diff options
Diffstat (limited to 'results/classifier/zero-shot/016/x86')
| -rw-r--r-- | results/classifier/zero-shot/016/x86/17743720 | 798 | ||||
| -rw-r--r-- | results/classifier/zero-shot/016/x86/28596630 | 140 | ||||
| -rw-r--r-- | results/classifier/zero-shot/016/x86/55367348 | 559 | ||||
| -rw-r--r-- | results/classifier/zero-shot/016/x86/57756589 | 1448 | ||||
| -rw-r--r-- | results/classifier/zero-shot/016/x86/92957605 | 445 | ||||
| -rw-r--r-- | results/classifier/zero-shot/016/x86/99674399 | 175 |
6 files changed, 3565 insertions, 0 deletions
diff --git a/results/classifier/zero-shot/016/x86/17743720 b/results/classifier/zero-shot/016/x86/17743720 new file mode 100644 index 000000000..0997166aa --- /dev/null +++ b/results/classifier/zero-shot/016/x86/17743720 @@ -0,0 +1,798 @@ +x86: 0.908 +hypervisor: 0.758 +virtual: 0.630 +debug: 0.447 +operating system: 0.100 +files: 0.081 +performance: 0.076 +PID: 0.049 +i386: 0.039 +TCG: 0.028 +assembly: 0.026 +register: 0.025 +user-level: 0.024 +VMM: 0.009 +semantic: 0.006 +kernel: 0.006 +ppc: 0.004 +device: 0.003 +KVM: 0.003 +architecture: 0.002 +alpha: 0.001 +graphic: 0.001 +network: 0.001 +arm: 0.001 +socket: 0.001 +permissions: 0.001 +risc-v: 0.001 +boot: 0.001 +mistranslation: 0.001 +peripherals: 0.001 +vnc: 0.000 + +[Qemu-devel] [BUG] living migrate vm pause forever + +Sometimes, living migrate vm pause forever, migrate job stop, but very small +probability, I canât reproduce. +qemu wait semaphore from libvirt send migrate continue, however libvirt wait +semaphore from qemu send vm pause. + +follow stack: +qemu: +Thread 6 (Thread 0x7f50445f3700 (LWP 18120)): +#0 0x00007f504b84d670 in sem_wait () from /lib/x86_64-linux-gnu/libpthread.so.0 +#1 0x00005574eda1e164 in qemu_sem_wait (sem=sem@entry=0x5574ef6930e0) at +qemu-2.12/util/qemu-thread-posix.c:322 +#2 0x00005574ed8dd72e in migration_maybe_pause (s=0x5574ef692f50, +current_active_state=0x7f50445f2ae4, new_state=10) + at qemu-2.12/migration/migration.c:2106 +#3 0x00005574ed8df51a in migration_completion (s=0x5574ef692f50) at +qemu-2.12/migration/migration.c:2137 +#4 migration_iteration_run (s=0x5574ef692f50) at +qemu-2.12/migration/migration.c:2311 +#5 migration_thread (opaque=0x5574ef692f50) +atqemu-2.12/migration/migration.c:2415 +#6 0x00007f504b847184 in start_thread () from +/lib/x86_64-linux-gnu/libpthread.so.0 +#7 0x00007f504b574bed in clone () from /lib/x86_64-linux-gnu/libc.so.6 + +libvirt: +Thread 95 (Thread 0x7fdb82ffd700 (LWP 28775)): +#0 0x00007fdd177dc404 in pthread_cond_wait@@GLIBC_2.3.2 () from +/lib/x86_64-linux-gnu/libpthread.so.0 +#1 0x00007fdd198c3b07 in virCondWait (c=0x7fdbc4003000, m=0x7fdbc4002f30) at +../../../src/util/virthread.c:252 +#2 0x00007fdd198f36d2 in virDomainObjWait (vm=0x7fdbc4002f20) at +../../../src/conf/domain_conf.c:3303 +#3 0x00007fdd09ffaa44 in qemuMigrationRun (driver=0x7fdd000037b0, +vm=0x7fdbc4002f20, persist_xml=0x0, + cookiein=0x7fdb780084e0 "<qemu-migration>\n <name>mss-pl_652</name>\n +<uuid>1f2b2334-451e-424b-822a-ea10452abb38</uuid>\n <hostname>mss +</hostname>\n +<hostuuid>334e344a-4130-4336-5534-323544543642</hostuuid>\n</qemu-migra"..., +cookieinlen=207, cookieout=0x7fdb82ffcad0, cookieoutlen=0x7fdb82ffcac8, +flags=777, + resource=0, spec=0x7fdb82ffc670, dconn=0x0, graphicsuri=0x0, +nmigrate_disks=0, migrate_disks=0x0, compression=0x7fdb78007990, +migParams=0x7fdb82ffc900) + at ../../../src/qemu/qemu_migration.c:3937 +#4 0x00007fdd09ffb26a in doNativeMigrate (driver=0x7fdd000037b0, +vm=0x7fdbc4002f20, persist_xml=0x0, uri=0x7fdb780073a0 +"tcp://172.16.202.17:49152", + cookiein=0x7fdb780084e0 "<qemu-migration>\n <name>mss-pl_652</name>\n +<uuid>1f2b2334-451e-424b-822a-ea10452abb38</uuid>\n <hostname>mss</hostname>\n + <hos---Type <return> to continue, or q <return> to quit--- +tuuid>334e344a-4130-4336-5534-323544543642</hostuuid>\n</qemu-migra"..., +cookieinlen=207, cookieout=0x7fdb82ffcad0, cookieoutlen=0x7fdb82ffcac8, +flags=777, + resource=0, dconn=0x0, graphicsuri=0x0, nmigrate_disks=0, +migrate_disks=0x0, compression=0x7fdb78007990, migParams=0x7fdb82ffc900) + at ../../../src/qemu/qemu_migration.c:4118 +#5 0x00007fdd09ffd808 in qemuMigrationPerformPhase (driver=0x7fdd000037b0, +conn=0x7fdb500205d0, vm=0x7fdbc4002f20, persist_xml=0x0, + uri=0x7fdb780073a0 "tcp://172.16.202.17:49152", graphicsuri=0x0, +nmigrate_disks=0, migrate_disks=0x0, compression=0x7fdb78007990, +migParams=0x7fdb82ffc900, + cookiein=0x7fdb780084e0 "<qemu-migration>\n <name>mss-pl_652</name>\n +<uuid>1f2b2334-451e-424b-822a-ea10452abb38</uuid>\n <hostname>mss</hostname>\n + <hostuuid>334e344a-4130-4336-5534-323544543642</hostuuid>\n</qemu-migra"..., +cookieinlen=207, cookieout=0x7fdb82ffcad0, cookieoutlen=0x7fdb82ffcac8, +flags=777, + resource=0) at ../../../src/qemu/qemu_migration.c:5030 +#6 0x00007fdd09ffdbb5 in qemuMigrationPerform (driver=0x7fdd000037b0, +conn=0x7fdb500205d0, vm=0x7fdbc4002f20, xmlin=0x0, persist_xml=0x0, +dconnuri=0x0, + uri=0x7fdb780073a0 "tcp://172.16.202.17:49152", graphicsuri=0x0, +listenAddress=0x0, nmigrate_disks=0, migrate_disks=0x0, nbdPort=0, +compression=0x7fdb78007990, + migParams=0x7fdb82ffc900, + cookiein=0x7fdb780084e0 "<qemu-migration>\n <name>mss-pl_652</name>\n +<uuid>1f2b2334-451e-424b-822a-ea10452abb38</uuid>\n <hostname>mss</hostname>\n + <hostuuid>334e344a-4130-4336-5534-323544543642</hostuuid>\n</qemu-migra"..., +cookieinlen=207, cookieout=0x7fdb82ffcad0, cookieoutlen=0x7fdb82ffcac8, +flags=777, + dname=0x0, resource=0, v3proto=true) at +../../../src/qemu/qemu_migration.c:5124 +#7 0x00007fdd0a054725 in qemuDomainMigratePerform3 (dom=0x7fdb78007b00, +xmlin=0x0, + cookiein=0x7fdb780084e0 "<qemu-migration>\n <name>mss-pl_652</name>\n +<uuid>1f2b2334-451e-424b-822a-ea10452abb38</uuid>\n <hostname>mss</hostname>\n + <hostuuid>334e344a-4130-4336-5534-323544543642</hostuuid>\n</qemu-migra"..., +cookieinlen=207, cookieout=0x7fdb82ffcad0, cookieoutlen=0x7fdb82ffcac8, +dconnuri=0x0, + uri=0x7fdb780073a0 "tcp://172.16.202.17:49152", flags=777, dname=0x0, +resource=0) at ../../../src/qemu/qemu_driver.c:12996 +#8 0x00007fdd199ad0f0 in virDomainMigratePerform3 (domain=0x7fdb78007b00, +xmlin=0x0, + cookiein=0x7fdb780084e0 "<qemu-migration>\n <name>mss-pl_652</name>\n +<uuid>1f2b2334-451e-424b-822a-ea10452abb38</uuid>\n <hostname>mss</hostname>\n + <hostuuid>334e344a-4130-4336-5534-323544543642</hostuuid>\n</qemu-migra"..., +cookieinlen=207, cookieout=0x7fdb82ffcad0, cookieoutlen=0x7fdb82ffcac8, +dconnuri=0x0, + uri=0x7fdb780073a0 "tcp://172.16.202.17:49152", flags=777, dname=0x0, +bandwidth=0) at ../../../src/libvirt-domain.c:4698 +#9 0x000055d13923a939 in remoteDispatchDomainMigratePerform3 +(server=0x55d13af90e60, client=0x55d13b0156f0, msg=0x55d13afbf620, +rerr=0x7fdb82ffcbc0, + args=0x7fdb7800b220, ret=0x7fdb78021e90) at ../../../daemon/remote.c:4528 +#10 0x000055d13921a043 in remoteDispatchDomainMigratePerform3Helper +(server=0x55d13af90e60, client=0x55d13b0156f0, msg=0x55d13afbf620, +rerr=0x7fdb82ffcbc0, + args=0x7fdb7800b220, ret=0x7fdb78021e90) at +../../../daemon/remote_dispatch.h:7944 +#11 0x00007fdd19a260b4 in virNetServerProgramDispatchCall (prog=0x55d13af98b50, +server=0x55d13af90e60, client=0x55d13b0156f0, msg=0x55d13afbf620) + at ../../../src/rpc/virnetserverprogram.c:436 +#12 0x00007fdd19a25c17 in virNetServerProgramDispatch (prog=0x55d13af98b50, +server=0x55d13af90e60, client=0x55d13b0156f0, msg=0x55d13afbf620) + at ../../../src/rpc/virnetserverprogram.c:307 +#13 0x000055d13925933b in virNetServerProcessMsg (srv=0x55d13af90e60, +client=0x55d13b0156f0, prog=0x55d13af98b50, msg=0x55d13afbf620) + at ../../../src/rpc/virnetserver.c:148 +------------------------------------------------------------------------------------------------------------------------------------- +æ¬é®ä»¶åå ¶é件å«ææ°åä¸éå¢çä¿å¯ä¿¡æ¯ï¼ä» éäºåéç»ä¸é¢å°åä¸ååº +ç个人æ群ç»ãç¦æ¢ä»»ä½å ¶ä»äººä»¥ä»»ä½å½¢å¼ä½¿ç¨ï¼å æ¬ä½ä¸éäºå ¨é¨æé¨åå°æ³é²ãå¤å¶ã +ææ£åï¼æ¬é®ä»¶ä¸çä¿¡æ¯ãå¦ææ¨éæ¶äºæ¬é®ä»¶ï¼è¯·æ¨ç«å³çµè¯æé®ä»¶éç¥å件人并å é¤æ¬ +é®ä»¶ï¼ +This e-mail and its attachments contain confidential information from New H3C, +which is +intended only for the person or entity whose address is listed above. Any use +of the +information contained herein in any way (including, but not limited to, total +or partial +disclosure, reproduction, or dissemination) by persons other than the intended +recipient(s) is prohibited. If you receive this e-mail in error, please notify +the sender +by phone or email immediately and delete it! + +* Yuchen (address@hidden) wrote: +> +Sometimes, living migrate vm pause forever, migrate job stop, but very small +> +probability, I canât reproduce. +> +qemu wait semaphore from libvirt send migrate continue, however libvirt wait +> +semaphore from qemu send vm pause. +Hi, + I've copied in Jiri Denemark from libvirt. +Can you confirm exactly which qemu and libvirt versions you're using +please. + +> +follow stack: +> +qemu: +> +Thread 6 (Thread 0x7f50445f3700 (LWP 18120)): +> +#0 0x00007f504b84d670 in sem_wait () from +> +/lib/x86_64-linux-gnu/libpthread.so.0 +> +#1 0x00005574eda1e164 in qemu_sem_wait (sem=sem@entry=0x5574ef6930e0) at +> +qemu-2.12/util/qemu-thread-posix.c:322 +> +#2 0x00005574ed8dd72e in migration_maybe_pause (s=0x5574ef692f50, +> +current_active_state=0x7f50445f2ae4, new_state=10) +> +at qemu-2.12/migration/migration.c:2106 +> +#3 0x00005574ed8df51a in migration_completion (s=0x5574ef692f50) at +> +qemu-2.12/migration/migration.c:2137 +> +#4 migration_iteration_run (s=0x5574ef692f50) at +> +qemu-2.12/migration/migration.c:2311 +> +#5 migration_thread (opaque=0x5574ef692f50) +> +atqemu-2.12/migration/migration.c:2415 +> +#6 0x00007f504b847184 in start_thread () from +> +/lib/x86_64-linux-gnu/libpthread.so.0 +> +#7 0x00007f504b574bed in clone () from /lib/x86_64-linux-gnu/libc.so.6 +In migration_maybe_pause we have: + + migrate_set_state(&s->state, *current_active_state, + MIGRATION_STATUS_PRE_SWITCHOVER); + qemu_sem_wait(&s->pause_sem); + migrate_set_state(&s->state, MIGRATION_STATUS_PRE_SWITCHOVER, + new_state); + +the line numbers don't match my 2.12.0 checkout; so I guess that it's +that qemu_sem_wait it's stuck at. + +QEMU must have sent the switch to PRE_SWITCHOVER and that should have +sent an event to libvirt, and libvirt should notice that - I'm +not sure how to tell whether libvirt has seen that event yet or not? + +Dave + +> +libvirt: +> +Thread 95 (Thread 0x7fdb82ffd700 (LWP 28775)): +> +#0 0x00007fdd177dc404 in pthread_cond_wait@@GLIBC_2.3.2 () from +> +/lib/x86_64-linux-gnu/libpthread.so.0 +> +#1 0x00007fdd198c3b07 in virCondWait (c=0x7fdbc4003000, m=0x7fdbc4002f30) at +> +../../../src/util/virthread.c:252 +> +#2 0x00007fdd198f36d2 in virDomainObjWait (vm=0x7fdbc4002f20) at +> +../../../src/conf/domain_conf.c:3303 +> +#3 0x00007fdd09ffaa44 in qemuMigrationRun (driver=0x7fdd000037b0, +> +vm=0x7fdbc4002f20, persist_xml=0x0, +> +cookiein=0x7fdb780084e0 "<qemu-migration>\n <name>mss-pl_652</name>\n +> +<uuid>1f2b2334-451e-424b-822a-ea10452abb38</uuid>\n <hostname>mss +> +</hostname>\n +> +<hostuuid>334e344a-4130-4336-5534-323544543642</hostuuid>\n</qemu-migra"..., +> +cookieinlen=207, cookieout=0x7fdb82ffcad0, cookieoutlen=0x7fdb82ffcac8, +> +flags=777, +> +resource=0, spec=0x7fdb82ffc670, dconn=0x0, graphicsuri=0x0, +> +nmigrate_disks=0, migrate_disks=0x0, compression=0x7fdb78007990, +> +migParams=0x7fdb82ffc900) +> +at ../../../src/qemu/qemu_migration.c:3937 +> +#4 0x00007fdd09ffb26a in doNativeMigrate (driver=0x7fdd000037b0, +> +vm=0x7fdbc4002f20, persist_xml=0x0, uri=0x7fdb780073a0 +> +"tcp://172.16.202.17:49152", +> +cookiein=0x7fdb780084e0 "<qemu-migration>\n <name>mss-pl_652</name>\n +> +<uuid>1f2b2334-451e-424b-822a-ea10452abb38</uuid>\n +> +<hostname>mss</hostname>\n <hos---Type <return> to continue, or q <return> +> +to quit--- +> +tuuid>334e344a-4130-4336-5534-323544543642</hostuuid>\n</qemu-migra"..., +> +cookieinlen=207, cookieout=0x7fdb82ffcad0, cookieoutlen=0x7fdb82ffcac8, +> +flags=777, +> +resource=0, dconn=0x0, graphicsuri=0x0, nmigrate_disks=0, +> +migrate_disks=0x0, compression=0x7fdb78007990, migParams=0x7fdb82ffc900) +> +at ../../../src/qemu/qemu_migration.c:4118 +> +#5 0x00007fdd09ffd808 in qemuMigrationPerformPhase (driver=0x7fdd000037b0, +> +conn=0x7fdb500205d0, vm=0x7fdbc4002f20, persist_xml=0x0, +> +uri=0x7fdb780073a0 "tcp://172.16.202.17:49152", graphicsuri=0x0, +> +nmigrate_disks=0, migrate_disks=0x0, compression=0x7fdb78007990, +> +migParams=0x7fdb82ffc900, +> +cookiein=0x7fdb780084e0 "<qemu-migration>\n <name>mss-pl_652</name>\n +> +<uuid>1f2b2334-451e-424b-822a-ea10452abb38</uuid>\n +> +<hostname>mss</hostname>\n +> +<hostuuid>334e344a-4130-4336-5534-323544543642</hostuuid>\n</qemu-migra"..., +> +cookieinlen=207, cookieout=0x7fdb82ffcad0, cookieoutlen=0x7fdb82ffcac8, +> +flags=777, +> +resource=0) at ../../../src/qemu/qemu_migration.c:5030 +> +#6 0x00007fdd09ffdbb5 in qemuMigrationPerform (driver=0x7fdd000037b0, +> +conn=0x7fdb500205d0, vm=0x7fdbc4002f20, xmlin=0x0, persist_xml=0x0, +> +dconnuri=0x0, +> +uri=0x7fdb780073a0 "tcp://172.16.202.17:49152", graphicsuri=0x0, +> +listenAddress=0x0, nmigrate_disks=0, migrate_disks=0x0, nbdPort=0, +> +compression=0x7fdb78007990, +> +migParams=0x7fdb82ffc900, +> +cookiein=0x7fdb780084e0 "<qemu-migration>\n <name>mss-pl_652</name>\n +> +<uuid>1f2b2334-451e-424b-822a-ea10452abb38</uuid>\n +> +<hostname>mss</hostname>\n +> +<hostuuid>334e344a-4130-4336-5534-323544543642</hostuuid>\n</qemu-migra"..., +> +cookieinlen=207, cookieout=0x7fdb82ffcad0, cookieoutlen=0x7fdb82ffcac8, +> +flags=777, +> +dname=0x0, resource=0, v3proto=true) at +> +../../../src/qemu/qemu_migration.c:5124 +> +#7 0x00007fdd0a054725 in qemuDomainMigratePerform3 (dom=0x7fdb78007b00, +> +xmlin=0x0, +> +cookiein=0x7fdb780084e0 "<qemu-migration>\n <name>mss-pl_652</name>\n +> +<uuid>1f2b2334-451e-424b-822a-ea10452abb38</uuid>\n +> +<hostname>mss</hostname>\n +> +<hostuuid>334e344a-4130-4336-5534-323544543642</hostuuid>\n</qemu-migra"..., +> +cookieinlen=207, cookieout=0x7fdb82ffcad0, cookieoutlen=0x7fdb82ffcac8, +> +dconnuri=0x0, +> +uri=0x7fdb780073a0 "tcp://172.16.202.17:49152", flags=777, dname=0x0, +> +resource=0) at ../../../src/qemu/qemu_driver.c:12996 +> +#8 0x00007fdd199ad0f0 in virDomainMigratePerform3 (domain=0x7fdb78007b00, +> +xmlin=0x0, +> +cookiein=0x7fdb780084e0 "<qemu-migration>\n <name>mss-pl_652</name>\n +> +<uuid>1f2b2334-451e-424b-822a-ea10452abb38</uuid>\n +> +<hostname>mss</hostname>\n +> +<hostuuid>334e344a-4130-4336-5534-323544543642</hostuuid>\n</qemu-migra"..., +> +cookieinlen=207, cookieout=0x7fdb82ffcad0, cookieoutlen=0x7fdb82ffcac8, +> +dconnuri=0x0, +> +uri=0x7fdb780073a0 "tcp://172.16.202.17:49152", flags=777, dname=0x0, +> +bandwidth=0) at ../../../src/libvirt-domain.c:4698 +> +#9 0x000055d13923a939 in remoteDispatchDomainMigratePerform3 +> +(server=0x55d13af90e60, client=0x55d13b0156f0, msg=0x55d13afbf620, +> +rerr=0x7fdb82ffcbc0, +> +args=0x7fdb7800b220, ret=0x7fdb78021e90) at ../../../daemon/remote.c:4528 +> +#10 0x000055d13921a043 in remoteDispatchDomainMigratePerform3Helper +> +(server=0x55d13af90e60, client=0x55d13b0156f0, msg=0x55d13afbf620, +> +rerr=0x7fdb82ffcbc0, +> +args=0x7fdb7800b220, ret=0x7fdb78021e90) at +> +../../../daemon/remote_dispatch.h:7944 +> +#11 0x00007fdd19a260b4 in virNetServerProgramDispatchCall +> +(prog=0x55d13af98b50, server=0x55d13af90e60, client=0x55d13b0156f0, +> +msg=0x55d13afbf620) +> +at ../../../src/rpc/virnetserverprogram.c:436 +> +#12 0x00007fdd19a25c17 in virNetServerProgramDispatch (prog=0x55d13af98b50, +> +server=0x55d13af90e60, client=0x55d13b0156f0, msg=0x55d13afbf620) +> +at ../../../src/rpc/virnetserverprogram.c:307 +> +#13 0x000055d13925933b in virNetServerProcessMsg (srv=0x55d13af90e60, +> +client=0x55d13b0156f0, prog=0x55d13af98b50, msg=0x55d13afbf620) +> +at ../../../src/rpc/virnetserver.c:148 +> +------------------------------------------------------------------------------------------------------------------------------------- +> +æ¬é®ä»¶åå ¶é件å«ææ°åä¸éå¢çä¿å¯ä¿¡æ¯ï¼ä» éäºåéç»ä¸é¢å°åä¸ååº +> +ç个人æ群ç»ãç¦æ¢ä»»ä½å ¶ä»äººä»¥ä»»ä½å½¢å¼ä½¿ç¨ï¼å æ¬ä½ä¸éäºå ¨é¨æé¨åå°æ³é²ãå¤å¶ã +> +ææ£åï¼æ¬é®ä»¶ä¸çä¿¡æ¯ãå¦ææ¨éæ¶äºæ¬é®ä»¶ï¼è¯·æ¨ç«å³çµè¯æé®ä»¶éç¥å件人并å é¤æ¬ +> +é®ä»¶ï¼ +> +This e-mail and its attachments contain confidential information from New +> +H3C, which is +> +intended only for the person or entity whose address is listed above. Any use +> +of the +> +information contained herein in any way (including, but not limited to, total +> +or partial +> +disclosure, reproduction, or dissemination) by persons other than the intended +> +recipient(s) is prohibited. If you receive this e-mail in error, please +> +notify the sender +> +by phone or email immediately and delete it! +-- +Dr. David Alan Gilbert / address@hidden / Manchester, UK + +In migration_maybe_pause we have: + + migrate_set_state(&s->state, *current_active_state, + MIGRATION_STATUS_PRE_SWITCHOVER); + qemu_sem_wait(&s->pause_sem); + migrate_set_state(&s->state, MIGRATION_STATUS_PRE_SWITCHOVER, + new_state); + +the line numbers don't match my 2.12.0 checkout; so I guess that it's that +qemu_sem_wait it's stuck at. + +QEMU must have sent the switch to PRE_SWITCHOVER and that should have sent an +event to libvirt, and libvirt should notice that - I'm not sure how to tell +whether libvirt has seen that event yet or not? + + +Thank you for your attention. +Yes, you are right, QEMU wait semaphore in this place. +I use qemu-2.12.1, libvirt-4.0.0. +Because I added some debug code, so the line numbers doesn't match open qemu + +-----é®ä»¶å件----- +å件人: Dr. David Alan Gilbert [ +mailto:address@hidden +] +åéæ¶é´: 2019å¹´8æ21æ¥ 19:13 +æ¶ä»¶äºº: yuchen (Cloud) <address@hidden>; address@hidden +æé: address@hidden +主é¢: Re: [Qemu-devel] [BUG] living migrate vm pause forever + +* Yuchen (address@hidden) wrote: +> +Sometimes, living migrate vm pause forever, migrate job stop, but very small +> +probability, I canât reproduce. +> +qemu wait semaphore from libvirt send migrate continue, however libvirt wait +> +semaphore from qemu send vm pause. +Hi, + I've copied in Jiri Denemark from libvirt. +Can you confirm exactly which qemu and libvirt versions you're using please. + +> +follow stack: +> +qemu: +> +Thread 6 (Thread 0x7f50445f3700 (LWP 18120)): +> +#0 0x00007f504b84d670 in sem_wait () from +> +/lib/x86_64-linux-gnu/libpthread.so.0 +> +#1 0x00005574eda1e164 in qemu_sem_wait (sem=sem@entry=0x5574ef6930e0) +> +at qemu-2.12/util/qemu-thread-posix.c:322 +> +#2 0x00005574ed8dd72e in migration_maybe_pause (s=0x5574ef692f50, +> +current_active_state=0x7f50445f2ae4, new_state=10) +> +at qemu-2.12/migration/migration.c:2106 +> +#3 0x00005574ed8df51a in migration_completion (s=0x5574ef692f50) at +> +qemu-2.12/migration/migration.c:2137 +> +#4 migration_iteration_run (s=0x5574ef692f50) at +> +qemu-2.12/migration/migration.c:2311 +> +#5 migration_thread (opaque=0x5574ef692f50) +> +atqemu-2.12/migration/migration.c:2415 +> +#6 0x00007f504b847184 in start_thread () from +> +/lib/x86_64-linux-gnu/libpthread.so.0 +> +#7 0x00007f504b574bed in clone () from +> +/lib/x86_64-linux-gnu/libc.so.6 +In migration_maybe_pause we have: + + migrate_set_state(&s->state, *current_active_state, + MIGRATION_STATUS_PRE_SWITCHOVER); + qemu_sem_wait(&s->pause_sem); + migrate_set_state(&s->state, MIGRATION_STATUS_PRE_SWITCHOVER, + new_state); + +the line numbers don't match my 2.12.0 checkout; so I guess that it's that +qemu_sem_wait it's stuck at. + +QEMU must have sent the switch to PRE_SWITCHOVER and that should have sent an +event to libvirt, and libvirt should notice that - I'm not sure how to tell +whether libvirt has seen that event yet or not? + +Dave + +> +libvirt: +> +Thread 95 (Thread 0x7fdb82ffd700 (LWP 28775)): +> +#0 0x00007fdd177dc404 in pthread_cond_wait@@GLIBC_2.3.2 () from +> +/lib/x86_64-linux-gnu/libpthread.so.0 +> +#1 0x00007fdd198c3b07 in virCondWait (c=0x7fdbc4003000, +> +m=0x7fdbc4002f30) at ../../../src/util/virthread.c:252 +> +#2 0x00007fdd198f36d2 in virDomainObjWait (vm=0x7fdbc4002f20) at +> +../../../src/conf/domain_conf.c:3303 +> +#3 0x00007fdd09ffaa44 in qemuMigrationRun (driver=0x7fdd000037b0, +> +vm=0x7fdbc4002f20, persist_xml=0x0, +> +cookiein=0x7fdb780084e0 "<qemu-migration>\n <name>mss-pl_652</name>\n +> +<uuid>1f2b2334-451e-424b-822a-ea10452abb38</uuid>\n <hostname>mss +> +</hostname>\n +> +<hostuuid>334e344a-4130-4336-5534-323544543642</hostuuid>\n</qemu-migra"..., +> +cookieinlen=207, cookieout=0x7fdb82ffcad0, cookieoutlen=0x7fdb82ffcac8, +> +flags=777, +> +resource=0, spec=0x7fdb82ffc670, dconn=0x0, graphicsuri=0x0, +> +nmigrate_disks=0, migrate_disks=0x0, compression=0x7fdb78007990, +> +migParams=0x7fdb82ffc900) +> +at ../../../src/qemu/qemu_migration.c:3937 +> +#4 0x00007fdd09ffb26a in doNativeMigrate (driver=0x7fdd000037b0, +> +vm=0x7fdbc4002f20, persist_xml=0x0, uri=0x7fdb780073a0 +> +"tcp://172.16.202.17:49152", +> +cookiein=0x7fdb780084e0 "<qemu-migration>\n +> +<name>mss-pl_652</name>\n +> +<uuid>1f2b2334-451e-424b-822a-ea10452abb38</uuid>\n +> +<hostname>mss</hostname>\n <hos---Type <return> to continue, or q +> +<return> to quit--- +> +tuuid>334e344a-4130-4336-5534-323544543642</hostuuid>\n</qemu-migra".. +> +tuuid>., cookieinlen=207, cookieout=0x7fdb82ffcad0, +> +tuuid>cookieoutlen=0x7fdb82ffcac8, flags=777, +> +resource=0, dconn=0x0, graphicsuri=0x0, nmigrate_disks=0, +> +migrate_disks=0x0, compression=0x7fdb78007990, migParams=0x7fdb82ffc900) +> +at ../../../src/qemu/qemu_migration.c:4118 +> +#5 0x00007fdd09ffd808 in qemuMigrationPerformPhase (driver=0x7fdd000037b0, +> +conn=0x7fdb500205d0, vm=0x7fdbc4002f20, persist_xml=0x0, +> +uri=0x7fdb780073a0 "tcp://172.16.202.17:49152", graphicsuri=0x0, +> +nmigrate_disks=0, migrate_disks=0x0, compression=0x7fdb78007990, +> +migParams=0x7fdb82ffc900, +> +cookiein=0x7fdb780084e0 "<qemu-migration>\n <name>mss-pl_652</name>\n +> +<uuid>1f2b2334-451e-424b-822a-ea10452abb38</uuid>\n +> +<hostname>mss</hostname>\n +> +<hostuuid>334e344a-4130-4336-5534-323544543642</hostuuid>\n</qemu-migra"..., +> +cookieinlen=207, cookieout=0x7fdb82ffcad0, cookieoutlen=0x7fdb82ffcac8, +> +flags=777, +> +resource=0) at ../../../src/qemu/qemu_migration.c:5030 +> +#6 0x00007fdd09ffdbb5 in qemuMigrationPerform (driver=0x7fdd000037b0, +> +conn=0x7fdb500205d0, vm=0x7fdbc4002f20, xmlin=0x0, persist_xml=0x0, +> +dconnuri=0x0, +> +uri=0x7fdb780073a0 "tcp://172.16.202.17:49152", graphicsuri=0x0, +> +listenAddress=0x0, nmigrate_disks=0, migrate_disks=0x0, nbdPort=0, +> +compression=0x7fdb78007990, +> +migParams=0x7fdb82ffc900, +> +cookiein=0x7fdb780084e0 "<qemu-migration>\n <name>mss-pl_652</name>\n +> +<uuid>1f2b2334-451e-424b-822a-ea10452abb38</uuid>\n +> +<hostname>mss</hostname>\n +> +<hostuuid>334e344a-4130-4336-5534-323544543642</hostuuid>\n</qemu-migra"..., +> +cookieinlen=207, cookieout=0x7fdb82ffcad0, cookieoutlen=0x7fdb82ffcac8, +> +flags=777, +> +dname=0x0, resource=0, v3proto=true) at +> +../../../src/qemu/qemu_migration.c:5124 +> +#7 0x00007fdd0a054725 in qemuDomainMigratePerform3 (dom=0x7fdb78007b00, +> +xmlin=0x0, +> +cookiein=0x7fdb780084e0 "<qemu-migration>\n <name>mss-pl_652</name>\n +> +<uuid>1f2b2334-451e-424b-822a-ea10452abb38</uuid>\n +> +<hostname>mss</hostname>\n +> +<hostuuid>334e344a-4130-4336-5534-323544543642</hostuuid>\n</qemu-migra"..., +> +cookieinlen=207, cookieout=0x7fdb82ffcad0, cookieoutlen=0x7fdb82ffcac8, +> +dconnuri=0x0, +> +uri=0x7fdb780073a0 "tcp://172.16.202.17:49152", flags=777, +> +dname=0x0, resource=0) at ../../../src/qemu/qemu_driver.c:12996 +> +#8 0x00007fdd199ad0f0 in virDomainMigratePerform3 (domain=0x7fdb78007b00, +> +xmlin=0x0, +> +cookiein=0x7fdb780084e0 "<qemu-migration>\n <name>mss-pl_652</name>\n +> +<uuid>1f2b2334-451e-424b-822a-ea10452abb38</uuid>\n +> +<hostname>mss</hostname>\n +> +<hostuuid>334e344a-4130-4336-5534-323544543642</hostuuid>\n</qemu-migra"..., +> +cookieinlen=207, cookieout=0x7fdb82ffcad0, cookieoutlen=0x7fdb82ffcac8, +> +dconnuri=0x0, +> +uri=0x7fdb780073a0 "tcp://172.16.202.17:49152", flags=777, +> +dname=0x0, bandwidth=0) at ../../../src/libvirt-domain.c:4698 +> +#9 0x000055d13923a939 in remoteDispatchDomainMigratePerform3 +> +(server=0x55d13af90e60, client=0x55d13b0156f0, msg=0x55d13afbf620, +> +rerr=0x7fdb82ffcbc0, +> +args=0x7fdb7800b220, ret=0x7fdb78021e90) at +> +../../../daemon/remote.c:4528 +> +#10 0x000055d13921a043 in remoteDispatchDomainMigratePerform3Helper +> +(server=0x55d13af90e60, client=0x55d13b0156f0, msg=0x55d13afbf620, +> +rerr=0x7fdb82ffcbc0, +> +args=0x7fdb7800b220, ret=0x7fdb78021e90) at +> +../../../daemon/remote_dispatch.h:7944 +> +#11 0x00007fdd19a260b4 in virNetServerProgramDispatchCall +> +(prog=0x55d13af98b50, server=0x55d13af90e60, client=0x55d13b0156f0, +> +msg=0x55d13afbf620) +> +at ../../../src/rpc/virnetserverprogram.c:436 +> +#12 0x00007fdd19a25c17 in virNetServerProgramDispatch (prog=0x55d13af98b50, +> +server=0x55d13af90e60, client=0x55d13b0156f0, msg=0x55d13afbf620) +> +at ../../../src/rpc/virnetserverprogram.c:307 +> +#13 0x000055d13925933b in virNetServerProcessMsg (srv=0x55d13af90e60, +> +client=0x55d13b0156f0, prog=0x55d13af98b50, msg=0x55d13afbf620) +> +at ../../../src/rpc/virnetserver.c:148 +> +---------------------------------------------------------------------- +> +--------------------------------------------------------------- +> +æ¬é®ä»¶åå ¶é件å«ææ°åä¸éå¢çä¿å¯ä¿¡æ¯ï¼ä» éäºåéç»ä¸é¢å°åä¸ååº +> +ç个人æ群ç»ãç¦æ¢ä»»ä½å ¶ä»äººä»¥ä»»ä½å½¢å¼ä½¿ç¨ï¼å æ¬ä½ä¸éäºå ¨é¨æé¨åå°æ³é²ãå¤å¶ã +> +ææ£åï¼æ¬é®ä»¶ä¸çä¿¡æ¯ãå¦ææ¨éæ¶äºæ¬é®ä»¶ï¼è¯·æ¨ç«å³çµè¯æé®ä»¶éç¥å件人并å é¤æ¬ +> +é®ä»¶ï¼ +> +This e-mail and its attachments contain confidential information from +> +New H3C, which is intended only for the person or entity whose address +> +is listed above. Any use of the information contained herein in any +> +way (including, but not limited to, total or partial disclosure, +> +reproduction, or dissemination) by persons other than the intended +> +recipient(s) is prohibited. If you receive this e-mail in error, +> +please notify the sender by phone or email immediately and delete it! +-- +Dr. David Alan Gilbert / address@hidden / Manchester, UK + diff --git a/results/classifier/zero-shot/016/x86/28596630 b/results/classifier/zero-shot/016/x86/28596630 new file mode 100644 index 000000000..4f1cca73b --- /dev/null +++ b/results/classifier/zero-shot/016/x86/28596630 @@ -0,0 +1,140 @@ +x86: 0.818 +hypervisor: 0.566 +i386: 0.555 +debug: 0.492 +files: 0.270 +operating system: 0.165 +user-level: 0.127 +TCG: 0.124 +register: 0.058 +risc-v: 0.046 +ppc: 0.046 +virtual: 0.044 +arm: 0.042 +VMM: 0.037 +PID: 0.035 +socket: 0.033 +device: 0.026 +network: 0.020 +vnc: 0.016 +alpha: 0.015 +performance: 0.015 +kernel: 0.013 +boot: 0.013 +assembly: 0.011 +peripherals: 0.009 +semantic: 0.009 +architecture: 0.006 +KVM: 0.005 +permissions: 0.004 +mistranslation: 0.003 +graphic: 0.002 + +[Qemu-devel] [BUG] [low severity] a strange appearance of message involving slirp while doing "empty" make + +Folks, + +If qemu tree is already fully built, and "make" is attempted, for 3.1, the +outcome is: + +$ make + CHK version_gen.h +$ + +For 4.0-rc0, the outcome seems to be different: + +$ make +make[1]: Entering directory '/home/build/malta-mips64r6/qemu-4.0/slirp' +make[1]: Nothing to be done for 'all'. +make[1]: Leaving directory '/home/build/malta-mips64r6/qemu-4.0/slirp' + CHK version_gen.h +$ + +Not sure how significant is that, but I report it just in case. + +Yours, +Aleksandar + +On 20/03/2019 22.08, Aleksandar Markovic wrote: +> +Folks, +> +> +If qemu tree is already fully built, and "make" is attempted, for 3.1, the +> +outcome is: +> +> +$ make +> +CHK version_gen.h +> +$ +> +> +For 4.0-rc0, the outcome seems to be different: +> +> +$ make +> +make[1]: Entering directory '/home/build/malta-mips64r6/qemu-4.0/slirp' +> +make[1]: Nothing to be done for 'all'. +> +make[1]: Leaving directory '/home/build/malta-mips64r6/qemu-4.0/slirp' +> +CHK version_gen.h +> +$ +> +> +Not sure how significant is that, but I report it just in case. +It's likely because slirp is currently being reworked to become a +separate project, so the makefiles have been changed a little bit. I +guess the message will go away again once slirp has become a stand-alone +library. + + Thomas + +On Fri, 22 Mar 2019 at 04:59, Thomas Huth <address@hidden> wrote: +> +On 20/03/2019 22.08, Aleksandar Markovic wrote: +> +> $ make +> +> make[1]: Entering directory '/home/build/malta-mips64r6/qemu-4.0/slirp' +> +> make[1]: Nothing to be done for 'all'. +> +> make[1]: Leaving directory '/home/build/malta-mips64r6/qemu-4.0/slirp' +> +> CHK version_gen.h +> +> $ +> +> +> +> Not sure how significant is that, but I report it just in case. +> +> +It's likely because slirp is currently being reworked to become a +> +separate project, so the makefiles have been changed a little bit. I +> +guess the message will go away again once slirp has become a stand-alone +> +library. +Well, we'll still need to ship slirp for the foreseeable future... + +I think the cause of this is that the rule in Makefile for +calling the slirp Makefile is not passing it $(SUBDIR_MAKEFLAGS) +like all the other recursive make invocations. If we do that +then we'll suppress the entering/leaving messages for +non-verbose builds. (Some tweaking will be needed as +it looks like the slirp makefile has picked an incompatible +meaning for $BUILD_DIR, which the SUBDIR_MAKEFLAGS will +also be passing to it.) + +thanks +-- PMM + diff --git a/results/classifier/zero-shot/016/x86/55367348 b/results/classifier/zero-shot/016/x86/55367348 new file mode 100644 index 000000000..0367eb524 --- /dev/null +++ b/results/classifier/zero-shot/016/x86/55367348 @@ -0,0 +1,559 @@ +x86: 0.960 +operating system: 0.814 +debug: 0.157 +kernel: 0.112 +files: 0.062 +register: 0.048 +virtual: 0.029 +alpha: 0.017 +TCG: 0.017 +PID: 0.013 +risc-v: 0.008 +VMM: 0.008 +hypervisor: 0.008 +semantic: 0.007 +socket: 0.007 +user-level: 0.006 +network: 0.006 +device: 0.005 +KVM: 0.004 +ppc: 0.002 +boot: 0.002 +performance: 0.002 +permissions: 0.002 +vnc: 0.002 +graphic: 0.001 +architecture: 0.001 +peripherals: 0.001 +mistranslation: 0.001 +i386: 0.001 +assembly: 0.001 +arm: 0.001 + +[Qemu-devel] [Bug] Docs build fails at interop.rst + +https://paste.fedoraproject.org/paste/kOPx4jhtUli---TmxSLrlw +running python3-sphinx-2.0.1-1.fc31.noarch on Fedora release 31 +(Rawhide) + +uname - a +Linux iouring 5.1.0-0.rc6.git3.1.fc31.x86_64 #1 SMP Thu Apr 25 14:25:32 +UTC 2019 x86_64 x86_64 x86_64 GNU/Linux + +Reverting commmit 90edef80a0852cf8a3d2668898ee40e8970e431 +allows for the build to occur + +Regards +Aarushi Mehta + +On 5/20/19 7:30 AM, Aarushi Mehta wrote: +> +https://paste.fedoraproject.org/paste/kOPx4jhtUli---TmxSLrlw +> +running python3-sphinx-2.0.1-1.fc31.noarch on Fedora release 31 +> +(Rawhide) +> +> +uname - a +> +Linux iouring 5.1.0-0.rc6.git3.1.fc31.x86_64 #1 SMP Thu Apr 25 14:25:32 +> +UTC 2019 x86_64 x86_64 x86_64 GNU/Linux +> +> +Reverting commmit 90edef80a0852cf8a3d2668898ee40e8970e431 +> +allows for the build to occur +> +> +Regards +> +Aarushi Mehta +> +> +Ah, dang. The blocks aren't strictly conforming json, but the version I +tested this under didn't seem to care. Your version is much newer. (I +was using 1.7 as provided by Fedora 29.) + +For now, try reverting 9e5b6cb87db66dfb606604fe6cf40e5ddf1ef0e7 instead, +which should at least turn off the "warnings as errors" option, but I +don't think that reverting -n will turn off this warning. + +I'll try to get ahold of this newer version and see if I can't fix it +more appropriately. + +--js + +On 5/20/19 12:37 PM, John Snow wrote: +> +> +> +On 5/20/19 7:30 AM, Aarushi Mehta wrote: +> +> +https://paste.fedoraproject.org/paste/kOPx4jhtUli---TmxSLrlw +> +> running python3-sphinx-2.0.1-1.fc31.noarch on Fedora release 31 +> +> (Rawhide) +> +> +> +> uname - a +> +> Linux iouring 5.1.0-0.rc6.git3.1.fc31.x86_64 #1 SMP Thu Apr 25 14:25:32 +> +> UTC 2019 x86_64 x86_64 x86_64 GNU/Linux +> +> +> +> Reverting commmit 90edef80a0852cf8a3d2668898ee40e8970e431 +> +> allows for the build to occur +> +> +> +> Regards +> +> Aarushi Mehta +> +> +> +> +> +> +Ah, dang. The blocks aren't strictly conforming json, but the version I +> +tested this under didn't seem to care. Your version is much newer. (I +> +was using 1.7 as provided by Fedora 29.) +> +> +For now, try reverting 9e5b6cb87db66dfb606604fe6cf40e5ddf1ef0e7 instead, +> +which should at least turn off the "warnings as errors" option, but I +> +don't think that reverting -n will turn off this warning. +> +> +I'll try to get ahold of this newer version and see if I can't fix it +> +more appropriately. +> +> +--js +> +...Sigh, okay. + +So, I am still not actually sure what changed from pygments 2.2 and +sphinx 1.7 to pygments 2.4 and sphinx 2.0.1, but it appears as if Sphinx +by default always tries to do add a filter to the pygments lexer that +raises an error on highlighting failure, instead of the default behavior +which is to just highlight those errors in the output. There is no +option to Sphinx that I am aware of to retain this lexing behavior. +(Effectively, it's strict or nothing.) + +This approach, apparently, is broken in Sphinx 1.7/Pygments 2.2, so the +build works with our malformed json. + +There are a few options: + +1. Update conf.py to ignore these warnings (and all future lexing +errors), and settle for the fact that there will be no QMP highlighting +wherever we use the directionality indicators ('->', '<-'). + +2. Update bitmaps.rst to remove the directionality indicators. + +3. Update bitmaps.rst to format the QMP blocks as raw text instead of JSON. + +4. Update bitmaps.rst to remove the "json" specification from the code +block. This will cause sphinx to "guess" the formatting, and the +pygments guesser will decide it's Python3. + +This will parse well enough, but will mis-highlight 'true' and 'false' +which are not python keywords. This approach may break in the future if +the Python3 lexer is upgraded to be stricter (because '->' and '<-' are +still invalid), and leaves us at the mercy of both the guesser and the +lexer. + +I'm not actually sure what I dislike the least; I think I dislike #1 the +most. #4 gets us most of what we want but is perhaps porcelain. + +I suspect if we attempt to move more of our documentation to ReST and +Sphinx that we will need to answer for ourselves how we intend to +document QMP code flow examples. + +--js + +On Mon, May 20, 2019 at 05:25:28PM -0400, John Snow wrote: +> +> +> +On 5/20/19 12:37 PM, John Snow wrote: +> +> +> +> +> +> On 5/20/19 7:30 AM, Aarushi Mehta wrote: +> +>> +https://paste.fedoraproject.org/paste/kOPx4jhtUli---TmxSLrlw +> +>> running python3-sphinx-2.0.1-1.fc31.noarch on Fedora release 31 +> +>> (Rawhide) +> +>> +> +>> uname - a +> +>> Linux iouring 5.1.0-0.rc6.git3.1.fc31.x86_64 #1 SMP Thu Apr 25 14:25:32 +> +>> UTC 2019 x86_64 x86_64 x86_64 GNU/Linux +> +>> +> +>> Reverting commmit 90edef80a0852cf8a3d2668898ee40e8970e431 +> +>> allows for the build to occur +> +>> +> +>> Regards +> +>> Aarushi Mehta +> +>> +> +>> +> +> +> +> Ah, dang. The blocks aren't strictly conforming json, but the version I +> +> tested this under didn't seem to care. Your version is much newer. (I +> +> was using 1.7 as provided by Fedora 29.) +> +> +> +> For now, try reverting 9e5b6cb87db66dfb606604fe6cf40e5ddf1ef0e7 instead, +> +> which should at least turn off the "warnings as errors" option, but I +> +> don't think that reverting -n will turn off this warning. +> +> +> +> I'll try to get ahold of this newer version and see if I can't fix it +> +> more appropriately. +> +> +> +> --js +> +> +> +> +...Sigh, okay. +> +> +So, I am still not actually sure what changed from pygments 2.2 and +> +sphinx 1.7 to pygments 2.4 and sphinx 2.0.1, but it appears as if Sphinx +> +by default always tries to do add a filter to the pygments lexer that +> +raises an error on highlighting failure, instead of the default behavior +> +which is to just highlight those errors in the output. There is no +> +option to Sphinx that I am aware of to retain this lexing behavior. +> +(Effectively, it's strict or nothing.) +> +> +This approach, apparently, is broken in Sphinx 1.7/Pygments 2.2, so the +> +build works with our malformed json. +> +> +There are a few options: +> +> +1. Update conf.py to ignore these warnings (and all future lexing +> +errors), and settle for the fact that there will be no QMP highlighting +> +wherever we use the directionality indicators ('->', '<-'). +> +> +2. Update bitmaps.rst to remove the directionality indicators. +> +> +3. Update bitmaps.rst to format the QMP blocks as raw text instead of JSON. +> +> +4. Update bitmaps.rst to remove the "json" specification from the code +> +block. This will cause sphinx to "guess" the formatting, and the +> +pygments guesser will decide it's Python3. +> +> +This will parse well enough, but will mis-highlight 'true' and 'false' +> +which are not python keywords. This approach may break in the future if +> +the Python3 lexer is upgraded to be stricter (because '->' and '<-' are +> +still invalid), and leaves us at the mercy of both the guesser and the +> +lexer. +> +> +I'm not actually sure what I dislike the least; I think I dislike #1 the +> +most. #4 gets us most of what we want but is perhaps porcelain. +> +> +I suspect if we attempt to move more of our documentation to ReST and +> +Sphinx that we will need to answer for ourselves how we intend to +> +document QMP code flow examples. +Writing a custom lexer that handles "<-" and "->" was simple (see below). + +Now, is it possible to convince Sphinx to register and use a custom lexer? + +$ cat > /tmp/lexer.py <<EOF +from pygments.lexer import RegexLexer, DelegatingLexer +from pygments.lexers.data import JsonLexer +import re +from pygments.token import * + +class QMPExampleMarkersLexer(RegexLexer): + tokens = { + 'root': [ + (r' *-> *', Generic.Prompt), + (r' *<- *', Generic.Output), + ] + } + +class QMPExampleLexer(DelegatingLexer): + def __init__(self, **options): + super(QMPExampleLexer, self).__init__(JsonLexer, +QMPExampleMarkersLexer, Error, **options) +EOF +$ pygmentize -l /tmp/lexer.py:QMPExampleLexer -x -f html <<EOF + -> { + "execute": "drive-backup", + "arguments": { + "device": "drive0", + "bitmap": "bitmap0", + "target": "drive0.inc0.qcow2", + "format": "qcow2", + "sync": "incremental", + "mode": "existing" + } + } + + <- { "return": {} } +EOF +<div class="highlight"><pre><span></span><span class="gp"> -> +</span><span class="p">{</span> + <span class="nt">"execute"</span><span class="p">:</span> +<span class="s2">"drive-backup"</span><span class="p">,</span> + <span class="nt">"arguments"</span><span class="p">:</span> +<span class="p">{</span> + <span class="nt">"device"</span><span class="p">:</span> +<span class="s2">"drive0"</span><span class="p">,</span> + <span class="nt">"bitmap"</span><span class="p">:</span> +<span class="s2">"bitmap0"</span><span class="p">,</span> + <span class="nt">"target"</span><span class="p">:</span> +<span class="s2">"drive0.inc0.qcow2"</span><span class="p">,</span> + <span class="nt">"format"</span><span class="p">:</span> +<span class="s2">"qcow2"</span><span class="p">,</span> + <span class="nt">"sync"</span><span class="p">:</span> +<span class="s2">"incremental"</span><span class="p">,</span> + <span class="nt">"mode"</span><span class="p">:</span> +<span class="s2">"existing"</span> + <span class="p">}</span> + <span class="p">}</span> + +<span class="go"> <- </span><span class="p">{</span> <span +class="nt">"return"</span><span class="p">:</span> <span +class="p">{}</span> <span class="p">}</span> +</pre></div> +$ + + +-- +Eduardo + +On 5/20/19 7:04 PM, Eduardo Habkost wrote: +> +On Mon, May 20, 2019 at 05:25:28PM -0400, John Snow wrote: +> +> +> +> +> +> On 5/20/19 12:37 PM, John Snow wrote: +> +>> +> +>> +> +>> On 5/20/19 7:30 AM, Aarushi Mehta wrote: +> +>>> +https://paste.fedoraproject.org/paste/kOPx4jhtUli---TmxSLrlw +> +>>> running python3-sphinx-2.0.1-1.fc31.noarch on Fedora release 31 +> +>>> (Rawhide) +> +>>> +> +>>> uname - a +> +>>> Linux iouring 5.1.0-0.rc6.git3.1.fc31.x86_64 #1 SMP Thu Apr 25 14:25:32 +> +>>> UTC 2019 x86_64 x86_64 x86_64 GNU/Linux +> +>>> +> +>>> Reverting commmit 90edef80a0852cf8a3d2668898ee40e8970e431 +> +>>> allows for the build to occur +> +>>> +> +>>> Regards +> +>>> Aarushi Mehta +> +>>> +> +>>> +> +>> +> +>> Ah, dang. The blocks aren't strictly conforming json, but the version I +> +>> tested this under didn't seem to care. Your version is much newer. (I +> +>> was using 1.7 as provided by Fedora 29.) +> +>> +> +>> For now, try reverting 9e5b6cb87db66dfb606604fe6cf40e5ddf1ef0e7 instead, +> +>> which should at least turn off the "warnings as errors" option, but I +> +>> don't think that reverting -n will turn off this warning. +> +>> +> +>> I'll try to get ahold of this newer version and see if I can't fix it +> +>> more appropriately. +> +>> +> +>> --js +> +>> +> +> +> +> ...Sigh, okay. +> +> +> +> So, I am still not actually sure what changed from pygments 2.2 and +> +> sphinx 1.7 to pygments 2.4 and sphinx 2.0.1, but it appears as if Sphinx +> +> by default always tries to do add a filter to the pygments lexer that +> +> raises an error on highlighting failure, instead of the default behavior +> +> which is to just highlight those errors in the output. There is no +> +> option to Sphinx that I am aware of to retain this lexing behavior. +> +> (Effectively, it's strict or nothing.) +> +> +> +> This approach, apparently, is broken in Sphinx 1.7/Pygments 2.2, so the +> +> build works with our malformed json. +> +> +> +> There are a few options: +> +> +> +> 1. Update conf.py to ignore these warnings (and all future lexing +> +> errors), and settle for the fact that there will be no QMP highlighting +> +> wherever we use the directionality indicators ('->', '<-'). +> +> +> +> 2. Update bitmaps.rst to remove the directionality indicators. +> +> +> +> 3. Update bitmaps.rst to format the QMP blocks as raw text instead of JSON. +> +> +> +> 4. Update bitmaps.rst to remove the "json" specification from the code +> +> block. This will cause sphinx to "guess" the formatting, and the +> +> pygments guesser will decide it's Python3. +> +> +> +> This will parse well enough, but will mis-highlight 'true' and 'false' +> +> which are not python keywords. This approach may break in the future if +> +> the Python3 lexer is upgraded to be stricter (because '->' and '<-' are +> +> still invalid), and leaves us at the mercy of both the guesser and the +> +> lexer. +> +> +> +> I'm not actually sure what I dislike the least; I think I dislike #1 the +> +> most. #4 gets us most of what we want but is perhaps porcelain. +> +> +> +> I suspect if we attempt to move more of our documentation to ReST and +> +> Sphinx that we will need to answer for ourselves how we intend to +> +> document QMP code flow examples. +> +> +Writing a custom lexer that handles "<-" and "->" was simple (see below). +> +> +Now, is it possible to convince Sphinx to register and use a custom lexer? +> +Spoilers, yes, and I've sent a patch to list. Thanks for your help! + diff --git a/results/classifier/zero-shot/016/x86/57756589 b/results/classifier/zero-shot/016/x86/57756589 new file mode 100644 index 000000000..c79fbe69f --- /dev/null +++ b/results/classifier/zero-shot/016/x86/57756589 @@ -0,0 +1,1448 @@ +x86: 0.867 +virtual: 0.827 +debug: 0.667 +hypervisor: 0.624 +vnc: 0.451 +socket: 0.358 +operating system: 0.243 +register: 0.146 +boot: 0.101 +KVM: 0.100 +kernel: 0.096 +files: 0.092 +PID: 0.083 +network: 0.075 +device: 0.070 +performance: 0.042 +TCG: 0.018 +ppc: 0.015 +VMM: 0.014 +architecture: 0.012 +permissions: 0.008 +semantic: 0.008 +assembly: 0.007 +peripherals: 0.007 +graphic: 0.004 +user-level: 0.004 +risc-v: 0.002 +mistranslation: 0.001 +alpha: 0.001 +i386: 0.000 +arm: 0.000 + +[Qemu-devel] 答复: Re: 答复: Re: 答复: Re: [BUG]COLO failover hang + +amost like wikiï¼but panic in Primary Node. + + + + +setp: + +1 + +Primary Node. + +x86_64-softmmu/qemu-system-x86_64 -enable-kvm -boot c -m 2048 -smp 2 -qmp stdio +-vnc :7 -name primary -cpu qemu64,+kvmclock -device piix3-usb-uhci -usb +-usbdevice tablet\ + + -drive +if=virtio,id=colo-disk0,driver=quorum,read-pattern=fifo,vote-threshold=1, + + +children.0.file.filename=/mnt/sdd/pure_IMG/linux/redhat/rhel_6.5_64_2U_ide,children.0.driver=qcow2 + -S \ + + -netdev +tap,id=hn1,vhost=off,script=/etc/qemu-ifup2,downscript=/etc/qemu-ifdown2 \ + + -device e1000,id=e1,netdev=hn1,mac=52:a4:00:12:78:67 \ + + -netdev +tap,id=hn0,vhost=off,script=/etc/qemu-ifup,downscript=/etc/qemu-ifdown \ + + -device e1000,id=e0,netdev=hn0,mac=52:a4:00:12:78:66 \ + + -chardev socket,id=mirror0,host=9.61.1.8,port=9003,server,nowait -chardev +socket,id=compare1,host=9.61.1.8,port=9004,server,nowait \ + + -chardev socket,id=compare0,host=9.61.1.8,port=9001,server,nowait -chardev +socket,id=compare0-0,host=9.61.1.8,port=9001 \ + + -chardev socket,id=compare_out,host=9.61.1.8,port=9005,server,nowait \ + + -chardev socket,id=compare_out0,host=9.61.1.8,port=9005 \ + + -object filter-mirror,id=m0,netdev=hn0,queue=tx,outdev=mirror0 \ + + -object filter-redirector,netdev=hn0,id=redire0,queue=rx,indev=compare_out +-object filter-redirector,netdev=hn0,id=redire1,queue=rx,outdev=compare0 \ + + -object +colo-compare,id=comp0,primary_in=compare0-0,secondary_in=compare1,outdev=compare_out0 + +2 Second node: + +x86_64-softmmu/qemu-system-x86_64 -boot c -m 2048 -smp 2 -qmp stdio -vnc :7 +-name secondary -enable-kvm -cpu qemu64,+kvmclock -device piix3-usb-uhci -usb +-usbdevice tablet\ + + -drive +if=none,id=colo-disk0,file.filename=/mnt/sdd/pure_IMG/linux/redhat/rhel_6.5_64_2U_ide,driver=qcow2,node-name=node0 + \ + + -drive +if=virtio,id=active-disk0,driver=replication,mode=secondary,file.driver=qcow2,top-id=active-disk0,file.file.filename=/mnt/ramfstest/active_disk.img,file.backing.driver=qcow2,file.backing.file.filename=/mnt/ramfstest/hidden_disk.img,file.backing.backing=colo-disk0 + \ + + -netdev +tap,id=hn1,vhost=off,script=/etc/qemu-ifup2,downscript=/etc/qemu-ifdown2 \ + + -device e1000,id=e1,netdev=hn1,mac=52:a4:00:12:78:67 \ + + -netdev +tap,id=hn0,vhost=off,script=/etc/qemu-ifup,downscript=/etc/qemu-ifdown \ + + -device e1000,netdev=hn0,mac=52:a4:00:12:78:66 -chardev +socket,id=red0,host=9.61.1.8,port=9003 \ + + -chardev socket,id=red1,host=9.61.1.8,port=9004 \ + + -object filter-redirector,id=f1,netdev=hn0,queue=tx,indev=red0 \ + + -object filter-redirector,id=f2,netdev=hn0,queue=rx,outdev=red1 \ + + -object filter-rewriter,id=rew0,netdev=hn0,queue=all -incoming tcp:0:8888 + +3 Secondary node: + +{'execute':'qmp_capabilities'} + +{ 'execute': 'nbd-server-start', + + 'arguments': {'addr': {'type': 'inet', 'data': {'host': '9.61.1.7', 'port': +'8889'} } } + +} + +{'execute': 'nbd-server-add', 'arguments': {'device': 'colo-disk0', 'writable': +true } } + +4:Primary Nodeï¼ + +{'execute':'qmp_capabilities'} + + +{ 'execute': 'human-monitor-command', + + 'arguments': {'command-line': 'drive_add -n buddy +driver=replication,mode=primary,file.driver=nbd,file.host=9.61.1.7,file.port=8889,file.export=colo-disk0,node-name=node0'}} + +{ 'execute':'x-blockdev-change', 'arguments':{'parent': 'colo-disk0', 'node': +'node0' } } + +{ 'execute': 'migrate-set-capabilities', + + 'arguments': {'capabilities': [ {'capability': 'x-colo', 'state': true } +] } } + +{ 'execute': 'migrate', 'arguments': {'uri': 'tcp:9.61.1.7:8888' } } + + + + +then can see two runing VMs, whenever you make changes to PVM, SVM will be +synced. + + + + +5ï¼Primary Nodeï¼ + +echo c ï¼ /proc/sysrq-trigger + + + + +ï¼ï¼Secondary node: + +{ 'execute': 'nbd-server-stop' } + +{ "execute": "x-colo-lost-heartbeat" } + + + + +then can see the Secondary node hang at recvmsg recvmsg . + + + + + + + + + + + + +åå§é®ä»¶ + + + +åä»¶äººï¼ address@hidden +æ¶ä»¶äººï¼ç广10165992 address@hidden +æéäººï¼ address@hidden address@hidden +æ¥ æ ï¼2017å¹´03æ21æ¥ 16:27 +主 é¢ ï¼Re: [Qemu-devel] çå¤: Re: çå¤: Re: [BUG]COLO failover hang + + + + + +Hi, + +On 2017/3/21 16:10, address@hidden wrote: +ï¼ Thank youã +ï¼ +ï¼ I have test areadyã +ï¼ +ï¼ When the Primary Node panic,the Secondary Node qemu hang at the same placeã +ï¼ +ï¼ Incorrding +http://wiki.qemu-project.org/Features/COLO +ï¼kill Primary Node qemu +will not produce the problem,but Primary Node panic canã +ï¼ +ï¼ I think due to the feature of channel does not support +QIO_CHANNEL_FEATURE_SHUTDOWN. +ï¼ +ï¼ + +Yes, you are right, when we do failover for primary/secondary VM, we will +shutdown the related +fd in case it is stuck in the read/write fd. + +It seems that you didn't follow the above introduction exactly to do the test. +Could you +share your test procedures ? Especially the commands used in the test. + +Thanks, +Hailiang + +ï¼ when failover,channel_shutdown could not shut down the channel. +ï¼ +ï¼ +ï¼ so the colo_process_incoming_thread will hang at recvmsg. +ï¼ +ï¼ +ï¼ I test a patch: +ï¼ +ï¼ +ï¼ diff --git a/migration/socket.c b/migration/socket.c +ï¼ +ï¼ +ï¼ index 13966f1..d65a0ea 100644 +ï¼ +ï¼ +ï¼ --- a/migration/socket.c +ï¼ +ï¼ +ï¼ +++ b/migration/socket.c +ï¼ +ï¼ +ï¼ @@ -147,8 +147,9 @@ static gboolean +socket_accept_incoming_migration(QIOChannel *ioc, +ï¼ +ï¼ +ï¼ } +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ trace_migration_socket_incoming_accepted() +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ qio_channel_set_name(QIO_CHANNEL(sioc), "migration-socket-incoming") +ï¼ +ï¼ +ï¼ + qio_channel_set_feature(QIO_CHANNEL(sioc), QIO_CHANNEL_FEATURE_SHUTDOWN) +ï¼ +ï¼ +ï¼ migration_channel_process_incoming(migrate_get_current(), +ï¼ +ï¼ +ï¼ QIO_CHANNEL(sioc)) +ï¼ +ï¼ +ï¼ object_unref(OBJECT(sioc)) +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ My test will not hang any more. +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ åå§é®ä»¶ +ï¼ +ï¼ +ï¼ +ï¼ åä»¶äººï¼ address@hidden +ï¼ æ¶ä»¶äººï¼ç广10165992 address@hidden +ï¼ æéäººï¼ address@hidden address@hidden +ï¼ æ¥ æ ï¼2017å¹´03æ21æ¥ 15:58 +ï¼ ä¸» é¢ ï¼Re: [Qemu-devel] çå¤: Re: [BUG]COLO failover hang +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ +ï¼ Hi,Wang. +ï¼ +ï¼ You can test this branch: +ï¼ +ï¼ +https://github.com/coloft/qemu/tree/colo-v5.1-developing-COLO-frame-v21-with-shared-disk +ï¼ +ï¼ and please follow wiki ensure your own configuration correctly. +ï¼ +ï¼ +http://wiki.qemu-project.org/Features/COLO +ï¼ +ï¼ +ï¼ Thanks +ï¼ +ï¼ Zhang Chen +ï¼ +ï¼ +ï¼ On 03/21/2017 03:27 PM, address@hidden wrote: +ï¼ ï¼ +ï¼ ï¼ hi. +ï¼ ï¼ +ï¼ ï¼ I test the git qemu master have the same problem. +ï¼ ï¼ +ï¼ ï¼ (gdb) bt +ï¼ ï¼ +ï¼ ï¼ #0 qio_channel_socket_readv (ioc=0x7f65911b4e50, iov=0x7f64ef3fd880, +ï¼ ï¼ niov=1, fds=0x0, nfds=0x0, errp=0x0) at io/channel-socket.c:461 +ï¼ ï¼ +ï¼ ï¼ #1 0x00007f658e4aa0c2 in qio_channel_read +ï¼ ï¼ (address@hidden, address@hidden "", +ï¼ ï¼ address@hidden, address@hidden) at io/channel.c:114 +ï¼ ï¼ +ï¼ ï¼ #2 0x00007f658e3ea990 in channel_get_buffer (opaque=ï¼optimized outï¼, +ï¼ ï¼ buf=0x7f65907cb838 "", pos=ï¼optimized outï¼, size=32768) at +ï¼ ï¼ migration/qemu-file-channel.c:78 +ï¼ ï¼ +ï¼ ï¼ #3 0x00007f658e3e97fc in qemu_fill_buffer (f=0x7f65907cb800) at +ï¼ ï¼ migration/qemu-file.c:295 +ï¼ ï¼ +ï¼ ï¼ #4 0x00007f658e3ea2e1 in qemu_peek_byte (address@hidden, +ï¼ ï¼ address@hidden) at migration/qemu-file.c:555 +ï¼ ï¼ +ï¼ ï¼ #5 0x00007f658e3ea34b in qemu_get_byte (address@hidden) at +ï¼ ï¼ migration/qemu-file.c:568 +ï¼ ï¼ +ï¼ ï¼ #6 0x00007f658e3ea552 in qemu_get_be32 (address@hidden) at +ï¼ ï¼ migration/qemu-file.c:648 +ï¼ ï¼ +ï¼ ï¼ #7 0x00007f658e3e66e5 in colo_receive_message (f=0x7f65907cb800, +ï¼ ï¼ address@hidden) at migration/colo.c:244 +ï¼ ï¼ +ï¼ ï¼ #8 0x00007f658e3e681e in colo_receive_check_message (f=ï¼optimized +ï¼ ï¼ outï¼, address@hidden, +ï¼ ï¼ address@hidden) +ï¼ ï¼ +ï¼ ï¼ at migration/colo.c:264 +ï¼ ï¼ +ï¼ ï¼ #9 0x00007f658e3e740e in colo_process_incoming_thread +ï¼ ï¼ (opaque=0x7f658eb30360 ï¼mis_current.31286ï¼) at migration/colo.c:577 +ï¼ ï¼ +ï¼ ï¼ #10 0x00007f658be09df3 in start_thread () from /lib64/libpthread.so.0 +ï¼ ï¼ +ï¼ ï¼ #11 0x00007f65881983ed in clone () from /lib64/libc.so.6 +ï¼ ï¼ +ï¼ ï¼ (gdb) p ioc-ï¼name +ï¼ ï¼ +ï¼ ï¼ $2 = 0x7f658ff7d5c0 "migration-socket-incoming" +ï¼ ï¼ +ï¼ ï¼ (gdb) p ioc-ï¼features Do not support QIO_CHANNEL_FEATURE_SHUTDOWN +ï¼ ï¼ +ï¼ ï¼ $3 = 0 +ï¼ ï¼ +ï¼ ï¼ +ï¼ ï¼ (gdb) bt +ï¼ ï¼ +ï¼ ï¼ #0 socket_accept_incoming_migration (ioc=0x7fdcceeafa90, +ï¼ ï¼ condition=G_IO_IN, opaque=0x7fdcceeafa90) at migration/socket.c:137 +ï¼ ï¼ +ï¼ ï¼ #1 0x00007fdcc6966350 in g_main_dispatch (context=ï¼optimized outï¼) at +ï¼ ï¼ gmain.c:3054 +ï¼ ï¼ +ï¼ ï¼ #2 g_main_context_dispatch (context=ï¼optimized outï¼, +ï¼ ï¼ address@hidden) at gmain.c:3630 +ï¼ ï¼ +ï¼ ï¼ #3 0x00007fdccb8a6dcc in glib_pollfds_poll () at util/main-loop.c:213 +ï¼ ï¼ +ï¼ ï¼ #4 os_host_main_loop_wait (timeout=ï¼optimized outï¼) at +ï¼ ï¼ util/main-loop.c:258 +ï¼ ï¼ +ï¼ ï¼ #5 main_loop_wait (address@hidden) at +ï¼ ï¼ util/main-loop.c:506 +ï¼ ï¼ +ï¼ ï¼ #6 0x00007fdccb526187 in main_loop () at vl.c:1898 +ï¼ ï¼ +ï¼ ï¼ #7 main (argc=ï¼optimized outï¼, argv=ï¼optimized outï¼, envp=ï¼optimized +ï¼ ï¼ outï¼) at vl.c:4709 +ï¼ ï¼ +ï¼ ï¼ (gdb) p ioc-ï¼features +ï¼ ï¼ +ï¼ ï¼ $1 = 6 +ï¼ ï¼ +ï¼ ï¼ (gdb) p ioc-ï¼name +ï¼ ï¼ +ï¼ ï¼ $2 = 0x7fdcce1b1ab0 "migration-socket-listener" +ï¼ ï¼ +ï¼ ï¼ +ï¼ ï¼ May be socket_accept_incoming_migration should +ï¼ ï¼ call qio_channel_set_feature(ioc, QIO_CHANNEL_FEATURE_SHUTDOWN)?? +ï¼ ï¼ +ï¼ ï¼ +ï¼ ï¼ thank you. +ï¼ ï¼ +ï¼ ï¼ +ï¼ ï¼ +ï¼ ï¼ +ï¼ ï¼ +ï¼ ï¼ åå§é®ä»¶ +ï¼ ï¼ address@hidden +ï¼ ï¼ address@hidden +ï¼ ï¼ address@hidden@huawei.comï¼ +ï¼ ï¼ *æ¥ æ ï¼*2017å¹´03æ16æ¥ 14:46 +ï¼ ï¼ *主 é¢ ï¼**Re: [Qemu-devel] COLO failover hang* +ï¼ ï¼ +ï¼ ï¼ +ï¼ ï¼ +ï¼ ï¼ +ï¼ ï¼ On 03/15/2017 05:06 PM, wangguang wrote: +ï¼ ï¼ ï¼ am testing QEMU COLO feature described here [QEMU +ï¼ ï¼ ï¼ Wiki]( +http://wiki.qemu-project.org/Features/COLO +). +ï¼ ï¼ ï¼ +ï¼ ï¼ ï¼ When the Primary Node panic,the Secondary Node qemu hang. +ï¼ ï¼ ï¼ hang at recvmsg in qio_channel_socket_readv. +ï¼ ï¼ ï¼ And I run { 'execute': 'nbd-server-stop' } and { "execute": +ï¼ ï¼ ï¼ "x-colo-lost-heartbeat" } in Secondary VM's +ï¼ ï¼ ï¼ monitor,the Secondary Node qemu still hang at recvmsg . +ï¼ ï¼ ï¼ +ï¼ ï¼ ï¼ I found that the colo in qemu is not complete yet. +ï¼ ï¼ ï¼ Do the colo have any plan for development? +ï¼ ï¼ +ï¼ ï¼ Yes, We are developing. You can see some of patch we pushing. +ï¼ ï¼ +ï¼ ï¼ ï¼ Has anyone ever run it successfully? Any help is appreciated! +ï¼ ï¼ +ï¼ ï¼ In our internal version can run it successfully, +ï¼ ï¼ The failover detail you can ask Zhanghailiang for help. +ï¼ ï¼ Next time if you have some question about COLO, +ï¼ ï¼ please cc me and zhanghailiang address@hidden +ï¼ ï¼ +ï¼ ï¼ +ï¼ ï¼ Thanks +ï¼ ï¼ Zhang Chen +ï¼ ï¼ +ï¼ ï¼ +ï¼ ï¼ ï¼ +ï¼ ï¼ ï¼ +ï¼ ï¼ ï¼ +ï¼ ï¼ ï¼ centos7.2+qemu2.7.50 +ï¼ ï¼ ï¼ (gdb) bt +ï¼ ï¼ ï¼ #0 0x00007f3e00cc86ad in recvmsg () from /lib64/libpthread.so.0 +ï¼ ï¼ ï¼ #1 0x00007f3e0332b738 in qio_channel_socket_readv (ioc=ï¼optimized outï¼, +ï¼ ï¼ ï¼ iov=ï¼optimized outï¼, niov=ï¼optimized outï¼, fds=0x0, nfds=0x0, errp=0x0) at +ï¼ ï¼ ï¼ io/channel-socket.c:497 +ï¼ ï¼ ï¼ #2 0x00007f3e03329472 in qio_channel_read (address@hidden, +ï¼ ï¼ ï¼ address@hidden "", address@hidden, +ï¼ ï¼ ï¼ address@hidden) at io/channel.c:97 +ï¼ ï¼ ï¼ #3 0x00007f3e032750e0 in channel_get_buffer (opaque=ï¼optimized outï¼, +ï¼ ï¼ ï¼ buf=0x7f3e05910f38 "", pos=ï¼optimized outï¼, size=32768) at +ï¼ ï¼ ï¼ migration/qemu-file-channel.c:78 +ï¼ ï¼ ï¼ #4 0x00007f3e0327412c in qemu_fill_buffer (f=0x7f3e05910f00) at +ï¼ ï¼ ï¼ migration/qemu-file.c:257 +ï¼ ï¼ ï¼ #5 0x00007f3e03274a41 in qemu_peek_byte (address@hidden, +ï¼ ï¼ ï¼ address@hidden) at migration/qemu-file.c:510 +ï¼ ï¼ ï¼ #6 0x00007f3e03274aab in qemu_get_byte (address@hidden) at +ï¼ ï¼ ï¼ migration/qemu-file.c:523 +ï¼ ï¼ ï¼ #7 0x00007f3e03274cb2 in qemu_get_be32 (address@hidden) at +ï¼ ï¼ ï¼ migration/qemu-file.c:603 +ï¼ ï¼ ï¼ #8 0x00007f3e03271735 in colo_receive_message (f=0x7f3e05910f00, +ï¼ ï¼ ï¼ address@hidden) at migration/colo..c:215 +ï¼ ï¼ ï¼ #9 0x00007f3e0327250d in colo_wait_handle_message (errp=0x7f3d62bfaa48, +ï¼ ï¼ ï¼ checkpoint_request=ï¼synthetic pointerï¼, f=ï¼optimized outï¼) at +ï¼ ï¼ ï¼ migration/colo.c:546 +ï¼ ï¼ ï¼ #10 colo_process_incoming_thread (opaque=0x7f3e067245e0) at +ï¼ ï¼ ï¼ migration/colo.c:649 +ï¼ ï¼ ï¼ #11 0x00007f3e00cc1df3 in start_thread () from /lib64/libpthread.so.0 +ï¼ ï¼ ï¼ #12 0x00007f3dfc9c03ed in clone () from /lib64/libc.so.6 +ï¼ ï¼ ï¼ +ï¼ ï¼ ï¼ +ï¼ ï¼ ï¼ +ï¼ ï¼ ï¼ +ï¼ ï¼ ï¼ +ï¼ ï¼ ï¼ -- +ï¼ ï¼ ï¼ View this message in context: +http://qemu.11.n7.nabble.com/COLO-failover-hang-tp473250.html +ï¼ ï¼ ï¼ Sent from the Developer mailing list archive at Nabble.com. +ï¼ ï¼ ï¼ +ï¼ ï¼ ï¼ +ï¼ ï¼ ï¼ +ï¼ ï¼ ï¼ +ï¼ ï¼ +ï¼ ï¼ -- +ï¼ ï¼ Thanks +ï¼ ï¼ Zhang Chen +ï¼ ï¼ +ï¼ ï¼ +ï¼ ï¼ +ï¼ ï¼ +ï¼ ï¼ +ï¼ + +diff --git a/migration/socket.c b/migration/socket.c + + +index 13966f1..d65a0ea 100644 + + +--- a/migration/socket.c + + ++++ b/migration/socket.c + + +@@ -147,8 +147,9 @@ static gboolean socket_accept_incoming_migration(QIOChannel +*ioc, + + + } + + + + + + trace_migration_socket_incoming_accepted() + + + + + + qio_channel_set_name(QIO_CHANNEL(sioc), "migration-socket-incoming") + + ++ qio_channel_set_feature(QIO_CHANNEL(sioc), QIO_CHANNEL_FEATURE_SHUTDOWN) + + + migration_channel_process_incoming(migrate_get_current(), + + + QIO_CHANNEL(sioc)) + + + object_unref(OBJECT(sioc)) + + + + +Is this patch ok? + +I have test it . The test could not hang any more. + + + + + + + + + + + + +åå§é®ä»¶ + + + +åä»¶äººï¼ address@hidden +æ¶ä»¶äººï¼ address@hidden address@hidden +æéäººï¼ address@hidden address@hidden address@hidden +æ¥ æ ï¼2017å¹´03æ22æ¥ 09:11 +主 é¢ ï¼Re: [Qemu-devel] çå¤: Re: çå¤: Re: [BUG]COLO failover hang + + + + + +On 2017/3/21 19:56, Dr. David Alan Gilbert wrote: +ï¼ * Hailiang Zhang (address@hidden) wrote: +ï¼ï¼ Hi, +ï¼ï¼ +ï¼ï¼ Thanks for reporting this, and i confirmed it in my test, and it is a bug. +ï¼ï¼ +ï¼ï¼ Though we tried to call qemu_file_shutdown() to shutdown the related fd, in +ï¼ï¼ case COLO thread/incoming thread is stuck in read/write() while do failover, +ï¼ï¼ but it didn't take effect, because all the fd used by COLO (also migration) +ï¼ï¼ has been wrapped by qio channel, and it will not call the shutdown API if +ï¼ï¼ we didn't qio_channel_set_feature(QIO_CHANNEL(sioc), +QIO_CHANNEL_FEATURE_SHUTDOWN). +ï¼ï¼ +ï¼ï¼ Cc: Dr. David Alan Gilbert address@hidden +ï¼ï¼ +ï¼ï¼ I doubted migration cancel has the same problem, it may be stuck in write() +ï¼ï¼ if we tried to cancel migration. +ï¼ï¼ +ï¼ï¼ void fd_start_outgoing_migration(MigrationState *s, const char *fdname, +Error **errp) +ï¼ï¼ { +ï¼ï¼ qio_channel_set_name(QIO_CHANNEL(ioc), "migration-fd-outgoing") +ï¼ï¼ migration_channel_connect(s, ioc, NULL) +ï¼ï¼ ... ... +ï¼ï¼ We didn't call qio_channel_set_feature(QIO_CHANNEL(sioc), +QIO_CHANNEL_FEATURE_SHUTDOWN) above, +ï¼ï¼ and the +ï¼ï¼ migrate_fd_cancel() +ï¼ï¼ { +ï¼ï¼ ... ... +ï¼ï¼ if (s-ï¼state == MIGRATION_STATUS_CANCELLING && f) { +ï¼ï¼ qemu_file_shutdown(f) --ï¼ This will not take effect. No ? +ï¼ï¼ } +ï¼ï¼ } +ï¼ +ï¼ (cc'd in Daniel Berrange). +ï¼ I see that we call qio_channel_set_feature(ioc, QIO_CHANNEL_FEATURE_SHUTDOWN) +at the +ï¼ top of qio_channel_socket_new so I think that's safe isn't it? +ï¼ + +Hmm, you are right, this problem is only exist for the migration incoming fd, +thanks. + +ï¼ Dave +ï¼ +ï¼ï¼ Thanks, +ï¼ï¼ Hailiang +ï¼ï¼ +ï¼ï¼ On 2017/3/21 16:10, address@hidden wrote: +ï¼ï¼ï¼ Thank youã +ï¼ï¼ï¼ +ï¼ï¼ï¼ I have test areadyã +ï¼ï¼ï¼ +ï¼ï¼ï¼ When the Primary Node panic,the Secondary Node qemu hang at the same placeã +ï¼ï¼ï¼ +ï¼ï¼ï¼ Incorrding +http://wiki.qemu-project.org/Features/COLO +ï¼kill Primary Node +qemu will not produce the problem,but Primary Node panic canã +ï¼ï¼ï¼ +ï¼ï¼ï¼ I think due to the feature of channel does not support +QIO_CHANNEL_FEATURE_SHUTDOWN. +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ when failover,channel_shutdown could not shut down the channel. +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ so the colo_process_incoming_thread will hang at recvmsg. +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ I test a patch: +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ diff --git a/migration/socket.c b/migration/socket.c +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ index 13966f1..d65a0ea 100644 +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ --- a/migration/socket.c +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +++ b/migration/socket.c +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ @@ -147,8 +147,9 @@ static gboolean +socket_accept_incoming_migration(QIOChannel *ioc, +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ } +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ trace_migration_socket_incoming_accepted() +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ qio_channel_set_name(QIO_CHANNEL(sioc), "migration-socket-incoming") +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ + qio_channel_set_feature(QIO_CHANNEL(sioc), +QIO_CHANNEL_FEATURE_SHUTDOWN) +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ migration_channel_process_incoming(migrate_get_current(), +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ QIO_CHANNEL(sioc)) +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ object_unref(OBJECT(sioc)) +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ My test will not hang any more. +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ åå§é®ä»¶ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ åä»¶äººï¼ address@hidden +ï¼ï¼ï¼ æ¶ä»¶äººï¼ç广10165992 address@hidden +ï¼ï¼ï¼ æéäººï¼ address@hidden address@hidden +ï¼ï¼ï¼ æ¥ æ ï¼2017å¹´03æ21æ¥ 15:58 +ï¼ï¼ï¼ 主 é¢ ï¼Re: [Qemu-devel] çå¤: Re: [BUG]COLO failover hang +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ Hi,Wang. +ï¼ï¼ï¼ +ï¼ï¼ï¼ You can test this branch: +ï¼ï¼ï¼ +ï¼ï¼ï¼ +https://github.com/coloft/qemu/tree/colo-v5.1-developing-COLO-frame-v21-with-shared-disk +ï¼ï¼ï¼ +ï¼ï¼ï¼ and please follow wiki ensure your own configuration correctly. +ï¼ï¼ï¼ +ï¼ï¼ï¼ +http://wiki.qemu-project.org/Features/COLO +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ Thanks +ï¼ï¼ï¼ +ï¼ï¼ï¼ Zhang Chen +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ On 03/21/2017 03:27 PM, address@hidden wrote: +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ hi. +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ I test the git qemu master have the same problem. +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ (gdb) bt +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #0 qio_channel_socket_readv (ioc=0x7f65911b4e50, iov=0x7f64ef3fd880, +ï¼ï¼ï¼ ï¼ niov=1, fds=0x0, nfds=0x0, errp=0x0) at io/channel-socket.c:461 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #1 0x00007f658e4aa0c2 in qio_channel_read +ï¼ï¼ï¼ ï¼ (address@hidden, address@hidden "", +ï¼ï¼ï¼ ï¼ address@hidden, address@hidden) at io/channel.c:114 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #2 0x00007f658e3ea990 in channel_get_buffer (opaque=ï¼optimized outï¼, +ï¼ï¼ï¼ ï¼ buf=0x7f65907cb838 "", pos=ï¼optimized outï¼, size=32768) at +ï¼ï¼ï¼ ï¼ migration/qemu-file-channel.c:78 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #3 0x00007f658e3e97fc in qemu_fill_buffer (f=0x7f65907cb800) at +ï¼ï¼ï¼ ï¼ migration/qemu-file.c:295 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #4 0x00007f658e3ea2e1 in qemu_peek_byte (address@hidden, +ï¼ï¼ï¼ ï¼ address@hidden) at migration/qemu-file.c:555 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #5 0x00007f658e3ea34b in qemu_get_byte (address@hidden) at +ï¼ï¼ï¼ ï¼ migration/qemu-file.c:568 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #6 0x00007f658e3ea552 in qemu_get_be32 (address@hidden) at +ï¼ï¼ï¼ ï¼ migration/qemu-file.c:648 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #7 0x00007f658e3e66e5 in colo_receive_message (f=0x7f65907cb800, +ï¼ï¼ï¼ ï¼ address@hidden) at migration/colo.c:244 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #8 0x00007f658e3e681e in colo_receive_check_message (f=ï¼optimized +ï¼ï¼ï¼ ï¼ outï¼, address@hidden, +ï¼ï¼ï¼ ï¼ address@hidden) +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ at migration/colo.c:264 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #9 0x00007f658e3e740e in colo_process_incoming_thread +ï¼ï¼ï¼ ï¼ (opaque=0x7f658eb30360 ï¼mis_current.31286ï¼) at migration/colo.c:577 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #10 0x00007f658be09df3 in start_thread () from /lib64/libpthread.so.0 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #11 0x00007f65881983ed in clone () from /lib64/libc.so.6 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ (gdb) p ioc-ï¼name +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ $2 = 0x7f658ff7d5c0 "migration-socket-incoming" +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ (gdb) p ioc-ï¼features Do not support QIO_CHANNEL_FEATURE_SHUTDOWN +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ $3 = 0 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ (gdb) bt +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #0 socket_accept_incoming_migration (ioc=0x7fdcceeafa90, +ï¼ï¼ï¼ ï¼ condition=G_IO_IN, opaque=0x7fdcceeafa90) at migration/socket.c:137 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #1 0x00007fdcc6966350 in g_main_dispatch (context=ï¼optimized outï¼) at +ï¼ï¼ï¼ ï¼ gmain.c:3054 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #2 g_main_context_dispatch (context=ï¼optimized outï¼, +ï¼ï¼ï¼ ï¼ address@hidden) at gmain.c:3630 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #3 0x00007fdccb8a6dcc in glib_pollfds_poll () at util/main-loop.c:213 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #4 os_host_main_loop_wait (timeout=ï¼optimized outï¼) at +ï¼ï¼ï¼ ï¼ util/main-loop.c:258 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #5 main_loop_wait (address@hidden) at +ï¼ï¼ï¼ ï¼ util/main-loop.c:506 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #6 0x00007fdccb526187 in main_loop () at vl.c:1898 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #7 main (argc=ï¼optimized outï¼, argv=ï¼optimized outï¼, envp=ï¼optimized +ï¼ï¼ï¼ ï¼ outï¼) at vl.c:4709 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ (gdb) p ioc-ï¼features +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ $1 = 6 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ (gdb) p ioc-ï¼name +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ $2 = 0x7fdcce1b1ab0 "migration-socket-listener" +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ May be socket_accept_incoming_migration should +ï¼ï¼ï¼ ï¼ call qio_channel_set_feature(ioc, QIO_CHANNEL_FEATURE_SHUTDOWN)?? +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ thank you. +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ åå§é®ä»¶ +ï¼ï¼ï¼ ï¼ address@hidden +ï¼ï¼ï¼ ï¼ address@hidden +ï¼ï¼ï¼ ï¼ address@hidden@huawei.comï¼ +ï¼ï¼ï¼ ï¼ *æ¥ æ ï¼*2017å¹´03æ16æ¥ 14:46 +ï¼ï¼ï¼ ï¼ *主 é¢ ï¼**Re: [Qemu-devel] COLO failover hang* +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ On 03/15/2017 05:06 PM, wangguang wrote: +ï¼ï¼ï¼ ï¼ ï¼ am testing QEMU COLO feature described here [QEMU +ï¼ï¼ï¼ ï¼ ï¼ Wiki]( +http://wiki.qemu-project.org/Features/COLO +). +ï¼ï¼ï¼ ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ When the Primary Node panic,the Secondary Node qemu hang. +ï¼ï¼ï¼ ï¼ ï¼ hang at recvmsg in qio_channel_socket_readv. +ï¼ï¼ï¼ ï¼ ï¼ And I run { 'execute': 'nbd-server-stop' } and { "execute": +ï¼ï¼ï¼ ï¼ ï¼ "x-colo-lost-heartbeat" } in Secondary VM's +ï¼ï¼ï¼ ï¼ ï¼ monitor,the Secondary Node qemu still hang at recvmsg . +ï¼ï¼ï¼ ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ I found that the colo in qemu is not complete yet. +ï¼ï¼ï¼ ï¼ ï¼ Do the colo have any plan for development? +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ Yes, We are developing. You can see some of patch we pushing. +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ Has anyone ever run it successfully? Any help is appreciated! +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ In our internal version can run it successfully, +ï¼ï¼ï¼ ï¼ The failover detail you can ask Zhanghailiang for help. +ï¼ï¼ï¼ ï¼ Next time if you have some question about COLO, +ï¼ï¼ï¼ ï¼ please cc me and zhanghailiang address@hidden +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ Thanks +ï¼ï¼ï¼ ï¼ Zhang Chen +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ centos7.2+qemu2.7.50 +ï¼ï¼ï¼ ï¼ ï¼ (gdb) bt +ï¼ï¼ï¼ ï¼ ï¼ #0 0x00007f3e00cc86ad in recvmsg () from /lib64/libpthread.so.0 +ï¼ï¼ï¼ ï¼ ï¼ #1 0x00007f3e0332b738 in qio_channel_socket_readv (ioc=ï¼optimized outï¼, +ï¼ï¼ï¼ ï¼ ï¼ iov=ï¼optimized outï¼, niov=ï¼optimized outï¼, fds=0x0, nfds=0x0, errp=0x0) +at +ï¼ï¼ï¼ ï¼ ï¼ io/channel-socket.c:497 +ï¼ï¼ï¼ ï¼ ï¼ #2 0x00007f3e03329472 in qio_channel_read (address@hidden, +ï¼ï¼ï¼ ï¼ ï¼ address@hidden "", address@hidden, +ï¼ï¼ï¼ ï¼ ï¼ address@hidden) at io/channel.c:97 +ï¼ï¼ï¼ ï¼ ï¼ #3 0x00007f3e032750e0 in channel_get_buffer (opaque=ï¼optimized outï¼, +ï¼ï¼ï¼ ï¼ ï¼ buf=0x7f3e05910f38 "", pos=ï¼optimized outï¼, size=32768) at +ï¼ï¼ï¼ ï¼ ï¼ migration/qemu-file-channel.c:78 +ï¼ï¼ï¼ ï¼ ï¼ #4 0x00007f3e0327412c in qemu_fill_buffer (f=0x7f3e05910f00) at +ï¼ï¼ï¼ ï¼ ï¼ migration/qemu-file.c:257 +ï¼ï¼ï¼ ï¼ ï¼ #5 0x00007f3e03274a41 in qemu_peek_byte (address@hidden, +ï¼ï¼ï¼ ï¼ ï¼ address@hidden) at migration/qemu-file.c:510 +ï¼ï¼ï¼ ï¼ ï¼ #6 0x00007f3e03274aab in qemu_get_byte (address@hidden) at +ï¼ï¼ï¼ ï¼ ï¼ migration/qemu-file.c:523 +ï¼ï¼ï¼ ï¼ ï¼ #7 0x00007f3e03274cb2 in qemu_get_be32 (address@hidden) at +ï¼ï¼ï¼ ï¼ ï¼ migration/qemu-file.c:603 +ï¼ï¼ï¼ ï¼ ï¼ #8 0x00007f3e03271735 in colo_receive_message (f=0x7f3e05910f00, +ï¼ï¼ï¼ ï¼ ï¼ address@hidden) at migration/colo.c:215 +ï¼ï¼ï¼ ï¼ ï¼ #9 0x00007f3e0327250d in colo_wait_handle_message (errp=0x7f3d62bfaa48, +ï¼ï¼ï¼ ï¼ ï¼ checkpoint_request=ï¼synthetic pointerï¼, f=ï¼optimized outï¼) at +ï¼ï¼ï¼ ï¼ ï¼ migration/colo.c:546 +ï¼ï¼ï¼ ï¼ ï¼ #10 colo_process_incoming_thread (opaque=0x7f3e067245e0) at +ï¼ï¼ï¼ ï¼ ï¼ migration/colo.c:649 +ï¼ï¼ï¼ ï¼ ï¼ #11 0x00007f3e00cc1df3 in start_thread () from /lib64/libpthread.so.0 +ï¼ï¼ï¼ ï¼ ï¼ #12 0x00007f3dfc9c03ed in clone () from /lib64/libc..so.6 +ï¼ï¼ï¼ ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ -- +ï¼ï¼ï¼ ï¼ ï¼ View this message in context: +http://qemu.11.n7.nabble.com/COLO-failover-hang-tp473250.html +ï¼ï¼ï¼ ï¼ ï¼ Sent from the Developer mailing list archive at Nabble.com. +ï¼ï¼ï¼ ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ -- +ï¼ï¼ï¼ ï¼ Thanks +ï¼ï¼ï¼ ï¼ Zhang Chen +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ +ï¼ï¼ +ï¼ -- +ï¼ Dr. David Alan Gilbert / address@hidden / Manchester, UK +ï¼ +ï¼ . +ï¼ + +Hi, + +On 2017/3/22 9:42, address@hidden wrote: +diff --git a/migration/socket.c b/migration/socket.c + + +index 13966f1..d65a0ea 100644 + + +--- a/migration/socket.c + + ++++ b/migration/socket.c + + +@@ -147,8 +147,9 @@ static gboolean socket_accept_incoming_migration(QIOChannel +*ioc, + + + } + + + + + + trace_migration_socket_incoming_accepted() + + + + + + qio_channel_set_name(QIO_CHANNEL(sioc), "migration-socket-incoming") + + ++ qio_channel_set_feature(QIO_CHANNEL(sioc), QIO_CHANNEL_FEATURE_SHUTDOWN) + + + migration_channel_process_incoming(migrate_get_current(), + + + QIO_CHANNEL(sioc)) + + + object_unref(OBJECT(sioc)) + + + + +Is this patch ok? +Yes, i think this works, but a better way maybe to call +qio_channel_set_feature() +in qio_channel_socket_accept(), we didn't set the SHUTDOWN feature for the +socket accept fd, +Or fix it by this: + +diff --git a/io/channel-socket.c b/io/channel-socket.c +index f546c68..ce6894c 100644 +--- a/io/channel-socket.c ++++ b/io/channel-socket.c +@@ -330,9 +330,8 @@ qio_channel_socket_accept(QIOChannelSocket *ioc, + Error **errp) + { + QIOChannelSocket *cioc; +- +- cioc = QIO_CHANNEL_SOCKET(object_new(TYPE_QIO_CHANNEL_SOCKET)); +- cioc->fd = -1; ++ ++ cioc = qio_channel_socket_new(); + cioc->remoteAddrLen = sizeof(ioc->remoteAddr); + cioc->localAddrLen = sizeof(ioc->localAddr); + + +Thanks, +Hailiang +I have test it . The test could not hang any more. + + + + + + + + + + + + +åå§é®ä»¶ + + + +åä»¶äººï¼ address@hidden +æ¶ä»¶äººï¼ address@hidden address@hidden +æéäººï¼ address@hidden address@hidden address@hidden +æ¥ æ ï¼2017å¹´03æ22æ¥ 09:11 +主 é¢ ï¼Re: [Qemu-devel] çå¤: Re: çå¤: Re: [BUG]COLO failover hang + + + + + +On 2017/3/21 19:56, Dr. David Alan Gilbert wrote: +ï¼ * Hailiang Zhang (address@hidden) wrote: +ï¼ï¼ Hi, +ï¼ï¼ +ï¼ï¼ Thanks for reporting this, and i confirmed it in my test, and it is a bug. +ï¼ï¼ +ï¼ï¼ Though we tried to call qemu_file_shutdown() to shutdown the related fd, in +ï¼ï¼ case COLO thread/incoming thread is stuck in read/write() while do failover, +ï¼ï¼ but it didn't take effect, because all the fd used by COLO (also migration) +ï¼ï¼ has been wrapped by qio channel, and it will not call the shutdown API if +ï¼ï¼ we didn't qio_channel_set_feature(QIO_CHANNEL(sioc), +QIO_CHANNEL_FEATURE_SHUTDOWN). +ï¼ï¼ +ï¼ï¼ Cc: Dr. David Alan Gilbert address@hidden +ï¼ï¼ +ï¼ï¼ I doubted migration cancel has the same problem, it may be stuck in write() +ï¼ï¼ if we tried to cancel migration. +ï¼ï¼ +ï¼ï¼ void fd_start_outgoing_migration(MigrationState *s, const char *fdname, +Error **errp) +ï¼ï¼ { +ï¼ï¼ qio_channel_set_name(QIO_CHANNEL(ioc), "migration-fd-outgoing") +ï¼ï¼ migration_channel_connect(s, ioc, NULL) +ï¼ï¼ ... ... +ï¼ï¼ We didn't call qio_channel_set_feature(QIO_CHANNEL(sioc), +QIO_CHANNEL_FEATURE_SHUTDOWN) above, +ï¼ï¼ and the +ï¼ï¼ migrate_fd_cancel() +ï¼ï¼ { +ï¼ï¼ ... ... +ï¼ï¼ if (s-ï¼state == MIGRATION_STATUS_CANCELLING && f) { +ï¼ï¼ qemu_file_shutdown(f) --ï¼ This will not take effect. No ? +ï¼ï¼ } +ï¼ï¼ } +ï¼ +ï¼ (cc'd in Daniel Berrange). +ï¼ I see that we call qio_channel_set_feature(ioc, QIO_CHANNEL_FEATURE_SHUTDOWN) +at the +ï¼ top of qio_channel_socket_new so I think that's safe isn't it? +ï¼ + +Hmm, you are right, this problem is only exist for the migration incoming fd, +thanks. + +ï¼ Dave +ï¼ +ï¼ï¼ Thanks, +ï¼ï¼ Hailiang +ï¼ï¼ +ï¼ï¼ On 2017/3/21 16:10, address@hidden wrote: +ï¼ï¼ï¼ Thank youã +ï¼ï¼ï¼ +ï¼ï¼ï¼ I have test areadyã +ï¼ï¼ï¼ +ï¼ï¼ï¼ When the Primary Node panic,the Secondary Node qemu hang at the same placeã +ï¼ï¼ï¼ +ï¼ï¼ï¼ Incorrding +http://wiki.qemu-project.org/Features/COLO +ï¼kill Primary Node +qemu will not produce the problem,but Primary Node panic canã +ï¼ï¼ï¼ +ï¼ï¼ï¼ I think due to the feature of channel does not support +QIO_CHANNEL_FEATURE_SHUTDOWN. +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ when failover,channel_shutdown could not shut down the channel. +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ so the colo_process_incoming_thread will hang at recvmsg. +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ I test a patch: +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ diff --git a/migration/socket.c b/migration/socket.c +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ index 13966f1..d65a0ea 100644 +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ --- a/migration/socket.c +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +++ b/migration/socket.c +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ @@ -147,8 +147,9 @@ static gboolean +socket_accept_incoming_migration(QIOChannel *ioc, +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ } +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ trace_migration_socket_incoming_accepted() +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ qio_channel_set_name(QIO_CHANNEL(sioc), "migration-socket-incoming") +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ + qio_channel_set_feature(QIO_CHANNEL(sioc), +QIO_CHANNEL_FEATURE_SHUTDOWN) +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ migration_channel_process_incoming(migrate_get_current(), +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ QIO_CHANNEL(sioc)) +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ object_unref(OBJECT(sioc)) +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ My test will not hang any more. +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ åå§é®ä»¶ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ åä»¶äººï¼ address@hidden +ï¼ï¼ï¼ æ¶ä»¶äººï¼ç广10165992 address@hidden +ï¼ï¼ï¼ æéäººï¼ address@hidden address@hidden +ï¼ï¼ï¼ æ¥ æ ï¼2017å¹´03æ21æ¥ 15:58 +ï¼ï¼ï¼ 主 é¢ ï¼Re: [Qemu-devel] çå¤: Re: [BUG]COLO failover hang +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ Hi,Wang. +ï¼ï¼ï¼ +ï¼ï¼ï¼ You can test this branch: +ï¼ï¼ï¼ +ï¼ï¼ï¼ +https://github.com/coloft/qemu/tree/colo-v5.1-developing-COLO-frame-v21-with-shared-disk +ï¼ï¼ï¼ +ï¼ï¼ï¼ and please follow wiki ensure your own configuration correctly. +ï¼ï¼ï¼ +ï¼ï¼ï¼ +http://wiki.qemu-project.org/Features/COLO +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ Thanks +ï¼ï¼ï¼ +ï¼ï¼ï¼ Zhang Chen +ï¼ï¼ï¼ +ï¼ï¼ï¼ +ï¼ï¼ï¼ On 03/21/2017 03:27 PM, address@hidden wrote: +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ hi. +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ I test the git qemu master have the same problem. +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ (gdb) bt +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #0 qio_channel_socket_readv (ioc=0x7f65911b4e50, iov=0x7f64ef3fd880, +ï¼ï¼ï¼ ï¼ niov=1, fds=0x0, nfds=0x0, errp=0x0) at io/channel-socket.c:461 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #1 0x00007f658e4aa0c2 in qio_channel_read +ï¼ï¼ï¼ ï¼ (address@hidden, address@hidden "", +ï¼ï¼ï¼ ï¼ address@hidden, address@hidden) at io/channel.c:114 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #2 0x00007f658e3ea990 in channel_get_buffer (opaque=ï¼optimized outï¼, +ï¼ï¼ï¼ ï¼ buf=0x7f65907cb838 "", pos=ï¼optimized outï¼, size=32768) at +ï¼ï¼ï¼ ï¼ migration/qemu-file-channel.c:78 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #3 0x00007f658e3e97fc in qemu_fill_buffer (f=0x7f65907cb800) at +ï¼ï¼ï¼ ï¼ migration/qemu-file.c:295 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #4 0x00007f658e3ea2e1 in qemu_peek_byte (address@hidden, +ï¼ï¼ï¼ ï¼ address@hidden) at migration/qemu-file.c:555 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #5 0x00007f658e3ea34b in qemu_get_byte (address@hidden) at +ï¼ï¼ï¼ ï¼ migration/qemu-file.c:568 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #6 0x00007f658e3ea552 in qemu_get_be32 (address@hidden) at +ï¼ï¼ï¼ ï¼ migration/qemu-file.c:648 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #7 0x00007f658e3e66e5 in colo_receive_message (f=0x7f65907cb800, +ï¼ï¼ï¼ ï¼ address@hidden) at migration/colo.c:244 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #8 0x00007f658e3e681e in colo_receive_check_message (f=ï¼optimized +ï¼ï¼ï¼ ï¼ outï¼, address@hidden, +ï¼ï¼ï¼ ï¼ address@hidden) +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ at migration/colo.c:264 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #9 0x00007f658e3e740e in colo_process_incoming_thread +ï¼ï¼ï¼ ï¼ (opaque=0x7f658eb30360 ï¼mis_current.31286ï¼) at migration/colo.c:577 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #10 0x00007f658be09df3 in start_thread () from /lib64/libpthread.so.0 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #11 0x00007f65881983ed in clone () from /lib64/libc.so.6 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ (gdb) p ioc-ï¼name +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ $2 = 0x7f658ff7d5c0 "migration-socket-incoming" +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ (gdb) p ioc-ï¼features Do not support QIO_CHANNEL_FEATURE_SHUTDOWN +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ $3 = 0 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ (gdb) bt +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #0 socket_accept_incoming_migration (ioc=0x7fdcceeafa90, +ï¼ï¼ï¼ ï¼ condition=G_IO_IN, opaque=0x7fdcceeafa90) at migration/socket.c:137 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #1 0x00007fdcc6966350 in g_main_dispatch (context=ï¼optimized outï¼) at +ï¼ï¼ï¼ ï¼ gmain.c:3054 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #2 g_main_context_dispatch (context=ï¼optimized outï¼, +ï¼ï¼ï¼ ï¼ address@hidden) at gmain.c:3630 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #3 0x00007fdccb8a6dcc in glib_pollfds_poll () at util/main-loop.c:213 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #4 os_host_main_loop_wait (timeout=ï¼optimized outï¼) at +ï¼ï¼ï¼ ï¼ util/main-loop.c:258 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #5 main_loop_wait (address@hidden) at +ï¼ï¼ï¼ ï¼ util/main-loop.c:506 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #6 0x00007fdccb526187 in main_loop () at vl.c:1898 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ #7 main (argc=ï¼optimized outï¼, argv=ï¼optimized outï¼, envp=ï¼optimized +ï¼ï¼ï¼ ï¼ outï¼) at vl.c:4709 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ (gdb) p ioc-ï¼features +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ $1 = 6 +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ (gdb) p ioc-ï¼name +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ $2 = 0x7fdcce1b1ab0 "migration-socket-listener" +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ May be socket_accept_incoming_migration should +ï¼ï¼ï¼ ï¼ call qio_channel_set_feature(ioc, QIO_CHANNEL_FEATURE_SHUTDOWN)?? +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ thank you. +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ åå§é®ä»¶ +ï¼ï¼ï¼ ï¼ address@hidden +ï¼ï¼ï¼ ï¼ address@hidden +ï¼ï¼ï¼ ï¼ address@hidden@huawei.comï¼ +ï¼ï¼ï¼ ï¼ *æ¥ æ ï¼*2017å¹´03æ16æ¥ 14:46 +ï¼ï¼ï¼ ï¼ *主 é¢ ï¼**Re: [Qemu-devel] COLO failover hang* +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ On 03/15/2017 05:06 PM, wangguang wrote: +ï¼ï¼ï¼ ï¼ ï¼ am testing QEMU COLO feature described here [QEMU +ï¼ï¼ï¼ ï¼ ï¼ Wiki]( +http://wiki.qemu-project.org/Features/COLO +). +ï¼ï¼ï¼ ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ When the Primary Node panic,the Secondary Node qemu hang. +ï¼ï¼ï¼ ï¼ ï¼ hang at recvmsg in qio_channel_socket_readv. +ï¼ï¼ï¼ ï¼ ï¼ And I run { 'execute': 'nbd-server-stop' } and { "execute": +ï¼ï¼ï¼ ï¼ ï¼ "x-colo-lost-heartbeat" } in Secondary VM's +ï¼ï¼ï¼ ï¼ ï¼ monitor,the Secondary Node qemu still hang at recvmsg . +ï¼ï¼ï¼ ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ I found that the colo in qemu is not complete yet. +ï¼ï¼ï¼ ï¼ ï¼ Do the colo have any plan for development? +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ Yes, We are developing. You can see some of patch we pushing. +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ Has anyone ever run it successfully? Any help is appreciated! +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ In our internal version can run it successfully, +ï¼ï¼ï¼ ï¼ The failover detail you can ask Zhanghailiang for help. +ï¼ï¼ï¼ ï¼ Next time if you have some question about COLO, +ï¼ï¼ï¼ ï¼ please cc me and zhanghailiang address@hidden +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ Thanks +ï¼ï¼ï¼ ï¼ Zhang Chen +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ centos7.2+qemu2.7.50 +ï¼ï¼ï¼ ï¼ ï¼ (gdb) bt +ï¼ï¼ï¼ ï¼ ï¼ #0 0x00007f3e00cc86ad in recvmsg () from /lib64/libpthread.so.0 +ï¼ï¼ï¼ ï¼ ï¼ #1 0x00007f3e0332b738 in qio_channel_socket_readv (ioc=ï¼optimized outï¼, +ï¼ï¼ï¼ ï¼ ï¼ iov=ï¼optimized outï¼, niov=ï¼optimized outï¼, fds=0x0, nfds=0x0, errp=0x0) +at +ï¼ï¼ï¼ ï¼ ï¼ io/channel-socket.c:497 +ï¼ï¼ï¼ ï¼ ï¼ #2 0x00007f3e03329472 in qio_channel_read (address@hidden, +ï¼ï¼ï¼ ï¼ ï¼ address@hidden "", address@hidden, +ï¼ï¼ï¼ ï¼ ï¼ address@hidden) at io/channel.c:97 +ï¼ï¼ï¼ ï¼ ï¼ #3 0x00007f3e032750e0 in channel_get_buffer (opaque=ï¼optimized outï¼, +ï¼ï¼ï¼ ï¼ ï¼ buf=0x7f3e05910f38 "", pos=ï¼optimized outï¼, size=32768) at +ï¼ï¼ï¼ ï¼ ï¼ migration/qemu-file-channel.c:78 +ï¼ï¼ï¼ ï¼ ï¼ #4 0x00007f3e0327412c in qemu_fill_buffer (f=0x7f3e05910f00) at +ï¼ï¼ï¼ ï¼ ï¼ migration/qemu-file.c:257 +ï¼ï¼ï¼ ï¼ ï¼ #5 0x00007f3e03274a41 in qemu_peek_byte (address@hidden, +ï¼ï¼ï¼ ï¼ ï¼ address@hidden) at migration/qemu-file.c:510 +ï¼ï¼ï¼ ï¼ ï¼ #6 0x00007f3e03274aab in qemu_get_byte (address@hidden) at +ï¼ï¼ï¼ ï¼ ï¼ migration/qemu-file.c:523 +ï¼ï¼ï¼ ï¼ ï¼ #7 0x00007f3e03274cb2 in qemu_get_be32 (address@hidden) at +ï¼ï¼ï¼ ï¼ ï¼ migration/qemu-file.c:603 +ï¼ï¼ï¼ ï¼ ï¼ #8 0x00007f3e03271735 in colo_receive_message (f=0x7f3e05910f00, +ï¼ï¼ï¼ ï¼ ï¼ address@hidden) at migration/colo.c:215 +ï¼ï¼ï¼ ï¼ ï¼ #9 0x00007f3e0327250d in colo_wait_handle_message (errp=0x7f3d62bfaa48, +ï¼ï¼ï¼ ï¼ ï¼ checkpoint_request=ï¼synthetic pointerï¼, f=ï¼optimized outï¼) at +ï¼ï¼ï¼ ï¼ ï¼ migration/colo.c:546 +ï¼ï¼ï¼ ï¼ ï¼ #10 colo_process_incoming_thread (opaque=0x7f3e067245e0) at +ï¼ï¼ï¼ ï¼ ï¼ migration/colo.c:649 +ï¼ï¼ï¼ ï¼ ï¼ #11 0x00007f3e00cc1df3 in start_thread () from /lib64/libpthread.so.0 +ï¼ï¼ï¼ ï¼ ï¼ #12 0x00007f3dfc9c03ed in clone () from /lib64/libc..so.6 +ï¼ï¼ï¼ ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ -- +ï¼ï¼ï¼ ï¼ ï¼ View this message in context: +http://qemu.11.n7.nabble.com/COLO-failover-hang-tp473250.html +ï¼ï¼ï¼ ï¼ ï¼ Sent from the Developer mailing list archive at Nabble.com. +ï¼ï¼ï¼ ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ +ï¼ï¼ï¼ ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ -- +ï¼ï¼ï¼ ï¼ Thanks +ï¼ï¼ï¼ ï¼ Zhang Chen +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ ï¼ +ï¼ï¼ï¼ +ï¼ï¼ +ï¼ -- +ï¼ Dr. David Alan Gilbert / address@hidden / Manchester, UK +ï¼ +ï¼ . +ï¼ + diff --git a/results/classifier/zero-shot/016/x86/92957605 b/results/classifier/zero-shot/016/x86/92957605 new file mode 100644 index 000000000..ca0e14db3 --- /dev/null +++ b/results/classifier/zero-shot/016/x86/92957605 @@ -0,0 +1,445 @@ +x86: 0.807 +debug: 0.518 +TCG: 0.317 +i386: 0.087 +files: 0.084 +PID: 0.043 +virtual: 0.037 +operating system: 0.036 +hypervisor: 0.031 +register: 0.026 +device: 0.024 +network: 0.021 +ppc: 0.021 +VMM: 0.017 +arm: 0.015 +socket: 0.013 +boot: 0.013 +alpha: 0.012 +semantic: 0.012 +risc-v: 0.011 +vnc: 0.007 +user-level: 0.006 +kernel: 0.006 +assembly: 0.006 +peripherals: 0.005 +performance: 0.004 +architecture: 0.004 +graphic: 0.003 +KVM: 0.002 +permissions: 0.001 +mistranslation: 0.001 + +[Qemu-devel] Fwd: [BUG] Failed to compile using gcc7.1 + +Hi all, +I encountered the same problem on gcc 7.1.1 and found Qu's mail in +this list from google search. + +Temporarily fix it by specifying the string length in snprintf +directive. Hope this is helpful to other people encountered the same +problem. + +@@ -1,9 +1,7 @@ +--- +--- a/block/blkdebug.c +- "blkdebug:%s:%s", s->config_file ?: "", +--- a/block/blkverify.c +- "blkverify:%s:%s", +--- a/hw/usb/bus.c +- snprintf(downstream->path, sizeof(downstream->path), "%s.%d", +- snprintf(downstream->path, sizeof(downstream->path), "%d", portnr); +-- ++++ b/block/blkdebug.c ++ "blkdebug:%.2037s:%.2037s", s->config_file ?: "", ++++ b/block/blkverify.c ++ "blkverify:%.2038s:%.2038s", ++++ b/hw/usb/bus.c ++ snprintf(downstream->path, sizeof(downstream->path), "%.12s.%d", ++ snprintf(downstream->path, sizeof(downstream->path), "%.12d", portnr); + +Tsung-en Hsiao + +> +Qu Wenruo Wrote: +> +> +Hi all, +> +> +After upgrading gcc from 6.3.1 to 7.1.1, qemu can't be compiled with gcc. +> +> +The error is: +> +> +------ +> +CC block/blkdebug.o +> +block/blkdebug.c: In function 'blkdebug_refresh_filename': +> +> +block/blkdebug.c:693:31: error: '%s' directive output may be truncated +> +writing up to 4095 bytes into a region of size 4086 +> +[-Werror=format-truncation=] +> +> +"blkdebug:%s:%s", s->config_file ?: "", +> +^~ +> +In file included from /usr/include/stdio.h:939:0, +> +from /home/adam/qemu/include/qemu/osdep.h:68, +> +from block/blkdebug.c:25: +> +> +/usr/include/bits/stdio2.h:64:10: note: '__builtin___snprintf_chk' output 11 +> +or more bytes (assuming 4106) into a destination of size 4096 +> +> +return __builtin___snprintf_chk (__s, __n, __USE_FORTIFY_LEVEL - 1, +> +^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +> +__bos (__s), __fmt, __va_arg_pack ()); +> +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +> +cc1: all warnings being treated as errors +> +make: *** [/home/adam/qemu/rules.mak:69: block/blkdebug.o] Error 1 +> +------ +> +> +It seems that gcc 7 is introducing more restrict check for printf. +> +> +If using clang, although there are some extra warning, it can at least pass +> +the compile. +> +> +Thanks, +> +Qu + +Hi Tsung-en, + +On 06/11/2017 04:08 PM, Tsung-en Hsiao wrote: +Hi all, +I encountered the same problem on gcc 7.1.1 and found Qu's mail in +this list from google search. + +Temporarily fix it by specifying the string length in snprintf +directive. Hope this is helpful to other people encountered the same +problem. +Thank your for sharing this. +@@ -1,9 +1,7 @@ +--- +--- a/block/blkdebug.c +- "blkdebug:%s:%s", s->config_file ?: "", +--- a/block/blkverify.c +- "blkverify:%s:%s", +--- a/hw/usb/bus.c +- snprintf(downstream->path, sizeof(downstream->path), "%s.%d", +- snprintf(downstream->path, sizeof(downstream->path), "%d", portnr); +-- ++++ b/block/blkdebug.c ++ "blkdebug:%.2037s:%.2037s", s->config_file ?: "", +It is a rather funny way to silent this warning :) Truncating the +filename until it fits. +However I don't think it is the correct way since there is indeed an +overflow of bs->exact_filename. +Apparently exact_filename from "block/block_int.h" is defined to hold a +pathname: +char exact_filename[PATH_MAX]; +but is used for more than that (for example in blkdebug.c it might use +until 10+2*PATH_MAX chars). +I suppose it started as a buffer to hold a pathname then more block +drivers were added and this buffer ended used differently. +If it is a multi-purpose buffer one safer option might be to declare it +as a GString* and use g_string_printf(). +I CC'ed the block folks to have their feedback. + +Regards, + +Phil. ++++ b/block/blkverify.c ++ "blkverify:%.2038s:%.2038s", ++++ b/hw/usb/bus.c ++ snprintf(downstream->path, sizeof(downstream->path), "%.12s.%d", ++ snprintf(downstream->path, sizeof(downstream->path), "%.12d", portnr); + +Tsung-en Hsiao +Qu Wenruo Wrote: + +Hi all, + +After upgrading gcc from 6.3.1 to 7.1.1, qemu can't be compiled with gcc. + +The error is: + +------ + CC block/blkdebug.o +block/blkdebug.c: In function 'blkdebug_refresh_filename': + +block/blkdebug.c:693:31: error: '%s' directive output may be truncated writing +up to 4095 bytes into a region of size 4086 [-Werror=format-truncation=] + + "blkdebug:%s:%s", s->config_file ?: "", + ^~ +In file included from /usr/include/stdio.h:939:0, + from /home/adam/qemu/include/qemu/osdep.h:68, + from block/blkdebug.c:25: + +/usr/include/bits/stdio2.h:64:10: note: '__builtin___snprintf_chk' output 11 or +more bytes (assuming 4106) into a destination of size 4096 + + return __builtin___snprintf_chk (__s, __n, __USE_FORTIFY_LEVEL - 1, + ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + __bos (__s), __fmt, __va_arg_pack ()); + ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +cc1: all warnings being treated as errors +make: *** [/home/adam/qemu/rules.mak:69: block/blkdebug.o] Error 1 +------ + +It seems that gcc 7 is introducing more restrict check for printf. + +If using clang, although there are some extra warning, it can at least pass the +compile. + +Thanks, +Qu + +On 2017-06-12 05:19, Philippe Mathieu-Daudé wrote: +> +Hi Tsung-en, +> +> +On 06/11/2017 04:08 PM, Tsung-en Hsiao wrote: +> +> Hi all, +> +> I encountered the same problem on gcc 7.1.1 and found Qu's mail in +> +> this list from google search. +> +> +> +> Temporarily fix it by specifying the string length in snprintf +> +> directive. Hope this is helpful to other people encountered the same +> +> problem. +> +> +Thank your for sharing this. +> +> +> +> +> @@ -1,9 +1,7 @@ +> +> --- +> +> --- a/block/blkdebug.c +> +> - "blkdebug:%s:%s", s->config_file ?: "", +> +> --- a/block/blkverify.c +> +> - "blkverify:%s:%s", +> +> --- a/hw/usb/bus.c +> +> - snprintf(downstream->path, sizeof(downstream->path), "%s.%d", +> +> - snprintf(downstream->path, sizeof(downstream->path), "%d", +> +> portnr); +> +> -- +> +> +++ b/block/blkdebug.c +> +> + "blkdebug:%.2037s:%.2037s", s->config_file ?: "", +> +> +It is a rather funny way to silent this warning :) Truncating the +> +filename until it fits. +> +> +However I don't think it is the correct way since there is indeed an +> +overflow of bs->exact_filename. +> +> +Apparently exact_filename from "block/block_int.h" is defined to hold a +> +pathname: +> +char exact_filename[PATH_MAX]; +> +> +but is used for more than that (for example in blkdebug.c it might use +> +until 10+2*PATH_MAX chars). +In any case, truncating the filenames will do just as much as truncating +the result: You'll get an unusable filename. + +> +I suppose it started as a buffer to hold a pathname then more block +> +drivers were added and this buffer ended used differently. +> +> +If it is a multi-purpose buffer one safer option might be to declare it +> +as a GString* and use g_string_printf(). +What it is supposed to be now is just an information string we can print +to the user, because strings are nicer than JSON objects. There are some +commands that take a filename for identifying a block node, but I dream +we can get rid of them in 3.0... + +The right solution is to remove it altogether and have a +"char *bdrv_filename(BlockDriverState *bs)" function (which generates +the filename every time it's called). I've been working on this for some +years now, actually, but it was never pressing enough to get it finished +(so I never had enough time). + +What we can do in the meantime is to not generate a plain filename if it +won't fit into bs->exact_filename. + +(The easiest way to do this probably would be to truncate +bs->exact_filename back to an empty string if snprintf() returns a value +greater than or equal to the length of bs->exact_filename.) + +What to do about hw/usb/bus.c I don't know (I guess the best solution +would be to ignore the warning, but I don't suppose that is going to work). + +Max + +> +> +I CC'ed the block folks to have their feedback. +> +> +Regards, +> +> +Phil. +> +> +> +++ b/block/blkverify.c +> +> + "blkverify:%.2038s:%.2038s", +> +> +++ b/hw/usb/bus.c +> +> + snprintf(downstream->path, sizeof(downstream->path), "%.12s.%d", +> +> + snprintf(downstream->path, sizeof(downstream->path), "%.12d", +> +> portnr); +> +> +> +> Tsung-en Hsiao +> +> +> +>> Qu Wenruo Wrote: +> +>> +> +>> Hi all, +> +>> +> +>> After upgrading gcc from 6.3.1 to 7.1.1, qemu can't be compiled with +> +>> gcc. +> +>> +> +>> The error is: +> +>> +> +>> ------ +> +>> CC block/blkdebug.o +> +>> block/blkdebug.c: In function 'blkdebug_refresh_filename': +> +>> +> +>> block/blkdebug.c:693:31: error: '%s' directive output may be +> +>> truncated writing up to 4095 bytes into a region of size 4086 +> +>> [-Werror=format-truncation=] +> +>> +> +>> "blkdebug:%s:%s", s->config_file ?: "", +> +>> ^~ +> +>> In file included from /usr/include/stdio.h:939:0, +> +>> from /home/adam/qemu/include/qemu/osdep.h:68, +> +>> from block/blkdebug.c:25: +> +>> +> +>> /usr/include/bits/stdio2.h:64:10: note: '__builtin___snprintf_chk' +> +>> output 11 or more bytes (assuming 4106) into a destination of size 4096 +> +>> +> +>> return __builtin___snprintf_chk (__s, __n, __USE_FORTIFY_LEVEL - 1, +> +>> ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +> +>> __bos (__s), __fmt, __va_arg_pack ()); +> +>> ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +> +>> cc1: all warnings being treated as errors +> +>> make: *** [/home/adam/qemu/rules.mak:69: block/blkdebug.o] Error 1 +> +>> ------ +> +>> +> +>> It seems that gcc 7 is introducing more restrict check for printf. +> +>> +> +>> If using clang, although there are some extra warning, it can at +> +>> least pass the compile. +> +>> +> +>> Thanks, +> +>> Qu +> +> +signature.asc +Description: +OpenPGP digital signature + diff --git a/results/classifier/zero-shot/016/x86/99674399 b/results/classifier/zero-shot/016/x86/99674399 new file mode 100644 index 000000000..ac24cb491 --- /dev/null +++ b/results/classifier/zero-shot/016/x86/99674399 @@ -0,0 +1,175 @@ +x86: 0.986 +i386: 0.928 +debug: 0.850 +kernel: 0.321 +operating system: 0.243 +KVM: 0.215 +files: 0.132 +TCG: 0.114 +hypervisor: 0.102 +performance: 0.099 +assembly: 0.080 +virtual: 0.062 +PID: 0.059 +register: 0.048 +semantic: 0.029 +risc-v: 0.017 +boot: 0.016 +user-level: 0.014 +socket: 0.011 +architecture: 0.010 +VMM: 0.010 +device: 0.010 +vnc: 0.007 +alpha: 0.004 +graphic: 0.003 +ppc: 0.002 +network: 0.002 +peripherals: 0.002 +permissions: 0.001 +arm: 0.001 +mistranslation: 0.000 + +[BUG] qemu crashes on assertion in cpu_asidx_from_attrs when cpu is in smm mode + +Hi all! + +First, I see this issue: +https://gitlab.com/qemu-project/qemu/-/issues/1198 +. +where some kvm/hardware failure leads to guest crash, and finally to this +assertion: + + cpu_asidx_from_attrs: Assertion `ret < cpu->num_ases && ret >= 0' failed. + +But in the ticket the talk is about the guest crash and fixing the kernel, not +about the final QEMU assertion (which definitely show that something should be +fixed in QEMU code too). + + +We've faced same stack one time: + +(gdb) bt +#0 raise () from /lib/x86_64-linux-gnu/libc.so.6 +#1 abort () from /lib/x86_64-linux-gnu/libc.so.6 +#2 ?? () from /lib/x86_64-linux-gnu/libc.so.6 +#3 __assert_fail () from /lib/x86_64-linux-gnu/libc.so.6 +#4 cpu_asidx_from_attrs at ../hw/core/cpu-sysemu.c:76 +#5 cpu_memory_rw_debug at ../softmmu/physmem.c:3529 +#6 x86_cpu_dump_state at ../target/i386/cpu-dump.c:560 +#7 kvm_cpu_exec at ../accel/kvm/kvm-all.c:3000 +#8 kvm_vcpu_thread_fn at ../accel/kvm/kvm-accel-ops.c:51 +#9 qemu_thread_start at ../util/qemu-thread-posix.c:505 +#10 start_thread () from /lib/x86_64-linux-gnu/libpthread.so.0 +#11 clone () from /lib/x86_64-linux-gnu/libc.so.6 + + +And what I see: + +static inline int x86_asidx_from_attrs(CPUState *cs, MemTxAttrs attrs) +{ + return !!attrs.secure; +} + +int cpu_asidx_from_attrs(CPUState *cpu, MemTxAttrs attrs) +{ + int ret = 0; + + if (cpu->cc->sysemu_ops->asidx_from_attrs) { + ret = cpu->cc->sysemu_ops->asidx_from_attrs(cpu, attrs); + assert(ret < cpu->num_ases && ret >= 0); <<<<<<<<<<<<<<<<< + } + return ret; +} + +(gdb) p cpu->num_ases +$3 = 1 + +(gdb) fr 5 +#5 0x00005578c8814ba3 in cpu_memory_rw_debug (cpu=c... +(gdb) p attrs +$6 = {unspecified = 0, secure = 1, user = 0, memory = 0, requester_id = 0, +byte_swap = 0, target_tlb_bit0 = 0, target_tlb_bit1 = 0, target_tlb_bit2 = 0} + +so .secure is 1, therefore ret is 1, in the same time num_ases is 1 too and +assertion fails. + + + +Where is .secure from? + +static inline MemTxAttrs cpu_get_mem_attrs(CPUX86State *env) +{ + return ((MemTxAttrs) { .secure = (env->hflags & HF_SMM_MASK) != 0 }); +} + +Ok, it means we in SMM mode. + + + +On the other hand, it seems that num_ases seems to be always 1 for x86: + +vsementsov@vsementsov-lin:~/work/src/qemu/yc-7.2$ git grep 'num_ases = ' +cpu.c: cpu->num_ases = 0; +softmmu/cpus.c: cpu->num_ases = 1; +target/arm/cpu.c: cs->num_ases = 3 + has_secure; +target/arm/cpu.c: cs->num_ases = 1 + has_secure; +target/i386/tcg/sysemu/tcg-cpu.c: cs->num_ases = 2; + + +So, something is wrong around cpu->num_ases and x86_asidx_from_attrs() which +may return more in SMM mode. + + +The stack starts in +//7 0x00005578c882f539 in kvm_cpu_exec (cpu=cpu@entry=0x5578ca2eb340) at +../accel/kvm/kvm-all.c:3000 + if (ret < 0) { + cpu_dump_state(cpu, stderr, CPU_DUMP_CODE); + vm_stop(RUN_STATE_INTERNAL_ERROR); + } + +So that was some kvm error, and we decided to call cpu_dump_state(). And it +crashes. cpu_dump_state() is also called from hmp_info_registers, so I can +reproduce the crash with a tiny patch to master (as only CPU_DUMP_CODE path +calls cpu_memory_rw_debug(), as it is in kvm_cpu_exec()): + +diff --git a/monitor/hmp-cmds-target.c b/monitor/hmp-cmds-target.c +index ff01cf9d8d..dcf0189048 100644 +--- a/monitor/hmp-cmds-target.c ++++ b/monitor/hmp-cmds-target.c +@@ -116,7 +116,7 @@ void hmp_info_registers(Monitor *mon, const QDict *qdict) + } + + monitor_printf(mon, "\nCPU#%d\n", cs->cpu_index); +- cpu_dump_state(cs, NULL, CPU_DUMP_FPU); ++ cpu_dump_state(cs, NULL, CPU_DUMP_CODE); + } + } + + +Than run + +yes "info registers" | ./build/qemu-system-x86_64 -accel kvm -monitor stdio \ + -global driver=cfi.pflash01,property=secure,value=on \ + -blockdev "{'driver': 'file', 'filename': +'/usr/share/OVMF/OVMF_CODE_4M.secboot.fd', 'node-name': 'ovmf-code', 'read-only': +true}" \ + -blockdev "{'driver': 'file', 'filename': '/usr/share/OVMF/OVMF_VARS_4M.fd', +'node-name': 'ovmf-vars', 'read-only': true}" \ + -machine q35,smm=on,pflash0=ovmf-code,pflash1=ovmf-vars -m 2G -nodefaults + +And after some time (less than 20 seconds for me) it leads to + +qemu-system-x86_64: ../hw/core/cpu-sysemu.c:76: cpu_asidx_from_attrs: Assertion `ret < +cpu->num_ases && ret >= 0' failed. +Aborted (core dumped) + + +I've no idea how to correctly fix this bug, but I hope that my reproducer and +investigation will help a bit. + +-- +Best regards, +Vladimir + |