual uses of block-commit supply arguments for both base and top, we can omit both arguments and use a bogus device string to trigger an interesting behavior in qemu. All QMP commands first do argument validation, failing with GenericError if a mandatory argument is missing. Once that passes, the code in the specific command gets to do further checking, and the qemu developers made sure that if device is the only supplied argument, then the block-commit code will look up the device first, with a failure of DeviceNotFound, before attempting any further argument validation (most other validations fail with GenericError). Thus, the category of error class can reliably be used to decipher whether the top argument was optional, which in turn implies a working active commit. Since we expect our bogus device string to trigger an error either way, the code is written to return a distinct return value without spamming the logs. * src/qemu/qemu_monitor.h (qemuMonitorSupportsActiveCommit): New prototype. * src/qemu/qemu_monitor.c (qemuMonitorSupportsActiveCommit): Implement it. * src/qemu/qemu_monitor_json.h (qemuMonitorJSONBlockCommit): Allow NULL for top and base, for probing purposes. * src/qemu/qemu_monitor_json.c (qemuMonitorJSONBlockCommit): Likewise, implementing the probe. * tests/qemumonitorjsontest.c (mymain): Enable... (testQemuMonitorJSONqemuMonitorSupportsActiveCommit): ...a new test. Signed-off-by: Eric Blake <eblake@redhat.com>
2014-06-17 03:42:49 +00:00
bool qemuMonitorSupportsActiveCommit(qemuMonitorPtr mon);
qemu: read backing chain names from qemu https://bugzilla.redhat.com/show_bug.cgi?id=1199182 documents that after a series of disk snapshots into existing destination images, followed by active commits of the top image, it is possible for qemu 2.2 and earlier to end up tracking a different name for the image than what it would have had when opening the chain afresh. That is, when starting with the chain 'a <- b <- c', the name associated with 'b' is how it was spelled in the metadata of 'c', but when starting with 'a', taking two snapshots into 'a <- b <- c', then committing 'c' back into 'b', the name associated with 'b' is now the name used when taking the first snapshot. Sadly, older qemu doesn't know how to treat different spellings of the same filename as identical files (it uses strcmp() instead of checking for the same inode), which means libvirt's attempt to commit an image using solely the names learned from qcow2 metadata fails with a cryptic: error: internal error: unable to execute QEMU command 'block-commit': Top image file /tmp/images/c/../b/b not found even though the file exists. Trying to teach libvirt the rules on which name qemu will expect is not worth the effort (besides, we'd have to remember it across libvirtd restarts, and track whether a file was opened via metadata or via snapshot creation for a given qemu process); it is easier to just always directly ask qemu what string it expects to see in the first place. As a safety valve, we validate that any name returned by qemu still maps to the same local file as we have tracked it, so that a compromised qemu cannot accidentally cause us to act on an incorrect file. * src/qemu/qemu_monitor.h (qemuMonitorDiskNameLookup): New prototype. * src/qemu/qemu_monitor_json.h (qemuMonitorJSONDiskNameLookup): Likewise. * src/qemu/qemu_monitor.c (qemuMonitorDiskNameLookup): New function. * src/qemu/qemu_monitor_json.c (qemuMonitorJSONDiskNameLookup) (qemuMonitorJSONDiskNameLookupOne): Likewise. * src/qemu/qemu_driver.c (qemuDomainBlockCommit) (qemuDomainBlockJobImpl): Use it. Signed-off-by: Eric Blake <eblake@redhat.com>
2015-03-11 20:37:04 +00:00
char *qemuMonitorDiskNameLookup(qemuMonitorPtr mon,
const char *device,
virStorageSourcePtr top,
virStorageSourcePtr target)
ATTRIBUTE_NONNULL(2) ATTRIBUTE_NONNULL(3) ATTRIBUTE_NONNULL(4);
int qemuMonitorArbitraryCommand(qemuMonitorPtr mon,
const char *cmd,
char **reply,
bool hmp);
int qemuMonitorInjectNMI(qemuMonitorPtr mon);
int qemuMonitorScreendump(qemuMonitorPtr mon,
const char *file);
int qemuMonitorSendKey(qemuMonitorPtr mon,
unsigned int holdtime,
unsigned int *keycodes,
unsigned int nkeycodes);
int qemuMonitorBlockStream(qemuMonitorPtr mon,
const char *device,
const char *base,
const char *backingName,
unsigned long long bandwidth,
bool modern)
ATTRIBUTE_NONNULL(2);
int qemuMonitorBlockJobCancel(qemuMonitorPtr mon,
const char *device,
bool modern)
ATTRIBUTE_NONNULL(2);
int qemuMonitorBlockJobSetSpeed(qemuMonitorPtr mon,
const char *device,
unsigned long long bandwidth,
bool modern);
typedef struct _qemuMonitorBlockJobInfo qemuMonitorBlockJobInfo;
typedef qemuMonitorBlockJobInfo *qemuMonitorBlockJobInfoPtr;
struct _qemuMonitorBlockJobInfo {
int type; /* virDomainBlockJobType */
unsigned long long bandwidth; /* in bytes/s */
virDomainBlockJobCursor cur;
virDomainBlockJobCursor end;
int ready; /* -1 if unknown, 0 if not ready, 1 if ready */
};
virHashTablePtr qemuMonitorGetAllBlockJobInfo(qemuMonitorPtr mon);
int qemuMonitorGetBlockJobInfo(qemuMonitorPtr mon,
const char *device,
qemuMonitorBlockJobInfoPtr info)
ATTRIBUTE_NONNULL(2) ATTRIBUTE_NONNULL(3);
int qemuMonitorOpenGraphics(qemuMonitorPtr mon,
const char *protocol,
int fd,
const char *fdname,
bool skipauth);
int qemuMonitorSetBlockIoThrottle(qemuMonitorPtr mon,
const char *device,
virDomainBlockIoTuneInfoPtr info,
bool supportMaxOptions);
int qemuMonitorGetBlockIoThrottle(qemuMonitorPtr mon,
const char *device,
virDomainBlockIoTuneInfoPtr reply,
bool supportMaxOptions);
int qemuMonitorSystemWakeup(qemuMonitorPtr mon);
int qemuMonitorGetVersion(qemuMonitorPtr mon,
int *major,
int *minor,
int *micro,
char **package)
ATTRIBUTE_NONNULL(2) ATTRIBUTE_NONNULL(3) ATTRIBUTE_NONNULL(4);
typedef struct _qemuMonitorMachineInfo qemuMonitorMachineInfo;
typedef qemuMonitorMachineInfo *qemuMonitorMachineInfoPtr;
struct _qemuMonitorMachineInfo {
char *name;
bool isDefault;
char *alias;
unsigned int maxCpus;
};
int qemuMonitorGetMachines(qemuMonitorPtr mon,
qemuMonitorMachineInfoPtr **machines);
void qemuMonitorMachineInfoFree(qemuMonitorMachineInfoPtr machine);
int qemuMonitorGetCPUDefinitions(qemuMonitorPtr mon,
char ***cpus);
int qemuMonitorGetCommands(qemuMonitorPtr mon,
char ***commands);
int qemuMonitorGetEvents(qemuMonitorPtr mon,
char ***events);
int qemuMonitorGetCommandLineOptionParameters(qemuMonitorPtr mon,
const char *option,
char ***params,
bool *found);
int qemuMonitorGetKVMState(qemuMonitorPtr mon,
bool *enabled,
bool *present);
int qemuMonitorGetObjectTypes(qemuMonitorPtr mon,
char ***types);
int qemuMonitorGetObjectProps(qemuMonitorPtr mon,
const char *type,
char ***props);
char *qemuMonitorGetTargetArch(qemuMonitorPtr mon);
int qemuMonitorNBDServerStart(qemuMonitorPtr mon,
const char *host,
unsigned int port);
int qemuMonitorNBDServerAdd(qemuMonitorPtr mon,
const char *deviceID,
bool writable);
int qemuMonitorNBDServerStop(qemuMonitorPtr);
int qemuMonitorGetTPMModels(qemuMonitorPtr mon,
char ***tpmmodels);
int qemuMonitorGetTPMTypes(qemuMonitorPtr mon,
char ***tpmtypes);
int qemuMonitorAttachCharDev(qemuMonitorPtr mon,
const char *chrID,
virDomainChrSourceDefPtr chr);
int qemuMonitorDetachCharDev(qemuMonitorPtr mon,
const char *chrID);
int qemuMonitorGetDeviceAliases(qemuMonitorPtr mon,
char ***aliases);
typedef void (*qemuMonitorReportDomainLogError)(qemuMonitorPtr mon,
const char *msg,
void *opaque);
void qemuMonitorSetDomainLog(qemuMonitorPtr mon,
qemuMonitorReportDomainLogError func,
void *opaque,
virFreeCallback destroy);
int qemuMonitorGetGuestCPU(qemuMonitorPtr mon,
virArch arch,
virCPUDataPtr *data);
int qemuMonitorRTCResetReinjection(qemuMonitorPtr mon);
typedef struct _qemuMonitorIOThreadInfo qemuMonitorIOThreadInfo;
typedef qemuMonitorIOThreadInfo *qemuMonitorIOThreadInfoPtr;
struct _qemuMonitorIOThreadInfo {
unsigned int iothread_id;
int thread_id;
};
int qemuMonitorGetIOThreads(qemuMonitorPtr mon,
qemuMonitorIOThreadInfoPtr **iothreads);
typedef struct _qemuMonitorMemoryDeviceInfo qemuMonitorMemoryDeviceInfo;
typedef qemuMonitorMemoryDeviceInfo *qemuMonitorMemoryDeviceInfoPtr;
struct _qemuMonitorMemoryDeviceInfo {
unsigned long long address;
unsigned int slot;
bool hotplugged;
bool hotpluggable;
};
int qemuMonitorGetMemoryDeviceInfo(qemuMonitorPtr mon,
virHashTablePtr *info)
ATTRIBUTE_NONNULL(2);
int qemuMonitorMigrateIncoming(qemuMonitorPtr mon,
const char *uri);
int qemuMonitorMigrateStartPostCopy(qemuMonitorPtr mon);
int qemuMonitorGetRTCTime(qemuMonitorPtr mon,
struct tm *tm);
#endif /* QEMU_MONITOR_H */