brintos

brintos / linux-shallow public Read only

0
0
Text · 5.3 KiB · c26524d Raw
159 lines · plain
1perf-kvm(1)2===========3 4NAME5----6perf-kvm - Tool to trace/measure kvm guest os7 8SYNOPSIS9--------10[verse]11'perf kvm' [--host] [--guest] [--guestmount=<path>12	[--guestkallsyms=<path> --guestmodules=<path> | --guestvmlinux=<path>]]13	{top|record|report|diff|buildid-list} [<options>]14'perf kvm' [--host] [--guest] [--guestkallsyms=<path> --guestmodules=<path>15	| --guestvmlinux=<path>] {top|record|report|diff|buildid-list|stat} [<options>]16'perf kvm stat [record|report|live] [<options>]17 18DESCRIPTION19-----------20There are a couple of variants of perf kvm:21 22  'perf kvm [options] top <command>' to generates and displays23  a performance counter profile of guest os in realtime24  of an arbitrary workload.25 26  'perf kvm record <command>' to record the performance counter profile27  of an arbitrary workload and save it into a perf data file. We set the28  default behavior of perf kvm as --guest, so if neither --host nor --guest29  is input, the perf data file name is perf.data.guest. If --host is input,30  the perf data file name is perf.data.kvm. If you want to record data into31  perf.data.host, please input --host --no-guest. The behaviors are shown as32  following:33    Default('')         ->  perf.data.guest34    --host              ->  perf.data.kvm35    --guest             ->  perf.data.guest36    --host --guest      ->  perf.data.kvm37    --host --no-guest   ->  perf.data.host38 39  'perf kvm report' to display the performance counter profile information40  recorded via perf kvm record.41 42  'perf kvm diff' to displays the performance difference amongst two perf.data43  files captured via perf record.44 45  'perf kvm buildid-list' to  display the buildids found in a perf data file,46  so that other tools can be used to fetch packages with matching symbol tables47  for use by perf report. As buildid is read from /sys/kernel/notes in os, then48  if you want to list the buildid for guest, please make sure your perf data file49  was captured with --guestmount in perf kvm record.50 51  'perf kvm stat <command>' to run a command and gather performance counter52  statistics.53  Especially, perf 'kvm stat record/report' generates a statistical analysis54  of KVM events. Currently, vmexit, mmio (x86 only) and ioport (x86 only)55  events are supported. 'perf kvm stat record <command>' records kvm events56  and the events between start and end <command>.57  And this command produces a file which contains tracing results of kvm58  events.59 60  'perf kvm stat report' reports statistical data which includes events61  handled sample, percent_sample, time, percent_time, max_t, min_t, mean_t.62 63  'perf kvm stat live' reports statistical data in a live mode (similar to64  record + report but with statistical data updated live at a given display65  rate).66 67OPTIONS68-------69-i::70--input=<path>::71        Input file name, for the 'report', 'diff' and 'buildid-list' subcommands.72-o::73--output=<path>::74        Output file name, for the 'record' subcommand. Doesn't work with 'report',75        just redirect the output to a file when using 'report'.76--host::77        Collect host side performance profile.78--guest::79        Collect guest side performance profile.80 81:GMEXAMPLECMD: kvm --host --guest82:GMEXAMPLESUBCMD: top83include::guest-files.txt[]84 85--stdio:: Use the stdio interface.86 87-v::88--verbose::89	Be more verbose (show counter open errors, etc).90 91STAT REPORT OPTIONS92-------------------93--vcpu=<value>::94       analyze events which occur on this vcpu. (default: all vcpus)95 96--event=<value>::97       event to be analyzed. Possible values: vmexit, mmio (x86 only),98       ioport (x86 only). (default: vmexit)99-k::100--key=<value>::101       Sorting key. Possible values: sample (default, sort by samples102       number), percent_sample (sort by sample percentage), time103       (sort by average time), precent_time (sort by time percentage),104       max_t (sort by maximum time), min_t (sort by minimum time), mean_t105       (sort by mean time).106-p::107--pid=::108    Analyze events only for given process ID(s) (comma separated list).109 110STAT LIVE OPTIONS111-----------------112-d::113--display::114        Time in seconds between display updates115 116-m::117--mmap-pages=::118        Number of mmap data pages (must be a power of two) or size119        specification in bytes with appended unit character - B/K/M/G.120        The size is rounded up to the nearest power-of-two page value.121 122-a::123--all-cpus::124        System-wide collection from all CPUs.125 126-p::127--pid=::128    Analyze events only for given process ID(s) (comma separated list).129 130--vcpu=<value>::131       analyze events which occur on this vcpu. (default: all vcpus)132 133 134--event=<value>::135       event to be analyzed. Possible values: vmexit,136       mmio (x86 only), ioport (x86 only).137       (default: vmexit)138 139-k::140--key=<value>::141       Sorting key. Possible values: sample (default, sort by samples142       number), time (sort by average time).143 144--duration=<value>::145       Show events other than HLT (x86 only) or Wait state (s390 only)146       that take longer than duration usecs.147 148--proc-map-timeout::149	When processing pre-existing threads /proc/XXX/mmap, it may take150	a long time, because the file may be huge. A time out is needed151	in such cases.152	This option sets the time out limit. The default value is 500 ms.153 154SEE ALSO155--------156linkperf:perf-top[1], linkperf:perf-record[1], linkperf:perf-report[1],157linkperf:perf-diff[1], linkperf:perf-buildid-list[1],158linkperf:perf-stat[1]159