libvirt/src/vz/vz_utils.c

657 lines
19 KiB
C
Raw Normal View History

/*
* vz_utils.c: core driver functions for managing
* Parallels Cloud Server hosts
*
* Copyright (C) 2012 Parallels, Inc.
*
* 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/>.
*
*/
#include <config.h>
#include <stdarg.h>
#include "vircommand.h"
#include "virerror.h"
2012-12-12 18:06:53 +00:00
#include "viralloc.h"
2012-12-12 17:53:50 +00:00
#include "virjson.h"
#include "vz_utils.h"
vz: fix race condition when adding domain to domains list Race condition: User calls defineXML to create new instance. The main thread from vzDomainDefineXMLFlags() creates new instance by prlsdkCreateVm. Then this thread calls prlsdkAddDomain to add new domain to domains list. The second thread receives notification from hypervisor that new VM was created. It calls prlsdkHandleVmAddedEvent() and also tries to add new domain to domains list. These two threads call virDomainObjListFindByUUID() from prlsdkAddDomain() and don't find new domain. So they add two domains with the same uuid to domains list. This fix splits logic of prlsdkAddDomain() into two functions. 1. vzNewDomain() creates new empty domain in domains list with the specific uuid. 2. prlsdkLoadDomain() add data from VM to domain object. New algorithm for creating an instance: In vzDomainDefineXMLFlags() we add new domain to domain list by calling vzNewDomain() and only after that we call CreateVm() to create VM. It means that we "reserve" domain object with the specific uuid. After creation of new VM we add info from this VM to reserved domain object by calling prlsdkLoadDomain(). Before this patch prlsdkLoadDomain() worked in 2 different cases: 1. It creates and initializes new domain. Then updates it from sdk handle. 2. It updates existed domain from sdk handle. In this patch we remove code which creates new domain from LoadDomain() and move it to vzNewDomain(). Now prlsdkLoadDomain() only updates domain from skd handle. In notification handler prlsdkHandleVmAddedEvent() we check the existence of a domain and if it doesn't exist we add new domain by calling vzNewDomain() and load info from sdk handle via prlsdkLoadDomain().
2016-02-10 09:39:14 +00:00
#include "vz_sdk.h"
#include "virstring.h"
#include "datatypes.h"
#include "virlog.h"
vz: make vz driver more responsive Current vz driver implementation is not usable when it comes to long runnig operations. Migration or saving a domain blocks all other operations even query ones which are expecteted to be available. This patch addresses this problem. All vz driver API calls fall into next 3 groups: 1. only query domain cache (virDomainObj, vz cache statistic) examples are vzDomainGetState, vzDomainGetXMLDesc etc. 2. use thread shared sdkdom object examples are vzDomainSetMemoryFlags, vzDomainAttachDevice etc. 3. use no thread shared sdkdom object nor domain cache examples are vzDomainSnapshotListNames, vzDomainSnapshotGetXMLDesc etc API calls from group 1 don't need to be changed as they hold domain lock only for short period of time. These calls [1] are easily distinguished. They query domain object thru libvirt common code or query vz sdk statistics handle thru vz sdk sync operations. vzDomainInterfaceStats is the only exception. It uses sdkdom object to convert interface name to its vz sdk stack index which could not be saved in domain cache. Interface statistics is available thru this stack index as a key rather than name. As a result we can have accidental 'not known interface' errors on quering intrerface stats. The reason is that in the process of updating domain configuration we drop all devices and then recreate them again in sdkdom object and domain lock can be dropped meanwhile (to remove networks for existing bridged interfaces and(or) (re)create new ones). We can fix this by changing the way we support bridged interfaces or by reordering operations and changing bridged networks beforehand. Anyway this is better than moving this API call into 2 group and making it an exclusive job. As to API calls from group 2, first thread shared sdkdom object needs to be explained. vz sdk has only one handle for a given domain, thus threads need exclusive access to operate on it. These calls are fixed to drop and reacquire domain lock on any lengthy operations - namely waiting the result of async vz sdk operation. As lock is dropped we need to take extra reference to domain object if it is not taken already as domain object can be deleted from list while lock is dropped. As this operations use thread shared sdkdom object, the simplest way to make calls from group 2 be consistent to each other is to make them mutually exclusive. This is done by taking/releasing job condition thru calling correspondent job routine. This approach makes group 1 and group 2 calls consistent to each other too. Not all calls of group 2 change the domain cache but those that do update it thru prlsdkUpdateDomain which holds the lock thoughout the update. API calls from group [2] are easily distinguished too. They use beginEdit/commit to change domain configuration (vzDomainSetMemoryFlags) or/and update domain cache from sdkdom at the end of operation (vzDomainSuspend). There is a known issue however. Frankly speaking it was introduced by ealier patch '[PATCH 6/9] vz: cleanup loading domain code' from a different series. The patch significantly reduced amount of time when the driver lock is held when creating domain from API call or as a result of domain added event from vz sdk. The problem is these two paths race on using thread shared sdkdom as we don't have libvirt domain object and can not lock on it. However this don't invalidates the patch as we can't use the former approach of preadding domain into the list as we need name at least and name is not given by event. Anyway i'm against adding half baked object into the list. Eventually this race can be fixed by extra measures. As to current situation races with different configurations are unlikely and race when adding domain thru vz driver and simultaneous event from vz sdk is not dangerous as configuration is the same. The last group [3] is API calls that need only sdkdom object to make vz sdk call and don't change thread shared sdkdom object or domain cache in any way. For now these are mostly domain snapshot API calls. The changes are similar to those of group 2 - they add extra reference and drop/reacquire the lock on waiting vz async call result. One can simply take the immutable sdkdom object from the cache and drop the lock for the rest of operations but the chosen approach makes implementation of these API calls somewhat similar to those of from group 2 and thus a bit futureproof. As calls of group 3 don't need vz driver domain/vz sdk cache in any way, they are consistent with respect to API calls from groups 1 and 3. There is another exception. Calls to make-snapshot/revert-to-snapshot/migrate are moved to group 2. That is they are made mutually exclusive. The reason is that libvirt API supports control/query only for one job per domain and these are jobs that are likely to be queried/aborted. Appendix. [1] API calls that only query domain cache. (marked [*] are included for a different reason) .domainLookupByID = vzDomainLookupByID, /* 0.10.0 */ .domainLookupByUUID = vzDomainLookupByUUID, /* 0.10.0 */ .domainLookupByName = vzDomainLookupByName, /* 0.10.0 */ .domainGetOSType = vzDomainGetOSType, /* 0.10.0 */ .domainGetInfo = vzDomainGetInfo, /* 0.10.0 */ .domainGetState = vzDomainGetState, /* 0.10.0 */ .domainGetXMLDesc = vzDomainGetXMLDesc, /* 0.10.0 */ .domainIsPersistent = vzDomainIsPersistent, /* 0.10.0 */ .domainGetAutostart = vzDomainGetAutostart, /* 0.10.0 */ .domainGetVcpus = vzDomainGetVcpus, /* 1.2.6 */ .domainIsActive = vzDomainIsActive, /* 1.2.10 */ .domainIsUpdated = vzDomainIsUpdated, /* 1.2.21 */ .domainGetVcpusFlags = vzDomainGetVcpusFlags, /* 1.2.21 */ .domainGetMaxVcpus = vzDomainGetMaxVcpus, /* 1.2.21 */ .domainHasManagedSaveImage = vzDomainHasManagedSaveImage, /* 1.2.13 */ .domainGetMaxMemory = vzDomainGetMaxMemory, /* 1.2.15 */ .domainBlockStats = vzDomainBlockStats, /* 1.2.17 */ .domainBlockStatsFlags = vzDomainBlockStatsFlags, /* 1.2.17 */ .domainInterfaceStats = vzDomainInterfaceStats, /* 1.2.17 */ [*] .domainMemoryStats = vzDomainMemoryStats, /* 1.2.17 */ .domainMigrateBegin3Params = vzDomainMigrateBegin3Params, /* 1.3.5 */ .domainMigrateConfirm3Params = vzDomainMigrateConfirm3Params, /* 1.3.5 */ [2] API calls that use thread shared sdkdom object (marked [*] are included for a different reason) .domainSuspend = vzDomainSuspend, /* 0.10.0 */ .domainResume = vzDomainResume, /* 0.10.0 */ .domainDestroy = vzDomainDestroy, /* 0.10.0 */ .domainShutdown = vzDomainShutdown, /* 0.10.0 */ .domainCreate = vzDomainCreate, /* 0.10.0 */ .domainCreateWithFlags = vzDomainCreateWithFlags, /* 1.2.10 */ .domainReboot = vzDomainReboot, /* 1.3.0 */ .domainDefineXML = vzDomainDefineXML, /* 0.10.0 */ .domainDefineXMLFlags = vzDomainDefineXMLFlags, /* 1.2.12 */ (update part) .domainUndefine = vzDomainUndefine, /* 1.2.10 */ .domainAttachDevice = vzDomainAttachDevice, /* 1.2.15 */ .domainAttachDeviceFlags = vzDomainAttachDeviceFlags, /* 1.2.15 */ .domainDetachDevice = vzDomainDetachDevice, /* 1.2.15 */ .domainDetachDeviceFlags = vzDomainDetachDeviceFlags, /* 1.2.15 */ .domainSetUserPassword = vzDomainSetUserPassword, /* 1.3.6 */ .domainManagedSave = vzDomainManagedSave, /* 1.2.14 */ .domainSetMemoryFlags = vzDomainSetMemoryFlags, /* 1.3.4 */ .domainSetMemory = vzDomainSetMemory, /* 1.3.4 */ .domainRevertToSnapshot = vzDomainRevertToSnapshot, /* 1.3.5 */ [*] .domainSnapshotCreateXML = vzDomainSnapshotCreateXML, /* 1.3.5 */ [*] .domainMigratePerform3Params = vzDomainMigratePerform3Params, /* 1.3.5 */ [*] .domainUpdateDeviceFlags = vzDomainUpdateDeviceFlags, /* 2.0.0 */ prlsdkHandleVmConfigEvent [3] API calls that do not use thread shared sdkdom object .domainManagedSaveRemove = vzDomainManagedSaveRemove, /* 1.2.14 */ .domainSnapshotNum = vzDomainSnapshotNum, /* 1.3.5 */ .domainSnapshotListNames = vzDomainSnapshotListNames, /* 1.3.5 */ .domainListAllSnapshots = vzDomainListAllSnapshots, /* 1.3.5 */ .domainSnapshotGetXMLDesc = vzDomainSnapshotGetXMLDesc, /* 1.3.5 */ .domainSnapshotNumChildren = vzDomainSnapshotNumChildren, /* 1.3.5 */ .domainSnapshotListChildrenNames = vzDomainSnapshotListChildrenNames, /* 1.3.5 */ .domainSnapshotListAllChildren = vzDomainSnapshotListAllChildren, /* 1.3.5 */ .domainSnapshotLookupByName = vzDomainSnapshotLookupByName, /* 1.3.5 */ .domainHasCurrentSnapshot = vzDomainHasCurrentSnapshot, /* 1.3.5 */ .domainSnapshotGetParent = vzDomainSnapshotGetParent, /* 1.3.5 */ .domainSnapshotCurrent = vzDomainSnapshotCurrent, /* 1.3.5 */ .domainSnapshotIsCurrent = vzDomainSnapshotIsCurrent, /* 1.3.5 */ .domainSnapshotHasMetadata = vzDomainSnapshotHasMetadata, /* 1.3.5 */ .domainSnapshotDelete = vzDomainSnapshotDelete, /* 1.3.5 */ [4] Known issues. 1. accidental errors on getting network statistics 2. race with simultaneous use of thread shared domain object on paths of adding domain thru API and adding domain on vz sdk domain added event.
2016-07-20 15:00:33 +00:00
#include "virtime.h"
#include "virutil.h"
#define VIR_FROM_THIS VIR_FROM_PARALLELS
#define PRLSRVCTL "prlsrvctl"
VIR_LOG_INIT("parallels.utils");
static virDomainDiskBus vz6DiskBuses[] = {VIR_DOMAIN_DISK_BUS_IDE,
VIR_DOMAIN_DISK_BUS_SCSI,
VIR_DOMAIN_DISK_BUS_SATA,
VIR_DOMAIN_DISK_BUS_LAST};
static virDomainDiskBus vz7DiskBuses[] = {VIR_DOMAIN_DISK_BUS_IDE,
VIR_DOMAIN_DISK_BUS_SCSI,
VIR_DOMAIN_DISK_BUS_LAST};
static virDomainControllerType vz6ControllerTypes[] = {VIR_DOMAIN_CONTROLLER_TYPE_SCSI,
VIR_DOMAIN_CONTROLLER_TYPE_IDE,
VIR_DOMAIN_CONTROLLER_TYPE_SATA,
VIR_DOMAIN_CONTROLLER_TYPE_LAST};
static virDomainControllerType vz7ControllerTypes[] = {VIR_DOMAIN_CONTROLLER_TYPE_SCSI,
VIR_DOMAIN_CONTROLLER_TYPE_IDE,
VIR_DOMAIN_CONTROLLER_TYPE_LAST};
/**
* vzDomObjFromDomain:
* @domain: Domain pointer that has to be looked up
*
* This function looks up @domain and returns the appropriate virDomainObjPtr
parallels: add block device statistics to driver Statistics provided through PCS SDK. As we have only async interface in SDK we need to be subscribed to statistics in order to get it. Trivial solution on every stat request to subscribe, wait event and then unsubscribe will lead to significant delays in case of a number of successive requests, as the event will be delivered on next PCS server notify cycle. On the other hand we don't want to keep unnesessary subscribtion. So we take an hibrid solution to subcsribe on first request and then keep a subscription while requests are active. We populate cache of statistics on subscribtion events and use this cache to serve libvirts requests. * Cache details. Cache is just handle to last arrived event, we call this cache as if this handle is valid it is used to serve synchronous statistics requests. We use number of successive events count to detect that user lost interest to statistics. We reset this count to 0 on every request. If more than PARALLELS_STATISTICS_DROP_COUNT successive events arrive we unsubscribe. Special value of -1 of this counter is used to differentiate between subscribed/unsubscribed state to protect from delayed events. Values of PARALLELS_STATISTICS_DROP_COUNT and PARALLELS_STATISTICS_TIMEOUT are just drop-ins, choosen without special consideration. * Thread safety issues Use parallelsDomObjFromDomainRef in parallelsDomainBlockStats as we could wait on domain lock down on stack in prlsdkGetStatsParam and if we won't keep reference we could get dangling pointer on return from wait. Signed-off-by: Nikolay Shirokovskiy <nshirokovskiy@parallels.com>
2015-06-09 07:35:53 +00:00
* that has to be released by calling virDomainObjEndAPI().
*
* Returns the domain object with incremented reference counter which is locked
* on success, NULL otherwise.
*/
virDomainObjPtr
vzDomObjFromDomain(virDomainPtr domain)
parallels: add block device statistics to driver Statistics provided through PCS SDK. As we have only async interface in SDK we need to be subscribed to statistics in order to get it. Trivial solution on every stat request to subscribe, wait event and then unsubscribe will lead to significant delays in case of a number of successive requests, as the event will be delivered on next PCS server notify cycle. On the other hand we don't want to keep unnesessary subscribtion. So we take an hibrid solution to subcsribe on first request and then keep a subscription while requests are active. We populate cache of statistics on subscribtion events and use this cache to serve libvirts requests. * Cache details. Cache is just handle to last arrived event, we call this cache as if this handle is valid it is used to serve synchronous statistics requests. We use number of successive events count to detect that user lost interest to statistics. We reset this count to 0 on every request. If more than PARALLELS_STATISTICS_DROP_COUNT successive events arrive we unsubscribe. Special value of -1 of this counter is used to differentiate between subscribed/unsubscribed state to protect from delayed events. Values of PARALLELS_STATISTICS_DROP_COUNT and PARALLELS_STATISTICS_TIMEOUT are just drop-ins, choosen without special consideration. * Thread safety issues Use parallelsDomObjFromDomainRef in parallelsDomainBlockStats as we could wait on domain lock down on stack in prlsdkGetStatsParam and if we won't keep reference we could get dangling pointer on return from wait. Signed-off-by: Nikolay Shirokovskiy <nshirokovskiy@parallels.com>
2015-06-09 07:35:53 +00:00
{
virDomainObjPtr vm;
vzConnPtr privconn = domain->conn->privateData;
parallels: add block device statistics to driver Statistics provided through PCS SDK. As we have only async interface in SDK we need to be subscribed to statistics in order to get it. Trivial solution on every stat request to subscribe, wait event and then unsubscribe will lead to significant delays in case of a number of successive requests, as the event will be delivered on next PCS server notify cycle. On the other hand we don't want to keep unnesessary subscribtion. So we take an hibrid solution to subcsribe on first request and then keep a subscription while requests are active. We populate cache of statistics on subscribtion events and use this cache to serve libvirts requests. * Cache details. Cache is just handle to last arrived event, we call this cache as if this handle is valid it is used to serve synchronous statistics requests. We use number of successive events count to detect that user lost interest to statistics. We reset this count to 0 on every request. If more than PARALLELS_STATISTICS_DROP_COUNT successive events arrive we unsubscribe. Special value of -1 of this counter is used to differentiate between subscribed/unsubscribed state to protect from delayed events. Values of PARALLELS_STATISTICS_DROP_COUNT and PARALLELS_STATISTICS_TIMEOUT are just drop-ins, choosen without special consideration. * Thread safety issues Use parallelsDomObjFromDomainRef in parallelsDomainBlockStats as we could wait on domain lock down on stack in prlsdkGetStatsParam and if we won't keep reference we could get dangling pointer on return from wait. Signed-off-by: Nikolay Shirokovskiy <nshirokovskiy@parallels.com>
2015-06-09 07:35:53 +00:00
char uuidstr[VIR_UUID_STRING_BUFLEN];
vzDriverPtr driver = privconn->driver;
parallels: add block device statistics to driver Statistics provided through PCS SDK. As we have only async interface in SDK we need to be subscribed to statistics in order to get it. Trivial solution on every stat request to subscribe, wait event and then unsubscribe will lead to significant delays in case of a number of successive requests, as the event will be delivered on next PCS server notify cycle. On the other hand we don't want to keep unnesessary subscribtion. So we take an hibrid solution to subcsribe on first request and then keep a subscription while requests are active. We populate cache of statistics on subscribtion events and use this cache to serve libvirts requests. * Cache details. Cache is just handle to last arrived event, we call this cache as if this handle is valid it is used to serve synchronous statistics requests. We use number of successive events count to detect that user lost interest to statistics. We reset this count to 0 on every request. If more than PARALLELS_STATISTICS_DROP_COUNT successive events arrive we unsubscribe. Special value of -1 of this counter is used to differentiate between subscribed/unsubscribed state to protect from delayed events. Values of PARALLELS_STATISTICS_DROP_COUNT and PARALLELS_STATISTICS_TIMEOUT are just drop-ins, choosen without special consideration. * Thread safety issues Use parallelsDomObjFromDomainRef in parallelsDomainBlockStats as we could wait on domain lock down on stack in prlsdkGetStatsParam and if we won't keep reference we could get dangling pointer on return from wait. Signed-off-by: Nikolay Shirokovskiy <nshirokovskiy@parallels.com>
2015-06-09 07:35:53 +00:00
vm = virDomainObjListFindByUUID(driver->domains, domain->uuid);
parallels: add block device statistics to driver Statistics provided through PCS SDK. As we have only async interface in SDK we need to be subscribed to statistics in order to get it. Trivial solution on every stat request to subscribe, wait event and then unsubscribe will lead to significant delays in case of a number of successive requests, as the event will be delivered on next PCS server notify cycle. On the other hand we don't want to keep unnesessary subscribtion. So we take an hibrid solution to subcsribe on first request and then keep a subscription while requests are active. We populate cache of statistics on subscribtion events and use this cache to serve libvirts requests. * Cache details. Cache is just handle to last arrived event, we call this cache as if this handle is valid it is used to serve synchronous statistics requests. We use number of successive events count to detect that user lost interest to statistics. We reset this count to 0 on every request. If more than PARALLELS_STATISTICS_DROP_COUNT successive events arrive we unsubscribe. Special value of -1 of this counter is used to differentiate between subscribed/unsubscribed state to protect from delayed events. Values of PARALLELS_STATISTICS_DROP_COUNT and PARALLELS_STATISTICS_TIMEOUT are just drop-ins, choosen without special consideration. * Thread safety issues Use parallelsDomObjFromDomainRef in parallelsDomainBlockStats as we could wait on domain lock down on stack in prlsdkGetStatsParam and if we won't keep reference we could get dangling pointer on return from wait. Signed-off-by: Nikolay Shirokovskiy <nshirokovskiy@parallels.com>
2015-06-09 07:35:53 +00:00
if (!vm) {
virUUIDFormat(domain->uuid, uuidstr);
virReportError(VIR_ERR_NO_DOMAIN,
_("no domain with matching uuid '%s' (%s)"),
uuidstr, domain->name);
return NULL;
}
return vm;
}
static int
vzDoCmdRun(char **outbuf, const char *binary, va_list list)
{
virCommandPtr cmd = virCommandNewVAList(binary, list);
int ret = -1;
if (outbuf)
virCommandSetOutputBuffer(cmd, outbuf);
if (virCommandRun(cmd, NULL) < 0)
goto cleanup;
ret = 0;
cleanup:
virCommandFree(cmd);
if (ret && outbuf)
VIR_FREE(*outbuf);
return ret;
}
/*
* Run command and return its output, pointer to
* buffer or NULL in case of error. Caller os responsible
* for freeing the buffer.
*/
char *
vzGetOutput(const char *binary, ...)
{
char *outbuf;
va_list list;
int ret;
va_start(list, binary);
ret = vzDoCmdRun(&outbuf, binary, list);
va_end(list);
if (ret)
return NULL;
return outbuf;
}
vz: fix race condition when adding domain to domains list Race condition: User calls defineXML to create new instance. The main thread from vzDomainDefineXMLFlags() creates new instance by prlsdkCreateVm. Then this thread calls prlsdkAddDomain to add new domain to domains list. The second thread receives notification from hypervisor that new VM was created. It calls prlsdkHandleVmAddedEvent() and also tries to add new domain to domains list. These two threads call virDomainObjListFindByUUID() from prlsdkAddDomain() and don't find new domain. So they add two domains with the same uuid to domains list. This fix splits logic of prlsdkAddDomain() into two functions. 1. vzNewDomain() creates new empty domain in domains list with the specific uuid. 2. prlsdkLoadDomain() add data from VM to domain object. New algorithm for creating an instance: In vzDomainDefineXMLFlags() we add new domain to domain list by calling vzNewDomain() and only after that we call CreateVm() to create VM. It means that we "reserve" domain object with the specific uuid. After creation of new VM we add info from this VM to reserved domain object by calling prlsdkLoadDomain(). Before this patch prlsdkLoadDomain() worked in 2 different cases: 1. It creates and initializes new domain. Then updates it from sdk handle. 2. It updates existed domain from sdk handle. In this patch we remove code which creates new domain from LoadDomain() and move it to vzNewDomain(). Now prlsdkLoadDomain() only updates domain from skd handle. In notification handler prlsdkHandleVmAddedEvent() we check the existence of a domain and if it doesn't exist we add new domain by calling vzNewDomain() and load info from sdk handle via prlsdkLoadDomain().
2016-02-10 09:39:14 +00:00
static void
vzInitCaps(unsigned long vzVersion, vzCapabilitiesPtr vzCaps)
{
if (vzVersion < VIRTUOZZO_VER_7) {
vzCaps->ctDiskFormat = VIR_STORAGE_FILE_PLOOP;
vzCaps->vmDiskFormat = VIR_STORAGE_FILE_PLOOP;
vzCaps->diskBuses = vz6DiskBuses;
vzCaps->controllerTypes = vz6ControllerTypes;
vzCaps->scsiControllerModel = VIR_DOMAIN_CONTROLLER_MODEL_SCSI_BUSLOGIC;
} else {
vzCaps->ctDiskFormat = VIR_STORAGE_FILE_PLOOP;
vzCaps->vmDiskFormat = VIR_STORAGE_FILE_QCOW2;
vzCaps->diskBuses = vz7DiskBuses;
vzCaps->controllerTypes = vz7ControllerTypes;
vzCaps->scsiControllerModel = VIR_DOMAIN_CONTROLLER_MODEL_SCSI_VIRTIO_SCSI;
}
}
int
vzInitVersion(vzDriverPtr driver)
{
char *output, *sVer, *tmp;
const char *searchStr = "prlsrvctl version ";
int ret = -1;
output = vzGetOutput(PRLSRVCTL, "--help", NULL);
if (!output) {
vzParseError();
goto cleanup;
}
if (!(sVer = strstr(output, searchStr))) {
vzParseError();
goto cleanup;
}
sVer = sVer + strlen(searchStr);
/* parallels server has versions number like 6.0.17977.782218 or 7.0.0,
* In libvirt we handle only first two numbers. */
if (!(tmp = strchr(sVer, '.'))) {
vzParseError();
goto cleanup;
}
if (!(tmp = strchr(tmp + 1, '.'))) {
vzParseError();
goto cleanup;
}
tmp[0] = '\0';
if (virParseVersionString(sVer, &(driver->vzVersion), true) < 0) {
vzParseError();
goto cleanup;
}
vzInitCaps(driver->vzVersion, &driver->vzCaps);
ret = 0;
cleanup:
VIR_FREE(output);
return ret;
}
static int
vzCheckDiskAddressDriveUnsupportedParams(virDomainDiskDefPtr disk)
{
virDomainDeviceDriveAddressPtr drive = &disk->info.addr.drive;
int devIdx, busIdx;
if (drive->controller > 0) {
/* We have only one controller of each type */
virReportError(VIR_ERR_CONFIG_UNSUPPORTED,
_("Invalid drive address of disk %s, vz driver "
"supports only one controller."), disk->dst);
return -1;
}
if (drive->target > 0) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED,
_("Invalid drive address of disk %s, vz driver "
"supports only target 0."), disk->dst);
return -1;
}
switch (disk->bus) {
case VIR_DOMAIN_DISK_BUS_IDE:
if (drive->unit > 1) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED,
_("Invalid drive address of disk %s, vz driver "
"supports only units 0-1 for IDE bus."),
disk->dst);
return -1;
}
break;
case VIR_DOMAIN_DISK_BUS_SCSI:
case VIR_DOMAIN_DISK_BUS_SATA:
if (drive->bus > 0) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED,
_("Invalid drive address of disk %s, vz driver "
"supports only bus 0 for SATA and SCSI bus."),
disk->dst);
return -1;
}
break;
default:
virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
_("Specified disk bus is not supported by vz driver."));
return -1;
}
if (virDiskNameToBusDeviceIndex(disk, &busIdx, &devIdx) < 0) {
virReportError(VIR_ERR_INTERNAL_ERROR,
_("cannot convert disk '%s' to bus/device index"),
disk->dst);
return -1;
}
if (busIdx != drive->bus || devIdx != drive->unit) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED,
_("Invalid drive address of disk %s, vz driver "
"does not support non default name mappings."),
disk->dst);
return -1;
}
return 0;
}
static int
vzCheckDiskUnsupportedParams(virDomainDiskDefPtr disk)
{
if (disk->device != VIR_DOMAIN_DISK_DEVICE_DISK &&
disk->device != VIR_DOMAIN_DISK_DEVICE_CDROM) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
_("Only hard disks and cdroms are supported "
"by vz driver."));
return -1;
}
if (disk->blockio.logical_block_size ||
disk->blockio.physical_block_size) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
_("Setting disk block sizes is not "
"supported by vz driver."));
return -1;
}
if (disk->blkdeviotune.total_bytes_sec ||
disk->blkdeviotune.read_bytes_sec ||
disk->blkdeviotune.write_bytes_sec ||
disk->blkdeviotune.total_iops_sec ||
disk->blkdeviotune.read_iops_sec ||
disk->blkdeviotune.write_iops_sec) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
_("Setting disk io limits is not "
"supported by vz driver yet."));
return -1;
}
if (disk->serial && disk->device != VIR_DOMAIN_DISK_DEVICE_DISK) {
VIR_INFO("%s", _("Setting disk serial number is "
"supported only for disk devices."));
}
if (disk->wwn) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
_("Setting disk wwn id is not "
"supported by vz driver."));
return -1;
}
if (disk->vendor) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
_("Setting disk vendor is not "
"supported by vz driver."));
return -1;
}
if (disk->product) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
_("Setting disk product id is not "
"supported by vz driver."));
return -1;
}
if (disk->error_policy != VIR_DOMAIN_DISK_ERROR_POLICY_DEFAULT) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
_("Setting disk error policy is not "
"supported by vz driver."));
return -1;
}
if (disk->iomode != VIR_DOMAIN_DISK_IO_DEFAULT &&
disk->iomode != VIR_DOMAIN_DISK_IO_NATIVE) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
_("Only native iomode is "
"supported by vz driver."));
return -1;
}
if (disk->copy_on_read) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
_("Disk copy_on_read is not "
"supported by vz driver."));
return -1;
}
if (disk->startupPolicy != VIR_DOMAIN_STARTUP_POLICY_DEFAULT) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
_("Setting up disk startup policy is not "
"supported by vz driver."));
return -1;
}
if (disk->transient) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
_("Transient disks are not "
"supported by vz driver."));
return -1;
}
if (disk->discard) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
_("Setting up disk discard parameter is not "
"supported by vz driver."));
return -1;
}
if (disk->iothread) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
_("Setting up disk io thread # is not "
"supported by vz driver."));
return -1;
}
if (disk->src->type != VIR_STORAGE_TYPE_FILE &&
disk->src->type != VIR_STORAGE_TYPE_BLOCK) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
_("Only disk and block storage types are "
"supported by vz driver."));
return -1;
}
if (vzCheckDiskAddressDriveUnsupportedParams(disk) < 0)
return -1;
return 0;
}
int
vzCheckUnsupportedDisk(const virDomainDef *def,
virDomainDiskDefPtr disk,
vzCapabilitiesPtr vzCaps)
{
size_t i;
virStorageFileFormat diskFormat;
if (vzCheckDiskUnsupportedParams(disk) < 0)
return -1;
if (disk->src->type == VIR_STORAGE_TYPE_FILE) {
if (disk->device == VIR_DOMAIN_DISK_DEVICE_DISK) {
if (IS_CT(def))
diskFormat = vzCaps->ctDiskFormat;
else
diskFormat = vzCaps->vmDiskFormat;
} else {
diskFormat = VIR_STORAGE_FILE_RAW;
}
} else {
diskFormat = VIR_STORAGE_FILE_RAW;
}
if (virDomainDiskGetFormat(disk) != VIR_STORAGE_FILE_NONE &&
virDomainDiskGetFormat(disk) != diskFormat) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED,
_("Unsupported format of disk %s"),
disk->src->path);
return -1;
}
for (i = 0; vzCaps->diskBuses[i] != VIR_DOMAIN_DISK_BUS_LAST; i++) {
if (disk->bus == vzCaps->diskBuses[i])
break;
}
if (vzCaps->diskBuses[i] == VIR_DOMAIN_DISK_BUS_LAST) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED,
_("Unsupported disk bus type %s"),
virDomainDiskBusTypeToString(disk->bus));
return -1;
}
return 0;
}
int
vzCheckUnsupportedControllers(const virDomainDef *def, vzCapabilitiesPtr vzCaps)
{
size_t i, j;
virDomainControllerDefPtr controller;
for (i = 0; i < def->ncontrollers; i++) {
controller = def->controllers[i];
for (j = 0; vzCaps->controllerTypes[j] != VIR_DOMAIN_CONTROLLER_TYPE_LAST; j++) {
if (controller->type == vzCaps->controllerTypes[j])
break;
}
if (vzCaps->controllerTypes[j] == VIR_DOMAIN_CONTROLLER_TYPE_LAST) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED,
_("Unsupported controller type %s"),
virDomainControllerTypeToString(controller->type));
return -1;
}
if (controller->type == VIR_DOMAIN_CONTROLLER_TYPE_SCSI &&
controller->model != -1 &&
controller->model != VIR_DOMAIN_CONTROLLER_MODEL_SCSI_AUTO &&
controller->model != vzCaps->scsiControllerModel) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED,
_("Unsupported SCSI controller model %s"),
virDomainControllerModelSCSITypeToString(controller->model));
return -1;
}
}
return 0;
}
int vzGetDefaultSCSIModel(vzDriverPtr driver,
PRL_CLUSTERED_DEVICE_SUBTYPE *scsiModel)
{
switch ((int)driver->vzCaps.scsiControllerModel) {
case VIR_DOMAIN_CONTROLLER_MODEL_SCSI_VIRTIO_SCSI:
*scsiModel = PCD_VIRTIO_SCSI;
break;
case VIR_DOMAIN_CONTROLLER_MODEL_SCSI_BUSLOGIC:
*scsiModel = PCD_BUSLOGIC;
break;
default:
virReportError(VIR_ERR_INTERNAL_ERROR,
_("Unknown SCSI controller model %s"),
virDomainControllerModelSCSITypeToString(
driver->vzCaps.scsiControllerModel));
return -1;
}
return 0;
}
int vzCheckUnsupportedGraphics(virDomainGraphicsDefPtr gr)
{
if (gr->type != VIR_DOMAIN_GRAPHICS_TYPE_VNC) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
_("vz driver supports only "
"VNC graphics."));
return -1;
}
if (gr->data.vnc.websocket != 0) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
_("vz driver doesn't support "
"websockets for VNC graphics."));
return -1;
}
if (gr->data.vnc.keymap != 0 &&
STRNEQ(gr->data.vnc.keymap, "en-us")) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
_("vz driver supports only "
"\"en-us\" keymap for VNC graphics."));
return -1;
}
if (gr->data.vnc.sharePolicy == VIR_DOMAIN_GRAPHICS_VNC_SHARE_ALLOW_EXCLUSIVE) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
_("vz driver doesn't support "
"exclusive share policy for VNC graphics."));
return -1;
}
if (gr->data.vnc.auth.connected == VIR_DOMAIN_GRAPHICS_AUTH_CONNECTED_FAIL ||
gr->data.vnc.auth.connected == VIR_DOMAIN_GRAPHICS_AUTH_CONNECTED_KEEP) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
_("vz driver doesn't support "
"given action in case of password change."));
return -1;
}
if (gr->data.vnc.auth.expires) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
_("vz driver doesn't support "
"setting password expire time."));
return -1;
}
if (gr->nListens > 1) {
virReportError(VIR_ERR_INVALID_ARG, "%s",
_("vz driver doesn't support more than "
"one listening VNC server per domain"));
return -1;
}
if (gr->nListens == 1 &&
gr->listens[0].type != VIR_DOMAIN_GRAPHICS_LISTEN_TYPE_ADDRESS) {
virReportError(VIR_ERR_INVALID_ARG, "%s",
_("vz driver supports only address-based VNC listening"));
return -1;
}
return 0;
}
void*
vzDomObjAlloc(void *opaque G_GNUC_UNUSED)
{
vzDomObjPtr pdom = NULL;
if (VIR_ALLOC(pdom) < 0)
return NULL;
if (virCondInit(&pdom->job.cond) < 0)
vz: make vz driver more responsive Current vz driver implementation is not usable when it comes to long runnig operations. Migration or saving a domain blocks all other operations even query ones which are expecteted to be available. This patch addresses this problem. All vz driver API calls fall into next 3 groups: 1. only query domain cache (virDomainObj, vz cache statistic) examples are vzDomainGetState, vzDomainGetXMLDesc etc. 2. use thread shared sdkdom object examples are vzDomainSetMemoryFlags, vzDomainAttachDevice etc. 3. use no thread shared sdkdom object nor domain cache examples are vzDomainSnapshotListNames, vzDomainSnapshotGetXMLDesc etc API calls from group 1 don't need to be changed as they hold domain lock only for short period of time. These calls [1] are easily distinguished. They query domain object thru libvirt common code or query vz sdk statistics handle thru vz sdk sync operations. vzDomainInterfaceStats is the only exception. It uses sdkdom object to convert interface name to its vz sdk stack index which could not be saved in domain cache. Interface statistics is available thru this stack index as a key rather than name. As a result we can have accidental 'not known interface' errors on quering intrerface stats. The reason is that in the process of updating domain configuration we drop all devices and then recreate them again in sdkdom object and domain lock can be dropped meanwhile (to remove networks for existing bridged interfaces and(or) (re)create new ones). We can fix this by changing the way we support bridged interfaces or by reordering operations and changing bridged networks beforehand. Anyway this is better than moving this API call into 2 group and making it an exclusive job. As to API calls from group 2, first thread shared sdkdom object needs to be explained. vz sdk has only one handle for a given domain, thus threads need exclusive access to operate on it. These calls are fixed to drop and reacquire domain lock on any lengthy operations - namely waiting the result of async vz sdk operation. As lock is dropped we need to take extra reference to domain object if it is not taken already as domain object can be deleted from list while lock is dropped. As this operations use thread shared sdkdom object, the simplest way to make calls from group 2 be consistent to each other is to make them mutually exclusive. This is done by taking/releasing job condition thru calling correspondent job routine. This approach makes group 1 and group 2 calls consistent to each other too. Not all calls of group 2 change the domain cache but those that do update it thru prlsdkUpdateDomain which holds the lock thoughout the update. API calls from group [2] are easily distinguished too. They use beginEdit/commit to change domain configuration (vzDomainSetMemoryFlags) or/and update domain cache from sdkdom at the end of operation (vzDomainSuspend). There is a known issue however. Frankly speaking it was introduced by ealier patch '[PATCH 6/9] vz: cleanup loading domain code' from a different series. The patch significantly reduced amount of time when the driver lock is held when creating domain from API call or as a result of domain added event from vz sdk. The problem is these two paths race on using thread shared sdkdom as we don't have libvirt domain object and can not lock on it. However this don't invalidates the patch as we can't use the former approach of preadding domain into the list as we need name at least and name is not given by event. Anyway i'm against adding half baked object into the list. Eventually this race can be fixed by extra measures. As to current situation races with different configurations are unlikely and race when adding domain thru vz driver and simultaneous event from vz sdk is not dangerous as configuration is the same. The last group [3] is API calls that need only sdkdom object to make vz sdk call and don't change thread shared sdkdom object or domain cache in any way. For now these are mostly domain snapshot API calls. The changes are similar to those of group 2 - they add extra reference and drop/reacquire the lock on waiting vz async call result. One can simply take the immutable sdkdom object from the cache and drop the lock for the rest of operations but the chosen approach makes implementation of these API calls somewhat similar to those of from group 2 and thus a bit futureproof. As calls of group 3 don't need vz driver domain/vz sdk cache in any way, they are consistent with respect to API calls from groups 1 and 3. There is another exception. Calls to make-snapshot/revert-to-snapshot/migrate are moved to group 2. That is they are made mutually exclusive. The reason is that libvirt API supports control/query only for one job per domain and these are jobs that are likely to be queried/aborted. Appendix. [1] API calls that only query domain cache. (marked [*] are included for a different reason) .domainLookupByID = vzDomainLookupByID, /* 0.10.0 */ .domainLookupByUUID = vzDomainLookupByUUID, /* 0.10.0 */ .domainLookupByName = vzDomainLookupByName, /* 0.10.0 */ .domainGetOSType = vzDomainGetOSType, /* 0.10.0 */ .domainGetInfo = vzDomainGetInfo, /* 0.10.0 */ .domainGetState = vzDomainGetState, /* 0.10.0 */ .domainGetXMLDesc = vzDomainGetXMLDesc, /* 0.10.0 */ .domainIsPersistent = vzDomainIsPersistent, /* 0.10.0 */ .domainGetAutostart = vzDomainGetAutostart, /* 0.10.0 */ .domainGetVcpus = vzDomainGetVcpus, /* 1.2.6 */ .domainIsActive = vzDomainIsActive, /* 1.2.10 */ .domainIsUpdated = vzDomainIsUpdated, /* 1.2.21 */ .domainGetVcpusFlags = vzDomainGetVcpusFlags, /* 1.2.21 */ .domainGetMaxVcpus = vzDomainGetMaxVcpus, /* 1.2.21 */ .domainHasManagedSaveImage = vzDomainHasManagedSaveImage, /* 1.2.13 */ .domainGetMaxMemory = vzDomainGetMaxMemory, /* 1.2.15 */ .domainBlockStats = vzDomainBlockStats, /* 1.2.17 */ .domainBlockStatsFlags = vzDomainBlockStatsFlags, /* 1.2.17 */ .domainInterfaceStats = vzDomainInterfaceStats, /* 1.2.17 */ [*] .domainMemoryStats = vzDomainMemoryStats, /* 1.2.17 */ .domainMigrateBegin3Params = vzDomainMigrateBegin3Params, /* 1.3.5 */ .domainMigrateConfirm3Params = vzDomainMigrateConfirm3Params, /* 1.3.5 */ [2] API calls that use thread shared sdkdom object (marked [*] are included for a different reason) .domainSuspend = vzDomainSuspend, /* 0.10.0 */ .domainResume = vzDomainResume, /* 0.10.0 */ .domainDestroy = vzDomainDestroy, /* 0.10.0 */ .domainShutdown = vzDomainShutdown, /* 0.10.0 */ .domainCreate = vzDomainCreate, /* 0.10.0 */ .domainCreateWithFlags = vzDomainCreateWithFlags, /* 1.2.10 */ .domainReboot = vzDomainReboot, /* 1.3.0 */ .domainDefineXML = vzDomainDefineXML, /* 0.10.0 */ .domainDefineXMLFlags = vzDomainDefineXMLFlags, /* 1.2.12 */ (update part) .domainUndefine = vzDomainUndefine, /* 1.2.10 */ .domainAttachDevice = vzDomainAttachDevice, /* 1.2.15 */ .domainAttachDeviceFlags = vzDomainAttachDeviceFlags, /* 1.2.15 */ .domainDetachDevice = vzDomainDetachDevice, /* 1.2.15 */ .domainDetachDeviceFlags = vzDomainDetachDeviceFlags, /* 1.2.15 */ .domainSetUserPassword = vzDomainSetUserPassword, /* 1.3.6 */ .domainManagedSave = vzDomainManagedSave, /* 1.2.14 */ .domainSetMemoryFlags = vzDomainSetMemoryFlags, /* 1.3.4 */ .domainSetMemory = vzDomainSetMemory, /* 1.3.4 */ .domainRevertToSnapshot = vzDomainRevertToSnapshot, /* 1.3.5 */ [*] .domainSnapshotCreateXML = vzDomainSnapshotCreateXML, /* 1.3.5 */ [*] .domainMigratePerform3Params = vzDomainMigratePerform3Params, /* 1.3.5 */ [*] .domainUpdateDeviceFlags = vzDomainUpdateDeviceFlags, /* 2.0.0 */ prlsdkHandleVmConfigEvent [3] API calls that do not use thread shared sdkdom object .domainManagedSaveRemove = vzDomainManagedSaveRemove, /* 1.2.14 */ .domainSnapshotNum = vzDomainSnapshotNum, /* 1.3.5 */ .domainSnapshotListNames = vzDomainSnapshotListNames, /* 1.3.5 */ .domainListAllSnapshots = vzDomainListAllSnapshots, /* 1.3.5 */ .domainSnapshotGetXMLDesc = vzDomainSnapshotGetXMLDesc, /* 1.3.5 */ .domainSnapshotNumChildren = vzDomainSnapshotNumChildren, /* 1.3.5 */ .domainSnapshotListChildrenNames = vzDomainSnapshotListChildrenNames, /* 1.3.5 */ .domainSnapshotListAllChildren = vzDomainSnapshotListAllChildren, /* 1.3.5 */ .domainSnapshotLookupByName = vzDomainSnapshotLookupByName, /* 1.3.5 */ .domainHasCurrentSnapshot = vzDomainHasCurrentSnapshot, /* 1.3.5 */ .domainSnapshotGetParent = vzDomainSnapshotGetParent, /* 1.3.5 */ .domainSnapshotCurrent = vzDomainSnapshotCurrent, /* 1.3.5 */ .domainSnapshotIsCurrent = vzDomainSnapshotIsCurrent, /* 1.3.5 */ .domainSnapshotHasMetadata = vzDomainSnapshotHasMetadata, /* 1.3.5 */ .domainSnapshotDelete = vzDomainSnapshotDelete, /* 1.3.5 */ [4] Known issues. 1. accidental errors on getting network statistics 2. race with simultaneous use of thread shared domain object on paths of adding domain thru API and adding domain on vz sdk domain added event.
2016-07-20 15:00:33 +00:00
goto error;
pdom->stats = PRL_INVALID_HANDLE;
return pdom;
vz: make vz driver more responsive Current vz driver implementation is not usable when it comes to long runnig operations. Migration or saving a domain blocks all other operations even query ones which are expecteted to be available. This patch addresses this problem. All vz driver API calls fall into next 3 groups: 1. only query domain cache (virDomainObj, vz cache statistic) examples are vzDomainGetState, vzDomainGetXMLDesc etc. 2. use thread shared sdkdom object examples are vzDomainSetMemoryFlags, vzDomainAttachDevice etc. 3. use no thread shared sdkdom object nor domain cache examples are vzDomainSnapshotListNames, vzDomainSnapshotGetXMLDesc etc API calls from group 1 don't need to be changed as they hold domain lock only for short period of time. These calls [1] are easily distinguished. They query domain object thru libvirt common code or query vz sdk statistics handle thru vz sdk sync operations. vzDomainInterfaceStats is the only exception. It uses sdkdom object to convert interface name to its vz sdk stack index which could not be saved in domain cache. Interface statistics is available thru this stack index as a key rather than name. As a result we can have accidental 'not known interface' errors on quering intrerface stats. The reason is that in the process of updating domain configuration we drop all devices and then recreate them again in sdkdom object and domain lock can be dropped meanwhile (to remove networks for existing bridged interfaces and(or) (re)create new ones). We can fix this by changing the way we support bridged interfaces or by reordering operations and changing bridged networks beforehand. Anyway this is better than moving this API call into 2 group and making it an exclusive job. As to API calls from group 2, first thread shared sdkdom object needs to be explained. vz sdk has only one handle for a given domain, thus threads need exclusive access to operate on it. These calls are fixed to drop and reacquire domain lock on any lengthy operations - namely waiting the result of async vz sdk operation. As lock is dropped we need to take extra reference to domain object if it is not taken already as domain object can be deleted from list while lock is dropped. As this operations use thread shared sdkdom object, the simplest way to make calls from group 2 be consistent to each other is to make them mutually exclusive. This is done by taking/releasing job condition thru calling correspondent job routine. This approach makes group 1 and group 2 calls consistent to each other too. Not all calls of group 2 change the domain cache but those that do update it thru prlsdkUpdateDomain which holds the lock thoughout the update. API calls from group [2] are easily distinguished too. They use beginEdit/commit to change domain configuration (vzDomainSetMemoryFlags) or/and update domain cache from sdkdom at the end of operation (vzDomainSuspend). There is a known issue however. Frankly speaking it was introduced by ealier patch '[PATCH 6/9] vz: cleanup loading domain code' from a different series. The patch significantly reduced amount of time when the driver lock is held when creating domain from API call or as a result of domain added event from vz sdk. The problem is these two paths race on using thread shared sdkdom as we don't have libvirt domain object and can not lock on it. However this don't invalidates the patch as we can't use the former approach of preadding domain into the list as we need name at least and name is not given by event. Anyway i'm against adding half baked object into the list. Eventually this race can be fixed by extra measures. As to current situation races with different configurations are unlikely and race when adding domain thru vz driver and simultaneous event from vz sdk is not dangerous as configuration is the same. The last group [3] is API calls that need only sdkdom object to make vz sdk call and don't change thread shared sdkdom object or domain cache in any way. For now these are mostly domain snapshot API calls. The changes are similar to those of group 2 - they add extra reference and drop/reacquire the lock on waiting vz async call result. One can simply take the immutable sdkdom object from the cache and drop the lock for the rest of operations but the chosen approach makes implementation of these API calls somewhat similar to those of from group 2 and thus a bit futureproof. As calls of group 3 don't need vz driver domain/vz sdk cache in any way, they are consistent with respect to API calls from groups 1 and 3. There is another exception. Calls to make-snapshot/revert-to-snapshot/migrate are moved to group 2. That is they are made mutually exclusive. The reason is that libvirt API supports control/query only for one job per domain and these are jobs that are likely to be queried/aborted. Appendix. [1] API calls that only query domain cache. (marked [*] are included for a different reason) .domainLookupByID = vzDomainLookupByID, /* 0.10.0 */ .domainLookupByUUID = vzDomainLookupByUUID, /* 0.10.0 */ .domainLookupByName = vzDomainLookupByName, /* 0.10.0 */ .domainGetOSType = vzDomainGetOSType, /* 0.10.0 */ .domainGetInfo = vzDomainGetInfo, /* 0.10.0 */ .domainGetState = vzDomainGetState, /* 0.10.0 */ .domainGetXMLDesc = vzDomainGetXMLDesc, /* 0.10.0 */ .domainIsPersistent = vzDomainIsPersistent, /* 0.10.0 */ .domainGetAutostart = vzDomainGetAutostart, /* 0.10.0 */ .domainGetVcpus = vzDomainGetVcpus, /* 1.2.6 */ .domainIsActive = vzDomainIsActive, /* 1.2.10 */ .domainIsUpdated = vzDomainIsUpdated, /* 1.2.21 */ .domainGetVcpusFlags = vzDomainGetVcpusFlags, /* 1.2.21 */ .domainGetMaxVcpus = vzDomainGetMaxVcpus, /* 1.2.21 */ .domainHasManagedSaveImage = vzDomainHasManagedSaveImage, /* 1.2.13 */ .domainGetMaxMemory = vzDomainGetMaxMemory, /* 1.2.15 */ .domainBlockStats = vzDomainBlockStats, /* 1.2.17 */ .domainBlockStatsFlags = vzDomainBlockStatsFlags, /* 1.2.17 */ .domainInterfaceStats = vzDomainInterfaceStats, /* 1.2.17 */ [*] .domainMemoryStats = vzDomainMemoryStats, /* 1.2.17 */ .domainMigrateBegin3Params = vzDomainMigrateBegin3Params, /* 1.3.5 */ .domainMigrateConfirm3Params = vzDomainMigrateConfirm3Params, /* 1.3.5 */ [2] API calls that use thread shared sdkdom object (marked [*] are included for a different reason) .domainSuspend = vzDomainSuspend, /* 0.10.0 */ .domainResume = vzDomainResume, /* 0.10.0 */ .domainDestroy = vzDomainDestroy, /* 0.10.0 */ .domainShutdown = vzDomainShutdown, /* 0.10.0 */ .domainCreate = vzDomainCreate, /* 0.10.0 */ .domainCreateWithFlags = vzDomainCreateWithFlags, /* 1.2.10 */ .domainReboot = vzDomainReboot, /* 1.3.0 */ .domainDefineXML = vzDomainDefineXML, /* 0.10.0 */ .domainDefineXMLFlags = vzDomainDefineXMLFlags, /* 1.2.12 */ (update part) .domainUndefine = vzDomainUndefine, /* 1.2.10 */ .domainAttachDevice = vzDomainAttachDevice, /* 1.2.15 */ .domainAttachDeviceFlags = vzDomainAttachDeviceFlags, /* 1.2.15 */ .domainDetachDevice = vzDomainDetachDevice, /* 1.2.15 */ .domainDetachDeviceFlags = vzDomainDetachDeviceFlags, /* 1.2.15 */ .domainSetUserPassword = vzDomainSetUserPassword, /* 1.3.6 */ .domainManagedSave = vzDomainManagedSave, /* 1.2.14 */ .domainSetMemoryFlags = vzDomainSetMemoryFlags, /* 1.3.4 */ .domainSetMemory = vzDomainSetMemory, /* 1.3.4 */ .domainRevertToSnapshot = vzDomainRevertToSnapshot, /* 1.3.5 */ [*] .domainSnapshotCreateXML = vzDomainSnapshotCreateXML, /* 1.3.5 */ [*] .domainMigratePerform3Params = vzDomainMigratePerform3Params, /* 1.3.5 */ [*] .domainUpdateDeviceFlags = vzDomainUpdateDeviceFlags, /* 2.0.0 */ prlsdkHandleVmConfigEvent [3] API calls that do not use thread shared sdkdom object .domainManagedSaveRemove = vzDomainManagedSaveRemove, /* 1.2.14 */ .domainSnapshotNum = vzDomainSnapshotNum, /* 1.3.5 */ .domainSnapshotListNames = vzDomainSnapshotListNames, /* 1.3.5 */ .domainListAllSnapshots = vzDomainListAllSnapshots, /* 1.3.5 */ .domainSnapshotGetXMLDesc = vzDomainSnapshotGetXMLDesc, /* 1.3.5 */ .domainSnapshotNumChildren = vzDomainSnapshotNumChildren, /* 1.3.5 */ .domainSnapshotListChildrenNames = vzDomainSnapshotListChildrenNames, /* 1.3.5 */ .domainSnapshotListAllChildren = vzDomainSnapshotListAllChildren, /* 1.3.5 */ .domainSnapshotLookupByName = vzDomainSnapshotLookupByName, /* 1.3.5 */ .domainHasCurrentSnapshot = vzDomainHasCurrentSnapshot, /* 1.3.5 */ .domainSnapshotGetParent = vzDomainSnapshotGetParent, /* 1.3.5 */ .domainSnapshotCurrent = vzDomainSnapshotCurrent, /* 1.3.5 */ .domainSnapshotIsCurrent = vzDomainSnapshotIsCurrent, /* 1.3.5 */ .domainSnapshotHasMetadata = vzDomainSnapshotHasMetadata, /* 1.3.5 */ .domainSnapshotDelete = vzDomainSnapshotDelete, /* 1.3.5 */ [4] Known issues. 1. accidental errors on getting network statistics 2. race with simultaneous use of thread shared domain object on paths of adding domain thru API and adding domain on vz sdk domain added event.
2016-07-20 15:00:33 +00:00
error:
VIR_FREE(pdom);
return NULL;
}
void
vzDomObjFree(void* p)
{
vzDomObjPtr pdom = p;
if (!pdom)
return;
PrlHandle_Free(pdom->sdkdom);
PrlHandle_Free(pdom->stats);
virCondDestroy(&pdom->job.cond);
VIR_FREE(pdom);
};
vz: make vz driver more responsive Current vz driver implementation is not usable when it comes to long runnig operations. Migration or saving a domain blocks all other operations even query ones which are expecteted to be available. This patch addresses this problem. All vz driver API calls fall into next 3 groups: 1. only query domain cache (virDomainObj, vz cache statistic) examples are vzDomainGetState, vzDomainGetXMLDesc etc. 2. use thread shared sdkdom object examples are vzDomainSetMemoryFlags, vzDomainAttachDevice etc. 3. use no thread shared sdkdom object nor domain cache examples are vzDomainSnapshotListNames, vzDomainSnapshotGetXMLDesc etc API calls from group 1 don't need to be changed as they hold domain lock only for short period of time. These calls [1] are easily distinguished. They query domain object thru libvirt common code or query vz sdk statistics handle thru vz sdk sync operations. vzDomainInterfaceStats is the only exception. It uses sdkdom object to convert interface name to its vz sdk stack index which could not be saved in domain cache. Interface statistics is available thru this stack index as a key rather than name. As a result we can have accidental 'not known interface' errors on quering intrerface stats. The reason is that in the process of updating domain configuration we drop all devices and then recreate them again in sdkdom object and domain lock can be dropped meanwhile (to remove networks for existing bridged interfaces and(or) (re)create new ones). We can fix this by changing the way we support bridged interfaces or by reordering operations and changing bridged networks beforehand. Anyway this is better than moving this API call into 2 group and making it an exclusive job. As to API calls from group 2, first thread shared sdkdom object needs to be explained. vz sdk has only one handle for a given domain, thus threads need exclusive access to operate on it. These calls are fixed to drop and reacquire domain lock on any lengthy operations - namely waiting the result of async vz sdk operation. As lock is dropped we need to take extra reference to domain object if it is not taken already as domain object can be deleted from list while lock is dropped. As this operations use thread shared sdkdom object, the simplest way to make calls from group 2 be consistent to each other is to make them mutually exclusive. This is done by taking/releasing job condition thru calling correspondent job routine. This approach makes group 1 and group 2 calls consistent to each other too. Not all calls of group 2 change the domain cache but those that do update it thru prlsdkUpdateDomain which holds the lock thoughout the update. API calls from group [2] are easily distinguished too. They use beginEdit/commit to change domain configuration (vzDomainSetMemoryFlags) or/and update domain cache from sdkdom at the end of operation (vzDomainSuspend). There is a known issue however. Frankly speaking it was introduced by ealier patch '[PATCH 6/9] vz: cleanup loading domain code' from a different series. The patch significantly reduced amount of time when the driver lock is held when creating domain from API call or as a result of domain added event from vz sdk. The problem is these two paths race on using thread shared sdkdom as we don't have libvirt domain object and can not lock on it. However this don't invalidates the patch as we can't use the former approach of preadding domain into the list as we need name at least and name is not given by event. Anyway i'm against adding half baked object into the list. Eventually this race can be fixed by extra measures. As to current situation races with different configurations are unlikely and race when adding domain thru vz driver and simultaneous event from vz sdk is not dangerous as configuration is the same. The last group [3] is API calls that need only sdkdom object to make vz sdk call and don't change thread shared sdkdom object or domain cache in any way. For now these are mostly domain snapshot API calls. The changes are similar to those of group 2 - they add extra reference and drop/reacquire the lock on waiting vz async call result. One can simply take the immutable sdkdom object from the cache and drop the lock for the rest of operations but the chosen approach makes implementation of these API calls somewhat similar to those of from group 2 and thus a bit futureproof. As calls of group 3 don't need vz driver domain/vz sdk cache in any way, they are consistent with respect to API calls from groups 1 and 3. There is another exception. Calls to make-snapshot/revert-to-snapshot/migrate are moved to group 2. That is they are made mutually exclusive. The reason is that libvirt API supports control/query only for one job per domain and these are jobs that are likely to be queried/aborted. Appendix. [1] API calls that only query domain cache. (marked [*] are included for a different reason) .domainLookupByID = vzDomainLookupByID, /* 0.10.0 */ .domainLookupByUUID = vzDomainLookupByUUID, /* 0.10.0 */ .domainLookupByName = vzDomainLookupByName, /* 0.10.0 */ .domainGetOSType = vzDomainGetOSType, /* 0.10.0 */ .domainGetInfo = vzDomainGetInfo, /* 0.10.0 */ .domainGetState = vzDomainGetState, /* 0.10.0 */ .domainGetXMLDesc = vzDomainGetXMLDesc, /* 0.10.0 */ .domainIsPersistent = vzDomainIsPersistent, /* 0.10.0 */ .domainGetAutostart = vzDomainGetAutostart, /* 0.10.0 */ .domainGetVcpus = vzDomainGetVcpus, /* 1.2.6 */ .domainIsActive = vzDomainIsActive, /* 1.2.10 */ .domainIsUpdated = vzDomainIsUpdated, /* 1.2.21 */ .domainGetVcpusFlags = vzDomainGetVcpusFlags, /* 1.2.21 */ .domainGetMaxVcpus = vzDomainGetMaxVcpus, /* 1.2.21 */ .domainHasManagedSaveImage = vzDomainHasManagedSaveImage, /* 1.2.13 */ .domainGetMaxMemory = vzDomainGetMaxMemory, /* 1.2.15 */ .domainBlockStats = vzDomainBlockStats, /* 1.2.17 */ .domainBlockStatsFlags = vzDomainBlockStatsFlags, /* 1.2.17 */ .domainInterfaceStats = vzDomainInterfaceStats, /* 1.2.17 */ [*] .domainMemoryStats = vzDomainMemoryStats, /* 1.2.17 */ .domainMigrateBegin3Params = vzDomainMigrateBegin3Params, /* 1.3.5 */ .domainMigrateConfirm3Params = vzDomainMigrateConfirm3Params, /* 1.3.5 */ [2] API calls that use thread shared sdkdom object (marked [*] are included for a different reason) .domainSuspend = vzDomainSuspend, /* 0.10.0 */ .domainResume = vzDomainResume, /* 0.10.0 */ .domainDestroy = vzDomainDestroy, /* 0.10.0 */ .domainShutdown = vzDomainShutdown, /* 0.10.0 */ .domainCreate = vzDomainCreate, /* 0.10.0 */ .domainCreateWithFlags = vzDomainCreateWithFlags, /* 1.2.10 */ .domainReboot = vzDomainReboot, /* 1.3.0 */ .domainDefineXML = vzDomainDefineXML, /* 0.10.0 */ .domainDefineXMLFlags = vzDomainDefineXMLFlags, /* 1.2.12 */ (update part) .domainUndefine = vzDomainUndefine, /* 1.2.10 */ .domainAttachDevice = vzDomainAttachDevice, /* 1.2.15 */ .domainAttachDeviceFlags = vzDomainAttachDeviceFlags, /* 1.2.15 */ .domainDetachDevice = vzDomainDetachDevice, /* 1.2.15 */ .domainDetachDeviceFlags = vzDomainDetachDeviceFlags, /* 1.2.15 */ .domainSetUserPassword = vzDomainSetUserPassword, /* 1.3.6 */ .domainManagedSave = vzDomainManagedSave, /* 1.2.14 */ .domainSetMemoryFlags = vzDomainSetMemoryFlags, /* 1.3.4 */ .domainSetMemory = vzDomainSetMemory, /* 1.3.4 */ .domainRevertToSnapshot = vzDomainRevertToSnapshot, /* 1.3.5 */ [*] .domainSnapshotCreateXML = vzDomainSnapshotCreateXML, /* 1.3.5 */ [*] .domainMigratePerform3Params = vzDomainMigratePerform3Params, /* 1.3.5 */ [*] .domainUpdateDeviceFlags = vzDomainUpdateDeviceFlags, /* 2.0.0 */ prlsdkHandleVmConfigEvent [3] API calls that do not use thread shared sdkdom object .domainManagedSaveRemove = vzDomainManagedSaveRemove, /* 1.2.14 */ .domainSnapshotNum = vzDomainSnapshotNum, /* 1.3.5 */ .domainSnapshotListNames = vzDomainSnapshotListNames, /* 1.3.5 */ .domainListAllSnapshots = vzDomainListAllSnapshots, /* 1.3.5 */ .domainSnapshotGetXMLDesc = vzDomainSnapshotGetXMLDesc, /* 1.3.5 */ .domainSnapshotNumChildren = vzDomainSnapshotNumChildren, /* 1.3.5 */ .domainSnapshotListChildrenNames = vzDomainSnapshotListChildrenNames, /* 1.3.5 */ .domainSnapshotListAllChildren = vzDomainSnapshotListAllChildren, /* 1.3.5 */ .domainSnapshotLookupByName = vzDomainSnapshotLookupByName, /* 1.3.5 */ .domainHasCurrentSnapshot = vzDomainHasCurrentSnapshot, /* 1.3.5 */ .domainSnapshotGetParent = vzDomainSnapshotGetParent, /* 1.3.5 */ .domainSnapshotCurrent = vzDomainSnapshotCurrent, /* 1.3.5 */ .domainSnapshotIsCurrent = vzDomainSnapshotIsCurrent, /* 1.3.5 */ .domainSnapshotHasMetadata = vzDomainSnapshotHasMetadata, /* 1.3.5 */ .domainSnapshotDelete = vzDomainSnapshotDelete, /* 1.3.5 */ [4] Known issues. 1. accidental errors on getting network statistics 2. race with simultaneous use of thread shared domain object on paths of adding domain thru API and adding domain on vz sdk domain added event.
2016-07-20 15:00:33 +00:00
#define VZ_JOB_WAIT_TIME (1000 * 30)
int
vzDomainObjBeginJob(virDomainObjPtr dom)
{
vzDomObjPtr pdom = dom->privateData;
unsigned long long now;
unsigned long long then;
if (virTimeMillisNow(&now) < 0)
return -1;
then = now + VZ_JOB_WAIT_TIME;
while (pdom->job.active) {
if (virCondWaitUntil(&pdom->job.cond, &dom->parent.lock, then) < 0)
vz: make vz driver more responsive Current vz driver implementation is not usable when it comes to long runnig operations. Migration or saving a domain blocks all other operations even query ones which are expecteted to be available. This patch addresses this problem. All vz driver API calls fall into next 3 groups: 1. only query domain cache (virDomainObj, vz cache statistic) examples are vzDomainGetState, vzDomainGetXMLDesc etc. 2. use thread shared sdkdom object examples are vzDomainSetMemoryFlags, vzDomainAttachDevice etc. 3. use no thread shared sdkdom object nor domain cache examples are vzDomainSnapshotListNames, vzDomainSnapshotGetXMLDesc etc API calls from group 1 don't need to be changed as they hold domain lock only for short period of time. These calls [1] are easily distinguished. They query domain object thru libvirt common code or query vz sdk statistics handle thru vz sdk sync operations. vzDomainInterfaceStats is the only exception. It uses sdkdom object to convert interface name to its vz sdk stack index which could not be saved in domain cache. Interface statistics is available thru this stack index as a key rather than name. As a result we can have accidental 'not known interface' errors on quering intrerface stats. The reason is that in the process of updating domain configuration we drop all devices and then recreate them again in sdkdom object and domain lock can be dropped meanwhile (to remove networks for existing bridged interfaces and(or) (re)create new ones). We can fix this by changing the way we support bridged interfaces or by reordering operations and changing bridged networks beforehand. Anyway this is better than moving this API call into 2 group and making it an exclusive job. As to API calls from group 2, first thread shared sdkdom object needs to be explained. vz sdk has only one handle for a given domain, thus threads need exclusive access to operate on it. These calls are fixed to drop and reacquire domain lock on any lengthy operations - namely waiting the result of async vz sdk operation. As lock is dropped we need to take extra reference to domain object if it is not taken already as domain object can be deleted from list while lock is dropped. As this operations use thread shared sdkdom object, the simplest way to make calls from group 2 be consistent to each other is to make them mutually exclusive. This is done by taking/releasing job condition thru calling correspondent job routine. This approach makes group 1 and group 2 calls consistent to each other too. Not all calls of group 2 change the domain cache but those that do update it thru prlsdkUpdateDomain which holds the lock thoughout the update. API calls from group [2] are easily distinguished too. They use beginEdit/commit to change domain configuration (vzDomainSetMemoryFlags) or/and update domain cache from sdkdom at the end of operation (vzDomainSuspend). There is a known issue however. Frankly speaking it was introduced by ealier patch '[PATCH 6/9] vz: cleanup loading domain code' from a different series. The patch significantly reduced amount of time when the driver lock is held when creating domain from API call or as a result of domain added event from vz sdk. The problem is these two paths race on using thread shared sdkdom as we don't have libvirt domain object and can not lock on it. However this don't invalidates the patch as we can't use the former approach of preadding domain into the list as we need name at least and name is not given by event. Anyway i'm against adding half baked object into the list. Eventually this race can be fixed by extra measures. As to current situation races with different configurations are unlikely and race when adding domain thru vz driver and simultaneous event from vz sdk is not dangerous as configuration is the same. The last group [3] is API calls that need only sdkdom object to make vz sdk call and don't change thread shared sdkdom object or domain cache in any way. For now these are mostly domain snapshot API calls. The changes are similar to those of group 2 - they add extra reference and drop/reacquire the lock on waiting vz async call result. One can simply take the immutable sdkdom object from the cache and drop the lock for the rest of operations but the chosen approach makes implementation of these API calls somewhat similar to those of from group 2 and thus a bit futureproof. As calls of group 3 don't need vz driver domain/vz sdk cache in any way, they are consistent with respect to API calls from groups 1 and 3. There is another exception. Calls to make-snapshot/revert-to-snapshot/migrate are moved to group 2. That is they are made mutually exclusive. The reason is that libvirt API supports control/query only for one job per domain and these are jobs that are likely to be queried/aborted. Appendix. [1] API calls that only query domain cache. (marked [*] are included for a different reason) .domainLookupByID = vzDomainLookupByID, /* 0.10.0 */ .domainLookupByUUID = vzDomainLookupByUUID, /* 0.10.0 */ .domainLookupByName = vzDomainLookupByName, /* 0.10.0 */ .domainGetOSType = vzDomainGetOSType, /* 0.10.0 */ .domainGetInfo = vzDomainGetInfo, /* 0.10.0 */ .domainGetState = vzDomainGetState, /* 0.10.0 */ .domainGetXMLDesc = vzDomainGetXMLDesc, /* 0.10.0 */ .domainIsPersistent = vzDomainIsPersistent, /* 0.10.0 */ .domainGetAutostart = vzDomainGetAutostart, /* 0.10.0 */ .domainGetVcpus = vzDomainGetVcpus, /* 1.2.6 */ .domainIsActive = vzDomainIsActive, /* 1.2.10 */ .domainIsUpdated = vzDomainIsUpdated, /* 1.2.21 */ .domainGetVcpusFlags = vzDomainGetVcpusFlags, /* 1.2.21 */ .domainGetMaxVcpus = vzDomainGetMaxVcpus, /* 1.2.21 */ .domainHasManagedSaveImage = vzDomainHasManagedSaveImage, /* 1.2.13 */ .domainGetMaxMemory = vzDomainGetMaxMemory, /* 1.2.15 */ .domainBlockStats = vzDomainBlockStats, /* 1.2.17 */ .domainBlockStatsFlags = vzDomainBlockStatsFlags, /* 1.2.17 */ .domainInterfaceStats = vzDomainInterfaceStats, /* 1.2.17 */ [*] .domainMemoryStats = vzDomainMemoryStats, /* 1.2.17 */ .domainMigrateBegin3Params = vzDomainMigrateBegin3Params, /* 1.3.5 */ .domainMigrateConfirm3Params = vzDomainMigrateConfirm3Params, /* 1.3.5 */ [2] API calls that use thread shared sdkdom object (marked [*] are included for a different reason) .domainSuspend = vzDomainSuspend, /* 0.10.0 */ .domainResume = vzDomainResume, /* 0.10.0 */ .domainDestroy = vzDomainDestroy, /* 0.10.0 */ .domainShutdown = vzDomainShutdown, /* 0.10.0 */ .domainCreate = vzDomainCreate, /* 0.10.0 */ .domainCreateWithFlags = vzDomainCreateWithFlags, /* 1.2.10 */ .domainReboot = vzDomainReboot, /* 1.3.0 */ .domainDefineXML = vzDomainDefineXML, /* 0.10.0 */ .domainDefineXMLFlags = vzDomainDefineXMLFlags, /* 1.2.12 */ (update part) .domainUndefine = vzDomainUndefine, /* 1.2.10 */ .domainAttachDevice = vzDomainAttachDevice, /* 1.2.15 */ .domainAttachDeviceFlags = vzDomainAttachDeviceFlags, /* 1.2.15 */ .domainDetachDevice = vzDomainDetachDevice, /* 1.2.15 */ .domainDetachDeviceFlags = vzDomainDetachDeviceFlags, /* 1.2.15 */ .domainSetUserPassword = vzDomainSetUserPassword, /* 1.3.6 */ .domainManagedSave = vzDomainManagedSave, /* 1.2.14 */ .domainSetMemoryFlags = vzDomainSetMemoryFlags, /* 1.3.4 */ .domainSetMemory = vzDomainSetMemory, /* 1.3.4 */ .domainRevertToSnapshot = vzDomainRevertToSnapshot, /* 1.3.5 */ [*] .domainSnapshotCreateXML = vzDomainSnapshotCreateXML, /* 1.3.5 */ [*] .domainMigratePerform3Params = vzDomainMigratePerform3Params, /* 1.3.5 */ [*] .domainUpdateDeviceFlags = vzDomainUpdateDeviceFlags, /* 2.0.0 */ prlsdkHandleVmConfigEvent [3] API calls that do not use thread shared sdkdom object .domainManagedSaveRemove = vzDomainManagedSaveRemove, /* 1.2.14 */ .domainSnapshotNum = vzDomainSnapshotNum, /* 1.3.5 */ .domainSnapshotListNames = vzDomainSnapshotListNames, /* 1.3.5 */ .domainListAllSnapshots = vzDomainListAllSnapshots, /* 1.3.5 */ .domainSnapshotGetXMLDesc = vzDomainSnapshotGetXMLDesc, /* 1.3.5 */ .domainSnapshotNumChildren = vzDomainSnapshotNumChildren, /* 1.3.5 */ .domainSnapshotListChildrenNames = vzDomainSnapshotListChildrenNames, /* 1.3.5 */ .domainSnapshotListAllChildren = vzDomainSnapshotListAllChildren, /* 1.3.5 */ .domainSnapshotLookupByName = vzDomainSnapshotLookupByName, /* 1.3.5 */ .domainHasCurrentSnapshot = vzDomainHasCurrentSnapshot, /* 1.3.5 */ .domainSnapshotGetParent = vzDomainSnapshotGetParent, /* 1.3.5 */ .domainSnapshotCurrent = vzDomainSnapshotCurrent, /* 1.3.5 */ .domainSnapshotIsCurrent = vzDomainSnapshotIsCurrent, /* 1.3.5 */ .domainSnapshotHasMetadata = vzDomainSnapshotHasMetadata, /* 1.3.5 */ .domainSnapshotDelete = vzDomainSnapshotDelete, /* 1.3.5 */ [4] Known issues. 1. accidental errors on getting network statistics 2. race with simultaneous use of thread shared domain object on paths of adding domain thru API and adding domain on vz sdk domain added event.
2016-07-20 15:00:33 +00:00
goto error;
}
if (virTimeMillisNow(&now) < 0)
return -1;
pdom->job.active = true;
pdom->job.started = now;
pdom->job.elapsed = 0;
pdom->job.progress = 0;
pdom->job.hasProgress = false;
vz: make vz driver more responsive Current vz driver implementation is not usable when it comes to long runnig operations. Migration or saving a domain blocks all other operations even query ones which are expecteted to be available. This patch addresses this problem. All vz driver API calls fall into next 3 groups: 1. only query domain cache (virDomainObj, vz cache statistic) examples are vzDomainGetState, vzDomainGetXMLDesc etc. 2. use thread shared sdkdom object examples are vzDomainSetMemoryFlags, vzDomainAttachDevice etc. 3. use no thread shared sdkdom object nor domain cache examples are vzDomainSnapshotListNames, vzDomainSnapshotGetXMLDesc etc API calls from group 1 don't need to be changed as they hold domain lock only for short period of time. These calls [1] are easily distinguished. They query domain object thru libvirt common code or query vz sdk statistics handle thru vz sdk sync operations. vzDomainInterfaceStats is the only exception. It uses sdkdom object to convert interface name to its vz sdk stack index which could not be saved in domain cache. Interface statistics is available thru this stack index as a key rather than name. As a result we can have accidental 'not known interface' errors on quering intrerface stats. The reason is that in the process of updating domain configuration we drop all devices and then recreate them again in sdkdom object and domain lock can be dropped meanwhile (to remove networks for existing bridged interfaces and(or) (re)create new ones). We can fix this by changing the way we support bridged interfaces or by reordering operations and changing bridged networks beforehand. Anyway this is better than moving this API call into 2 group and making it an exclusive job. As to API calls from group 2, first thread shared sdkdom object needs to be explained. vz sdk has only one handle for a given domain, thus threads need exclusive access to operate on it. These calls are fixed to drop and reacquire domain lock on any lengthy operations - namely waiting the result of async vz sdk operation. As lock is dropped we need to take extra reference to domain object if it is not taken already as domain object can be deleted from list while lock is dropped. As this operations use thread shared sdkdom object, the simplest way to make calls from group 2 be consistent to each other is to make them mutually exclusive. This is done by taking/releasing job condition thru calling correspondent job routine. This approach makes group 1 and group 2 calls consistent to each other too. Not all calls of group 2 change the domain cache but those that do update it thru prlsdkUpdateDomain which holds the lock thoughout the update. API calls from group [2] are easily distinguished too. They use beginEdit/commit to change domain configuration (vzDomainSetMemoryFlags) or/and update domain cache from sdkdom at the end of operation (vzDomainSuspend). There is a known issue however. Frankly speaking it was introduced by ealier patch '[PATCH 6/9] vz: cleanup loading domain code' from a different series. The patch significantly reduced amount of time when the driver lock is held when creating domain from API call or as a result of domain added event from vz sdk. The problem is these two paths race on using thread shared sdkdom as we don't have libvirt domain object and can not lock on it. However this don't invalidates the patch as we can't use the former approach of preadding domain into the list as we need name at least and name is not given by event. Anyway i'm against adding half baked object into the list. Eventually this race can be fixed by extra measures. As to current situation races with different configurations are unlikely and race when adding domain thru vz driver and simultaneous event from vz sdk is not dangerous as configuration is the same. The last group [3] is API calls that need only sdkdom object to make vz sdk call and don't change thread shared sdkdom object or domain cache in any way. For now these are mostly domain snapshot API calls. The changes are similar to those of group 2 - they add extra reference and drop/reacquire the lock on waiting vz async call result. One can simply take the immutable sdkdom object from the cache and drop the lock for the rest of operations but the chosen approach makes implementation of these API calls somewhat similar to those of from group 2 and thus a bit futureproof. As calls of group 3 don't need vz driver domain/vz sdk cache in any way, they are consistent with respect to API calls from groups 1 and 3. There is another exception. Calls to make-snapshot/revert-to-snapshot/migrate are moved to group 2. That is they are made mutually exclusive. The reason is that libvirt API supports control/query only for one job per domain and these are jobs that are likely to be queried/aborted. Appendix. [1] API calls that only query domain cache. (marked [*] are included for a different reason) .domainLookupByID = vzDomainLookupByID, /* 0.10.0 */ .domainLookupByUUID = vzDomainLookupByUUID, /* 0.10.0 */ .domainLookupByName = vzDomainLookupByName, /* 0.10.0 */ .domainGetOSType = vzDomainGetOSType, /* 0.10.0 */ .domainGetInfo = vzDomainGetInfo, /* 0.10.0 */ .domainGetState = vzDomainGetState, /* 0.10.0 */ .domainGetXMLDesc = vzDomainGetXMLDesc, /* 0.10.0 */ .domainIsPersistent = vzDomainIsPersistent, /* 0.10.0 */ .domainGetAutostart = vzDomainGetAutostart, /* 0.10.0 */ .domainGetVcpus = vzDomainGetVcpus, /* 1.2.6 */ .domainIsActive = vzDomainIsActive, /* 1.2.10 */ .domainIsUpdated = vzDomainIsUpdated, /* 1.2.21 */ .domainGetVcpusFlags = vzDomainGetVcpusFlags, /* 1.2.21 */ .domainGetMaxVcpus = vzDomainGetMaxVcpus, /* 1.2.21 */ .domainHasManagedSaveImage = vzDomainHasManagedSaveImage, /* 1.2.13 */ .domainGetMaxMemory = vzDomainGetMaxMemory, /* 1.2.15 */ .domainBlockStats = vzDomainBlockStats, /* 1.2.17 */ .domainBlockStatsFlags = vzDomainBlockStatsFlags, /* 1.2.17 */ .domainInterfaceStats = vzDomainInterfaceStats, /* 1.2.17 */ [*] .domainMemoryStats = vzDomainMemoryStats, /* 1.2.17 */ .domainMigrateBegin3Params = vzDomainMigrateBegin3Params, /* 1.3.5 */ .domainMigrateConfirm3Params = vzDomainMigrateConfirm3Params, /* 1.3.5 */ [2] API calls that use thread shared sdkdom object (marked [*] are included for a different reason) .domainSuspend = vzDomainSuspend, /* 0.10.0 */ .domainResume = vzDomainResume, /* 0.10.0 */ .domainDestroy = vzDomainDestroy, /* 0.10.0 */ .domainShutdown = vzDomainShutdown, /* 0.10.0 */ .domainCreate = vzDomainCreate, /* 0.10.0 */ .domainCreateWithFlags = vzDomainCreateWithFlags, /* 1.2.10 */ .domainReboot = vzDomainReboot, /* 1.3.0 */ .domainDefineXML = vzDomainDefineXML, /* 0.10.0 */ .domainDefineXMLFlags = vzDomainDefineXMLFlags, /* 1.2.12 */ (update part) .domainUndefine = vzDomainUndefine, /* 1.2.10 */ .domainAttachDevice = vzDomainAttachDevice, /* 1.2.15 */ .domainAttachDeviceFlags = vzDomainAttachDeviceFlags, /* 1.2.15 */ .domainDetachDevice = vzDomainDetachDevice, /* 1.2.15 */ .domainDetachDeviceFlags = vzDomainDetachDeviceFlags, /* 1.2.15 */ .domainSetUserPassword = vzDomainSetUserPassword, /* 1.3.6 */ .domainManagedSave = vzDomainManagedSave, /* 1.2.14 */ .domainSetMemoryFlags = vzDomainSetMemoryFlags, /* 1.3.4 */ .domainSetMemory = vzDomainSetMemory, /* 1.3.4 */ .domainRevertToSnapshot = vzDomainRevertToSnapshot, /* 1.3.5 */ [*] .domainSnapshotCreateXML = vzDomainSnapshotCreateXML, /* 1.3.5 */ [*] .domainMigratePerform3Params = vzDomainMigratePerform3Params, /* 1.3.5 */ [*] .domainUpdateDeviceFlags = vzDomainUpdateDeviceFlags, /* 2.0.0 */ prlsdkHandleVmConfigEvent [3] API calls that do not use thread shared sdkdom object .domainManagedSaveRemove = vzDomainManagedSaveRemove, /* 1.2.14 */ .domainSnapshotNum = vzDomainSnapshotNum, /* 1.3.5 */ .domainSnapshotListNames = vzDomainSnapshotListNames, /* 1.3.5 */ .domainListAllSnapshots = vzDomainListAllSnapshots, /* 1.3.5 */ .domainSnapshotGetXMLDesc = vzDomainSnapshotGetXMLDesc, /* 1.3.5 */ .domainSnapshotNumChildren = vzDomainSnapshotNumChildren, /* 1.3.5 */ .domainSnapshotListChildrenNames = vzDomainSnapshotListChildrenNames, /* 1.3.5 */ .domainSnapshotListAllChildren = vzDomainSnapshotListAllChildren, /* 1.3.5 */ .domainSnapshotLookupByName = vzDomainSnapshotLookupByName, /* 1.3.5 */ .domainHasCurrentSnapshot = vzDomainHasCurrentSnapshot, /* 1.3.5 */ .domainSnapshotGetParent = vzDomainSnapshotGetParent, /* 1.3.5 */ .domainSnapshotCurrent = vzDomainSnapshotCurrent, /* 1.3.5 */ .domainSnapshotIsCurrent = vzDomainSnapshotIsCurrent, /* 1.3.5 */ .domainSnapshotHasMetadata = vzDomainSnapshotHasMetadata, /* 1.3.5 */ .domainSnapshotDelete = vzDomainSnapshotDelete, /* 1.3.5 */ [4] Known issues. 1. accidental errors on getting network statistics 2. race with simultaneous use of thread shared domain object on paths of adding domain thru API and adding domain on vz sdk domain added event.
2016-07-20 15:00:33 +00:00
return 0;
error:
if (errno == ETIMEDOUT)
virReportError(VIR_ERR_OPERATION_TIMEOUT,
"%s", _("cannot acquire state change lock"));
else
virReportSystemError(errno,
"%s", _("cannot acquire job mutex"));
return -1;
}
void
vzDomainObjEndJob(virDomainObjPtr dom)
{
vzDomObjPtr pdom = dom->privateData;
pdom->job.active = false;
2017-01-31 07:44:12 +00:00
pdom->job.cancelled = false;
virCondSignal(&pdom->job.cond);
}
int
vzDomainJobUpdateTime(vzDomainJobObjPtr job)
{
unsigned long long now;
if (!job->started)
return 0;
if (virTimeMillisNow(&now) < 0)
return -1;
if (now < job->started) {
VIR_WARN("Async job starts in the future");
job->started = 0;
return 0;
}
job->elapsed = now - job->started;
return 0;
vz: make vz driver more responsive Current vz driver implementation is not usable when it comes to long runnig operations. Migration or saving a domain blocks all other operations even query ones which are expecteted to be available. This patch addresses this problem. All vz driver API calls fall into next 3 groups: 1. only query domain cache (virDomainObj, vz cache statistic) examples are vzDomainGetState, vzDomainGetXMLDesc etc. 2. use thread shared sdkdom object examples are vzDomainSetMemoryFlags, vzDomainAttachDevice etc. 3. use no thread shared sdkdom object nor domain cache examples are vzDomainSnapshotListNames, vzDomainSnapshotGetXMLDesc etc API calls from group 1 don't need to be changed as they hold domain lock only for short period of time. These calls [1] are easily distinguished. They query domain object thru libvirt common code or query vz sdk statistics handle thru vz sdk sync operations. vzDomainInterfaceStats is the only exception. It uses sdkdom object to convert interface name to its vz sdk stack index which could not be saved in domain cache. Interface statistics is available thru this stack index as a key rather than name. As a result we can have accidental 'not known interface' errors on quering intrerface stats. The reason is that in the process of updating domain configuration we drop all devices and then recreate them again in sdkdom object and domain lock can be dropped meanwhile (to remove networks for existing bridged interfaces and(or) (re)create new ones). We can fix this by changing the way we support bridged interfaces or by reordering operations and changing bridged networks beforehand. Anyway this is better than moving this API call into 2 group and making it an exclusive job. As to API calls from group 2, first thread shared sdkdom object needs to be explained. vz sdk has only one handle for a given domain, thus threads need exclusive access to operate on it. These calls are fixed to drop and reacquire domain lock on any lengthy operations - namely waiting the result of async vz sdk operation. As lock is dropped we need to take extra reference to domain object if it is not taken already as domain object can be deleted from list while lock is dropped. As this operations use thread shared sdkdom object, the simplest way to make calls from group 2 be consistent to each other is to make them mutually exclusive. This is done by taking/releasing job condition thru calling correspondent job routine. This approach makes group 1 and group 2 calls consistent to each other too. Not all calls of group 2 change the domain cache but those that do update it thru prlsdkUpdateDomain which holds the lock thoughout the update. API calls from group [2] are easily distinguished too. They use beginEdit/commit to change domain configuration (vzDomainSetMemoryFlags) or/and update domain cache from sdkdom at the end of operation (vzDomainSuspend). There is a known issue however. Frankly speaking it was introduced by ealier patch '[PATCH 6/9] vz: cleanup loading domain code' from a different series. The patch significantly reduced amount of time when the driver lock is held when creating domain from API call or as a result of domain added event from vz sdk. The problem is these two paths race on using thread shared sdkdom as we don't have libvirt domain object and can not lock on it. However this don't invalidates the patch as we can't use the former approach of preadding domain into the list as we need name at least and name is not given by event. Anyway i'm against adding half baked object into the list. Eventually this race can be fixed by extra measures. As to current situation races with different configurations are unlikely and race when adding domain thru vz driver and simultaneous event from vz sdk is not dangerous as configuration is the same. The last group [3] is API calls that need only sdkdom object to make vz sdk call and don't change thread shared sdkdom object or domain cache in any way. For now these are mostly domain snapshot API calls. The changes are similar to those of group 2 - they add extra reference and drop/reacquire the lock on waiting vz async call result. One can simply take the immutable sdkdom object from the cache and drop the lock for the rest of operations but the chosen approach makes implementation of these API calls somewhat similar to those of from group 2 and thus a bit futureproof. As calls of group 3 don't need vz driver domain/vz sdk cache in any way, they are consistent with respect to API calls from groups 1 and 3. There is another exception. Calls to make-snapshot/revert-to-snapshot/migrate are moved to group 2. That is they are made mutually exclusive. The reason is that libvirt API supports control/query only for one job per domain and these are jobs that are likely to be queried/aborted. Appendix. [1] API calls that only query domain cache. (marked [*] are included for a different reason) .domainLookupByID = vzDomainLookupByID, /* 0.10.0 */ .domainLookupByUUID = vzDomainLookupByUUID, /* 0.10.0 */ .domainLookupByName = vzDomainLookupByName, /* 0.10.0 */ .domainGetOSType = vzDomainGetOSType, /* 0.10.0 */ .domainGetInfo = vzDomainGetInfo, /* 0.10.0 */ .domainGetState = vzDomainGetState, /* 0.10.0 */ .domainGetXMLDesc = vzDomainGetXMLDesc, /* 0.10.0 */ .domainIsPersistent = vzDomainIsPersistent, /* 0.10.0 */ .domainGetAutostart = vzDomainGetAutostart, /* 0.10.0 */ .domainGetVcpus = vzDomainGetVcpus, /* 1.2.6 */ .domainIsActive = vzDomainIsActive, /* 1.2.10 */ .domainIsUpdated = vzDomainIsUpdated, /* 1.2.21 */ .domainGetVcpusFlags = vzDomainGetVcpusFlags, /* 1.2.21 */ .domainGetMaxVcpus = vzDomainGetMaxVcpus, /* 1.2.21 */ .domainHasManagedSaveImage = vzDomainHasManagedSaveImage, /* 1.2.13 */ .domainGetMaxMemory = vzDomainGetMaxMemory, /* 1.2.15 */ .domainBlockStats = vzDomainBlockStats, /* 1.2.17 */ .domainBlockStatsFlags = vzDomainBlockStatsFlags, /* 1.2.17 */ .domainInterfaceStats = vzDomainInterfaceStats, /* 1.2.17 */ [*] .domainMemoryStats = vzDomainMemoryStats, /* 1.2.17 */ .domainMigrateBegin3Params = vzDomainMigrateBegin3Params, /* 1.3.5 */ .domainMigrateConfirm3Params = vzDomainMigrateConfirm3Params, /* 1.3.5 */ [2] API calls that use thread shared sdkdom object (marked [*] are included for a different reason) .domainSuspend = vzDomainSuspend, /* 0.10.0 */ .domainResume = vzDomainResume, /* 0.10.0 */ .domainDestroy = vzDomainDestroy, /* 0.10.0 */ .domainShutdown = vzDomainShutdown, /* 0.10.0 */ .domainCreate = vzDomainCreate, /* 0.10.0 */ .domainCreateWithFlags = vzDomainCreateWithFlags, /* 1.2.10 */ .domainReboot = vzDomainReboot, /* 1.3.0 */ .domainDefineXML = vzDomainDefineXML, /* 0.10.0 */ .domainDefineXMLFlags = vzDomainDefineXMLFlags, /* 1.2.12 */ (update part) .domainUndefine = vzDomainUndefine, /* 1.2.10 */ .domainAttachDevice = vzDomainAttachDevice, /* 1.2.15 */ .domainAttachDeviceFlags = vzDomainAttachDeviceFlags, /* 1.2.15 */ .domainDetachDevice = vzDomainDetachDevice, /* 1.2.15 */ .domainDetachDeviceFlags = vzDomainDetachDeviceFlags, /* 1.2.15 */ .domainSetUserPassword = vzDomainSetUserPassword, /* 1.3.6 */ .domainManagedSave = vzDomainManagedSave, /* 1.2.14 */ .domainSetMemoryFlags = vzDomainSetMemoryFlags, /* 1.3.4 */ .domainSetMemory = vzDomainSetMemory, /* 1.3.4 */ .domainRevertToSnapshot = vzDomainRevertToSnapshot, /* 1.3.5 */ [*] .domainSnapshotCreateXML = vzDomainSnapshotCreateXML, /* 1.3.5 */ [*] .domainMigratePerform3Params = vzDomainMigratePerform3Params, /* 1.3.5 */ [*] .domainUpdateDeviceFlags = vzDomainUpdateDeviceFlags, /* 2.0.0 */ prlsdkHandleVmConfigEvent [3] API calls that do not use thread shared sdkdom object .domainManagedSaveRemove = vzDomainManagedSaveRemove, /* 1.2.14 */ .domainSnapshotNum = vzDomainSnapshotNum, /* 1.3.5 */ .domainSnapshotListNames = vzDomainSnapshotListNames, /* 1.3.5 */ .domainListAllSnapshots = vzDomainListAllSnapshots, /* 1.3.5 */ .domainSnapshotGetXMLDesc = vzDomainSnapshotGetXMLDesc, /* 1.3.5 */ .domainSnapshotNumChildren = vzDomainSnapshotNumChildren, /* 1.3.5 */ .domainSnapshotListChildrenNames = vzDomainSnapshotListChildrenNames, /* 1.3.5 */ .domainSnapshotListAllChildren = vzDomainSnapshotListAllChildren, /* 1.3.5 */ .domainSnapshotLookupByName = vzDomainSnapshotLookupByName, /* 1.3.5 */ .domainHasCurrentSnapshot = vzDomainHasCurrentSnapshot, /* 1.3.5 */ .domainSnapshotGetParent = vzDomainSnapshotGetParent, /* 1.3.5 */ .domainSnapshotCurrent = vzDomainSnapshotCurrent, /* 1.3.5 */ .domainSnapshotIsCurrent = vzDomainSnapshotIsCurrent, /* 1.3.5 */ .domainSnapshotHasMetadata = vzDomainSnapshotHasMetadata, /* 1.3.5 */ .domainSnapshotDelete = vzDomainSnapshotDelete, /* 1.3.5 */ [4] Known issues. 1. accidental errors on getting network statistics 2. race with simultaneous use of thread shared domain object on paths of adding domain thru API and adding domain on vz sdk domain added event.
2016-07-20 15:00:33 +00:00
}