/usr/bin/kvm_stat is in linux-tools-host 4.15.0-30.32.
This file is owned by root:root, with mode 0o755.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 | #!/usr/bin/python
#
# top-like utility for displaying kvm statistics
#
# Copyright 2006-2008 Qumranet Technologies
# Copyright 2008-2011 Red Hat, Inc.
#
# Authors:
# Avi Kivity <avi@redhat.com>
#
# This work is licensed under the terms of the GNU GPL, version 2. See
# the COPYING file in the top-level directory.
"""The kvm_stat module outputs statistics about running KVM VMs
Three different ways of output formatting are available:
- as a top-like text ui
- in a key -> value format
- in an all keys, all values format
The data is sampled from the KVM's debugfs entries and its perf events.
"""
from __future__ import print_function
import curses
import sys
import locale
import os
import time
import optparse
import ctypes
import fcntl
import resource
import struct
import re
import subprocess
from collections import defaultdict, namedtuple
VMX_EXIT_REASONS = {
'EXCEPTION_NMI': 0,
'EXTERNAL_INTERRUPT': 1,
'TRIPLE_FAULT': 2,
'PENDING_INTERRUPT': 7,
'NMI_WINDOW': 8,
'TASK_SWITCH': 9,
'CPUID': 10,
'HLT': 12,
'INVLPG': 14,
'RDPMC': 15,
'RDTSC': 16,
'VMCALL': 18,
'VMCLEAR': 19,
'VMLAUNCH': 20,
'VMPTRLD': 21,
'VMPTRST': 22,
'VMREAD': 23,
'VMRESUME': 24,
'VMWRITE': 25,
'VMOFF': 26,
'VMON': 27,
'CR_ACCESS': 28,
'DR_ACCESS': 29,
'IO_INSTRUCTION': 30,
'MSR_READ': 31,
'MSR_WRITE': 32,
'INVALID_STATE': 33,
'MWAIT_INSTRUCTION': 36,
'MONITOR_INSTRUCTION': 39,
'PAUSE_INSTRUCTION': 40,
'MCE_DURING_VMENTRY': 41,
'TPR_BELOW_THRESHOLD': 43,
'APIC_ACCESS': 44,
'EPT_VIOLATION': 48,
'EPT_MISCONFIG': 49,
'WBINVD': 54,
'XSETBV': 55,
'APIC_WRITE': 56,
'INVPCID': 58,
}
SVM_EXIT_REASONS = {
'READ_CR0': 0x000,
'READ_CR3': 0x003,
'READ_CR4': 0x004,
'READ_CR8': 0x008,
'WRITE_CR0': 0x010,
'WRITE_CR3': 0x013,
'WRITE_CR4': 0x014,
'WRITE_CR8': 0x018,
'READ_DR0': 0x020,
'READ_DR1': 0x021,
'READ_DR2': 0x022,
'READ_DR3': 0x023,
'READ_DR4': 0x024,
'READ_DR5': 0x025,
'READ_DR6': 0x026,
'READ_DR7': 0x027,
'WRITE_DR0': 0x030,
'WRITE_DR1': 0x031,
'WRITE_DR2': 0x032,
'WRITE_DR3': 0x033,
'WRITE_DR4': 0x034,
'WRITE_DR5': 0x035,
'WRITE_DR6': 0x036,
'WRITE_DR7': 0x037,
'EXCP_BASE': 0x040,
'INTR': 0x060,
'NMI': 0x061,
'SMI': 0x062,
'INIT': 0x063,
'VINTR': 0x064,
'CR0_SEL_WRITE': 0x065,
'IDTR_READ': 0x066,
'GDTR_READ': 0x067,
'LDTR_READ': 0x068,
'TR_READ': 0x069,
'IDTR_WRITE': 0x06a,
'GDTR_WRITE': 0x06b,
'LDTR_WRITE': 0x06c,
'TR_WRITE': 0x06d,
'RDTSC': 0x06e,
'RDPMC': 0x06f,
'PUSHF': 0x070,
'POPF': 0x071,
'CPUID': 0x072,
'RSM': 0x073,
'IRET': 0x074,
'SWINT': 0x075,
'INVD': 0x076,
'PAUSE': 0x077,
'HLT': 0x078,
'INVLPG': 0x079,
'INVLPGA': 0x07a,
'IOIO': 0x07b,
'MSR': 0x07c,
'TASK_SWITCH': 0x07d,
'FERR_FREEZE': 0x07e,
'SHUTDOWN': 0x07f,
'VMRUN': 0x080,
'VMMCALL': 0x081,
'VMLOAD': 0x082,
'VMSAVE': 0x083,
'STGI': 0x084,
'CLGI': 0x085,
'SKINIT': 0x086,
'RDTSCP': 0x087,
'ICEBP': 0x088,
'WBINVD': 0x089,
'MONITOR': 0x08a,
'MWAIT': 0x08b,
'MWAIT_COND': 0x08c,
'XSETBV': 0x08d,
'NPF': 0x400,
}
# EC definition of HSR (from arch/arm64/include/asm/kvm_arm.h)
AARCH64_EXIT_REASONS = {
'UNKNOWN': 0x00,
'WFI': 0x01,
'CP15_32': 0x03,
'CP15_64': 0x04,
'CP14_MR': 0x05,
'CP14_LS': 0x06,
'FP_ASIMD': 0x07,
'CP10_ID': 0x08,
'CP14_64': 0x0C,
'ILL_ISS': 0x0E,
'SVC32': 0x11,
'HVC32': 0x12,
'SMC32': 0x13,
'SVC64': 0x15,
'HVC64': 0x16,
'SMC64': 0x17,
'SYS64': 0x18,
'IABT': 0x20,
'IABT_HYP': 0x21,
'PC_ALIGN': 0x22,
'DABT': 0x24,
'DABT_HYP': 0x25,
'SP_ALIGN': 0x26,
'FP_EXC32': 0x28,
'FP_EXC64': 0x2C,
'SERROR': 0x2F,
'BREAKPT': 0x30,
'BREAKPT_HYP': 0x31,
'SOFTSTP': 0x32,
'SOFTSTP_HYP': 0x33,
'WATCHPT': 0x34,
'WATCHPT_HYP': 0x35,
'BKPT32': 0x38,
'VECTOR32': 0x3A,
'BRK64': 0x3C,
}
# From include/uapi/linux/kvm.h, KVM_EXIT_xxx
USERSPACE_EXIT_REASONS = {
'UNKNOWN': 0,
'EXCEPTION': 1,
'IO': 2,
'HYPERCALL': 3,
'DEBUG': 4,
'HLT': 5,
'MMIO': 6,
'IRQ_WINDOW_OPEN': 7,
'SHUTDOWN': 8,
'FAIL_ENTRY': 9,
'INTR': 10,
'SET_TPR': 11,
'TPR_ACCESS': 12,
'S390_SIEIC': 13,
'S390_RESET': 14,
'DCR': 15,
'NMI': 16,
'INTERNAL_ERROR': 17,
'OSI': 18,
'PAPR_HCALL': 19,
'S390_UCONTROL': 20,
'WATCHDOG': 21,
'S390_TSCH': 22,
'EPR': 23,
'SYSTEM_EVENT': 24,
}
IOCTL_NUMBERS = {
'SET_FILTER': 0x40082406,
'ENABLE': 0x00002400,
'DISABLE': 0x00002401,
'RESET': 0x00002403,
}
ENCODING = locale.getpreferredencoding(False)
TRACE_FILTER = re.compile(r'^[^\(]*$')
class Arch(object):
"""Encapsulates global architecture specific data.
Contains the performance event open syscall and ioctl numbers, as
well as the VM exit reasons for the architecture it runs on.
"""
@staticmethod
def get_arch():
machine = os.uname()[4]
if machine.startswith('ppc'):
return ArchPPC()
elif machine.startswith('aarch64'):
return ArchA64()
elif machine.startswith('s390'):
return ArchS390()
else:
# X86_64
for line in open('/proc/cpuinfo'):
if not line.startswith('flags'):
continue
flags = line.split()
if 'vmx' in flags:
return ArchX86(VMX_EXIT_REASONS)
if 'svm' in flags:
return ArchX86(SVM_EXIT_REASONS)
return
def tracepoint_is_child(self, field):
if (TRACE_FILTER.match(field)):
return None
return field.split('(', 1)[0]
class ArchX86(Arch):
def __init__(self, exit_reasons):
self.sc_perf_evt_open = 298
self.ioctl_numbers = IOCTL_NUMBERS
self.exit_reasons = exit_reasons
def debugfs_is_child(self, field):
""" Returns name of parent if 'field' is a child, None otherwise """
return None
class ArchPPC(Arch):
def __init__(self):
self.sc_perf_evt_open = 319
self.ioctl_numbers = IOCTL_NUMBERS
self.ioctl_numbers['ENABLE'] = 0x20002400
self.ioctl_numbers['DISABLE'] = 0x20002401
self.ioctl_numbers['RESET'] = 0x20002403
# PPC comes in 32 and 64 bit and some generated ioctl
# numbers depend on the wordsize.
char_ptr_size = ctypes.sizeof(ctypes.c_char_p)
self.ioctl_numbers['SET_FILTER'] = 0x80002406 | char_ptr_size << 16
self.exit_reasons = {}
def debugfs_is_child(self, field):
""" Returns name of parent if 'field' is a child, None otherwise """
return None
class ArchA64(Arch):
def __init__(self):
self.sc_perf_evt_open = 241
self.ioctl_numbers = IOCTL_NUMBERS
self.exit_reasons = AARCH64_EXIT_REASONS
def debugfs_is_child(self, field):
""" Returns name of parent if 'field' is a child, None otherwise """
return None
class ArchS390(Arch):
def __init__(self):
self.sc_perf_evt_open = 331
self.ioctl_numbers = IOCTL_NUMBERS
self.exit_reasons = None
def debugfs_is_child(self, field):
""" Returns name of parent if 'field' is a child, None otherwise """
if field.startswith('instruction_'):
return 'exit_instruction'
ARCH = Arch.get_arch()
class perf_event_attr(ctypes.Structure):
"""Struct that holds the necessary data to set up a trace event.
For an extensive explanation see perf_event_open(2) and
include/uapi/linux/perf_event.h, struct perf_event_attr
All fields that are not initialized in the constructor are 0.
"""
_fields_ = [('type', ctypes.c_uint32),
('size', ctypes.c_uint32),
('config', ctypes.c_uint64),
('sample_freq', ctypes.c_uint64),
('sample_type', ctypes.c_uint64),
('read_format', ctypes.c_uint64),
('flags', ctypes.c_uint64),
('wakeup_events', ctypes.c_uint32),
('bp_type', ctypes.c_uint32),
('bp_addr', ctypes.c_uint64),
('bp_len', ctypes.c_uint64),
]
def __init__(self):
super(self.__class__, self).__init__()
self.type = PERF_TYPE_TRACEPOINT
self.size = ctypes.sizeof(self)
self.read_format = PERF_FORMAT_GROUP
PERF_TYPE_TRACEPOINT = 2
PERF_FORMAT_GROUP = 1 << 3
class Group(object):
"""Represents a perf event group."""
def __init__(self):
self.events = []
def add_event(self, event):
self.events.append(event)
def read(self):
"""Returns a dict with 'event name: value' for all events in the
group.
Values are read by reading from the file descriptor of the
event that is the group leader. See perf_event_open(2) for
details.
Read format for the used event configuration is:
struct read_format {
u64 nr; /* The number of events */
struct {
u64 value; /* The value of the event */
} values[nr];
};
"""
length = 8 * (1 + len(self.events))
read_format = 'xxxxxxxx' + 'Q' * len(self.events)
return dict(zip([event.name for event in self.events],
struct.unpack(read_format,
os.read(self.events[0].fd, length))))
class Event(object):
"""Represents a performance event and manages its life cycle."""
def __init__(self, name, group, trace_cpu, trace_pid, trace_point,
trace_filter, trace_set='kvm'):
self.libc = ctypes.CDLL('libc.so.6', use_errno=True)
self.syscall = self.libc.syscall
self.name = name
self.fd = None
self._setup_event(group, trace_cpu, trace_pid, trace_point,
trace_filter, trace_set)
def __del__(self):
"""Closes the event's file descriptor.
As no python file object was created for the file descriptor,
python will not reference count the descriptor and will not
close it itself automatically, so we do it.
"""
if self.fd:
os.close(self.fd)
def _perf_event_open(self, attr, pid, cpu, group_fd, flags):
"""Wrapper for the sys_perf_evt_open() syscall.
Used to set up performance events, returns a file descriptor or -1
on error.
Attributes are:
- syscall number
- struct perf_event_attr *
- pid or -1 to monitor all pids
- cpu number or -1 to monitor all cpus
- The file descriptor of the group leader or -1 to create a group.
- flags
"""
return self.syscall(ARCH.sc_perf_evt_open, ctypes.pointer(attr),
ctypes.c_int(pid), ctypes.c_int(cpu),
ctypes.c_int(group_fd), ctypes.c_long(flags))
def _setup_event_attribute(self, trace_set, trace_point):
"""Returns an initialized ctype perf_event_attr struct."""
id_path = os.path.join(PATH_DEBUGFS_TRACING, 'events', trace_set,
trace_point, 'id')
event_attr = perf_event_attr()
event_attr.config = int(open(id_path).read())
return event_attr
def _setup_event(self, group, trace_cpu, trace_pid, trace_point,
trace_filter, trace_set):
"""Sets up the perf event in Linux.
Issues the syscall to register the event in the kernel and
then sets the optional filter.
"""
event_attr = self._setup_event_attribute(trace_set, trace_point)
# First event will be group leader.
group_leader = -1
# All others have to pass the leader's descriptor instead.
if group.events:
group_leader = group.events[0].fd
fd = self._perf_event_open(event_attr, trace_pid,
trace_cpu, group_leader, 0)
if fd == -1:
err = ctypes.get_errno()
raise OSError(err, os.strerror(err),
'while calling sys_perf_event_open().')
if trace_filter:
fcntl.ioctl(fd, ARCH.ioctl_numbers['SET_FILTER'],
trace_filter)
self.fd = fd
def enable(self):
"""Enables the trace event in the kernel.
Enabling the group leader makes reading counters from it and the
events under it possible.
"""
fcntl.ioctl(self.fd, ARCH.ioctl_numbers['ENABLE'], 0)
def disable(self):
"""Disables the trace event in the kernel.
Disabling the group leader makes reading all counters under it
impossible.
"""
fcntl.ioctl(self.fd, ARCH.ioctl_numbers['DISABLE'], 0)
def reset(self):
"""Resets the count of the trace event in the kernel."""
fcntl.ioctl(self.fd, ARCH.ioctl_numbers['RESET'], 0)
class Provider(object):
"""Encapsulates functionalities used by all providers."""
def __init__(self, pid):
self.child_events = False
self.pid = pid
@staticmethod
def is_field_wanted(fields_filter, field):
"""Indicate whether field is valid according to fields_filter."""
if not fields_filter:
return True
return re.match(fields_filter, field) is not None
@staticmethod
def walkdir(path):
"""Returns os.walk() data for specified directory.
As it is only a wrapper it returns the same 3-tuple of (dirpath,
dirnames, filenames).
"""
return next(os.walk(path))
class TracepointProvider(Provider):
"""Data provider for the stats class.
Manages the events/groups from which it acquires its data.
"""
def __init__(self, pid, fields_filter):
self.group_leaders = []
self.filters = self._get_filters()
self.update_fields(fields_filter)
super(TracepointProvider, self).__init__(pid)
@staticmethod
def _get_filters():
"""Returns a dict of trace events, their filter ids and
the values that can be filtered.
Trace events can be filtered for special values by setting a
filter string via an ioctl. The string normally has the format
identifier==value. For each filter a new event will be created, to
be able to distinguish the events.
"""
filters = {}
filters['kvm_userspace_exit'] = ('reason', USERSPACE_EXIT_REASONS)
if ARCH.exit_reasons:
filters['kvm_exit'] = ('exit_reason', ARCH.exit_reasons)
return filters
def _get_available_fields(self):
"""Returns a list of available events of format 'event name(filter
name)'.
All available events have directories under
/sys/kernel/debug/tracing/events/ which export information
about the specific event. Therefore, listing the dirs gives us
a list of all available events.
Some events like the vm exit reasons can be filtered for
specific values. To take account for that, the routine below
creates special fields with the following format:
event name(filter name)
"""
path = os.path.join(PATH_DEBUGFS_TRACING, 'events', 'kvm')
fields = self.walkdir(path)[1]
extra = []
for field in fields:
if field in self.filters:
filter_name_, filter_dicts = self.filters[field]
for name in filter_dicts:
extra.append(field + '(' + name + ')')
fields += extra
return fields
def update_fields(self, fields_filter):
"""Refresh fields, applying fields_filter"""
self.fields = [field for field in self._get_available_fields()
if self.is_field_wanted(fields_filter, field) or
ARCH.tracepoint_is_child(field)]
@staticmethod
def _get_online_cpus():
"""Returns a list of cpu id integers."""
def parse_int_list(list_string):
"""Returns an int list from a string of comma separated integers and
integer ranges."""
integers = []
members = list_string.split(',')
for member in members:
if '-' not in member:
integers.append(int(member))
else:
int_range = member.split('-')
integers.extend(range(int(int_range[0]),
int(int_range[1]) + 1))
return integers
with open('/sys/devices/system/cpu/online') as cpu_list:
cpu_string = cpu_list.readline()
return parse_int_list(cpu_string)
def _setup_traces(self):
"""Creates all event and group objects needed to be able to retrieve
data."""
fields = self._get_available_fields()
if self._pid > 0:
# Fetch list of all threads of the monitored pid, as qemu
# starts a thread for each vcpu.
path = os.path.join('/proc', str(self._pid), 'task')
groupids = self.walkdir(path)[1]
else:
groupids = self._get_online_cpus()
# The constant is needed as a buffer for python libs, std
# streams and other files that the script opens.
newlim = len(groupids) * len(fields) + 50
try:
softlim_, hardlim = resource.getrlimit(resource.RLIMIT_NOFILE)
if hardlim < newlim:
# Now we need CAP_SYS_RESOURCE, to increase the hard limit.
resource.setrlimit(resource.RLIMIT_NOFILE, (newlim, newlim))
else:
# Raising the soft limit is sufficient.
resource.setrlimit(resource.RLIMIT_NOFILE, (newlim, hardlim))
except ValueError:
sys.exit("NOFILE rlimit could not be raised to {0}".format(newlim))
for groupid in groupids:
group = Group()
for name in fields:
tracepoint = name
tracefilter = None
match = re.match(r'(.*)\((.*)\)', name)
if match:
tracepoint, sub = match.groups()
tracefilter = ('%s==%d\0' %
(self.filters[tracepoint][0],
self.filters[tracepoint][1][sub]))
# From perf_event_open(2):
# pid > 0 and cpu == -1
# This measures the specified process/thread on any CPU.
#
# pid == -1 and cpu >= 0
# This measures all processes/threads on the specified CPU.
trace_cpu = groupid if self._pid == 0 else -1
trace_pid = int(groupid) if self._pid != 0 else -1
group.add_event(Event(name=name,
group=group,
trace_cpu=trace_cpu,
trace_pid=trace_pid,
trace_point=tracepoint,
trace_filter=tracefilter))
self.group_leaders.append(group)
@property
def fields(self):
return self._fields
@fields.setter
def fields(self, fields):
"""Enables/disables the (un)wanted events"""
self._fields = fields
for group in self.group_leaders:
for index, event in enumerate(group.events):
if event.name in fields:
event.reset()
event.enable()
else:
# Do not disable the group leader.
# It would disable all of its events.
if index != 0:
event.disable()
@property
def pid(self):
return self._pid
@pid.setter
def pid(self, pid):
"""Changes the monitored pid by setting new traces."""
self._pid = pid
# The garbage collector will get rid of all Event/Group
# objects and open files after removing the references.
self.group_leaders = []
self._setup_traces()
self.fields = self._fields
def read(self, by_guest=0):
"""Returns 'event name: current value' for all enabled events."""
ret = defaultdict(int)
for group in self.group_leaders:
for name, val in group.read().items():
if name not in self._fields:
continue
parent = ARCH.tracepoint_is_child(name)
if parent:
name += ' ' + parent
ret[name] += val
return ret
def reset(self):
"""Reset all field counters"""
for group in self.group_leaders:
for event in group.events:
event.reset()
class DebugfsProvider(Provider):
"""Provides data from the files that KVM creates in the kvm debugfs
folder."""
def __init__(self, pid, fields_filter, include_past):
self.update_fields(fields_filter)
self._baseline = {}
self.do_read = True
self.paths = []
super(DebugfsProvider, self).__init__(pid)
if include_past:
self._restore()
def _get_available_fields(self):
""""Returns a list of available fields.
The fields are all available KVM debugfs files
"""
return self.walkdir(PATH_DEBUGFS_KVM)[2]
def update_fields(self, fields_filter):
"""Refresh fields, applying fields_filter"""
self._fields = [field for field in self._get_available_fields()
if self.is_field_wanted(fields_filter, field) or
ARCH.debugfs_is_child(field)]
@property
def fields(self):
return self._fields
@fields.setter
def fields(self, fields):
self._fields = fields
self.reset()
@property
def pid(self):
return self._pid
@pid.setter
def pid(self, pid):
self._pid = pid
if pid != 0:
vms = self.walkdir(PATH_DEBUGFS_KVM)[1]
if len(vms) == 0:
self.do_read = False
self.paths = filter(lambda x: "{}-".format(pid) in x, vms)
else:
self.paths = []
self.do_read = True
self.reset()
def read(self, reset=0, by_guest=0):
"""Returns a dict with format:'file name / field -> current value'.
Parameter 'reset':
0 plain read
1 reset field counts to 0
2 restore the original field counts
"""
results = {}
# If no debugfs filtering support is available, then don't read.
if not self.do_read:
return results
paths = self.paths
if self._pid == 0:
paths = []
for entry in os.walk(PATH_DEBUGFS_KVM):
for dir in entry[1]:
paths.append(dir)
for path in paths:
for field in self._fields:
value = self._read_field(field, path)
key = path + field
if reset == 1:
self._baseline[key] = value
if reset == 2:
self._baseline[key] = 0
if self._baseline.get(key, -1) == -1:
self._baseline[key] = value
parent = ARCH.debugfs_is_child(field)
if parent:
field = field + ' ' + parent
else:
if by_guest:
field = key.split('-')[0] # set 'field' to 'pid'
increment = value - self._baseline.get(key, 0)
if field in results:
results[field] += increment
else:
results[field] = increment
return results
def _read_field(self, field, path):
"""Returns the value of a single field from a specific VM."""
try:
return int(open(os.path.join(PATH_DEBUGFS_KVM,
path,
field))
.read())
except IOError:
return 0
def reset(self):
"""Reset field counters"""
self._baseline = {}
self.read(1)
def _restore(self):
"""Reset field counters"""
self._baseline = {}
self.read(2)
EventStat = namedtuple('EventStat', ['value', 'delta'])
class Stats(object):
"""Manages the data providers and the data they provide.
It is used to set filters on the provider's data and collect all
provider data.
"""
def __init__(self, options):
self.providers = self._get_providers(options)
self._pid_filter = options.pid
self._fields_filter = options.fields
self.values = {}
self._child_events = False
def _get_providers(self, options):
"""Returns a list of data providers depending on the passed options."""
providers = []
if options.debugfs:
providers.append(DebugfsProvider(options.pid, options.fields,
options.dbgfs_include_past))
if options.tracepoints or not providers:
providers.append(TracepointProvider(options.pid, options.fields))
return providers
def _update_provider_filters(self):
"""Propagates fields filters to providers."""
# As we reset the counters when updating the fields we can
# also clear the cache of old values.
self.values = {}
for provider in self.providers:
provider.update_fields(self._fields_filter)
def reset(self):
self.values = {}
for provider in self.providers:
provider.reset()
@property
def fields_filter(self):
return self._fields_filter
@fields_filter.setter
def fields_filter(self, fields_filter):
if fields_filter != self._fields_filter:
self._fields_filter = fields_filter
self._update_provider_filters()
@property
def pid_filter(self):
return self._pid_filter
@pid_filter.setter
def pid_filter(self, pid):
if pid != self._pid_filter:
self._pid_filter = pid
self.values = {}
for provider in self.providers:
provider.pid = self._pid_filter
@property
def child_events(self):
return self._child_events
@child_events.setter
def child_events(self, val):
self._child_events = val
for provider in self.providers:
provider.child_events = val
def get(self, by_guest=0):
"""Returns a dict with field -> (value, delta to last value) of all
provider data.
Key formats:
* plain: 'key' is event name
* child-parent: 'key' is in format '<child> <parent>'
* pid: 'key' is the pid of the guest, and the record contains the
aggregated event data
These formats are generated by the providers, and handled in class TUI.
"""
for provider in self.providers:
new = provider.read(by_guest=by_guest)
for key in new:
oldval = self.values.get(key, EventStat(0, 0)).value
newval = new.get(key, 0)
newdelta = newval - oldval
self.values[key] = EventStat(newval, newdelta)
return self.values
def toggle_display_guests(self, to_pid):
"""Toggle between collection of stats by individual event and by
guest pid
Events reported by DebugfsProvider change when switching to/from
reading by guest values. Hence we have to remove the excess event
names from self.values.
"""
if any(isinstance(ins, TracepointProvider) for ins in self.providers):
return 1
if to_pid:
for provider in self.providers:
if isinstance(provider, DebugfsProvider):
for key in provider.fields:
if key in self.values.keys():
del self.values[key]
else:
oldvals = self.values.copy()
for key in oldvals:
if key.isdigit():
del self.values[key]
# Update oldval (see get())
self.get(to_pid)
return 0
DELAY_DEFAULT = 3.0
MAX_GUEST_NAME_LEN = 48
MAX_REGEX_LEN = 44
SORT_DEFAULT = 0
class Tui(object):
"""Instruments curses to draw a nice text ui."""
def __init__(self, stats):
self.stats = stats
self.screen = None
self._delay_initial = 0.25
self._delay_regular = DELAY_DEFAULT
self._sorting = SORT_DEFAULT
self._display_guests = 0
def __enter__(self):
"""Initialises curses for later use. Based on curses.wrapper
implementation from the Python standard library."""
self.screen = curses.initscr()
curses.noecho()
curses.cbreak()
# The try/catch works around a minor bit of
# over-conscientiousness in the curses module, the error
# return from C start_color() is ignorable.
try:
curses.start_color()
except curses.error:
pass
# Hide cursor in extra statement as some monochrome terminals
# might support hiding but not colors.
try:
curses.curs_set(0)
except curses.error:
pass
curses.use_default_colors()
return self
def __exit__(self, *exception):
"""Resets the terminal to its normal state. Based on curses.wrapper
implementation from the Python standard library."""
if self.screen:
self.screen.keypad(0)
curses.echo()
curses.nocbreak()
curses.endwin()
@staticmethod
def get_all_gnames():
"""Returns a list of (pid, gname) tuples of all running guests"""
res = []
try:
child = subprocess.Popen(['ps', '-A', '--format', 'pid,args'],
stdout=subprocess.PIPE)
except:
raise Exception
for line in child.stdout:
line = line.decode(ENCODING).lstrip().split(' ', 1)
# perform a sanity check before calling the more expensive
# function to possibly extract the guest name
if ' -name ' in line[1]:
res.append((line[0], Tui.get_gname_from_pid(line[0])))
child.stdout.close()
return res
def _print_all_gnames(self, row):
"""Print a list of all running guests along with their pids."""
self.screen.addstr(row, 2, '%8s %-60s' %
('Pid', 'Guest Name (fuzzy list, might be '
'inaccurate!)'),
curses.A_UNDERLINE)
row += 1
try:
for line in self.get_all_gnames():
self.screen.addstr(row, 2, '%8s %-60s' % (line[0], line[1]))
row += 1
if row >= self.screen.getmaxyx()[0]:
break
except Exception:
self.screen.addstr(row + 1, 2, 'Not available')
@staticmethod
def get_pid_from_gname(gname):
"""Fuzzy function to convert guest name to QEMU process pid.
Returns a list of potential pids, can be empty if no match found.
Throws an exception on processing errors.
"""
pids = []
for line in Tui.get_all_gnames():
if gname == line[1]:
pids.append(int(line[0]))
return pids
@staticmethod
def get_gname_from_pid(pid):
"""Returns the guest name for a QEMU process pid.
Extracts the guest name from the QEMU comma line by processing the
'-name' option. Will also handle names specified out of sequence.
"""
name = ''
try:
line = open('/proc/{}/cmdline'
.format(pid), 'r').read().split('\0')
parms = line[line.index('-name') + 1].split(',')
while '' in parms:
# commas are escaped (i.e. ',,'), hence e.g. 'foo,bar' results
# in # ['foo', '', 'bar'], which we revert here
idx = parms.index('')
parms[idx - 1] += ',' + parms[idx + 1]
del parms[idx:idx+2]
# the '-name' switch allows for two ways to specify the guest name,
# where the plain name overrides the name specified via 'guest='
for arg in parms:
if '=' not in arg:
name = arg
break
if arg[:6] == 'guest=':
name = arg[6:]
except (ValueError, IOError, IndexError):
pass
return name
def _update_pid(self, pid):
"""Propagates pid selection to stats object."""
self.screen.addstr(4, 1, 'Updating pid filter...')
self.screen.refresh()
self.stats.pid_filter = pid
def _refresh_header(self, pid=None):
"""Refreshes the header."""
if pid is None:
pid = self.stats.pid_filter
self.screen.erase()
gname = self.get_gname_from_pid(pid)
if gname:
gname = ('({})'.format(gname[:MAX_GUEST_NAME_LEN] + '...'
if len(gname) > MAX_GUEST_NAME_LEN
else gname))
if pid > 0:
self.screen.addstr(0, 0, 'kvm statistics - pid {0} {1}'
.format(pid, gname), curses.A_BOLD)
else:
self.screen.addstr(0, 0, 'kvm statistics - summary', curses.A_BOLD)
if self.stats.fields_filter:
regex = self.stats.fields_filter
if len(regex) > MAX_REGEX_LEN:
regex = regex[:MAX_REGEX_LEN] + '...'
self.screen.addstr(1, 17, 'regex filter: {0}'.format(regex))
if self._display_guests:
col_name = 'Guest Name'
else:
col_name = 'Event'
self.screen.addstr(2, 1, '%-40s %10s%7s %8s' %
(col_name, 'Total', '%Total', 'CurAvg/s'),
curses.A_STANDOUT)
self.screen.addstr(4, 1, 'Collecting data...')
self.screen.refresh()
def _refresh_body(self, sleeptime):
def insert_child(sorted_items, child, values, parent):
num = len(sorted_items)
for i in range(0, num):
# only add child if parent is present
if parent.startswith(sorted_items[i][0]):
sorted_items.insert(i + 1, (' ' + child, values))
def get_sorted_events(self, stats):
""" separate parent and child events """
if self._sorting == SORT_DEFAULT:
def sortkey(pair):
# sort by (delta value, overall value)
v = pair[1]
return (v.delta, v.value)
else:
def sortkey(pair):
# sort by overall value
v = pair[1]
return v.value
childs = []
sorted_items = []
# we can't rule out child events to appear prior to parents even
# when sorted - separate out all children first, and add in later
for key, values in sorted(stats.items(), key=sortkey,
reverse=True):
if values == (0, 0):
continue
if key.find(' ') != -1:
if not self.stats.child_events:
continue
childs.insert(0, (key, values))
else:
sorted_items.append((key, values))
if self.stats.child_events:
for key, values in childs:
(child, parent) = key.split(' ')
insert_child(sorted_items, child, values, parent)
return sorted_items
row = 3
self.screen.move(row, 0)
self.screen.clrtobot()
stats = self.stats.get(self._display_guests)
total = 0.
ctotal = 0.
for key, values in stats.items():
if self._display_guests:
if self.get_gname_from_pid(key):
total += values.value
continue
if not key.find(' ') != -1:
total += values.value
else:
ctotal += values.value
if total == 0.:
# we don't have any fields, or all non-child events are filtered
total = ctotal
# print events
tavg = 0
tcur = 0
for key, values in get_sorted_events(self, stats):
if row >= self.screen.getmaxyx()[0] - 1 or values == (0, 0):
break
if self._display_guests:
key = self.get_gname_from_pid(key)
if not key:
continue
cur = int(round(values.delta / sleeptime)) if values.delta else ''
if key[0] != ' ':
if values.delta:
tcur += values.delta
ptotal = values.value
ltotal = total
else:
ltotal = ptotal
self.screen.addstr(row, 1, '%-40s %10d%7.1f %8s' % (key,
values.value,
values.value * 100 / float(ltotal), cur))
row += 1
if row == 3:
self.screen.addstr(4, 1, 'No matching events reported yet')
if row > 4:
tavg = int(round(tcur / sleeptime)) if tcur > 0 else ''
self.screen.addstr(row, 1, '%-40s %10d %8s' %
('Total', total, tavg), curses.A_BOLD)
self.screen.refresh()
def _show_msg(self, text):
"""Display message centered text and exit on key press"""
hint = 'Press any key to continue'
curses.cbreak()
self.screen.erase()
(x, term_width) = self.screen.getmaxyx()
row = 2
for line in text:
start = (term_width - len(line)) / 2
self.screen.addstr(row, start, line)
row += 1
self.screen.addstr(row + 1, (term_width - len(hint)) / 2, hint,
curses.A_STANDOUT)
self.screen.getkey()
def _show_help_interactive(self):
"""Display help with list of interactive commands"""
msg = (' b toggle events by guests (debugfs only, honors'
' filters)',
' c clear filter',
' f filter by regular expression',
' g filter by guest name/PID',
' h display interactive commands reference',
' o toggle sorting order (Total vs CurAvg/s)',
' p filter by guest name/PID',
' q quit',
' r reset stats',
' s set update interval',
' x toggle reporting of stats for individual child trace'
' events',
'Any other key refreshes statistics immediately')
curses.cbreak()
self.screen.erase()
self.screen.addstr(0, 0, "Interactive commands reference",
curses.A_BOLD)
self.screen.addstr(2, 0, "Press any key to exit", curses.A_STANDOUT)
row = 4
for line in msg:
self.screen.addstr(row, 0, line)
row += 1
self.screen.getkey()
self._refresh_header()
def _show_filter_selection(self):
"""Draws filter selection mask.
Asks for a valid regex and sets the fields filter accordingly.
"""
msg = ''
while True:
self.screen.erase()
self.screen.addstr(0, 0,
"Show statistics for events matching a regex.",
curses.A_BOLD)
self.screen.addstr(2, 0,
"Current regex: {0}"
.format(self.stats.fields_filter))
self.screen.addstr(5, 0, msg)
self.screen.addstr(3, 0, "New regex: ")
curses.echo()
regex = self.screen.getstr().decode(ENCODING)
curses.noecho()
if len(regex) == 0:
self.stats.fields_filter = ''
self._refresh_header()
return
try:
re.compile(regex)
self.stats.fields_filter = regex
self._refresh_header()
return
except re.error:
msg = '"' + regex + '": Not a valid regular expression'
continue
def _show_set_update_interval(self):
"""Draws update interval selection mask."""
msg = ''
while True:
self.screen.erase()
self.screen.addstr(0, 0, 'Set update interval (defaults to %fs).' %
DELAY_DEFAULT, curses.A_BOLD)
self.screen.addstr(4, 0, msg)
self.screen.addstr(2, 0, 'Change delay from %.1fs to ' %
self._delay_regular)
curses.echo()
val = self.screen.getstr().decode(ENCODING)
curses.noecho()
try:
if len(val) > 0:
delay = float(val)
if delay < 0.1:
msg = '"' + str(val) + '": Value must be >=0.1'
continue
if delay > 25.5:
msg = '"' + str(val) + '": Value must be <=25.5'
continue
else:
delay = DELAY_DEFAULT
self._delay_regular = delay
break
except ValueError:
msg = '"' + str(val) + '": Invalid value'
self._refresh_header()
def _show_vm_selection_by_guest(self):
"""Draws guest selection mask.
Asks for a guest name or pid until a valid guest name or '' is entered.
"""
msg = ''
while True:
self.screen.erase()
self.screen.addstr(0, 0,
'Show statistics for specific guest or pid.',
curses.A_BOLD)
self.screen.addstr(1, 0,
'This might limit the shown data to the trace '
'statistics.')
self.screen.addstr(5, 0, msg)
self._print_all_gnames(7)
curses.echo()
curses.curs_set(1)
self.screen.addstr(3, 0, "Guest or pid [ENTER exits]: ")
guest = self.screen.getstr().decode(ENCODING)
curses.noecho()
pid = 0
if not guest or guest == '0':
break
if guest.isdigit():
if not os.path.isdir(os.path.join('/proc/', guest)):
msg = '"' + guest + '": Not a running process'
continue
pid = int(guest)
break
pids = []
try:
pids = self.get_pid_from_gname(guest)
except:
msg = '"' + guest + '": Internal error while searching, ' \
'use pid filter instead'
continue
if len(pids) == 0:
msg = '"' + guest + '": Not an active guest'
continue
if len(pids) > 1:
msg = '"' + guest + '": Multiple matches found, use pid ' \
'filter instead'
continue
pid = pids[0]
break
curses.curs_set(0)
self._refresh_header(pid)
self._update_pid(pid)
def show_stats(self):
"""Refreshes the screen and processes user input."""
sleeptime = self._delay_initial
self._refresh_header()
start = 0.0 # result based on init value never appears on screen
while True:
self._refresh_body(time.time() - start)
curses.halfdelay(int(sleeptime * 10))
start = time.time()
sleeptime = self._delay_regular
try:
char = self.screen.getkey()
if char == 'b':
self._display_guests = not self._display_guests
if self.stats.toggle_display_guests(self._display_guests):
self._show_msg(['Command not available with '
'tracepoints enabled', 'Restart with '
'debugfs only (see option \'-d\') and '
'try again!'])
self._display_guests = not self._display_guests
self._refresh_header()
if char == 'c':
self.stats.fields_filter = ''
self._refresh_header(0)
self._update_pid(0)
if char == 'f':
curses.curs_set(1)
self._show_filter_selection()
curses.curs_set(0)
sleeptime = self._delay_initial
if char == 'g' or char == 'p':
self._show_vm_selection_by_guest()
sleeptime = self._delay_initial
if char == 'h':
self._show_help_interactive()
if char == 'o':
self._sorting = not self._sorting
if char == 'q':
break
if char == 'r':
self.stats.reset()
if char == 's':
curses.curs_set(1)
self._show_set_update_interval()
curses.curs_set(0)
sleeptime = self._delay_initial
if char == 'x':
self.stats.child_events = not self.stats.child_events
except KeyboardInterrupt:
break
except curses.error:
continue
def batch(stats):
"""Prints statistics in a key, value format."""
try:
s = stats.get()
time.sleep(1)
s = stats.get()
for key, values in sorted(s.items()):
print('%-42s%10d%10d' % (key.split(' ')[0], values.value,
values.delta))
except KeyboardInterrupt:
pass
def log(stats):
"""Prints statistics as reiterating key block, multiple value blocks."""
keys = sorted(stats.get().keys())
def banner():
for key in keys:
print(key.split(' ')[0], end=' ')
print()
def statline():
s = stats.get()
for key in keys:
print(' %9d' % s[key].delta, end=' ')
print()
line = 0
banner_repeat = 20
while True:
try:
time.sleep(1)
if line % banner_repeat == 0:
banner()
statline()
line += 1
except KeyboardInterrupt:
break
def get_options():
"""Returns processed program arguments."""
description_text = """
This script displays various statistics about VMs running under KVM.
The statistics are gathered from the KVM debugfs entries and / or the
currently available perf traces.
The monitoring takes additional cpu cycles and might affect the VM's
performance.
Requirements:
- Access to:
%s
%s/events/*
/proc/pid/task
- /proc/sys/kernel/perf_event_paranoid < 1 if user has no
CAP_SYS_ADMIN and perf events are used.
- CAP_SYS_RESOURCE if the hard limit is not high enough to allow
the large number of files that are possibly opened.
Interactive Commands:
b toggle events by guests (debugfs only, honors filters)
c clear filter
f filter by regular expression
g filter by guest name
h display interactive commands reference
o toggle sorting order (Total vs CurAvg/s)
p filter by PID
q quit
r reset stats
s set update interval
x toggle reporting of stats for individual child trace events
Press any other key to refresh statistics immediately.
""" % (PATH_DEBUGFS_KVM, PATH_DEBUGFS_TRACING)
class PlainHelpFormatter(optparse.IndentedHelpFormatter):
def format_description(self, description):
if description:
return description + "\n"
else:
return ""
def cb_guest_to_pid(option, opt, val, parser):
try:
pids = Tui.get_pid_from_gname(val)
except:
sys.exit('Error while searching for guest "{}". Use "-p" to '
'specify a pid instead?'.format(val))
if len(pids) == 0:
sys.exit('Error: No guest by the name "{}" found'.format(val))
if len(pids) > 1:
sys.exit('Error: Multiple processes found (pids: {}). Use "-p" '
'to specify the desired pid'.format(" ".join(pids)))
parser.values.pid = pids[0]
optparser = optparse.OptionParser(description=description_text,
formatter=PlainHelpFormatter())
optparser.add_option('-1', '--once', '--batch',
action='store_true',
default=False,
dest='once',
help='run in batch mode for one second',
)
optparser.add_option('-i', '--debugfs-include-past',
action='store_true',
default=False,
dest='dbgfs_include_past',
help='include all available data on past events for '
'debugfs',
)
optparser.add_option('-l', '--log',
action='store_true',
default=False,
dest='log',
help='run in logging mode (like vmstat)',
)
optparser.add_option('-t', '--tracepoints',
action='store_true',
default=False,
dest='tracepoints',
help='retrieve statistics from tracepoints',
)
optparser.add_option('-d', '--debugfs',
action='store_true',
default=False,
dest='debugfs',
help='retrieve statistics from debugfs',
)
optparser.add_option('-f', '--fields',
action='store',
default='',
dest='fields',
help='''fields to display (regex)
"-f help" for a list of available events''',
)
optparser.add_option('-p', '--pid',
action='store',
default=0,
type='int',
dest='pid',
help='restrict statistics to pid',
)
optparser.add_option('-g', '--guest',
action='callback',
type='string',
dest='pid',
metavar='GUEST',
help='restrict statistics to guest by name',
callback=cb_guest_to_pid,
)
options, unkn = optparser.parse_args(sys.argv)
if len(unkn) != 1:
sys.exit('Error: Extra argument(s): ' + ' '.join(unkn[1:]))
try:
# verify that we were passed a valid regex up front
re.compile(options.fields)
except re.error:
sys.exit('Error: "' + options.fields + '" is not a valid regular '
'expression')
return options
def check_access(options):
"""Exits if the current user can't access all needed directories."""
if not os.path.exists(PATH_DEBUGFS_TRACING) and (options.tracepoints or
not options.debugfs):
sys.stderr.write("Please enable CONFIG_TRACING in your kernel "
"when using the option -t (default).\n"
"If it is enabled, make {0} readable by the "
"current user.\n"
.format(PATH_DEBUGFS_TRACING))
if options.tracepoints:
sys.exit(1)
sys.stderr.write("Falling back to debugfs statistics!\n")
options.debugfs = True
time.sleep(5)
return options
def assign_globals():
global PATH_DEBUGFS_KVM
global PATH_DEBUGFS_TRACING
debugfs = ''
for line in open('/proc/mounts'):
if line.split(' ')[0] == 'debugfs':
debugfs = line.split(' ')[1]
break
if debugfs == '':
sys.stderr.write("Please make sure that CONFIG_DEBUG_FS is enabled in "
"your kernel, mounted and\nreadable by the current "
"user:\n"
"('mount -t debugfs debugfs /sys/kernel/debug')\n")
sys.exit(1)
PATH_DEBUGFS_KVM = os.path.join(debugfs, 'kvm')
PATH_DEBUGFS_TRACING = os.path.join(debugfs, 'tracing')
if not os.path.exists(PATH_DEBUGFS_KVM):
sys.stderr.write("Please make sure that CONFIG_KVM is enabled in "
"your kernel and that the modules are loaded.\n")
sys.exit(1)
def main():
assign_globals()
options = get_options()
options = check_access(options)
if (options.pid > 0 and
not os.path.isdir(os.path.join('/proc/',
str(options.pid)))):
sys.stderr.write('Did you use a (unsupported) tid instead of a pid?\n')
sys.exit('Specified pid does not exist.')
stats = Stats(options)
if options.fields == 'help':
stats.fields_filter = None
event_list = []
for key in stats.get().keys():
event_list.append(key.split('(', 1)[0])
sys.stdout.write(' ' + '\n '.join(sorted(set(event_list))) + '\n')
sys.exit(0)
if options.log:
log(stats)
elif not options.once:
with Tui(stats) as tui:
tui.show_stats()
else:
batch(stats)
if __name__ == "__main__":
main()
|