- Devel - libvirt List Archives

[libvirt] [PATCH v3] cgroup: Use system reported "unlimited" value for comparison
by Viktor Mihajlovski 07 Dec '16

07 Dec '16

With kernel 3.18 (since commit 3e32cb2e0a12b6915056ff04601cf1bb9b44f967) the "unlimited" value for cgroup memory limits has changed once again as its byte value is now computed from a page counter. The new "unlimited" value reported by the cgroup fs is therefore 2**51-1 pages which is (VIR_DOMAIN_MEMORY_PARAM_UNLIMITED - 3072). This results e.g. in virsh memtune displaying 9007199254740988 instead of unlimited for the limits. This patch uses the value of memory.limit_in_bytes from the cgroup memory root which is the system's "real" unlimited value for comparison. See also libvirt commit 231656bbeb9e4d3bedc44362784c35eee21cf0f4 for the history for kernel 3.12 and before. Signed-off-by: Viktor Mihajlovski <mihajlov(a)linux.vnet.ibm.com> --- v2: - removed RFC verbiage from commit message - per Martin's review comment, cache the cgroup memory.limit_in_bytes - used the cgroup detection logic proposed by Martin, much nicer now indeed - other than initially planned, fall back to VIR_DOMAIN_MEMORY_PARAM_UNLIMITED in case of cgroup read failure, since the usual paranoia fits in nicely with the "already initialized" check. With the current code structure this will never be called when the memory controller is not configured or mounted anyway... - while at it, replaced the goto cleanups with direct returns as there's really no cleanup to be done in the GetMemoryxxxLimit functions v3: - use thread safe one time initialization for the "unlimited" value, to account for 64-bit architectures which do not guarantee atomic memory updates of long long values (which reportedly is the case for ARM). src/util/vircgroup.c | 73 +++++++++++++++++++++++++++++++++++++++------------- 1 file changed, 55 insertions(+), 18 deletions(-) diff --git a/src/util/vircgroup.c b/src/util/vircgroup.c index f151193..b6affe3 100644 --- a/src/util/vircgroup.c +++ b/src/util/vircgroup.c @@ -60,6 +60,7 @@ #include "virsystemd.h" #include "virtypedparam.h" #include "virhostcpu.h" +#include "virthread.h" VIR_LOG_INIT("util.cgroup"); @@ -2452,6 +2453,51 @@ virCgroupGetBlkioDeviceWeight(virCgroupPtr group, } +/* + * Retrieve the "memory.limit_in_bytes" value from the memory controller + * root dir. This value cannot be modified by userspace and therefore + * is the maximum limit value supported by cgroups on the local system. + * Returns this value scaled to KB or falls back to the original + * VIR_DOMAIN_MEMORY_PARAM_UNLIMITED. Either way, remember the return + * value to avoid unnecessary cgroup filesystem access. + */ +static unsigned long long int virCgroupMemoryUnlimitedKB; +static virOnceControl virCgroupMemoryOnce = VIR_ONCE_CONTROL_INITIALIZER; + +static void +virCgroupMemoryOnceInit(void) +{ + virCgroupPtr group; + unsigned long long int mem_unlimited = 0ULL; + + if (virCgroupNew(-1, "/", NULL, -1, &group) < 0) + goto cleanup; + + if (!virCgroupHasController(group, VIR_CGROUP_CONTROLLER_MEMORY)) + goto cleanup; + + ignore_value(virCgroupGetValueU64(group, + VIR_CGROUP_CONTROLLER_MEMORY, + "memory.limit_in_bytes", + &mem_unlimited)); + cleanup: + virCgroupFree(&group); + virCgroupMemoryUnlimitedKB = mem_unlimited >> 10; +} + +static unsigned long long int +virCgroupGetMemoryUnlimitedKB(void) +{ + if (virOnce(&virCgroupMemoryOnce, virCgroupMemoryOnceInit) < 0) + VIR_DEBUG("Init failed, will fall back to defaults."); + + if (virCgroupMemoryUnlimitedKB) + return virCgroupMemoryUnlimitedKB; + else + return VIR_DOMAIN_MEMORY_PARAM_UNLIMITED; +} + + /** * virCgroupSetMemory: * @@ -2534,20 +2580,17 @@ int virCgroupGetMemoryHardLimit(virCgroupPtr group, unsigned long long *kb) { long long unsigned int limit_in_bytes; - int ret = -1; if (virCgroupGetValueU64(group, VIR_CGROUP_CONTROLLER_MEMORY, "memory.limit_in_bytes", &limit_in_bytes) < 0) - goto cleanup; + return -1; *kb = limit_in_bytes >> 10; - if (*kb > VIR_DOMAIN_MEMORY_PARAM_UNLIMITED) + if (*kb >= virCgroupGetMemoryUnlimitedKB()) *kb = VIR_DOMAIN_MEMORY_PARAM_UNLIMITED; - ret = 0; - cleanup: - return ret; + return 0; } @@ -2596,20 +2639,17 @@ int virCgroupGetMemorySoftLimit(virCgroupPtr group, unsigned long long *kb) { long long unsigned int limit_in_bytes; - int ret = -1; if (virCgroupGetValueU64(group, VIR_CGROUP_CONTROLLER_MEMORY, "memory.soft_limit_in_bytes", &limit_in_bytes) < 0) - goto cleanup; + return -1; *kb = limit_in_bytes >> 10; - if (*kb > VIR_DOMAIN_MEMORY_PARAM_UNLIMITED) + if (*kb >= virCgroupGetMemoryUnlimitedKB()) *kb = VIR_DOMAIN_MEMORY_PARAM_UNLIMITED; - ret = 0; - cleanup: - return ret; + return 0; } @@ -2658,20 +2698,17 @@ int virCgroupGetMemSwapHardLimit(virCgroupPtr group, unsigned long long *kb) { long long unsigned int limit_in_bytes; - int ret = -1; if (virCgroupGetValueU64(group, VIR_CGROUP_CONTROLLER_MEMORY, "memory.memsw.limit_in_bytes", &limit_in_bytes) < 0) - goto cleanup; + return -1; *kb = limit_in_bytes >> 10; - if (*kb > VIR_DOMAIN_MEMORY_PARAM_UNLIMITED) + if (*kb >= virCgroupGetMemoryUnlimitedKB()) *kb = VIR_DOMAIN_MEMORY_PARAM_UNLIMITED; - ret = 0; - cleanup: - return ret; + return 0; } -- 1.9.1

2 2

[libvirt] [libvirt-perl PATCH] Add blkdeviotune group_name parameter
by John Ferlan 07 Dec '16

07 Dec '16

Add VIR_DOMAIN_{BLOCK_IOTUNE|TUNABLE_BLKDEV}_GROUP_NAME parameters and the description. Signed-off-by: John Ferlan <jferlan(a)redhat.com> --- Changes | 2 +- Virt.xs | 2 ++ lib/Sys/Virt/Domain.pm | 5 +++++ 3 files changed, 8 insertions(+), 1 deletion(-) diff --git a/Changes b/Changes index 721f036..c9a36dd 100644 --- a/Changes +++ b/Changes @@ -2,7 +2,7 @@ Revision history for perl module Sys::Virt 3.0.0 2017-00-00 - - XXX + - Add group_name for block iotune 2.5.0 2016-12-05 diff --git a/Virt.xs b/Virt.xs index cbf2e7b..ac14feb 100644 --- a/Virt.xs +++ b/Virt.xs @@ -8275,6 +8275,7 @@ BOOT: REGISTER_CONSTANT_STR(VIR_DOMAIN_BLOCK_IOTUNE_READ_IOPS_SEC_MAX, BLOCK_IOTUNE_READ_IOPS_SEC_MAX); REGISTER_CONSTANT_STR(VIR_DOMAIN_BLOCK_IOTUNE_WRITE_IOPS_SEC_MAX, BLOCK_IOTUNE_WRITE_IOPS_SEC_MAX); REGISTER_CONSTANT_STR(VIR_DOMAIN_BLOCK_IOTUNE_SIZE_IOPS_SEC, BLOCK_IOTUNE_SIZE_IOPS_SEC); + REGISTER_CONSTANT_STR(VIR_DOMAIN_BLOCK_IOTUNE_GROUP_NAME, BLOCK_IOTUNE_GROUP_NAME); REGISTER_CONSTANT_STR(VIR_DOMAIN_BLOCK_IOTUNE_TOTAL_BYTES_SEC_MAX_LENGTH, BLOCK_IOTUNE_TOTAL_BYTES_SEC_MAX_LENGTH); REGISTER_CONSTANT_STR(VIR_DOMAIN_BLOCK_IOTUNE_READ_BYTES_SEC_MAX_LENGTH, BLOCK_IOTUNE_READ_BYTES_SEC_MAX_LENGTH); REGISTER_CONSTANT_STR(VIR_DOMAIN_BLOCK_IOTUNE_WRITE_BYTES_SEC_MAX_LENGTH, BLOCK_IOTUNE_WRITE_BYTES_SEC_MAX_LENGTH); @@ -8491,6 +8492,7 @@ BOOT: REGISTER_CONSTANT_STR(VIR_DOMAIN_TUNABLE_BLKDEV_TOTAL_BYTES_SEC_MAX, TUNABLE_BLKDEV_TOTAL_BYTES_SEC_MAX); REGISTER_CONSTANT_STR(VIR_DOMAIN_TUNABLE_BLKDEV_TOTAL_IOPS_SEC_MAX, TUNABLE_BLKDEV_TOTAL_IOPS_SEC_MAX); REGISTER_CONSTANT_STR(VIR_DOMAIN_TUNABLE_BLKDEV_SIZE_IOPS_SEC, TUNABLE_BLKDEV_SIZE_IOPS_SEC); + REGISTER_CONSTANT_STR(VIR_DOMAIN_TUNABLE_BLKDEV_GROUP_NAME, TUNABLE_BLKDEV_GROUP_NAME); REGISTER_CONSTANT_STR(VIR_DOMAIN_TUNABLE_BLKDEV_READ_BYTES_SEC_MAX_LENGTH, TUNABLE_BLKDEV_READ_BYTES_SEC_MAX_LENGTH); REGISTER_CONSTANT_STR(VIR_DOMAIN_TUNABLE_BLKDEV_READ_IOPS_SEC_MAX_LENGTH, TUNABLE_BLKDEV_READ_IOPS_SEC_MAX_LENGTH); REGISTER_CONSTANT_STR(VIR_DOMAIN_TUNABLE_BLKDEV_WRITE_BYTES_SEC_MAX_LENGTH, TUNABLE_BLKDEV_WRITE_BYTES_SEC_MAX_LENGTH); diff --git a/lib/Sys/Virt/Domain.pm b/lib/Sys/Virt/Domain.pm index ba58f26..e11440d 100644 --- a/lib/Sys/Virt/Domain.pm +++ b/lib/Sys/Virt/Domain.pm @@ -2566,6 +2566,11 @@ The maximum I/O operations written per second. The maximum I/O operations per second +=item Sys::Virt::Domain::BLOCK_IOTUNE_GROUP_NAME + +A string representing a group name to allow sharing of I/O +throttling quota between multiple drives + =item Sys::Virt::Domain::BLOCK_IOTUNE_TOTAL_BYTES_SEC_MAX_LENGTH The duration in seconds allowed for maximum total bytes processed per second. -- 2.7.4

2 1

[libvirt] [PATCH] qemu: capabilities: Add gluster.debug_level detection for 2.8.0+
by Peter Krempa 07 Dec '16

07 Dec '16

Qemu 2.8.0+ changes arguments structure for blockdev-add in the effort to make it finally stable. Since libvirt recently added the detection of gluster debug support relying on the old syntax we need to add the new as well. --- src/qemu/qemu_capabilities.c | 1 + tests/qemucapabilitiesdata/caps_2.8.0.x86_64.xml | 1 + 2 files changed, 2 insertions(+) diff --git a/src/qemu/qemu_capabilities.c b/src/qemu/qemu_capabilities.c index df417f2..214f848 100644 --- a/src/qemu/qemu_capabilities.c +++ b/src/qemu/qemu_capabilities.c @@ -1725,6 +1725,7 @@ static struct virQEMUCapsStringFlags virQEMUCapsObjectPropsUSBNECXHCI[] = { /* see documentation for virQEMUCapsQMPSchemaGetByPath for the query format */ static struct virQEMUCapsStringFlags virQEMUCapsQMPSchemaQueries[] = { { "blockdev-add/arg-type/options/+gluster/debug-level", QEMU_CAPS_GLUSTER_DEBUG_LEVEL}, + { "blockdev-add/arg-type/+gluster/debug-level", QEMU_CAPS_GLUSTER_DEBUG_LEVEL}, }; struct virQEMUCapsObjectTypeProps { diff --git a/tests/qemucapabilitiesdata/caps_2.8.0.x86_64.xml b/tests/qemucapabilitiesdata/caps_2.8.0.x86_64.xml index f5e467c..60c53bc 100644 --- a/tests/qemucapabilitiesdata/caps_2.8.0.x86_64.xml +++ b/tests/qemucapabilitiesdata/caps_2.8.0.x86_64.xml @@ -195,6 +195,7 @@ <flag name='ivshmem-plain'/> <flag name='ivshmem-doorbell'/> <flag name='query-qmp-schema'/> + <flag name='gluster.debug_level'/> <flag name='vhost-scsi'/> <flag name='drive-iotune-group'/> <version>2007091</version> -- 2.10.2

2 3

[libvirt] [PATCH] perf: add one more perf event support
by Nitesh Konkar 06 Dec '16

06 Dec '16

With current perf framework, this patch adds support and documentation for branch instructions perf event. Signed-off-by: Nitesh Konkar <nitkon12(a)linux.vnet.ibm.com> --- docs/formatdomain.html.in | 6 ++++ docs/schemas/domaincommon.rng | 1 + include/libvirt/libvirt-domain.h | 10 +++++++ src/libvirt-domain.c | 38 +++++++++++++------------ src/qemu/qemu_driver.c | 1 + src/util/virperf.c | 6 +++- src/util/virperf.h | 9 +++--- tests/genericxml2xmlindata/generic-perf.xml | 1 + tools/virsh.pod | 43 +++++++++++++++-------------- 9 files changed, 72 insertions(+), 43 deletions(-) diff --git a/docs/formatdomain.html.in b/docs/formatdomain.html.in index 6bd02cc..259b2c6 100644 --- a/docs/formatdomain.html.in +++ b/docs/formatdomain.html.in @@ -1927,6 +1927,7 @@ <event name='instructions' enabled='yes'/> <event name='cache_references' enabled='no'/> <event name='cache_misses' enabled='no'/> + <event name='branch_instructions' enabled='no'/> </perf> ... </pre> @@ -1972,6 +1973,11 @@ <td>the count of cache misses by applications running on the platform</td> <td><code>perf.cache_misses</code></td> </tr> + <tr> + <td><code>hardware_instructions</code></td> + <td>the count of hardware instructions by applications running on the platform</td> + <td><code>perf.hardware_instructions</code></td> + </tr> </table> <h3><a name="elementsDevices">Devices</a></h3> diff --git a/docs/schemas/domaincommon.rng b/docs/schemas/domaincommon.rng index bb903ef..5fdc036 100644 --- a/docs/schemas/domaincommon.rng +++ b/docs/schemas/domaincommon.rng @@ -427,6 +427,7 @@ <value>instructions</value> <value>cache_references</value> <value>cache_misses</value> + <value>branch_instructions</value> </choice> </attribute> <attribute name="enabled"> diff --git a/include/libvirt/libvirt-domain.h b/include/libvirt/libvirt-domain.h index a8435ab..aad2541 100644 --- a/include/libvirt/libvirt-domain.h +++ b/include/libvirt/libvirt-domain.h @@ -2125,6 +2125,16 @@ void virDomainStatsRecordListFree(virDomainStatsRecordPtr *stats); */ # define VIR_PERF_PARAM_CPU_CYCLES "cpu_cycles" +/** + * VIR_PERF_PARAM_BRANCH_INSTRUCTIONS: + * + * Macro for typed parameter name that represents branch instructions + * perf event which can be used to measure the count of branch instructions + * by applications running on the platform. It corresponds to the + * "perf.branch_instructions" field in the *Stats APIs. + */ +# define VIR_PERF_PARAM_BRANCH_INSTRUCTIONS "branch_instructions" + int virDomainGetPerfEvents(virDomainPtr dom, virTypedParameterPtr *params, int *nparams, diff --git a/src/libvirt-domain.c b/src/libvirt-domain.c index ce199f0..c12c87f 100644 --- a/src/libvirt-domain.c +++ b/src/libvirt-domain.c @@ -11195,24 +11195,26 @@ virConnectGetDomainCapabilities(virConnectPtr conn, * * VIR_DOMAIN_STATS_PERF: Return perf event statistics. * The typed parameter keys are in this format: - * "perf.cmt" - the usage of l3 cache (bytes) by applications running on the - * platform as unsigned long long. It is produced by cmt perf - * event. - * "perf.mbmt" - the total system bandwidth (bytes/s) from one level of cache - * to another as unsigned long long. It is produced by mbmt perf - * event. - * "perf.mbml" - the amount of data (bytes/s) sent through the memory controller - * on the socket as unsigned long long. It is produced by mbml - * perf event. - * "perf.cache_misses" - the count of cache misses as unsigned long long. - * It is produced by cache_misses perf event. - * "perf.cache_references" - the count of cache hits as unsigned long long. - * It is produced by cache_references perf event. - * "perf.instructions" - The count of instructions as unsigned long long. - * It is produced by instructions perf event. - * "perf.cpu_cycles" - The count of cpu cycles (total/elapsed) as an - * unsigned long long. It is produced by cpu_cycles - * perf event. + * "perf.cmt" - the usage of l3 cache (bytes) by applications running on the + * platform as unsigned long long. It is produced by cmt perf + * event. + * "perf.mbmt" - the total system bandwidth (bytes/s) from one level of cache + * to another as unsigned long long. It is produced by mbmt perf + * event. + * "perf.mbml" - the amount of data (bytes/s) sent through the memory controller + * on the socket as unsigned long long. It is produced by mbml + * perf event. + * "perf.cache_misses" - the count of cache misses as unsigned long long. + * It is produced by cache_misses perf event. + * "perf.cache_references" - the count of cache hits as unsigned long long. + * It is produced by cache_references perf event. + * "perf.instructions" - The count of instructions as unsigned long long. + * It is produced by instructions perf event. + * "perf.cpu_cycles" - The count of cpu cycles (total/elapsed) as an + * unsigned long long. It is produced by cpu_cycles + * perf event. + * "perf.branch_instructions" - The count of branch instructions as unsigned long long. + * It is produced by branch_instructions perf event. * * Note that entire stats groups or individual stat fields may be missing from * the output in case they are not supported by the given hypervisor, are not diff --git a/src/qemu/qemu_driver.c b/src/qemu/qemu_driver.c index 3517aa2..c7fad30 100644 --- a/src/qemu/qemu_driver.c +++ b/src/qemu/qemu_driver.c @@ -9852,6 +9852,7 @@ qemuDomainSetPerfEvents(virDomainPtr dom, VIR_PERF_PARAM_INSTRUCTIONS, VIR_TYPED_PARAM_BOOLEAN, VIR_PERF_PARAM_CACHE_REFERENCES, VIR_TYPED_PARAM_BOOLEAN, VIR_PERF_PARAM_CACHE_MISSES, VIR_TYPED_PARAM_BOOLEAN, + VIR_PERF_PARAM_BRANCH_INSTRUCTIONS, VIR_TYPED_PARAM_BOOLEAN, NULL) < 0) return -1; diff --git a/src/util/virperf.c b/src/util/virperf.c index 5d57962..635faf1 100644 --- a/src/util/virperf.c +++ b/src/util/virperf.c @@ -40,7 +40,8 @@ VIR_LOG_INIT("util.perf"); VIR_ENUM_IMPL(virPerfEvent, VIR_PERF_EVENT_LAST, "cmt", "mbmt", "mbml", "cpu_cycles", "instructions", - "cache_references", "cache_misses"); + "cache_references", "cache_misses", + "branch_instructions"); struct virPerfEvent { int type; @@ -85,6 +86,9 @@ static struct virPerfEventAttr attrs[] = { {.type = VIR_PERF_EVENT_CACHE_MISSES, .attrType = PERF_TYPE_HARDWARE, .attrConfig = PERF_COUNT_HW_CACHE_MISSES}, + {.type = VIR_PERF_EVENT_BRANCH_INSTRUCTIONS, + .attrType = PERF_TYPE_HARDWARE, + .attrConfig = PERF_COUNT_HW_BRANCH_INSTRUCTIONS}, }; typedef struct virPerfEventAttr *virPerfEventAttrPtr; diff --git a/src/util/virperf.h b/src/util/virperf.h index 3fca2d0..e43f332 100644 --- a/src/util/virperf.h +++ b/src/util/virperf.h @@ -32,10 +32,11 @@ typedef enum { VIR_PERF_EVENT_MBMT, /* Memory Bandwidth Monitoring Total */ VIR_PERF_EVENT_MBML, /* Memory Bandwidth Monitor Limit for controller */ - VIR_PERF_EVENT_CPU_CYCLES, /* Count of CPU Cycles (total/elapsed) */ - VIR_PERF_EVENT_INSTRUCTIONS, /* Count of instructions for application */ - VIR_PERF_EVENT_CACHE_REFERENCES, /* Cache hits by applications */ - VIR_PERF_EVENT_CACHE_MISSES, /* Cache misses by applications */ + VIR_PERF_EVENT_CPU_CYCLES, /* Count of CPU Cycles (total/elapsed) */ + VIR_PERF_EVENT_INSTRUCTIONS, /* Count of instructions for application */ + VIR_PERF_EVENT_CACHE_REFERENCES, /* Cache hits by applications */ + VIR_PERF_EVENT_CACHE_MISSES, /* Cache misses by applications */ + VIR_PERF_EVENT_BRANCH_INSTRUCTIONS, /* Count of branch instructions by applications*/ VIR_PERF_EVENT_LAST } virPerfEventType; diff --git a/tests/genericxml2xmlindata/generic-perf.xml b/tests/genericxml2xmlindata/generic-perf.xml index a914133..92e5847 100644 --- a/tests/genericxml2xmlindata/generic-perf.xml +++ b/tests/genericxml2xmlindata/generic-perf.xml @@ -20,6 +20,7 @@ <event name='instructions' enabled='yes'/> <event name='cache_references' enabled='no'/> <event name='cache_misses' enabled='no'/> + <event name='branch_instructions' enabled='yes'/> </perf> <devices> </devices> diff --git a/tools/virsh.pod b/tools/virsh.pod index 247d235..aa5b756 100644 --- a/tools/virsh.pod +++ b/tools/virsh.pod @@ -945,7 +945,8 @@ I<--perf> returns the statistics of all enabled perf events: "perf.cpu_cycles" - the count of cpu cycles (total/elapsed), "perf.instructions" - the count of instructions, "perf.cache_references" - the count of cache hits, -"perf.cache_misses" - the count of caches misses +"perf.cache_misses" - the count of caches misses, +"perf.branch_instructions" - the count of branch instructions See the B<perf> command for more details about each event. @@ -2270,25 +2271,27 @@ performance event. B<eventSpec> is a string list of one or more events separated by commas. Valid event names are as follows: B<Valid perf event names> - cmt - A PQos (Platform Qos) feature to monitor the - usage of cache by applications running on the - platform. - mbmt - Provides a way to monitor the total system - memory bandwidth between one level of cache - and another. - mbml - Provides a way to limit the amount of data - (bytes/s) send through the memory controller - on the socket. - cache_misses - Provides the count of cache misses by - applications running on the platform. - cache_references - Provides the count of cache hits by - applications running on th e platform. - instructions - Provides the count of instructions executed - by applications running on the platform. - cpu_cycles - Provides the count of cpu cycles - (total/elapsed). May be used with - instructions in order to get a cycles - per instruction. + cmt - A PQos (Platform Qos) feature to monitor the + usage of cache by applications running on the + platform. + mbmt - Provides a way to monitor the total system + memory bandwidth between one level of cache + and another. + mbml - Provides a way to limit the amount of data + (bytes/s) send through the memory controller + on the socket. + cache_misses - Provides the count of cache misses by + applications running on the platform. + cache_references - Provides the count of cache hits by + applications running on th e platform. + instructions - Provides the count of instructions executed + by applications running on the platform. + cpu_cycles - Provides the count of cpu cycles + (total/elapsed). May be used with + instructions in order to get a cycles + per instruction. + branch_instructions - Provides the count of branch instructions + executed by applications running on the platform. B<Note>: The statistics can be retrieved using the B<domstats> command using the I<--perf> flag. -- 1.9.3

3 2

[libvirt] [PATCH v5 0/2] List only online cpus for vcpupin/emulatorpin when vcpu placement static
by Nitesh Konkar 06 Dec '16

06 Dec '16

Currently when the vcpu placement is static and cpuset is not specified, CPU Affinity shows 0.. CPUMAX. This patchset will result in display of only online CPU's under CPU Affinity on linux. Fixes the following Bug: virsh dumpxml Fedora <domain type='kvm' id='4'> <name>Fedora</name> <uuid>aecf3e5e-6f9a-42a3-9d6a-223a75569a66</uuid> <maxMemory slots='32' unit='KiB'>3145728</maxMemory> <memory unit='KiB'>524288</memory> <currentMemory unit='KiB'>524288</currentMemory> <vcpu placement='static' current='8'>160</vcpu> <resource> <partition>/machine</partition> </resource> ..................... ....................... ......................... <memballoon model='virtio'> <alias name='balloon0'/> <address type='pci' domain='0x0000' bus='0x00' slot='0x06' function='0x0'/> </memballoon> </devices> <seclabel type='dynamic' model='dac' relabel='yes'> <label>+0:+0</label> <imagelabel>+0:+0</imagelabel> </seclabel> </domain> lscpu Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian CPU(s): 8 On-line CPU(s) list: 0-2,4-7 Off-line CPU(s) list: 3 Thread(s) per core: 1 Core(s) per socket: 7 Socket(s): 1 .......... .......... NUMA node0 CPU(s): 0-2,4-7 NUMA node1 CPU(s): cat /sys/devices/system/cpu/online 0-2,4-7 Before Patch virsh vcpupin Fedora VCPU: CPU Affinity ---------------------------------- 0: 0-7 1: 0-7 ... ... 158: 0-7 159: 0-7 virsh emulatorpin Fedora emulator: CPU Affinity ---------------------------------- *: 0-7 After Patch virsh vcpupin Fedora VCPU: CPU Affinity ---------------------------------- 0: 0-2,4-7 1: 0-2,4-7 ... ... 158: 0-2,4-7 159: 0-2,4-7 virsh emulatorpin Fedora emulator: CPU Affinity ---------------------------------- *: 0-2,4-7 Nitesh Konkar (2): conf: List only online cpus for virsh vcpupin conf: List only online cpus for virsh emulatorpin src/conf/domain_conf.c | 6 ++++++ src/qemu/qemu_driver.c | 5 +++++ 2 files changed, 11 insertions(+) -- 2.1.0

3 7

[libvirt] [RFC PATCH] cgroup: Use system reported "unlimited" value for comparison
by Viktor Mihajlovski 06 Dec '16

06 Dec '16

With kernel 3.18 (since commit 3e32cb2e0a12b6915056ff04601cf1bb9b44f967) the "unlimited" value for cgroup memory limits has changed once again as its byte value is now computed from a page counter. The new "unlimited" value reported by the cgroup fs is therefore 2**51-1 pages which is (VIR_DOMAIN_MEMORY_PARAM_UNLIMITED - 3072). This results e.g. in virsh memtune displaying 9007199254740988 instead of unlimited for the limits. This patch uses the value of memory.limit_in_bytes from the cgroup memory root which is the system's "real" unlimited value for comparison. See also libvirt commit 231656bbeb9e4d3bedc44362784c35eee21cf0f4 for the history for kernel 3.12 and before. I've tested this on F24 with the following configurations: - no memory cgroup controller mounted - memory cgroup controller mounted but not configured for libvirt - memory cgroup controller mounted and configured The first two fail as expected (and as before), the third case works as expected. Testing on other kernel versions highly welcome! Not perfect yet in that we still provide a fallback to the old value. We might consider failing right away if we can't get the system value. I'd be inclined to do that, since we're probably facing principal cgroup issues in this case. Further, it's not the most efficient implementation. Obviously, the unlimited value can be read once and cached. However, I'd like to see the question above resolved first. Signed-off-by: Viktor Mihajlovski <mihajlov(a)linux.vnet.ibm.com> --- src/util/vircgroup.c | 61 ++++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 55 insertions(+), 6 deletions(-) diff --git a/src/util/vircgroup.c b/src/util/vircgroup.c index f151193..969dca5 100644 --- a/src/util/vircgroup.c +++ b/src/util/vircgroup.c @@ -2452,6 +2452,40 @@ virCgroupGetBlkioDeviceWeight(virCgroupPtr group, } +/* + * Retrieve the "memory.limit_in_bytes" value from the memory controller + * root dir. This value cannot be modified by userspace and therefore + * is the maximum limit value supported by cgroups on the local system. + */ +static int +virCgroupGetMemoryUnlimited(unsigned long long int * mem_unlimited) +{ + int ret = -1; + virCgroupPtr group; + + if (VIR_ALLOC(group)) + goto cleanup; + + if (virCgroupDetectMounts(group)) + goto cleanup; + + if (!group->controllers[VIR_CGROUP_CONTROLLER_MEMORY].mountPoint) + goto cleanup; + + if (VIR_STRDUP(group->controllers[VIR_CGROUP_CONTROLLER_MEMORY].placement, + "/.") < 0) + goto cleanup; + + ret = virCgroupGetValueU64(group, + VIR_CGROUP_CONTROLLER_MEMORY, + "memory.limit_in_bytes", + mem_unlimited); + cleanup: + virCgroupFree(&group); + return ret; +} + + /** * virCgroupSetMemory: * @@ -2534,6 +2568,7 @@ int virCgroupGetMemoryHardLimit(virCgroupPtr group, unsigned long long *kb) { long long unsigned int limit_in_bytes; + long long unsigned int unlimited_in_bytes; int ret = -1; if (virCgroupGetValueU64(group, @@ -2541,9 +2576,13 @@ virCgroupGetMemoryHardLimit(virCgroupPtr group, unsigned long long *kb) "memory.limit_in_bytes", &limit_in_bytes) < 0) goto cleanup; - *kb = limit_in_bytes >> 10; - if (*kb > VIR_DOMAIN_MEMORY_PARAM_UNLIMITED) + if (virCgroupGetMemoryUnlimited(&unlimited_in_bytes) < 0) + unlimited_in_bytes = VIR_DOMAIN_MEMORY_PARAM_UNLIMITED << 10; + + if (limit_in_bytes == unlimited_in_bytes) *kb = VIR_DOMAIN_MEMORY_PARAM_UNLIMITED; + else + *kb = limit_in_bytes >> 10; ret = 0; cleanup: @@ -2596,6 +2635,7 @@ int virCgroupGetMemorySoftLimit(virCgroupPtr group, unsigned long long *kb) { long long unsigned int limit_in_bytes; + long long unsigned int unlimited_in_bytes; int ret = -1; if (virCgroupGetValueU64(group, @@ -2603,9 +2643,13 @@ virCgroupGetMemorySoftLimit(virCgroupPtr group, unsigned long long *kb) "memory.soft_limit_in_bytes", &limit_in_bytes) < 0) goto cleanup; - *kb = limit_in_bytes >> 10; - if (*kb > VIR_DOMAIN_MEMORY_PARAM_UNLIMITED) + if (virCgroupGetMemoryUnlimited(&unlimited_in_bytes) < 0) + unlimited_in_bytes = VIR_DOMAIN_MEMORY_PARAM_UNLIMITED << 10; + + if (limit_in_bytes == unlimited_in_bytes) *kb = VIR_DOMAIN_MEMORY_PARAM_UNLIMITED; + else + *kb = limit_in_bytes >> 10; ret = 0; cleanup: @@ -2658,6 +2702,7 @@ int virCgroupGetMemSwapHardLimit(virCgroupPtr group, unsigned long long *kb) { long long unsigned int limit_in_bytes; + long long unsigned int unlimited_in_bytes; int ret = -1; if (virCgroupGetValueU64(group, @@ -2665,9 +2710,13 @@ virCgroupGetMemSwapHardLimit(virCgroupPtr group, unsigned long long *kb) "memory.memsw.limit_in_bytes", &limit_in_bytes) < 0) goto cleanup; - *kb = limit_in_bytes >> 10; - if (*kb > VIR_DOMAIN_MEMORY_PARAM_UNLIMITED) + if (virCgroupGetMemoryUnlimited(&unlimited_in_bytes) < 0) + unlimited_in_bytes = VIR_DOMAIN_MEMORY_PARAM_UNLIMITED << 10; + + if (limit_in_bytes == unlimited_in_bytes) *kb = VIR_DOMAIN_MEMORY_PARAM_UNLIMITED; + else + *kb = limit_in_bytes >> 10; ret = 0; cleanup: -- 1.9.1

2 3

[libvirt] [PATCH python] libvirt-override: fix setBlockIoTune failure passed
by xieyingtai＠huawei.com 06 Dec '16

06 Dec '16

From: Yingtai Xie <xieyingtai(a)huawei.com> virDomainGetBlockIoTune() will be called before setBlockIoTune, as a result, it leads to a failure if set flags with VIR_DOMAIN_AFFECT_LIVE | VIR_DOMAIN_AFFECT_CONFIG which is an reasonable option. Signed-off-by: Yingtai Xie <xieyingtai(a)huawei.com> --- libvirt-override.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/libvirt-override.c b/libvirt-override.c index 2de95ce..caa52fb 100644 --- a/libvirt-override.c +++ b/libvirt-override.c @@ -4805,6 +4805,7 @@ libvirt_virDomainSetBlockIoTune(PyObject *self ATTRIBUTE_UNUSED, Py_ssize_t size = 0; const char *disk; unsigned int flags; + unsigned int flags1 = 0; virTypedParameterPtr params = NULL, new_params = NULL; if (!PyArg_ParseTuple(args, (char *)"OzOI:virDomainSetBlockIoTune", @@ -4822,7 +4823,7 @@ libvirt_virDomainSetBlockIoTune(PyObject *self ATTRIBUTE_UNUSED, } LIBVIRT_BEGIN_ALLOW_THREADS; - i_retval = virDomainGetBlockIoTune(domain, disk, NULL, &nparams, flags); + i_retval = virDomainGetBlockIoTune(domain, disk, NULL, &nparams, flags1); LIBVIRT_END_ALLOW_THREADS; if (i_retval < 0) @@ -4838,7 +4839,7 @@ libvirt_virDomainSetBlockIoTune(PyObject *self ATTRIBUTE_UNUSED, return PyErr_NoMemory(); LIBVIRT_BEGIN_ALLOW_THREADS; - i_retval = virDomainGetBlockIoTune(domain, disk, params, &nparams, flags); + i_retval = virDomainGetBlockIoTune(domain, disk, params, &nparams, flags1); LIBVIRT_END_ALLOW_THREADS; if (i_retval < 0) { -- 1.8.3.1

3 2

[libvirt] [PATCH] Add support for parsing -vga virtio
by Nehal J Wani 06 Dec '16

06 Dec '16

Since a94f0c5c qemu supports '-vga virtio'. Libvirt also supports it since 21373feb. This patch enables libvirt to parse the qemu-argv: virsh domxml-from-native qemu-argv <(echo '/usr/bin/qemu-system-x86_64 -vga virtio') Signed-off-by: Nehal J Wani <nehaljw.kkd1(a)gmail.com> --- src/qemu/qemu_command.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/qemu/qemu_command.c b/src/qemu/qemu_command.c index 4a5fce3..d92bf9d 100644 --- a/src/qemu/qemu_command.c +++ b/src/qemu/qemu_command.c @@ -100,7 +100,7 @@ VIR_ENUM_IMPL(qemuVideo, VIR_DOMAIN_VIDEO_TYPE_LAST, "", /* don't support vbox */ "qxl", "", /* don't support parallels */ - "" /* no need for virtio */); + "virtio"); VIR_ENUM_DECL(qemuDeviceVideo) -- 2.7.4

2 2

[libvirt] [REPOST PATCH v2 0/9] Add group_name support for <iotune>
by John Ferlan 06 Dec '16

06 Dec '16

This is just a REPOST of the v2 series: http://www.redhat.com/archives/libvir-list/2016-November/msg00363.html The only difference being updating to the current top of tree of commit id '0b4c3bd30'. I did *not* add the NEWS change yet as that's newer than this, but will update NEWS with this once/if this is ACK'd using whatever format becomes agreed upon for the file contents/formatting options. John Ferlan (9): include: Add new "group_name" definition for iotune throttling caps: Add new capability for the iotune group name qemu: Adjust maxparams logic for qemuDomainGetBlockIoTune qemu: Alter qemuMonitorJSONSetBlockIoThrottle command logic qemu: Adjust various bool BlockIoTune set_ values into mask qemu: Add support for parsing iotune group setting conf: Add support for blkiotune group_name option qemu: Add the group name option to the iotune command line virsh: Add group name to blkdeviotune output docs/formatdomain.html.in | 11 ++ docs/schemas/domaincommon.rng | 5 + include/libvirt/libvirt-domain.h | 15 ++ src/conf/domain_conf.c | 10 ++ src/conf/domain_conf.h | 1 + src/qemu/qemu_capabilities.c | 2 + src/qemu/qemu_capabilities.h | 1 + src/qemu/qemu_command.c | 13 ++ src/qemu/qemu_driver.c | 177 +++++++++++++-------- src/qemu/qemu_monitor.c | 2 + src/qemu/qemu_monitor.h | 1 + src/qemu/qemu_monitor_json.c | 97 ++++++----- src/qemu/qemu_monitor_json.h | 1 + tests/qemucapabilitiesdata/caps_2.4.0.x86_64.xml | 1 + tests/qemucapabilitiesdata/caps_2.5.0.x86_64.xml | 1 + .../caps_2.6.0-gicv2.aarch64.xml | 1 + .../caps_2.6.0-gicv3.aarch64.xml | 1 + tests/qemucapabilitiesdata/caps_2.6.0.ppc64le.xml | 1 + tests/qemucapabilitiesdata/caps_2.6.0.x86_64.xml | 1 + tests/qemucapabilitiesdata/caps_2.7.0.x86_64.xml | 1 + tests/qemumonitorjsontest.c | 88 +++++++--- .../qemuxml2argv-blkdeviotune-group-num.args | 32 ++++ .../qemuxml2argv-blkdeviotune-group-num.xml | 61 +++++++ tests/qemuxml2argvtest.c | 4 + .../qemuxml2xmlout-blkdeviotune-group-num.xml | 1 + tests/qemuxml2xmltest.c | 1 + tools/virsh-domain.c | 17 ++ tools/virsh.pod | 5 +- 28 files changed, 428 insertions(+), 124 deletions(-) create mode 100644 tests/qemuxml2argvdata/qemuxml2argv-blkdeviotune-group-num.args create mode 100644 tests/qemuxml2argvdata/qemuxml2argv-blkdeviotune-group-num.xml create mode 120000 tests/qemuxml2xmloutdata/qemuxml2xmlout-blkdeviotune-group-num.xml -- 2.7.4

2 26

[libvirt] [PATCH] cpu: Add support for pku and ospke Intel features for Memory Protection Keys
by Lin Ma 06 Dec '16

06 Dec '16

qemu commit: f74eefe0 https://lwn.net/Articles/667156/ Signed-off-by: Lin Ma <lma(a)suse.com> --- src/cpu/cpu_map.xml | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/src/cpu/cpu_map.xml b/src/cpu/cpu_map.xml index 6da8321..dca5720 100644 --- a/src/cpu/cpu_map.xml +++ b/src/cpu/cpu_map.xml @@ -255,6 +255,13 @@ <cpuid eax_in='0x07' ebx='0x10000000'/> </feature> + <feature name='pku'> + <cpuid eax_in='0x07' ecx='0x00000008'/> + </feature> + <feature name='ospke'> + <cpuid eax_in='0x07' ecx='0x00000010'/> + </feature> +  <feature name='xsaveopt'> <cpuid eax_in='0x0d' ecx_in='0x01' eax='0x00000001'/> -- 2.9.2

2 1