January 2015 - Devel - libvirt List Archives

[libvirt] [PATCH] LXC: create a bind mount for sysfs when enable userns but disable netns
by Chen Hanxiao 20 Mar '15

20 Mar '15

kernel commit 7dc5dbc879bd0779924b5132a48b731a0bc04a1e forbid us doing a fresh mount for sysfs when enable userns but disable netns. This patch will create a bind mount in this senario. Signed-off-by: Chen Hanxiao <chenhanxiao(a)cn.fujitsu.com> --- src/lxc/lxc_container.c | 44 +++++++++++++++++++++++++++++++++----------- 1 file changed, 33 insertions(+), 11 deletions(-) diff --git a/src/lxc/lxc_container.c b/src/lxc/lxc_container.c index 4d89677..8a27215 100644 --- a/src/lxc/lxc_container.c +++ b/src/lxc/lxc_container.c @@ -815,10 +815,13 @@ static int lxcContainerSetReadOnly(void) } -static int lxcContainerMountBasicFS(bool userns_enabled) +static int lxcContainerMountBasicFS(bool userns_enabled, + bool netns_disabled) { size_t i; int rc = -1; + char* mnt_src = NULL; + int mnt_mflags; VIR_DEBUG("Mounting basic filesystems"); @@ -826,8 +829,25 @@ static int lxcContainerMountBasicFS(bool userns_enabled) bool bindOverReadonly; virLXCBasicMountInfo const *mnt = &lxcBasicMounts[i]; + /* When enable userns but disable netns, kernel will + * forbid us doing a new fresh mount for sysfs. + * So we had to do a bind mount for sysfs instead. + */ + if (userns_enabled && netns_disabled && + STREQ(mnt->src, "sysfs")) { + if (VIR_STRDUP(mnt_src, "/sys") < 0) { + goto cleanup; + } + mnt_mflags = MS_NOSUID|MS_NOEXEC|MS_NODEV|MS_RDONLY|MS_BIND; + } else { + if (VIR_STRDUP(mnt_src, mnt->src) < 0) { + goto cleanup; + } + mnt_mflags = mnt->mflags; + } + VIR_DEBUG("Processing %s -> %s", - mnt->src, mnt->dst); + mnt_src, mnt->dst); if (mnt->skipUnmounted) { char *hostdir; @@ -856,7 +876,7 @@ static int lxcContainerMountBasicFS(bool userns_enabled) if (virFileMakePath(mnt->dst) < 0) { virReportSystemError(errno, _("Failed to mkdir %s"), - mnt->src); + mnt_src); goto cleanup; } @@ -867,24 +887,24 @@ static int lxcContainerMountBasicFS(bool userns_enabled) * we mount the filesystem in read-write mode initially, and then do a * separate read-only bind mount on top of that. */ - bindOverReadonly = !!(mnt->mflags & MS_RDONLY); + bindOverReadonly = !!(mnt_mflags & MS_RDONLY); VIR_DEBUG("Mount %s on %s type=%s flags=%x", - mnt->src, mnt->dst, mnt->type, mnt->mflags & ~MS_RDONLY); - if (mount(mnt->src, mnt->dst, mnt->type, mnt->mflags & ~MS_RDONLY, NULL) < 0) { + mnt_src, mnt->dst, mnt->type, mnt_mflags & ~MS_RDONLY); + if (mount(mnt_src, mnt->dst, mnt->type, mnt_mflags & ~MS_RDONLY, NULL) < 0) { virReportSystemError(errno, _("Failed to mount %s on %s type %s flags=%x"), - mnt->src, mnt->dst, NULLSTR(mnt->type), - mnt->mflags & ~MS_RDONLY); + mnt_src, mnt->dst, NULLSTR(mnt->type), + mnt_mflags & ~MS_RDONLY); goto cleanup; } if (bindOverReadonly && - mount(mnt->src, mnt->dst, NULL, + mount(mnt_src, mnt->dst, NULL, MS_BIND|MS_REMOUNT|MS_RDONLY, NULL) < 0) { virReportSystemError(errno, _("Failed to re-mount %s on %s flags=%x"), - mnt->src, mnt->dst, + mnt_src, mnt->dst, MS_BIND|MS_REMOUNT|MS_RDONLY); goto cleanup; } @@ -893,6 +913,7 @@ static int lxcContainerMountBasicFS(bool userns_enabled) rc = 0; cleanup: + VIR_FREE(mnt_src); VIR_DEBUG("rc=%d", rc); return rc; } @@ -1643,7 +1664,8 @@ static int lxcContainerSetupPivotRoot(virDomainDefPtr vmDef, goto cleanup; /* Mounts the core /proc, /sys, etc filesystems */ - if (lxcContainerMountBasicFS(vmDef->idmap.nuidmap) < 0) + if (lxcContainerMountBasicFS(vmDef->idmap.nuidmap, + !vmDef->nnets) < 0) goto cleanup; /* Ensure entire root filesystem (except /.oldroot) is readonly */ -- 1.9.0

7 13

[libvirt] [libvirt-test-API][PATCH] Rewrite case for listAllInterfaces() API
by jiahu 12 Mar '15

12 Mar '15

Using actual python API to validate test case, rather than use virsh iface-* command lines. --- cases/basic_interface.conf | 12 ++ repos/interface/iface_list.py | 299 ++++++++++++------------------------------ 2 files changed, 99 insertions(+), 212 deletions(-) diff --git a/cases/basic_interface.conf b/cases/basic_interface.conf index e2125bb..43e37e8 100644 --- a/cases/basic_interface.conf +++ b/cases/basic_interface.conf @@ -15,3 +15,15 @@ interface:define interface:create ifacename $testnic + +interface:iface_list + flags + all + +interface:iface_list + flags + active + +interface:iface_list + flags + inactive diff --git a/repos/interface/iface_list.py b/repos/interface/iface_list.py index 49f0c05..85f9df9 100644 --- a/repos/interface/iface_list.py +++ b/repos/interface/iface_list.py @@ -1,65 +1,26 @@ #!/usr/bin/env python +# test listAllInterfaces() API import os -import sys -import re -import commands +import libvirt -required_params = ('ifaceopt',) -optional_params = {} - -VIRSH_QUIET_IFACE_LIST = "virsh --quiet iface-list %s | awk '{print ""$%s""}'" -NETWORK_CONFIG = "/etc/sysconfig/network-scripts/" -IFCONFIG_DRIVER = "ifconfig %s | sed 's/[ \t].*//;/^$/d'" -GET_MAC = "ip link show %s |sed -n '2p'| awk '{print $2}'" -VIRSH_IFACE_LIST = "virsh iface-list %s" - -names = [] -state = [] -macs = [] - -def get_option_list(params): - """return options we need to test - """ - logger = params['logger'] - option_list=[] +from libvirt import libvirtError +from src import sharedmod +from utils import utils - value = params['ifaceopt'] - if value == 'all': - option_list = [' ', '--all', '--inactive'] - elif value == '--all' or value == '--inactive': - option_list.append(value) - else: - logger.error("value %s is not supported" % value) - return 1, option_list +required_params = ('flags',) +optional_params = {} - return 0, option_list +NETWORK_CONFIG = "/etc/sysconfig/network-scripts/" +IFCONFIG_DRIVER = "ifconfig %s | sed 's/[ \t].*//;/^$/d'| cut -d \":\" -f -1" -def get_output(command, logger): - """execute shell command +def get_inteface_list_from_ifcfg(logger): + """ + return host interface list from ifcfg-* """ - status, ret = commands.getstatusoutput(command) - if status: - logger.error("executing "+ "\"" + command + "\"" + " failed") - logger.error(ret) - return status, ret - -def get_interface_list(option, logger): - """ return active host interface list """ - interface_list = [] - status, interface_str = get_output(IFCONFIG_DRIVER % option, logger) - if not status: - interface_list = interface_str.split('\n') - return interface_list - else: - logger.error("\"" + IFCONFIG_DRIVER % option + "\"" + "error") - logger.error(interface_str) - return interface_list - -def check_ifacename(names, option, logger): - """ verify the validity of output data """ ifcfg_files = [] + nic_names = [] for f in os.listdir(NETWORK_CONFIG): if f.startswith("ifcfg-"): f_path = os.path.join(NETWORK_CONFIG, f) @@ -67,18 +28,6 @@ def check_ifacename(names, option, logger): ifcfg_files.append(f_path) else: logger.warn("%s is not a regular file" % f_path) - - interface_active = get_interface_list('', logger) - logger.debug("list of active host interface: %s" % interface_active) - if interface_active == None: - return 1 - - interface_all = get_interface_list('-a', logger) - logger.debug("list of all host interface: %s" % interface_all) - if interface_all == None: - return 1 - - for ifcfg_file in ifcfg_files: fp = open(ifcfg_file, 'r') fp.seek(0,0) @@ -87,165 +36,91 @@ def check_ifacename(names, option, logger): device_str = eachLine.rstrip() nic_string = device_str.split("=")[1] if nic_string.startswith("\""): - nic_name = nic_string[1:-1] + nic_names = nic_string[1:-1] else: - nic_name = nic_string + nic_names.append(nic_string) break - fp.close() + return list(set(nic_names)) - if option == ' ': - if nic_name not in interface_active: - continue - else: - if nic_name in names: - logger.info("it contains interface %s in %s" % (nic_name, ifcfg_file)) - else: - logger.error("interface %s in %s couldn't \n\ - be in the output of virsh iface-list with option %s" % \ - (nic_name, ifcfg_file, option)) - return 1 - elif option == '--all': - if nic_name in names: - logger.info("it contains interface %s in %s" % (nic_name, ifcfg_file)) - else: - logger.error("interface %s in %s couldn't \n\ - be in the output of virsh iface-list with option %s" % \ - (nic_name, ifcfg_file, option)) - - return 1 - elif option == '--inactive': - if nic_name in interface_active: - continue - else: - if nic_name in names: - logger.info("it contains interface %s in %s" % (nic_name, ifcfg_file)) - else: - logger.error("interface %s in %s couldn't \n\ - be in the output of virsh iface-list with option %s" % \ - (nic_name, ifcfg_file, option)) - return 1 - - return 0 - -def check_ifacestate(names, state, logger): - """ check the state of give host interface """ - - interface_active = get_interface_list('', logger) - if interface_active == None: - return 1 - - interface_all = get_interface_list('-a', logger) - if interface_all == None: - return 1 - - index = 0 - count = len(names) - while(index < count): - if names[index] in interface_active and state[index] == 'active': - logger.info("interface %s is %s" % (names[index], state[index])) - elif names[index] not in interface_active and \ - names[index] in interface_all and \ - state[index] == 'inactive': - logger.info("interface %s is %s" % (names[index], state[index])) - else: - logger.error("interface %s is %s, but not we expected" % \ - (names[index], state[index])) - return 1 - - index = index + 1 - - return 0 - -def check_ifacemac(names, macs, logger): - """ check if the mac corresponding to approriate name is correct """ - index = 0 - count = len(names) - while(index < count): - status, mac_shell = get_output(GET_MAC % names[index], logger) - if not status: - if mac_shell == macs[index]: - logger.info("interface %s's mac address is %s" % \ - (names[index], macs[index])) - else: - logger.error("interface %s's mac address from iface-list: %s \ - is different from one from ip link show: %s" % \ - (name[index], macs[indesx], mac_shell)) - return 1 - index = index + 1 - - return 0 - -def iface_list_output(option, logger): - """ check the output of virsh iface-list with appropriate option """ - global names, state, macs - - status, ret = get_output(VIRSH_QUIET_IFACE_LIST % (option, 1), logger) - if not status: - names = ret.split('\n') - logger.info("interface names from option '%s' : %s" % (option, names)) - - else: - return 1 - - status, ret = get_output(VIRSH_QUIET_IFACE_LIST % (option, 2), logger) - if not status: - state = ret.split('\n') - logger.info("interface state from option '%s' : %s" % (option, state)) - else: - return 1 - - status, ret = get_output(VIRSH_QUIET_IFACE_LIST % (option, 3), logger) +def get_interface_list(option, logger): + """ + return host interface list + """ + nic_names = [] + status, nic_names = utils.exec_cmd(IFCONFIG_DRIVER % option, shell=True) if not status: - macs = ret.split('\n') - logger.info("interface macs from option '%s' : %s" % (option, macs)) + return nic_names else: - return 1 + logger.error("\"" + IFCONFIG_DRIVER % option + "\"" + "error") + logger.error(nic_names) + return nic_names - return 0 +def iface_list_output_from_ifconfig(flags, logger): + """ + get all host interface using ifconfig command + """ + nic_names = [] + if flags == 0: + nic_names = get_interface_list('-a', logger) + elif flags == 1: + interface_all = get_interface_list('-a', logger) + interface_active = get_interface_list('', logger) + nic_names = list(set(interface_all) - set(interface_active)) + elif flags == 2: + nic_names = get_interface_list('', logger) + + if nic_names == None: + return False + return nic_names + +def iface_list_output_from_api(flags,logger): + """ + get interface list using listAllInterfaces() + """ + nic_names_api = [] + for interface in conn.listAllInterfaces(flags): + nic_names_api.append(str(interface.name())) + return nic_names_api def iface_list(params): - """ test the validity of the output of iface_list with - default, --all, --inactive option, including - interface name, state, and mac + """ + test listAllInterfaces() api """ + global conn logger = params['logger'] - ret, option_list = get_option_list(params) - global names, state, macs - - if ret: - return 1 - - for option in option_list: - logger.info("CHECK the output of virsh pool-list with option '%s'" % option) - logger.info("get the name, corresponding state and mac address of interfaces") - if iface_list_output(option, logger): - logger.error("faied to name, state, and mac from iface-list") - return 1 + flags = params['flags'] + conn = sharedmod.libvirtobj['conn'] + logger.info("The given flags is %s " % flags) + if flags == "all": + flag = 0 + elif flags == "inactive": + flag = 1 + elif flags == "active": + flag = 2 + try: + iface_list = iface_list_output_from_api(flag, logger) + iface_list_ifconfig = iface_list_output_from_ifconfig(flag, logger) + if iface_list_ifconfig == False: + return 1 + ifcfg = get_inteface_list_from_ifcfg(logger) + logger.info("interface list from API: %s" % iface_list) + logger.debug("interface list from ifcfg: %s" % ifcfg) + for interface in iface_list_ifconfig: + if interface not in ifcfg: + iface_list_ifconfig.remove(interface) + logger.debug("%s has not regular ifcfg file" % interface) + + logger.info("interface list from ifconfig cmd: %s" % iface_list_ifconfig) + for interface in iface_list: + if interface in iface_list_ifconfig: + logger.debug("%s :Pass" % interface) else: - logger.info("then, check the validity of these interface names") - if check_ifacename(names, option, logger): - logger.error("checking interface names FAILED") - return 1 - else: - logger.info("checking interface names SUCCESSFULLY") - - logger.info("check the state of these interfaces") - if check_ifacestate(names, state, logger): - logger.error("checking interface state FAILED") - return 1 - else: - logger.info("checking interface state SUCCESSFULLY") - - logger.info("check the interface mac address") - if check_ifacemac(names, macs, logger): - logger.error("checking interface mac address FAILED") - return 1 - else: - logger.info("checking interface mac address SUCESSFULLY") - - status, ret = get_output(VIRSH_IFACE_LIST % option, logger) - if not status: - logger.info("\n" + ret) + logger.debug("%s :Fail" % interface) + return 1 + + except libvirtError, e: + logger.error("API error message: %s" % e.message) + return 1 return 0 -- 1.8.3.1

2 1

[libvirt] [RFC PATCH v2 0/4] Enable spapr-pci-vfio-host-bridge controllers for VFIO passthrough support
by Shivaprasad G Bhat 09 Mar '15

09 Mar '15

The following series of patches enable spapr-pci-vfio-host-bridge controllers on PPC64-pseries machine which is required for supporting host device passthrough using VFIO. There were some initial enablement work on the same at http://www.redhat.com/archives/libvir-list/2013-September/msg00838.html. On pseries(ppc64), the vfio host devices(will refer as hostdevs here on) cannot be assigned to the default emulated pci-host-bus(phb) controller(like the default pci.0). The hostdevs goto spapr-pci-vfio-host-bridge. The hostdevs belonging to the same iommu group share the same spapr-pci-vfio-host-bridge. Henceforth, new spapr-pci-host-bridge needs to be added for every hostdev belonging to any new iommu group. The hostdevs should be attached to their respective spapr-pci-vfio-host-bridge. Libvirt today adds all the devices to the default pci domain. The patch series take care to add the new controller. A new pci domain in the guest per controller is created. The hostdevs get their pci address in the respective domain. The patch series taskes care of device addressing in vfio hostdevs, SR-IOV interfaces and network interfaces from SRIOV virtual function pools. Reference: ====== v1: http://www.redhat.com/archives/libvir-list/2014-October/msg00500.html Changes Since v1: * Some minor code clean up and rebase to latest code base after review with Prerna * Patch 2 : Added logic to remove redundant spapr-vfio controllers. * : Moved domaincommon.rng from Patch 4 to Patch 2. --- Shivaprasad G Bhat (4): qemu: Add SPAPR_VFIO_HOST_BRIDGE capability for PPC platform qemu: parse spapr-vfio-pci controller from xml qemu: assign addresses for spapr vfio hostdevices and generate cli qemu: add test case for spapr-pci-vfio-host-bridge docs/schemas/domaincommon.rng | 28 ++ src/bhyve/bhyve_domain.c | 2 src/conf/domain_addr.c | 8 - src/conf/domain_addr.h | 2 src/conf/domain_conf.c | 165 +++++++++++- src/conf/domain_conf.h | 19 + src/libvirt_private.syms | 2 src/qemu/qemu_capabilities.c | 2 src/qemu/qemu_capabilities.h | 1 src/qemu/qemu_command.c | 276 +++++++++++++++++++- src/qemu/qemu_command.h | 17 + src/qemu/qemu_domain.c | 12 - src/qemu/qemu_driver.c | 6 tests/qemuhotplugtest.c | 2 .../qemuxml2argv-hostdev-spapr-vfio.args | 20 + .../qemuxml2argv-hostdev-spapr-vfio.xml | 75 +++++ tests/qemuxml2argvtest.c | 8 + 17 files changed, 609 insertions(+), 36 deletions(-) create mode 100644 tests/qemuxml2argvdata/qemuxml2argv-hostdev-spapr-vfio.args create mode 100644 tests/qemuxml2argvdata/qemuxml2argv-hostdev-spapr-vfio.xml -- Signature

3 10

[libvirt] [PATCH v8 0/4] Introduce API to query IP addresses for given domain
by Nehal J Wani 05 Mar '15

05 Mar '15

This feature has been requested for a very long time. Since qemu guest agent and leaseshelper give us reliable results, now the wait is over. The RFC was first proposed by Michal Privoznik: http://www.redhat.com/archives/libvir-list/2012-February/msg00437.html A patch was submitted, using structs: https://www.redhat.com/archives/libvir-list/2012-June/msg00220.html Another patch was submitted, using XML: https://www.redhat.com/archives/libvir-list/2012-June/msg00904.html Neither of the patches were accepted, probably due to lack of extensibility and usability. Hence, we thought of using virTypedParameters for reporting list of interfaces along with their MAC address and IP addresses. The RFC can be found here: https://www.redhat.com/archives/libvir-list/2013-July/msg00084.html The idea of extensibility was rejected and rendered out of scope of libvirt. Hence, we were back to structs. This API is called virDomainInterfaceAddresses which returns a dynamically allocated array of virDomainInterface struct. The great disadvantage is once this gets released, it's written in stone and we cannot change or add an item into it. The virsh CLI supports two methods: * Return information (list of all associated interfaces with MAC address and IP addresses) of all of the domain interfaces by default (if no interface name is provided) * Return information for the specified interface (if an interface name is provided) v8: * qemuDomainInterfaceAddresses: redo logic related to flags * Make sure that NIC(s) on guest is/are using libvirt virtual network before querying leaseshelper * domifaddr: change --network option from VSH_OT_DATA to VSH_OT_STRING v7: * Enable support for DHCP lease file parsing method * http://www.redhat.com/archives/libvir-list/2014-December/msg00866.html v6: * Inclusion of flags, readonly check for guest agent connection * Correction of memory leaks, other small nits. * https://www.redhat.com/archives/libvir-list/2013-September/msg00350.html v5: * s/virDomainInterfacesAddresses/virDomainInterfaceAddresses. * Case for IP aliasing handled using virHashTable. * New test cases added, involving multiple and 0 IP addresse(s) per interface. * IP prefix changed from int to unsigned int. * Changes to practice libvirt habits. * https://www.redhat.com/archives/libvir-list/2013-September/msg00003.html v4: * Various style nits, indentation errors, memory leaks fixed. * https://www.redhat.com/archives/libvir-list/2013-August/msg01265.html v3: * Upper bounds to number of interfaces and addresses per interface introduced. * Change from array of structs to array of pointers * ifaces_count moved from function argument to return value * Changes in variable names * Test cases added for qemuAgentGetInterfaces. * https://www.redhat.com/archives/libvir-list/2013-August/msg01215.html v2: * Logical errors, memory leaks and few other errors fixed. * https://www.redhat.com/archives/libvir-list/2013-August/msg00631.html v1: * http://www.redhat.com/archives/libvir-list/2013-July/msg01553.html Nehal J Wani (4): domifaddr: Implement the public APIs domifaddr: Implement the remote protocol domifaddr: Implement the API for qemu domifaddr: Add virsh support daemon/remote.c | 134 ++++++++++++++++++++++++++ include/libvirt/libvirt-domain.h | 27 ++++++ src/driver-hypervisor.h | 5 + src/libvirt-domain.c | 129 +++++++++++++++++++++++++ src/libvirt_public.syms | 6 ++ src/qemu/qemu_agent.c | 202 +++++++++++++++++++++++++++++++++++++++ src/qemu/qemu_agent.h | 4 + src/qemu/qemu_driver.c | 173 +++++++++++++++++++++++++++++++++ src/remote/remote_driver.c | 100 +++++++++++++++++++ src/remote/remote_protocol.x | 36 ++++++- src/remote_protocol-structs | 24 +++++ tests/qemuagenttest.c | 188 ++++++++++++++++++++++++++++++++++++ tools/virsh-domain-monitor.c | 141 +++++++++++++++++++++++++++ tools/virsh.pod | 16 ++++ 14 files changed, 1184 insertions(+), 1 deletion(-) -- 2.1.0

4 12

[libvirt] [PATCH] Add ability to set rlimits at container boot
by Ryan Cleere 02 Mar '15

02 Mar '15

--- docs/formatdomain.html.in | 49 +++++++++++++++++++++++ docs/schemas/domaincommon.rng | 89 +++++++++++++++++++++++++++++++++++++++++ src/conf/domain_conf.c | 92 +++++++++++++++++++++++++++++++++++++++++++ src/conf/domain_conf.h | 33 ++++++++++++++++ src/libvirt_private.syms | 1 + src/lxc/lxc_controller.c | 32 +++++++++++++++ src/util/virprocess.c | 4 +- src/util/virprocess.h | 2 + 8 files changed, 300 insertions(+), 2 deletions(-) diff --git a/docs/formatdomain.html.in b/docs/formatdomain.html.in index f8d5f89..5aec51c 100644 --- a/docs/formatdomain.html.in +++ b/docs/formatdomain.html.in @@ -348,6 +348,55 @@ </pre> + <p> + If you want to set an rlimit of the containter init process instead of + inheriting from the host init, set the <code>rlimits</code> element. You + are able to set any of the rlimits that setrlimits is able to set using + any of the following sub-elements: + </p> + + <dl> + <dt><code>as</code></dt> + <dd>Used to set RLIMIT_AS.</dd> + <dt><code>core</code></dt> + <dd>Used to set RLIMIT_CORE.</dd> + <dt><code>cpu</code></dt> + <dd>Used to set RLIMIT_CPU.</dd> + <dt><code>data</code></dt> + <dd>Used to set RLIMIT_DATA.</dd> + <dt><code>fsize</code></dt> + <dd>Used to set RLIMIT_FSIZE.</dd> + <dt><code>locks</code></dt> + <dd>Used to set RLIMIT_LOCKS.</dd> + <dt><code>memlock</code></dt> + <dd>Used to set RLIMIT_MEMLOCK.</dd> + <dt><code>msgqueue</code></dt> + <dd>Used to set RLIMIT_MSGQUEUE.</dd> + <dt><code>nice</code></dt> + <dd>Used to set RLIMIT_NICE.</dd> + <dt><code>nofile</code></dt> + <dd>Used to set RLIMIT_NOFILE.</dd> + <dt><code>nproc</code></dt> + <dd>Used to set RLIMIT_NPROC.</dd> + <dt><code>rss</code></dt> + <dd>Used to set RLIMIT_RSS.</dd> + <dt><code>rtprio</code></dt> + <dd>Used to set RLIMIT_RTPRIO.</dd> + <dt><code>rttime</code></dt> + <dd>Used to set RLIMIT_RTTIME.</dd> + <dt><code>sigpending</code></dt> + <dd>Used to set RLIMIT_SIGPENDING.</dd> + <dt><code>stack</code></dt> + <dd>Used to set RLIMIT_STACK.</dd> + </dl> + + <pre> + <rlimits> + <nofile>10240</nofile> + </rlimits> + </pre> + + <h3><a name="elementsSysinfo">SMBIOS System Information</a></h3> <p> diff --git a/docs/schemas/domaincommon.rng b/docs/schemas/domaincommon.rng index d467dce..b98f8d5 100644 --- a/docs/schemas/domaincommon.rng +++ b/docs/schemas/domaincommon.rng @@ -59,6 +59,9 @@ <ref name="idmap"/> </optional> <optional> + <ref name="rlimits"/> + </optional> + <optional> <ref name="devices"/> </optional> <zeroOrMore> @@ -570,6 +573,92 @@ </interleave> </element> </define> + <define name="rlimits"> + <element name="rlimits"> + <interleave> + <optional> + <element name="cpu"> + <ref name='scaledInteger'/> + </element> + </optional> + <optional> + <element name="fsize"> + <ref name='scaledInteger'/> + </element> + </optional> + <optional> + <element name="data"> + <ref name='scaledInteger'/> + </element> + </optional> + <optional> + <element name="stack"> + <ref name='scaledInteger'/> + </element> + </optional> + <optional> + <element name="core"> + <ref name='scaledInteger'/> + </element> + </optional> + <optional> + <element name="rss"> + <ref name='scaledInteger'/> + </element> + </optional> + <optional> + <element name="nproc"> + <ref name='scaledInteger'/> + </element> + </optional> + <optional> + <element name="nofile"> + <ref name='scaledInteger'/> + </element> + </optional> + <optional> + <element name="memlock"> + <ref name='scaledInteger'/> + </element> + </optional> + <optional> + <element name="as"> + <ref name='scaledInteger'/> + </element> + </optional> + <optional> + <element name="locks"> + <ref name='scaledInteger'/> + </element> + </optional> + <optional> + <element name="sigpending"> + <ref name='scaledInteger'/> + </element> + </optional> + <optional> + <element name="msgqueue"> + <ref name='scaledInteger'/> + </element> + </optional> + <optional> + <element name="nice"> + <ref name='scaledInteger'/> + </element> + </optional> + <optional> + <element name="rtprio"> + <ref name='scaledInteger'/> + </element> + </optional> + <optional> + <element name="rttime"> + <ref name='scaledInteger'/> + </element> + </optional> + </interleave> + </element> + </define> <!-- Resources usage defines the amount of memory (maximum and possibly current usage) and number of virtual CPUs used by that domain. diff --git a/src/conf/domain_conf.c b/src/conf/domain_conf.c index d562e1a..399976e 100644 --- a/src/conf/domain_conf.c +++ b/src/conf/domain_conf.c @@ -772,6 +772,24 @@ VIR_ENUM_IMPL(virDomainLoader, "rom", "pflash") +VIR_ENUM_IMPL(virDomainRLimit, VIR_DOMAIN_RLIMIT_LAST, + "cpu", + "fsize", + "data", + "stack", + "core", + "rss", + "nproc", + "nofile", + "memlock", + "as", + "locks", + "sigpending", + "msgqueue", + "nice", + "rtprio", + "rttime") + /* Internal mapping: subset of block job types that can be present in * <mirror> XML (remaining types are not two-phase). */ VIR_ENUM_DECL(virDomainBlockJob) @@ -979,7 +997,40 @@ virDomainBlkioDeviceParseXML(xmlNodePtr root, return -1; } +static virDomainRLimitsPtr +virDomainRLimitParseXML(xmlNodePtr node) +{ + char *c = NULL; + long long val; + virDomainRLimitsPtr def; + + if (VIR_ALLOC(def) < 0) + return NULL; + if (node->type == XML_ELEMENT_NODE) { + c = (char *)xmlNodeGetContent(node); + if (virStrToLong_ll(c, NULL, 10, &val) < 0) { + virReportError(VIR_ERR_CONFIG_UNSUPPORTED, + _("could not parse rlimit value of %s"), + c); + goto error; + } + VIR_FREE(c); + + def->limit = val; + if ((def->resource = virDomainRLimitTypeFromString((const char *)node->name)) < 0) { + virReportError(VIR_ERR_CONFIG_UNSUPPORTED, + _("could not determine resource type of '%s'"), + node->name); + goto error; + } + } + return def; + error: + VIR_FREE(c); + VIR_FREE(def); + return NULL; +} static void virDomainObjListDataFree(void *payload, const void *name ATTRIBUTE_UNUSED) @@ -14423,6 +14474,34 @@ virDomainDefParseXML(xmlDocPtr xml, virHashFree(bootHash); + if ((node = virXPathNode("./rlimits[1]", ctxt)) != NULL && (n = virXMLChildElementCount(node)) > 0) { + xmlNodePtr cur = node->children; + if (n && VIR_ALLOC_N(def->rlimits, n) < 0) + goto error; + + for (i = 0; i < n; i++) { + if (!(def->rlimits[i] = virDomainRLimitParseXML(cur))) { + for (j = 0; j < i; j++) + VIR_FREE(def->rlimits[j]); + VIR_FREE(def->rlimits); + goto error; + } + def->nrlimits++; + for (j = 0; j < i; j++) { + if (def->rlimits[j]->resource == def->rlimits[i]->resource) { + virReportError(VIR_ERR_XML_ERROR, + _("duplicate rlimit resources '%s'"), + virDomainRLimitTypeToString(def->rlimits[j]->resource)); + for (int k = 0; k < i; k++) + VIR_FREE(def->rlimits[k]); + VIR_FREE(def->rlimits); + goto error; + } + } + cur = cur->next; + } + } + return def; error: @@ -20048,6 +20127,19 @@ virDomainDefFormatInternal(virDomainDefPtr def, goto error; } + if (def->nrlimits > 0) { + virBufferAddLit(buf, "<rlimits>\n"); + virBufferAdjustIndent(buf, 2); + for (n = 0; n < def->nrlimits; n++) { + virBufferAsprintf(buf, "<%s>%lld</%s>\n", + virDomainRLimitTypeToString(def->rlimits[n]->resource), + def->rlimits[n]->limit, + virDomainRLimitTypeToString(def->rlimits[n]->resource)); + } + virBufferAdjustIndent(buf, -2); + virBufferAddLit(buf, "</rlimits>\n"); + } + virBufferAdjustIndent(buf, -2); virBufferAddLit(buf, "</domain>\n"); diff --git a/src/conf/domain_conf.h b/src/conf/domain_conf.h index 93f2314..b032202 100644 --- a/src/conf/domain_conf.h +++ b/src/conf/domain_conf.h @@ -1851,6 +1851,27 @@ typedef enum { VIR_DOMAIN_CLOCK_BASIS_LAST } virDomainClockBasis; +typedef enum { + VIR_DOMAIN_RLIMIT_CPU, + VIR_DOMAIN_RLIMIT_FSIZE, + VIR_DOMAIN_RLIMIT_DATA, + VIR_DOMAIN_RLIMIT_STACK, + VIR_DOMAIN_RLIMIT_CORE, + VIR_DOMAIN_RLIMIT_RSS, + VIR_DOMAIN_RLIMIT_NPROC, + VIR_DOMAIN_RLIMIT_NOFILE, + VIR_DOMAIN_RLIMIT_MEMLOCK, + VIR_DOMAIN_RLIMIT_AS, + VIR_DOMAIN_RLIMIT_LOCKS, + VIR_DOMAIN_RLIMIT_SIGPENDING, + VIR_DOMAIN_RLIMIT_MSGQUEUE, + VIR_DOMAIN_RLIMIT_NICE, + VIR_DOMAIN_RLIMIT_RTPRIO, + VIR_DOMAIN_RLIMIT_RTTIME, + + VIR_DOMAIN_RLIMIT_LAST +} virDomainRLimit; + typedef struct _virDomainClockDef virDomainClockDef; typedef virDomainClockDef *virDomainClockDefPtr; struct _virDomainClockDef { @@ -2039,6 +2060,14 @@ struct _virDomainPowerManagement { int s4; }; +typedef struct _virDomainRLimits virDomainRLimits; +typedef virDomainRLimits *virDomainRLimitsPtr; + +struct _virDomainRLimits { + int resource; + long long limit; +}; + /* * Guest VM main configuration * @@ -2156,6 +2185,9 @@ struct _virDomainDef { size_t nshmems; virDomainShmemDefPtr *shmems; + size_t nrlimits; + virDomainRLimitsPtr *rlimits; + /* Only 1 */ virDomainWatchdogDefPtr watchdog; virDomainMemballoonDefPtr memballoon; @@ -2844,6 +2876,7 @@ VIR_ENUM_DECL(virDomainRNGModel) VIR_ENUM_DECL(virDomainRNGBackend) VIR_ENUM_DECL(virDomainTPMModel) VIR_ENUM_DECL(virDomainTPMBackend) +VIR_ENUM_DECL(virDomainRLimit) /* from libvirt.h */ VIR_ENUM_DECL(virDomainState) VIR_ENUM_DECL(virDomainNostateReason) diff --git a/src/libvirt_private.syms b/src/libvirt_private.syms index bd7870f..7b71ff1 100644 --- a/src/libvirt_private.syms +++ b/src/libvirt_private.syms @@ -1896,6 +1896,7 @@ virProcessGetNamespaces; virProcessGetStartTime; virProcessKill; virProcessKillPainfully; +virProcessPrLimit; virProcessRunInMountNamespace; virProcessSetAffinity; virProcessSetMaxFiles; diff --git a/src/lxc/lxc_controller.c b/src/lxc/lxc_controller.c index 8a7c7e8..5c63a1b 100644 --- a/src/lxc/lxc_controller.c +++ b/src/lxc/lxc_controller.c @@ -798,6 +798,35 @@ static int virLXCControllerSetupCgroupLimits(virLXCControllerPtr ctrl) return ret; } +static int virLXCControllerSetupRLimits(virLXCControllerPtr ctrl) +{ + int i, ret = -1; + struct rlimit rlim; + + VIR_DEBUG("Setting up rlimits"); + + VIR_DEBUG("nrlimits = %d", (int)ctrl->def->nrlimits); + VIR_DEBUG("setting limits on process %d", ctrl->initpid); + if (ctrl->def->nrlimits > 0) { + for (i = 0; i < ctrl->def->nrlimits; i++) { + rlim.rlim_max = rlim.rlim_cur = ctrl->def->rlimits[i]->limit; + VIR_DEBUG("Setting rlimit %s(%d) on pid %d to %lld", + virDomainRLimitTypeToString(ctrl->def->rlimits[i]->resource), + ctrl->def->rlimits[i]->resource, + ctrl->initpid, + ctrl->def->rlimits[i]->limit); + if (virProcessPrLimit(ctrl->initpid, ctrl->def->rlimits[i]->resource, &rlim) < 0) { + virReportSystemError(errno, "%s", + _("Unable to set rlimit")); + goto cleanup; + } + } + } + ret = 0; + cleanup: + return ret; +} + static void virLXCControllerClientCloseHook(virNetServerClientPtr client) { @@ -2318,6 +2347,9 @@ virLXCControllerRun(virLXCControllerPtr ctrl) if (virLXCControllerSetupCgroupLimits(ctrl) < 0) goto cleanup; + if (virLXCControllerSetupRLimits(ctrl) < 0) + goto cleanup; + if (virLXCControllerSetupUserns(ctrl) < 0) goto cleanup; diff --git a/src/util/virprocess.c b/src/util/virprocess.c index d0a1500..d83ae28 100644 --- a/src/util/virprocess.c +++ b/src/util/virprocess.c @@ -676,13 +676,13 @@ int virProcessSetNamespaces(size_t nfdlist, } #if HAVE_PRLIMIT -static int +int virProcessPrLimit(pid_t pid, int resource, struct rlimit *rlim) { return prlimit(pid, resource, rlim, NULL); } #elif HAVE_SETRLIMIT -static int +int virProcessPrLimit(pid_t pid ATTRIBUTE_UNUSED, int resource ATTRIBUTE_UNUSED, struct rlimit *rlim ATTRIBUTE_UNUSED) diff --git a/src/util/virprocess.h b/src/util/virprocess.h index bcaede5..c40b41a 100644 --- a/src/util/virprocess.h +++ b/src/util/virprocess.h @@ -22,6 +22,7 @@ #ifndef __VIR_PROCESS_H__ # define __VIR_PROCESS_H__ +# include <sys/resource.h> # include <sys/types.h> # include "internal.h" @@ -73,4 +74,5 @@ typedef int (*virProcessNamespaceCallback)(pid_t pid, void *opaque); int virProcessRunInMountNamespace(pid_t pid, virProcessNamespaceCallback cb, void *opaque); +int virProcessPrLimit(pid_t pid, int resource, struct rlimit *rlim); #endif /* __VIR_PROCESS_H__ */ -- 1.9.3 (Apple Git-50)

4 6

[libvirt] [PATCH] Fix reporting of i/o errors by iohelper process
by Jason J. Herne 18 Feb '15

18 Feb '15

From: "Jason J. Herne" <jjherne(a)us.ibm.com> libvirt_iohelper is a helper process that is exec'ed and used to handle I/O during a Qemu managed save operation. Due to a missing call to virFileWrapperFdClose, all I/O error messages reported by iohelper are lost. This patch adds a call to virFileWrapperFdClose to the cleanup phase of qemuDomainSaveMemory. This patch also modifies virFileWrapperFdClose such that errors are only reported when the length of the err_msg buffer is > 0. Before now, the existence of the buffer would trigger error reporting in virFileWrapperFdClose. Signed-off-by: Jason J. Herne <jjherne(a)us.ibm.com> --- src/qemu/qemu_driver.c | 1 + src/util/virfile.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/src/qemu/qemu_driver.c b/src/qemu/qemu_driver.c index ecccf6c..8d78805 100644 --- a/src/qemu/qemu_driver.c +++ b/src/qemu/qemu_driver.c @@ -3015,6 +3015,7 @@ qemuDomainSaveMemory(virQEMUDriverPtr driver, cleanup: VIR_FORCE_CLOSE(fd); + virFileWrapperFdClose(wrapperFd); virFileWrapperFdFree(wrapperFd); VIR_FREE(xml); diff --git a/src/util/virfile.c b/src/util/virfile.c index 463064c..813b4f5 100644 --- a/src/util/virfile.c +++ b/src/util/virfile.c @@ -322,7 +322,7 @@ virFileWrapperFdClose(virFileWrapperFdPtr wfd) return 0; ret = virCommandWait(wfd->cmd, NULL); - if (wfd->err_msg) + if (wfd->err_msg && strlen(wfd->err_msg)) VIR_WARN("iohelper reports: %s", wfd->err_msg); return ret; -- 1.8.3.2

4 8

[libvirt] Tunnelled post-copy live migration - support of bidirectional communication over the tunnel
by Vojtech Cima 14 Feb '15

14 Feb '15

Hello everyone, we are very interested about the post-copy live migration mechanism in libvirt [1] using QEMU. Mentioning post-copy in this context means the setup with the first full iteration of standard pre-copy and then switching to the post-copy. VIR_MIGRATE_ENABLE_POSTCOPY, VIR_MIGRATE_POSTCOPY_AFTER_PRECOPY together with VIR_MIGRATE_TUNNELLED flag. Recently we have noticed the issue that post-copy live migration doesn't work over the tunnel since since current tunnel implementation in libvirt supports only uni-directional communication. I spent some time trying to enable bidirectional communication over the tunnel but still facing several issues and I would appreciate any hints how to move forward. The idea is to add a function (probably a callback function) responsible for handling the traffic in the opposite direction (dest->src) reading from the virStream and writing to the QEMU [2]. To be able to do so I replaced the current 'pipe' calls with the 'socketpair' calls to create bidirectional paths. Now, trying to use tunnelled post-copy live migration, it gets initiated, there is some traffic going from source to destination (obviously the pre-copy phase) but at some point it gets stuck on the 'saferead' function [3] which is now blocking. Can this issue issue be linked with the default socket blocking policy? Trying to use standard 'read' function instead of 'saferead' results that the lower data transfers and it seems it's missing significant part of information. Another point is that we suppose that the virStream on its own supports bidirectional communication, is that correct? [1] https://github.com/orbitfp7/qemu/tree/wp3-postcopy [2] http://libvirt.org/git/?p=libvirt.git;a=blob;f=src/qemu/qemu_migration.c;h=… [3] http://libvirt.org/git/?p=libvirt.git;a=blob;f=src/qemu/qemu_migration.c;h=… Thank you very much for any ideas on this topic. Regards, Vojtech

2 3

[libvirt] [PATCH v2 0/2] Followup for NFS root squashed domain save issue
by John Ferlan 11 Feb '15

11 Feb '15

v1 here: http://www.redhat.com/archives/libvir-list/2015-January/msg01029.html Patch 1 of 2 replaces patch 4 from the original series Patch 2 of 2 is the same from the original series John Ferlan (2): virfile: Adjust error path for virFileOpenForked qemu: qemuOpenFileAs - set flag VIR_FILE_OPEN_FORCE_MODE src/qemu/qemu_driver.c | 3 +++ src/util/virfile.c | 65 ++++++++++++++++++++++++++++---------------------- 2 files changed, 40 insertions(+), 28 deletions(-) -- 2.1.0

2 5

[libvirt] [PATCH 0/4] parallels: Better bridged network interfaces support and some fixes
by Maxim Nestratov 09 Feb '15

09 Feb '15

Maxim Nestratov (3): parallels: Fix connecting to parallels driver parallels: better bridge network interface support parallels: don't forget to unlock domain if unregister fails Mikhail Feoktistov (1): parallels: set cpu mode when applying xml configuration

2 9

[libvirt] [RFC PATCH 00/12] Add support for memory hotplug
by Peter Krempa 09 Feb '15

09 Feb '15

!! this series applies on top of the cleanup series posted earlier !! Hi, this is my try to implement memory hotplug in libvirt (for the qemu) driver. This series is almost code-complete but is lacking tests and docs as I wanted to agree on design first before attempting to write the documentation. Additionally this series is also lacking code that would fix memballoon handling but I'm waiting on a clousure how it's supposed to work from qemu's side as it appears to be broken there too. The basic XML used to add a memory device: <memory model='acpi-dimm'> <target> <size unit='KiB'>524287</size> <node>0</node> </target> </memory> The <target> subelement is mandatory, whereas the <source> subelement (that contains source numa nodes, source page size ) is optional and is inferred from the NUMA tuning for given target numa node. Please note that at least one guest numa node has to be configured for the guest for this to work (limitation of qemu). What's missing in this series: - tests - docs - commit message touch-up - code to audit the memory size changes - code to make memory balloning working with correct size Peter Krempa (12): qemu: caps: Add capability bit for the "pc-dimm" device conf: Add support for parsing and formatting max memory and slot count qemu: Implement setup of memory hotplug parameters conf: Add device address type for dimm devices conf: Add interface to parse and format memory device information qemu: memdev: Add infrastructure to load memory device information qemu: migration: Forbid migration with memory modules lacking info qemu: add support for memory devices conf: Introduce helper to find duplicate device address qemu: conf: Add support for memory device cold(un)plug qemu: Implement memory device hotplug qemu: Implement memory device hotunplug docs/formatdomain.html.in | 19 + docs/schemas/domaincommon.rng | 76 +++ src/bhyve/bhyve_domain.c | 9 +- src/conf/domain_conf.c | 655 ++++++++++++++++++++- src/conf/domain_conf.h | 63 ++ src/libvirt_private.syms | 7 + src/libxl/libxl_domain.c | 8 + src/lxc/lxc_domain.c | 8 + src/openvz/openvz_driver.c | 14 +- src/parallels/parallels_driver.c | 6 +- src/phyp/phyp_driver.c | 6 +- src/qemu/qemu_capabilities.c | 2 + src/qemu/qemu_capabilities.h | 1 + src/qemu/qemu_command.c | 157 ++++- src/qemu/qemu_command.h | 15 + src/qemu/qemu_domain.c | 58 ++ src/qemu/qemu_domain.h | 6 + src/qemu/qemu_driver.c | 29 + src/qemu/qemu_hotplug.c | 178 ++++++ src/qemu/qemu_hotplug.h | 6 + src/qemu/qemu_migration.c | 14 + src/qemu/qemu_monitor.c | 45 ++ src/qemu/qemu_monitor.h | 14 + src/qemu/qemu_monitor_json.c | 116 ++++ src/qemu/qemu_monitor_json.h | 5 + src/qemu/qemu_process.c | 4 + src/uml/uml_driver.c | 9 +- src/vbox/vbox_common.c | 6 +- src/vmware/vmware_driver.c | 6 +- src/vmx/vmx.c | 6 +- src/xen/xen_driver.c | 7 + src/xenapi/xenapi_driver.c | 9 +- tests/domainschemadata/maxMemory.xml | 19 + tests/qemucapabilitiesdata/caps_2.1.1-1.caps | 1 + .../qemuxml2argv-memory-hotplug-dimm.xml | 47 ++ .../qemuxml2argv-memory-hotplug-nonuma.xml | 22 + .../qemuxml2argv-memory-hotplug.args | 6 + .../qemuxml2argv-memory-hotplug.xml | 34 ++ tests/qemuxml2argvtest.c | 4 + tests/qemuxml2xmltest.c | 4 + 40 files changed, 1682 insertions(+), 19 deletions(-) create mode 100644 tests/domainschemadata/maxMemory.xml create mode 100644 tests/qemuxml2argvdata/qemuxml2argv-memory-hotplug-dimm.xml create mode 100644 tests/qemuxml2argvdata/qemuxml2argv-memory-hotplug-nonuma.xml create mode 100644 tests/qemuxml2argvdata/qemuxml2argv-memory-hotplug.args create mode 100644 tests/qemuxml2argvdata/qemuxml2argv-memory-hotplug.xml -- 2.2.2

5 33