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&gt; --- 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 @@ &lt;event name='instructions' enabled='yes'/&gt; &lt;event name='cache_references' enabled='no'/&gt; &lt;event name='cache_misses' enabled='no'/&gt; + &lt;event name='branch_instructions' enabled='no'/&gt; &lt;/perf&gt; ... </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