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
|
#
# Copyright (c) 2009-Present, Redis Ltd.
# All rights reserved.
#
# Copyright (c) 2024-present, Valkey contributors.
# All rights reserved.
#
# Licensed under your choice of (a) the Redis Source Available License 2.0
# (RSALv2); or (b) the Server Side Public License v1 (SSPLv1); or (c) the
# GNU Affero General Public License v3 (AGPLv3).
#
# Portions of this file are available under BSD3 terms; see REDISCONTRIBUTIONS for more information.
#
proc log_file_matches {log pattern} {
set fp [open $log r]
set content [read $fp]
close $fp
string match $pattern $content
}
start_server {tags {"repl network external:skip"}} {
set slave [srv 0 client]
set slave_host [srv 0 host]
set slave_port [srv 0 port]
set slave_log [srv 0 stdout]
start_server {} {
set master [srv 0 client]
set master_host [srv 0 host]
set master_port [srv 0 port]
# Configure the master in order to hang waiting for the BGSAVE
# operation, so that the slave remains in the handshake state.
$master config set repl-diskless-sync yes
$master config set repl-diskless-sync-delay 1000
# Start the replication process...
$slave slaveof $master_host $master_port
test {Slave enters handshake} {
wait_for_condition 50 1000 {
[string match *handshake* [$slave role]]
} else {
fail "Replica does not enter handshake state"
}
}
test {Slave enters wait_bgsave} {
# Wait until the rdbchannel is connected to prevent the following
# 'debug sleep' occurring during the rdbchannel handshake.
wait_for_condition 50 1000 {
[string match *state=wait_bgsave* [$master info replication]] &&
[llength [split [string trim [$master client list type slave]] "\r\n"]] == 2
} else {
fail "Replica does not enter wait_bgsave state"
}
}
# Use a short replication timeout on the slave, so that if there
# are no bugs the timeout is triggered in a reasonable amount
# of time.
$slave config set repl-timeout 5
# But make the master unable to send
# the periodic newlines to refresh the connection. The slave
# should detect the timeout.
$master debug sleep 10
test {Slave is able to detect timeout during handshake} {
wait_for_condition 50 1000 {
[log_file_matches $slave_log "*Timeout connecting to the MASTER*"]
} else {
fail "Replica is not able to detect timeout"
}
}
}
}
start_server {tags {"repl external:skip"}} {
set A [srv 0 client]
set A_host [srv 0 host]
set A_port [srv 0 port]
start_server {} {
set B [srv 0 client]
set B_host [srv 0 host]
set B_port [srv 0 port]
test {Set instance A as slave of B} {
$A slaveof $B_host $B_port
wait_for_condition 50 100 {
[lindex [$A role] 0] eq {slave} &&
[string match {*master_link_status:up*} [$A info replication]]
} else {
fail "Can't turn the instance into a replica"
}
}
test {INCRBYFLOAT replication, should not remove expire} {
r set test 1 EX 100
r incrbyfloat test 0.1
wait_for_ofs_sync $A $B
assert_equal [$A debug digest] [$B debug digest]
}
test {GETSET replication} {
$A config resetstat
$A config set loglevel debug
$B config set loglevel debug
r set test foo
assert_equal [r getset test bar] foo
wait_for_condition 500 10 {
[$A get test] eq "bar"
} else {
fail "getset wasn't propagated"
}
assert_equal [r set test vaz get] bar
wait_for_condition 500 10 {
[$A get test] eq "vaz"
} else {
fail "set get wasn't propagated"
}
assert_match {*calls=3,*} [cmdrstat set $A]
assert_match {} [cmdrstat getset $A]
}
test {BRPOPLPUSH replication, when blocking against empty list} {
$A config resetstat
set rd [redis_deferring_client]
$rd brpoplpush a b 5
wait_for_blocked_client
r lpush a foo
wait_for_ofs_sync $B $A
assert_equal [$A debug digest] [$B debug digest]
assert_match {*calls=1,*} [cmdrstat rpoplpush $A]
assert_match {} [cmdrstat lmove $A]
assert_equal [$rd read] {foo}
$rd close
}
test {BRPOPLPUSH replication, list exists} {
$A config resetstat
r lpush c 1
r lpush c 2
r lpush c 3
assert_equal [r brpoplpush c d 5] {1}
wait_for_ofs_sync $B $A
assert_equal [$A debug digest] [$B debug digest]
assert_match {*calls=1,*} [cmdrstat rpoplpush $A]
assert_match {} [cmdrstat lmove $A]
}
foreach wherefrom {left right} {
foreach whereto {left right} {
test "BLMOVE ($wherefrom, $whereto) replication, when blocking against empty list" {
$A config resetstat
set rd [redis_deferring_client]
$rd blmove a b $wherefrom $whereto 5
$rd flush
wait_for_blocked_client
r lpush a foo
wait_for_ofs_sync $B $A
assert_equal [$A debug digest] [$B debug digest]
assert_match {*calls=1,*} [cmdrstat lmove $A]
assert_match {} [cmdrstat rpoplpush $A]
assert_equal [$rd read] {foo}
$rd close
}
test "BLMOVE ($wherefrom, $whereto) replication, list exists" {
$A config resetstat
r lpush c 1
r lpush c 2
r lpush c 3
r blmove c d $wherefrom $whereto 5
wait_for_ofs_sync $B $A
assert_equal [$A debug digest] [$B debug digest]
assert_match {*calls=1,*} [cmdrstat lmove $A]
assert_match {} [cmdrstat rpoplpush $A]
}
}
}
test {BLPOP followed by role change, issue #2473} {
set rd [redis_deferring_client]
$rd blpop foo 0 ; # Block while B is a master
wait_for_blocked_client
# Turn B into master of A
$A slaveof no one
$B slaveof $A_host $A_port
wait_for_condition 50 100 {
[lindex [$B role] 0] eq {slave} &&
[string match {*master_link_status:up*} [$B info replication]]
} else {
fail "Can't turn the instance into a replica"
}
# Push elements into the "foo" list of the new replica.
# If the client is still attached to the instance, we'll get
# a desync between the two instances.
$A rpush foo a b c
wait_for_ofs_sync $B $A
wait_for_condition 50 100 {
[$A debug digest] eq [$B debug digest] &&
[$A lrange foo 0 -1] eq {a b c} &&
[$B lrange foo 0 -1] eq {a b c}
} else {
fail "Master and replica have different digest: [$A debug digest] VS [$B debug digest]"
}
assert_match {*calls=1,*,rejected_calls=0,failed_calls=1*} [cmdrstat blpop $B]
assert_error {UNBLOCKED*} {$rd read}
$rd close
}
}
}
start_server {tags {"repl external:skip"}} {
r set mykey foo
start_server {} {
test {Second server should have role master at first} {
s role
} {master}
test {SLAVEOF should start with link status "down"} {
r multi
r slaveof [srv -1 host] [srv -1 port]
r info replication
r exec
} {*master_link_status:down*}
test {The role should immediately be changed to "replica"} {
s role
} {slave}
wait_for_sync r
test {Sync should have transferred keys from master} {
r get mykey
} {foo}
test {The link status should be up} {
s master_link_status
} {up}
test {SET on the master should immediately propagate} {
r -1 set mykey bar
wait_for_condition 500 100 {
[r 0 get mykey] eq {bar}
} else {
fail "SET on master did not propagated on replica"
}
}
test {FLUSHDB / FLUSHALL should replicate} {
# we're attaching to a sub-replica, so we need to stop pings on the real master
r -1 config set repl-ping-replica-period 3600
set repl [attach_to_replication_stream]
r -1 set key value
r -1 flushdb
r -1 set key value2
r -1 flushall
wait_for_ofs_sync [srv 0 client] [srv -1 client]
assert_equal [r -1 dbsize] 0
assert_equal [r 0 dbsize] 0
# DB is empty.
r -1 flushdb
r -1 flushdb
r -1 eval {redis.call("flushdb")} 0
# DBs are empty.
r -1 flushall
r -1 flushall
r -1 eval {redis.call("flushall")} 0
# add another command to check nothing else was propagated after the above
r -1 incr x
# Assert that each FLUSHDB command is replicated even the DB is empty.
# Assert that each FLUSHALL command is replicated even the DBs are empty.
assert_replication_stream $repl {
{set key value}
{flushdb}
{set key value2}
{flushall}
{flushdb}
{flushdb}
{flushdb}
{flushall}
{flushall}
{flushall}
{incr x}
}
close_replication_stream $repl
}
test {ROLE in master reports master with a slave} {
set res [r -1 role]
lassign $res role offset slaves
assert {$role eq {master}}
assert {$offset > 0}
assert {[llength $slaves] == 1}
lassign [lindex $slaves 0] master_host master_port slave_offset
assert {$slave_offset <= $offset}
}
test {ROLE in slave reports slave in connected state} {
set res [r role]
lassign $res role master_host master_port slave_state slave_offset
assert {$role eq {slave}}
assert {$slave_state eq {connected}}
}
}
}
foreach mdl {no yes} rdbchannel {no yes} {
foreach sdl {disabled swapdb} {
start_server {tags {"repl external:skip"} overrides {save {}}} {
set master [srv 0 client]
$master config set repl-diskless-sync $mdl
$master config set repl-diskless-sync-delay 5
$master config set repl-diskless-sync-max-replicas 3
set master_host [srv 0 host]
set master_port [srv 0 port]
set slaves {}
start_server {overrides {save {}}} {
lappend slaves [srv 0 client]
start_server {overrides {save {}}} {
lappend slaves [srv 0 client]
start_server {overrides {save {}}} {
lappend slaves [srv 0 client]
test "Connect multiple replicas at the same time (issue #141), master diskless=$mdl, replica diskless=$sdl, rdbchannel=$rdbchannel" {
$master config set repl-rdb-channel $rdbchannel
[lindex $slaves 0] config set repl-rdb-channel $rdbchannel
[lindex $slaves 1] config set repl-rdb-channel $rdbchannel
[lindex $slaves 2] config set repl-rdb-channel $rdbchannel
# start load handles only inside the test, so that the test can be skipped
set load_handle0 [start_bg_complex_data $master_host $master_port 9 100000000]
set load_handle1 [start_bg_complex_data $master_host $master_port 11 100000000]
set load_handle2 [start_bg_complex_data $master_host $master_port 12 100000000]
set load_handle3 [start_write_load $master_host $master_port 8]
set load_handle4 [start_write_load $master_host $master_port 4]
after 5000 ;# wait for some data to accumulate so that we have RDB part for the fork
# Send SLAVEOF commands to slaves
[lindex $slaves 0] config set repl-diskless-load $sdl
[lindex $slaves 1] config set repl-diskless-load $sdl
[lindex $slaves 2] config set repl-diskless-load $sdl
[lindex $slaves 0] slaveof $master_host $master_port
[lindex $slaves 1] slaveof $master_host $master_port
[lindex $slaves 2] slaveof $master_host $master_port
# Wait for all the three slaves to reach the "online"
# state from the POV of the master.
set retry 500
while {$retry} {
set info [r -3 info]
if {[string match {*slave0:*state=online*slave1:*state=online*slave2:*state=online*} $info]} {
break
} else {
incr retry -1
after 100
}
}
if {$retry == 0} {
error "assertion:Slaves not correctly synchronized"
}
# Wait that slaves acknowledge they are online so
# we are sure that DBSIZE and DEBUG DIGEST will not
# fail because of timing issues.
wait_for_condition 500 100 {
[lindex [[lindex $slaves 0] role] 3] eq {connected} &&
[lindex [[lindex $slaves 1] role] 3] eq {connected} &&
[lindex [[lindex $slaves 2] role] 3] eq {connected}
} else {
fail "Slaves still not connected after some time"
}
# Stop the write load
stop_bg_complex_data $load_handle0
stop_bg_complex_data $load_handle1
stop_bg_complex_data $load_handle2
stop_write_load $load_handle3
stop_write_load $load_handle4
# Make sure no more commands processed
wait_load_handlers_disconnected -3
wait_for_ofs_sync $master [lindex $slaves 0]
wait_for_ofs_sync $master [lindex $slaves 1]
wait_for_ofs_sync $master [lindex $slaves 2]
# Check digests
set digest [$master debug digest]
set digest0 [[lindex $slaves 0] debug digest]
set digest1 [[lindex $slaves 1] debug digest]
set digest2 [[lindex $slaves 2] debug digest]
assert {$digest ne 0000000000000000000000000000000000000000}
assert {$digest eq $digest0}
assert {$digest eq $digest1}
assert {$digest eq $digest2}
}
}
}
}
}
}
}
start_server {tags {"repl external:skip"} overrides {save {}}} {
set master [srv 0 client]
set master_host [srv 0 host]
set master_port [srv 0 port]
start_server {overrides {save {}}} {
test "Master stream is correctly processed while the replica has a script in -BUSY state" {
set load_handle0 [start_write_load $master_host $master_port 3]
set slave [srv 0 client]
$slave config set lua-time-limit 500
$slave slaveof $master_host $master_port
# Wait for the slave to be online
wait_for_condition 500 100 {
[lindex [$slave role] 3] eq {connected}
} else {
fail "Replica still not connected after some time"
}
# Wait some time to make sure the master is sending data
# to the slave.
after 5000
# Stop the ability of the slave to process data by sendig
# a script that will put it in BUSY state.
$slave eval {for i=1,3000000000 do end} 0
# Wait some time again so that more master stream will
# be processed.
after 2000
# Stop the write load
stop_write_load $load_handle0
# number of keys
wait_for_condition 500 100 {
[$master debug digest] eq [$slave debug digest]
} else {
fail "Different datasets between replica and master"
}
}
}
}
# Diskless load swapdb when NOT async_loading (different master replid)
foreach testType {Successful Aborted} rdbchannel {yes no} {
start_server {tags {"repl external:skip"}} {
set replica [srv 0 client]
set replica_host [srv 0 host]
set replica_port [srv 0 port]
set replica_log [srv 0 stdout]
start_server {} {
set master [srv 0 client]
set master_host [srv 0 host]
set master_port [srv 0 port]
# Set master and replica to use diskless replication on swapdb mode
$master config set repl-diskless-sync yes
$master config set repl-diskless-sync-delay 0
$master config set save ""
$master config set repl-rdb-channel $rdbchannel
$replica config set repl-diskless-load swapdb
$replica config set save ""
# Put different data sets on the master and replica
# We need to put large keys on the master since the replica replies to info only once in 2mb
$replica debug populate 200 slave 10
$master debug populate 1000 master 100000
$master config set rdbcompression no
# Set a key value on replica to check status on failure and after swapping db
$replica set mykey myvalue
switch $testType {
"Aborted" {
# Set master with a slow rdb generation, so that we can easily intercept loading
# 10ms per key, with 1000 keys is 10 seconds
$master config set rdb-key-save-delay 10000
# Start the replication process
$replica replicaof $master_host $master_port
test "Diskless load swapdb (different replid): replica enter loading rdbchannel=$rdbchannel" {
# Wait for the replica to start reading the rdb
wait_for_condition 100 100 {
[s -1 loading] eq 1
} else {
fail "Replica didn't get into loading mode"
}
assert_equal [s -1 async_loading] 0
}
# Make sure that next sync will not start immediately so that we can catch the replica in between syncs
$master config set repl-diskless-sync-delay 5
# Kill the replica connection on the master
set killed [$master client kill type replica]
# Wait for loading to stop (fail)
wait_for_condition 100 100 {
[s -1 loading] eq 0
} else {
fail "Replica didn't disconnect"
}
test "Diskless load swapdb (different replid): old database is exposed after replication fails rdbchannel=$rdbchannel" {
# Ensure we see old values from replica
assert_equal [$replica get mykey] "myvalue"
# Make sure amount of replica keys didn't change
assert_equal [$replica dbsize] 201
}
# Speed up shutdown
$master config set rdb-key-save-delay 0
}
"Successful" {
# Start the replication process
$replica replicaof $master_host $master_port
# Let replica finish sync with master
wait_for_condition 100 100 {
[s -1 master_link_status] eq "up"
} else {
fail "Master <-> Replica didn't finish sync"
}
test {Diskless load swapdb (different replid): new database is exposed after swapping} {
# Ensure we don't see anymore the key that was stored only to replica and also that we don't get LOADING status
assert_equal [$replica GET mykey] ""
# Make sure amount of keys matches master
assert_equal [$replica dbsize] 1000
}
}
}
}
}
}
# Diskless load swapdb when async_loading (matching master replid)
foreach testType {Successful Aborted} {
start_server {tags {"repl external:skip"}} {
set replica [srv 0 client]
set replica_host [srv 0 host]
set replica_port [srv 0 port]
set replica_log [srv 0 stdout]
start_server {} {
set master [srv 0 client]
set master_host [srv 0 host]
set master_port [srv 0 port]
# Set master and replica to use diskless replication on swapdb mode
$master config set repl-diskless-sync yes
$master config set repl-diskless-sync-delay 0
$master config set save ""
$replica config set repl-diskless-load swapdb
$replica config set save ""
# Set replica writable so we can check that a key we manually added is served
# during replication and after failure, but disappears on success
$replica config set replica-read-only no
# Initial sync to have matching replids between master and replica
$replica replicaof $master_host $master_port
# Let replica finish initial sync with master
wait_for_condition 100 100 {
[s -1 master_link_status] eq "up"
} else {
fail "Master <-> Replica didn't finish sync"
}
# Put different data sets on the master and replica
# We need to put large keys on the master since the replica replies to info only once in 2mb
$replica debug populate 2000 slave 10
$master debug populate 2000 master 100000
$master config set rdbcompression no
# Set a key value on replica to check status during loading, on failure and after swapping db
$replica set mykey myvalue
# Set a function value on replica to check status during loading, on failure and after swapping db
$replica function load {#!lua name=test
redis.register_function('test', function() return 'hello1' end)
}
# Set a function value on master to check it reaches the replica when replication ends
$master function load {#!lua name=test
redis.register_function('test', function() return 'hello2' end)
}
# Remember the sync_full stat before the client kill.
set sync_full [s 0 sync_full]
if {$testType == "Aborted"} {
# Set master with a slow rdb generation, so that we can easily intercept loading
# 20ms per key, with 2000 keys is 40 seconds
$master config set rdb-key-save-delay 20000
}
# Force the replica to try another full sync (this time it will have matching master replid)
$master multi
$master client kill type replica
# Fill replication backlog with new content
$master config set repl-backlog-size 16384
for {set keyid 0} {$keyid < 10} {incr keyid} {
$master set "$keyid string_$keyid" [string repeat A 16384]
}
$master exec
# Wait for sync_full to get incremented from the previous value.
# After the client kill, make sure we do a reconnect, and do a FULL SYNC.
wait_for_condition 100 100 {
[s 0 sync_full] > $sync_full
} else {
fail "Master <-> Replica didn't start the full sync"
}
switch $testType {
"Aborted" {
test {Diskless load swapdb (async_loading): replica enter async_loading} {
# Wait for the replica to start reading the rdb
wait_for_condition 100 100 {
[s -1 async_loading] eq 1
} else {
fail "Replica didn't get into async_loading mode"
}
assert_equal [s -1 loading] 0
}
test {Diskless load swapdb (async_loading): old database is exposed while async replication is in progress} {
# Ensure we still see old values while async_loading is in progress and also not LOADING status
assert_equal [$replica get mykey] "myvalue"
# Ensure we still can call old function while async_loading is in progress
assert_equal [$replica fcall test 0] "hello1"
# Make sure we're still async_loading to validate previous assertion
assert_equal [s -1 async_loading] 1
# Make sure amount of replica keys didn't change
assert_equal [$replica dbsize] 2001
}
test {Busy script during async loading} {
set rd_replica [redis_deferring_client -1]
$replica config set lua-time-limit 10
$rd_replica eval {while true do end} 0
after 200
assert_error {BUSY*} {$replica ping}
$replica script kill
after 200 ; # Give some time to Lua to call the hook again...
assert_equal [$replica ping] "PONG"
$rd_replica close
}
test {Blocked commands and configs during async-loading} {
assert_error {LOADING*} {$replica REPLICAOF no one}
}
# Make sure that next sync will not start immediately so that we can catch the replica in between syncs
$master config set repl-diskless-sync-delay 5
# Kill the replica connection on the master
set killed [$master client kill type replica]
# Wait for loading to stop (fail)
wait_for_condition 100 100 {
[s -1 async_loading] eq 0
} else {
fail "Replica didn't disconnect"
}
test {Diskless load swapdb (async_loading): old database is exposed after async replication fails} {
# Ensure we see old values from replica
assert_equal [$replica get mykey] "myvalue"
# Ensure we still can call old function
assert_equal [$replica fcall test 0] "hello1"
# Make sure amount of replica keys didn't change
assert_equal [$replica dbsize] 2001
}
# Speed up shutdown
$master config set rdb-key-save-delay 0
}
"Successful" {
# Let replica finish sync with master
wait_for_condition 100 100 {
[s -1 master_link_status] eq "up"
} else {
fail "Master <-> Replica didn't finish sync"
}
test {Diskless load swapdb (async_loading): new database is exposed after swapping} {
# Ensure we don't see anymore the key that was stored only to replica and also that we don't get LOADING status
assert_equal [$replica GET mykey] ""
# Ensure we got the new function
assert_equal [$replica fcall test 0] "hello2"
# Make sure amount of keys matches master
assert_equal [$replica dbsize] 2010
}
}
}
}
}
}
test {diskless loading short read} {
start_server {tags {"repl"} overrides {save ""}} {
set replica [srv 0 client]
set replica_host [srv 0 host]
set replica_port [srv 0 port]
start_server {overrides {save ""}} {
set master [srv 0 client]
set master_host [srv 0 host]
set master_port [srv 0 port]
# Set master and replica to use diskless replication
$master config set repl-diskless-sync yes
$master config set rdbcompression no
$replica config set repl-diskless-load swapdb
$master config set hz 500
$replica config set hz 500
$master config set dynamic-hz no
$replica config set dynamic-hz no
# Try to fill the master with all types of data types / encodings
set start [clock clicks -milliseconds]
# Set a function value to check short read handling on functions
r function load {#!lua name=test
redis.register_function('test', function() return 'hello1' end)
}
set has_vector_sets [server_has_command vadd]
for {set k 0} {$k < 3} {incr k} {
for {set i 0} {$i < 10} {incr i} {
r set "$k int_$i" [expr {int(rand()*10000)}]
r expire "$k int_$i" [expr {int(rand()*10000)}]
r set "$k string_$i" [string repeat A [expr {int(rand()*1000000)}]]
r hset "$k hash_small" [string repeat A [expr {int(rand()*10)}]] 0[string repeat A [expr {int(rand()*10)}]]
r hset "$k hash_large" [string repeat A [expr {int(rand()*10000)}]] [string repeat A [expr {int(rand()*1000000)}]]
r sadd "$k set_small" [string repeat A [expr {int(rand()*10)}]]
r sadd "$k set_large" [string repeat A [expr {int(rand()*1000000)}]]
r zadd "$k zset_small" [expr {rand()}] [string repeat A [expr {int(rand()*10)}]]
r zadd "$k zset_large" [expr {rand()}] [string repeat A [expr {int(rand()*1000000)}]]
r lpush "$k list_small" [string repeat A [expr {int(rand()*10)}]]
r lpush "$k list_large" [string repeat A [expr {int(rand()*1000000)}]]
if {$has_vector_sets} {
r vadd "$k vector_set" VALUES 3 [expr {rand()}] [expr {rand()}] [expr {rand()}] [string repeat A [expr {int(rand()*1000)}]]
}
for {set j 0} {$j < 10} {incr j} {
r xadd "$k stream" * foo "asdf" bar "1234"
}
r xgroup create "$k stream" "mygroup_$i" 0
r xreadgroup GROUP "mygroup_$i" Alice COUNT 1 STREAMS "$k stream" >
}
}
if {$::verbose} {
set end [clock clicks -milliseconds]
set duration [expr $end - $start]
puts "filling took $duration ms (TODO: use pipeline)"
set start [clock clicks -milliseconds]
}
# Start the replication process...
set loglines [count_log_lines -1]
$master config set repl-diskless-sync-delay 0
$replica replicaof $master_host $master_port
# kill the replication at various points
set attempts 100
if {$::accurate} { set attempts 500 }
for {set i 0} {$i < $attempts} {incr i} {
# wait for the replica to start reading the rdb
# using the log file since the replica only responds to INFO once in 2mb
set res [wait_for_log_messages -1 {"*Loading DB in memory*"} $loglines 2000 1]
set loglines [lindex $res 1]
# add some additional random sleep so that we kill the master on a different place each time
after [expr {int(rand()*50)}]
# kill the replica connection on the master
set killed [$master client kill type replica]
set res [wait_for_log_messages -1 {"*Internal error in RDB*" "*Finished with success*" "*Successful partial resynchronization*"} $loglines 500 10]
if {$::verbose} { puts $res }
set log_text [lindex $res 0]
set loglines [lindex $res 1]
if {![string match "*Internal error in RDB*" $log_text]} {
# force the replica to try another full sync
$master multi
$master client kill type replica
$master set asdf asdf
# fill replication backlog with new content
$master config set repl-backlog-size 16384
for {set keyid 0} {$keyid < 10} {incr keyid} {
$master set "$keyid string_$keyid" [string repeat A 16384]
}
$master exec
}
# wait for loading to stop (fail)
# After a loading successfully, next loop will enter `async_loading`
wait_for_condition 1000 1 {
[s -1 async_loading] eq 0 &&
[s -1 loading] eq 0
} else {
fail "Replica didn't disconnect"
}
}
if {$::verbose} {
set end [clock clicks -milliseconds]
set duration [expr $end - $start]
puts "test took $duration ms"
}
# enable fast shutdown
$master config set rdb-key-save-delay 0
}
}
} {} {external:skip}
# get current stime and utime metrics for a thread (since it's creation)
proc get_cpu_metrics { statfile } {
if { [ catch {
set fid [ open $statfile r ]
set data [ read $fid 1024 ]
::close $fid
set data [ split $data ]
;## number of jiffies it has been scheduled...
set utime [ lindex $data 13 ]
set stime [ lindex $data 14 ]
} err ] } {
error "assertion:can't parse /proc: $err"
}
set mstime [clock milliseconds]
return [ list $mstime $utime $stime ]
}
# compute %utime and %stime of a thread between two measurements
proc compute_cpu_usage {start end} {
set clock_ticks [exec getconf CLK_TCK]
# convert ms time to jiffies and calc delta
set dtime [ expr { ([lindex $end 0] - [lindex $start 0]) * double($clock_ticks) / 1000 } ]
set utime [ expr { [lindex $end 1] - [lindex $start 1] } ]
set stime [ expr { [lindex $end 2] - [lindex $start 2] } ]
set pucpu [ expr { ($utime / $dtime) * 100 } ]
set pscpu [ expr { ($stime / $dtime) * 100 } ]
return [ list $pucpu $pscpu ]
}
# test diskless rdb pipe with multiple replicas, which may drop half way
start_server {tags {"repl external:skip"} overrides {save ""}} {
set master [srv 0 client]
$master config set repl-diskless-sync yes
$master config set repl-diskless-sync-delay 5
$master config set repl-diskless-sync-max-replicas 2
set master_host [srv 0 host]
set master_port [srv 0 port]
set master_pid [srv 0 pid]
# put enough data in the db that the rdb file will be bigger than the socket buffers
# and since we'll have key-load-delay of 100, 20000 keys will take at least 2 seconds
# we also need the replica to process requests during transfer (which it does only once in 2mb)
$master debug populate 20000 test 10000
$master config set rdbcompression no
$master config set repl-rdb-channel no
# If running on Linux, we also measure utime/stime to detect possible I/O handling issues
set os [catch {exec uname}]
set measure_time [expr {$os == "Linux"} ? 1 : 0]
foreach all_drop {no slow fast all timeout} {
test "diskless $all_drop replicas drop during rdb pipe" {
set replicas {}
set replicas_alive {}
# start one replica that will read the rdb fast, and one that will be slow
start_server {overrides {save ""}} {
lappend replicas [srv 0 client]
lappend replicas_alive [srv 0 client]
start_server {overrides {save ""}} {
lappend replicas [srv 0 client]
lappend replicas_alive [srv 0 client]
# start replication
# it's enough for just one replica to be slow, and have it's write handler enabled
# so that the whole rdb generation process is bound to that
set loglines [count_log_lines -2]
[lindex $replicas 0] config set repl-diskless-load swapdb
[lindex $replicas 0] config set key-load-delay 100 ;# 20k keys and 100 microseconds sleep means at least 2 seconds
[lindex $replicas 0] replicaof $master_host $master_port
[lindex $replicas 1] replicaof $master_host $master_port
# wait for the replicas to start reading the rdb
# using the log file since the replica only responds to INFO once in 2mb
wait_for_log_messages -1 {"*Loading DB in memory*"} 0 1500 10
if {$measure_time} {
set master_statfile "/proc/$master_pid/stat"
set master_start_metrics [get_cpu_metrics $master_statfile]
set start_time [clock seconds]
}
# wait a while so that the pipe socket writer will be
# blocked on write (since replica 0 is slow to read from the socket)
after 500
# add some command to be present in the command stream after the rdb.
$master incr $all_drop
# disconnect replicas depending on the current test
if {$all_drop == "all" || $all_drop == "fast"} {
exec kill [srv 0 pid]
set replicas_alive [lreplace $replicas_alive 1 1]
}
if {$all_drop == "all" || $all_drop == "slow"} {
exec kill [srv -1 pid]
set replicas_alive [lreplace $replicas_alive 0 0]
}
if {$all_drop == "timeout"} {
$master config set repl-timeout 2
# we want the slow replica to hang on a key for very long so it'll reach repl-timeout
pause_process [srv -1 pid]
after 2000
}
# wait for rdb child to exit
wait_for_condition 500 100 {
[s -2 rdb_bgsave_in_progress] == 0
} else {
fail "rdb child didn't terminate"
}
# make sure we got what we were aiming for, by looking for the message in the log file
if {$all_drop == "all"} {
wait_for_log_messages -2 {"*Diskless rdb transfer, last replica dropped, killing fork child*"} $loglines 1 1
}
if {$all_drop == "no"} {
wait_for_log_messages -2 {"*Diskless rdb transfer, done reading from pipe, 2 replicas still up*"} $loglines 1 1
}
if {$all_drop == "slow" || $all_drop == "fast"} {
wait_for_log_messages -2 {"*Diskless rdb transfer, done reading from pipe, 1 replicas still up*"} $loglines 1 1
}
if {$all_drop == "timeout"} {
wait_for_log_messages -2 {"*Disconnecting timedout replica (full sync)*"} $loglines 1 1
wait_for_log_messages -2 {"*Diskless rdb transfer, done reading from pipe, 1 replicas still up*"} $loglines 1 1
# master disconnected the slow replica, remove from array
set replicas_alive [lreplace $replicas_alive 0 0]
# release it
resume_process [srv -1 pid]
}
# make sure we don't have a busy loop going thought epoll_wait
if {$measure_time} {
set master_end_metrics [get_cpu_metrics $master_statfile]
set time_elapsed [expr {[clock seconds]-$start_time}]
set master_cpu [compute_cpu_usage $master_start_metrics $master_end_metrics]
set master_utime [lindex $master_cpu 0]
set master_stime [lindex $master_cpu 1]
if {$::verbose} {
puts "elapsed: $time_elapsed"
puts "master utime: $master_utime"
puts "master stime: $master_stime"
}
if {!$::no_latency && ($all_drop == "all" || $all_drop == "slow" || $all_drop == "timeout")} {
assert {$master_utime < 70}
assert {$master_stime < 70}
}
if {!$::no_latency && ($all_drop == "none" || $all_drop == "fast")} {
assert {$master_utime < 15}
assert {$master_stime < 15}
}
}
# verify the data integrity
foreach replica $replicas_alive {
# Wait that replicas acknowledge they are online so
# we are sure that DBSIZE and DEBUG DIGEST will not
# fail because of timing issues.
wait_for_condition 150 100 {
[lindex [$replica role] 3] eq {connected}
} else {
fail "replicas still not connected after some time"
}
# Make sure that replicas and master have same
# number of keys
wait_for_condition 50 100 {
[$master dbsize] == [$replica dbsize]
} else {
fail "Different number of keys between master and replicas after too long time."
}
# Check digests
set digest [$master debug digest]
set digest0 [$replica debug digest]
assert {$digest ne 0000000000000000000000000000000000000000}
assert {$digest eq $digest0}
}
}
}
}
}
}
test "diskless replication child being killed is collected" {
# when diskless master is waiting for the replica to become writable
# it removes the read event from the rdb pipe so if the child gets killed
# the replica will hung. and the master may not collect the pid with waitpid
start_server {tags {"repl"} overrides {save ""}} {
set master [srv 0 client]
set master_host [srv 0 host]
set master_port [srv 0 port]
set master_pid [srv 0 pid]
$master config set repl-diskless-sync yes
$master config set repl-diskless-sync-delay 0
$master config set repl-rdb-channel no
# put enough data in the db that the rdb file will be bigger than the socket buffers
$master debug populate 20000 test 10000
$master config set rdbcompression no
start_server {overrides {save ""}} {
set replica [srv 0 client]
set loglines [count_log_lines 0]
$replica config set repl-diskless-load swapdb
$replica config set key-load-delay 1000000
$replica config set loading-process-events-interval-bytes 1024
$replica replicaof $master_host $master_port
# wait for the replicas to start reading the rdb
wait_for_log_messages 0 {"*Loading DB in memory*"} $loglines 1500 10
# wait to be sure the replica is hung and the master is blocked on write
after 500
# simulate the OOM killer or anyone else kills the child
set fork_child_pid [get_child_pid -1]
exec kill -9 $fork_child_pid
# wait for the parent to notice the child have exited
wait_for_condition 50 100 {
[s -1 rdb_bgsave_in_progress] == 0
} else {
fail "rdb child didn't terminate"
}
# Speed up shutdown
$replica config set key-load-delay 0
}
}
} {} {external:skip}
foreach mdl {yes no} {
test "replication child dies when parent is killed - diskless: $mdl" {
# when master is killed, make sure the fork child can detect that and exit
start_server {tags {"repl"} overrides {save ""}} {
set master [srv 0 client]
set master_host [srv 0 host]
set master_port [srv 0 port]
set master_pid [srv 0 pid]
$master config set repl-diskless-sync $mdl
$master config set repl-diskless-sync-delay 0
# create keys that will take 10 seconds to save
$master config set rdb-key-save-delay 1000
$master debug populate 10000
start_server {overrides {save ""}} {
set replica [srv 0 client]
$replica replicaof $master_host $master_port
# wait for rdb child to start
wait_for_condition 5000 10 {
[s -1 rdb_bgsave_in_progress] == 1
} else {
fail "rdb child didn't start"
}
set fork_child_pid [get_child_pid -1]
# simulate the OOM killer or anyone else kills the parent
exec kill -9 $master_pid
# wait for the child to notice the parent died have exited
wait_for_condition 500 10 {
[process_is_alive $fork_child_pid] == 0
} else {
fail "rdb child didn't terminate"
}
}
}
} {} {external:skip}
}
test "diskless replication read pipe cleanup" {
# In diskless replication, we create a read pipe for the RDB, between the child and the parent.
# When we close this pipe (fd), the read handler also needs to be removed from the event loop (if it still registered).
# Otherwise, next time we will use the same fd, the registration will be fail (panic), because
# we will use EPOLL_CTL_MOD (the fd still register in the event loop), on fd that already removed from epoll_ctl
start_server {tags {"repl"} overrides {save ""}} {
set master [srv 0 client]
set master_host [srv 0 host]
set master_port [srv 0 port]
set master_pid [srv 0 pid]
$master config set repl-diskless-sync yes
$master config set repl-diskless-sync-delay 0
# put enough data in the db, and slowdown the save, to keep the parent busy at the read process
$master config set rdb-key-save-delay 100000
$master debug populate 20000 test 10000
$master config set rdbcompression no
start_server {overrides {save ""}} {
set replica [srv 0 client]
set loglines [count_log_lines 0]
$replica config set repl-diskless-load swapdb
$replica replicaof $master_host $master_port
# wait for the replicas to start reading the rdb
wait_for_log_messages 0 {"*Loading DB in memory*"} $loglines 1500 10
set loglines [count_log_lines -1]
# send FLUSHALL so the RDB child will be killed
$master flushall
# wait for another RDB child process to be started
wait_for_log_messages -1 {"*Background RDB transfer started by pid*"} $loglines 800 10
# make sure master is alive
$master ping
}
}
} {} {external:skip}
test {replicaof right after disconnection} {
# this is a rare race condition that was reproduced sporadically by the psync2 unit.
# see details in #7205
start_server {tags {"repl"} overrides {save ""}} {
set replica1 [srv 0 client]
set replica1_host [srv 0 host]
set replica1_port [srv 0 port]
set replica1_log [srv 0 stdout]
start_server {overrides {save ""}} {
set replica2 [srv 0 client]
set replica2_host [srv 0 host]
set replica2_port [srv 0 port]
set replica2_log [srv 0 stdout]
start_server {overrides {save ""}} {
set master [srv 0 client]
set master_host [srv 0 host]
set master_port [srv 0 port]
$replica1 replicaof $master_host $master_port
$replica2 replicaof $master_host $master_port
wait_for_condition 50 100 {
[string match {*master_link_status:up*} [$replica1 info replication]] &&
[string match {*master_link_status:up*} [$replica2 info replication]]
} else {
fail "Can't turn the instance into a replica"
}
set rd [redis_deferring_client -1]
$rd debug sleep 1
after 100
# when replica2 will wake up from the sleep it will find both disconnection
# from it's master and also a replicaof command at the same event loop
$master client kill type replica
$replica2 replicaof $replica1_host $replica1_port
$rd read
wait_for_condition 50 100 {
[string match {*master_link_status:up*} [$replica2 info replication]]
} else {
fail "role change failed."
}
# make sure psync succeeded, and there were no unexpected full syncs.
assert_equal [status $master sync_full] 2
assert_equal [status $replica1 sync_full] 0
assert_equal [status $replica2 sync_full] 0
}
}
}
} {} {external:skip}
test {Kill rdb child process if its dumping RDB is not useful} {
start_server {tags {"repl"}} {
set slave1 [srv 0 client]
start_server {} {
set slave2 [srv 0 client]
start_server {} {
set master [srv 0 client]
set master_host [srv 0 host]
set master_port [srv 0 port]
for {set i 0} {$i < 10} {incr i} {
$master set $i $i
}
# Generating RDB will cost 10s(10 * 1s)
$master config set rdb-key-save-delay 1000000
$master config set repl-diskless-sync no
$master config set save ""
$slave1 slaveof $master_host $master_port
$slave2 slaveof $master_host $master_port
# Wait for starting child
wait_for_condition 50 100 {
([s 0 rdb_bgsave_in_progress] == 1) &&
([string match "*wait_bgsave*" [s 0 slave0]]) &&
([string match "*wait_bgsave*" [s 0 slave1]])
} else {
fail "rdb child didn't start"
}
# Slave1 disconnect with master
$slave1 slaveof no one
# Shouldn't kill child since another slave wait for rdb
after 100
assert {[s 0 rdb_bgsave_in_progress] == 1}
# Slave2 disconnect with master
$slave2 slaveof no one
# Should kill child
wait_for_condition 100 10 {
[s 0 rdb_bgsave_in_progress] eq 0
} else {
fail "can't kill rdb child"
}
# If have save parameters, won't kill child
$master config set save "900 1"
$slave1 slaveof $master_host $master_port
$slave2 slaveof $master_host $master_port
wait_for_condition 50 100 {
([s 0 rdb_bgsave_in_progress] == 1) &&
([string match "*wait_bgsave*" [s 0 slave0]]) &&
([string match "*wait_bgsave*" [s 0 slave1]])
} else {
fail "rdb child didn't start"
}
$slave1 slaveof no one
$slave2 slaveof no one
after 200
assert {[s 0 rdb_bgsave_in_progress] == 1}
catch {$master shutdown nosave}
}
}
}
} {} {external:skip}
start_server {tags {"repl external:skip"}} {
set master1_host [srv 0 host]
set master1_port [srv 0 port]
r set a b
start_server {} {
set master2 [srv 0 client]
set master2_host [srv 0 host]
set master2_port [srv 0 port]
# Take 10s for dumping RDB
$master2 debug populate 10 master2 10
$master2 config set rdb-key-save-delay 1000000
start_server {} {
set sub_replica [srv 0 client]
start_server {} {
# Full sync with master1
r slaveof $master1_host $master1_port
wait_for_sync r
assert_equal "b" [r get a]
# Let sub replicas sync with me
$sub_replica slaveof [srv 0 host] [srv 0 port]
wait_for_sync $sub_replica
assert_equal "b" [$sub_replica get a]
# Full sync with master2, and then kill master2 before finishing dumping RDB
r slaveof $master2_host $master2_port
wait_for_condition 50 100 {
([s -2 rdb_bgsave_in_progress] == 1) &&
([string match "*wait_bgsave*" [s -2 slave0]] ||
[string match "*send_bulk_and_stream*" [s -2 slave0]])
} else {
fail "full sync didn't start"
}
catch {$master2 shutdown nosave}
test {Don't disconnect with replicas before loading transferred RDB when full sync} {
assert ![log_file_matches [srv -1 stdout] "*Connection with master lost*"]
# The replication id is not changed in entire replication chain
assert_equal [s master_replid] [s -3 master_replid]
assert_equal [s master_replid] [s -1 master_replid]
}
test {Discard cache master before loading transferred RDB when full sync} {
set full_sync [s -3 sync_full]
set partial_sync [s -3 sync_partial_ok]
# Partial sync with master1
r slaveof $master1_host $master1_port
wait_for_sync r
# master1 accepts partial sync instead of full sync
assert_equal $full_sync [s -3 sync_full]
assert_equal [expr $partial_sync+1] [s -3 sync_partial_ok]
# Since master only partially sync replica, and repl id is not changed,
# the replica doesn't disconnect with its sub-replicas
assert_equal [s master_replid] [s -3 master_replid]
assert_equal [s master_replid] [s -1 master_replid]
assert ![log_file_matches [srv -1 stdout] "*Connection with master lost*"]
# Sub replica just has one full sync, no partial resync.
assert_equal 1 [s sync_full]
assert_equal 0 [s sync_partial_ok]
}
}
}
}
}
test {replica can handle EINTR if use diskless load} {
start_server {tags {"repl"}} {
set replica [srv 0 client]
set replica_log [srv 0 stdout]
start_server {} {
set master [srv 0 client]
set master_host [srv 0 host]
set master_port [srv 0 port]
$master debug populate 100 master 100000
$master config set rdbcompression no
$master config set repl-diskless-sync yes
$master config set repl-diskless-sync-delay 0
$replica config set repl-diskless-load on-empty-db
# Construct EINTR error by using the built in watchdog
$replica config set watchdog-period 200
# Block replica in read()
$master config set rdb-key-save-delay 10000
# set speedy shutdown
$master config set save ""
# Start the replication process...
$replica replicaof $master_host $master_port
# Wait for the replica to start reading the rdb
set res [wait_for_log_messages -1 {"*Loading DB in memory*"} 0 200 10]
set loglines [lindex $res 1]
# Wait till we see the watchgod log line AFTER the loading started
wait_for_log_messages -1 {"*WATCHDOG TIMER EXPIRED*"} $loglines 200 10
# Make sure we're still loading, and that there was just one full sync attempt
assert ![log_file_matches [srv -1 stdout] "*Reconnecting to MASTER*"]
assert_equal 1 [s 0 sync_full]
assert_equal 1 [s -1 loading]
}
}
} {} {external:skip}
start_server {tags {"repl" "external:skip"}} {
test "replica do not write the reply to the replication link - SYNC (_addReplyToBufferOrList)" {
set rd [redis_deferring_client]
set lines [count_log_lines 0]
$rd sync
$rd ping
catch {$rd read} e
if {$::verbose} { puts "SYNC _addReplyToBufferOrList: $e" }
assert_equal "PONG" [r ping]
# Check we got the warning logs about the PING command.
verify_log_message 0 "*Replica generated a reply to command 'ping', disconnecting it: *" $lines
$rd close
waitForBgsave r
}
test "replica do not write the reply to the replication link - SYNC (addReplyDeferredLen)" {
set rd [redis_deferring_client]
set lines [count_log_lines 0]
$rd sync
$rd xinfo help
catch {$rd read} e
if {$::verbose} { puts "SYNC addReplyDeferredLen: $e" }
assert_equal "PONG" [r ping]
# Check we got the warning logs about the XINFO HELP command.
verify_log_message 0 "*Replica generated a reply to command 'xinfo|help', disconnecting it: *" $lines
$rd close
waitForBgsave r
}
test "replica do not write the reply to the replication link - PSYNC (_addReplyToBufferOrList)" {
set rd [redis_deferring_client]
set lines [count_log_lines 0]
$rd psync replicationid -1
assert_match {FULLRESYNC * 0} [$rd read]
$rd get foo
catch {$rd read} e
if {$::verbose} { puts "PSYNC _addReplyToBufferOrList: $e" }
assert_equal "PONG" [r ping]
# Check we got the warning logs about the GET command.
verify_log_message 0 "*Replica generated a reply to command 'get', disconnecting it: *" $lines
verify_log_message 0 "*== CRITICAL == This master is sending an error to its replica: *" $lines
verify_log_message 0 "*Replica can't interact with the keyspace*" $lines
$rd close
waitForBgsave r
}
test "replica do not write the reply to the replication link - PSYNC (addReplyDeferredLen)" {
set rd [redis_deferring_client]
set lines [count_log_lines 0]
$rd psync replicationid -1
assert_match {FULLRESYNC * 0} [$rd read]
$rd slowlog get
catch {$rd read} e
if {$::verbose} { puts "PSYNC addReplyDeferredLen: $e" }
assert_equal "PONG" [r ping]
# Check we got the warning logs about the SLOWLOG GET command.
verify_log_message 0 "*Replica generated a reply to command 'slowlog|get', disconnecting it: *" $lines
$rd close
waitForBgsave r
}
test "PSYNC with wrong offset should throw error" {
# It used to accept the FULL SYNC, but also replied with an error.
assert_error {ERR value is not an integer or out of range} {r psync replicationid offset_str}
set logs [exec tail -n 100 < [srv 0 stdout]]
assert_match {*Replica * asks for synchronization but with a wrong offset} $logs
assert_equal "PONG" [r ping]
}
}
start_server {tags {"repl external:skip"}} {
set master [srv 0 client]
set master_host [srv 0 host]
set master_port [srv 0 port]
$master debug SET-ACTIVE-EXPIRE 0
start_server {} {
set slave [srv 0 client]
$slave debug SET-ACTIVE-EXPIRE 0
$slave slaveof $master_host $master_port
test "Test replication with lazy expire" {
# wait for replication to be in sync
wait_for_condition 50 100 {
[lindex [$slave role] 0] eq {slave} &&
[string match {*master_link_status:up*} [$slave info replication]]
} else {
fail "Can't turn the instance into a replica"
}
$master sadd s foo
$master pexpire s 1
after 10
$master sadd s foo
assert_equal 1 [$master wait 1 0]
assert_equal "set" [$master type s]
assert_equal "set" [$slave type s]
}
}
}
foreach disklessload {disabled on-empty-db} {
test "Replica should reply LOADING while flushing a large db (disklessload: $disklessload)" {
start_server {} {
set replica [srv 0 client]
start_server {} {
set master [srv 0 client]
set master_host [srv 0 host]
set master_port [srv 0 port]
$replica config set repl-diskless-load $disklessload
# Populate replica with many keys, master with a few keys.
$replica debug populate 2000000
populate 3 master 10
# Start the replication process...
$replica replicaof $master_host $master_port
wait_for_condition 100 100 {
[s -1 loading] eq 1
} else {
fail "Replica didn't get into loading mode"
}
# If replica has a large db, it may take some time to discard it
# after receiving new db from the master. In this case, replica
# should reply -LOADING. Replica may reply -LOADING while
# loading the new db as well. To test the first case, populated
# replica with large amount of keys and master with a few keys.
# Discarding old db will take a long time and loading new one
# will be quick. So, if we receive -LOADING, most probably it is
# when flushing the db.
wait_for_condition 1 10000 {
[catch {$replica ping} err] &&
[string match *LOADING* $err]
} else {
# There is a chance that we may not catch LOADING response
# if flushing db happens too fast compared to test execution
# Then, we may consider increasing key count or introducing
# artificial delay to db flush.
fail "Replica did not reply LOADING."
}
catch {$replica shutdown nosave}
}
}
} {} {repl external:skip}
}
start_server {tags {"repl external:skip"} overrides {save {}}} {
set master [srv 0 client]
set master_host [srv 0 host]
set master_port [srv 0 port]
populate 10000 master 10
start_server {overrides {save {} rdb-del-sync-files yes loading-process-events-interval-bytes 1024}} {
test "Allow appendonly config change while loading rdb on slave" {
set replica [srv 0 client]
# While loading rdb on slave, verify appendonly config changes are allowed
# 1- Change appendonly config from no to yes
$replica config set appendonly no
$replica config set key-load-delay 100
$replica debug populate 1000
# Start the replication process...
$replica replicaof $master_host $master_port
wait_for_condition 10 1000 {
[s loading] eq 1
} else {
fail "Replica didn't get into loading mode"
}
# Change config while replica is loading data
$replica config set appendonly yes
assert_equal 1 [s loading]
# Speed up loading and verify aof is enabled
$replica config set key-load-delay 0
wait_done_loading $replica
assert_equal 1 [s aof_enabled]
# Quick sanity for AOF
$replica replicaof no one
set prev [s aof_current_size]
$replica set x 100
assert_morethan [s aof_current_size] $prev
# 2- While loading rdb, change appendonly from yes to no
$replica config set appendonly yes
$replica config set key-load-delay 100
$replica flushall
# Start the replication process...
$replica replicaof $master_host $master_port
wait_for_condition 10 1000 {
[s loading] eq 1
} else {
fail "Replica didn't get into loading mode"
}
# Change config while replica is loading data
$replica config set appendonly no
assert_equal 1 [s loading]
# Speed up loading and verify aof is disabled
$replica config set key-load-delay 0
wait_done_loading $replica
assert_equal 0 [s 0 aof_enabled]
}
}
}
start_server {tags {"repl external:skip"}} {
set replica [srv 0 client]
start_server {} {
set master [srv 0 client]
set master_host [srv 0 host]
set master_port [srv 0 port]
test "Replica flushes db lazily when replica-lazy-flush enabled" {
$replica config set replica-lazy-flush yes
$replica debug populate 1000
populate 1 master 10
# Start the replication process...
$replica replicaof $master_host $master_port
wait_for_condition 100 100 {
[s -1 lazyfreed_objects] >= 1000 &&
[s -1 master_link_status] eq {up}
} else {
fail "Replica did not free db lazily"
}
}
}
}
start_server {tags {"repl external:skip"}} {
set replica [srv 0 client]
start_server {} {
set master [srv 0 client]
set master_host [srv 0 host]
set master_port [srv 0 port]
test "Test replication with functions when repl-diskless-load is set to on-empty-db" {
$replica config set repl-diskless-load on-empty-db
populate 10 master 10
$master function load {#!lua name=test
redis.register_function{function_name='func1', callback=function() return 'hello' end, flags={'no-writes'}}
}
$replica replicaof $master_host $master_port
# Wait until replication is completed
wait_for_sync $replica
wait_for_ofs_sync $master $replica
# Sanity check
assert_equal [$replica fcall func1 0] "hello"
assert_morethan [$replica dbsize] 0
assert_equal [$master debug digest] [$replica debug digest]
}
}
}
|