| Message ID | 1bf88958-e3d1-d456-96f0-464cfcdb6212@cn.fujitsu.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
Thanks zhijian. On Fri, Mar 23, 2018 at 4:34 PM, Li Zhijian <lizhijian@cn.fujitsu.com> wrote: > Just noticed that's a little old, you may need to rebase it > > > Thanks > > > On 03/23/2018 11:51 AM, Li Zhijian wrote: > >> >> >> On 03/21/2018 02:04 PM, Zhang Chen wrote: >> >>> Hi Suiheng, >>> >>> I made a new guest image and retest it, and got the same bug from latest >>> branch. >>> I found that after the COLO checkpoint begin, the secondary guest always >>> send >>> reset request to Qemu like someone still push the reset button in the >>> guest. >>> And this bug occurred in COLO frame related codes. This part of codes >>> wrote >>> by Li zhijian and Zhang hailiang and currently maintained by Zhang >>> hailiang. >>> So, I add them to this thread. >>> >>> CC Zhijian and Hailiang: >>> Any idea or comments about this bug? >>> >> >> One clue is the memory of SVM not is same with PVM. >> we can try to compare the memory after checkpoint, i had a draft patch to >> do this before. >> >> >> Thanks >> >> >> >> >> >>> If you want to test COLO currently, you can try the old version of COLO: >>> https://github.com/zhangckid/qemu/tree/qemu-colo-18mar10-legacy >>> >>> >>> Thanks >>> Zhang Chen >>> >>> On Mon, Mar 19, 2018 at 10:08 AM, 李穗恒 <1754542@bugs.launchpad.net >>> <mailto:1754542@bugs.launchpad.net>> wrote: >>> >>> Hi Zhang Chen， >>> I follow the https://wiki.qemu.org/Features/COLO < >>> https://wiki.qemu.org/Features/COLO>, And Vm no crash. >>> >>> But SVM rebooting constantly after print RESET, PVM normal startup. >>> >>> Secondary: >>> {"timestamp": {"seconds": 1521421788, "microseconds": 541058}, >>> "event": "RESUME"} >>> {"timestamp": {"seconds": 1521421808, "microseconds": 493484}, >>> "event": "STOP"} >>> {"timestamp": {"seconds": 1521421808, "microseconds": 686466}, >>> "event": "RESUME"} >>> {"timestamp": {"seconds": 1521421808, "microseconds": 696152}, >>> "event": "RESET", "data": {"guest": true}} >>> {"timestamp": {"seconds": 1521421808, "microseconds": 740653}, >>> "event": "RESET", "data": {"guest": true}} >>> {"timestamp": {"seconds": 1521421818, "microseconds": 742222}, >>> "event": "STOP"} >>> {"timestamp": {"seconds": 1521421818, "microseconds": 969883}, >>> "event": "RESUME"} >>> {"timestamp": {"seconds": 1521421818, "microseconds": 979986}, >>> "event": "RESET", "data": {"guest": true}} >>> {"timestamp": {"seconds": 1521421819, "microseconds": 22652}, >>> "event": "RESET", "data": {"guest": true}} >>> >>> >>> The command(I run two VM in sample machine): >>> >>> Primary: >>> sudo /home/lee/Documents/qemu/x86_64-softmmu/qemu-system-x86_64 >>> -enable-kvm -boot c -m 2048 -smp 2 -qmp stdio -name primary -cpu >>> qemu64,+kvmclock -device piix3-usb-uhci -device usb-tablet \ >>> -netdev tap,id=hn0,vhost=off,script=/e >>> tc/qemu-ifup,downscript=/etc/qemu-ifdown -device >>> rtl8139,id=e0,netdev=hn0 \ >>> -chardev socket,id=mirror0,host=192.168.0.33,port=9003,server,nowait >>> \ >>> -chardev socket,id=compare1,host=192.168.0.33,port=9004,server,wait >>> \ >>> -chardev socket,id=compare0,host=192.168.0.33,port=9001,server,nowait >>> \ >>> -chardev socket,id=compare0-0,host=192.168.0.33,port=9001 \ >>> -chardev socket,id=compare_out,host=192 >>> .168.0.33,port=9005,server,nowait \ >>> -chardev socket,id=compare_out0,host=192.168.0.33,port=9005 \ >>> -object filter-mirror,id=m0,netdev=hn0,queue=tx,outdev=mirror0 \ >>> -object filter-redirector,netdev=hn0,i >>> d=redire0,queue=rx,indev=compare_out \ >>> -object filter-redirector,netdev=hn0,i >>> d=redire1,queue=rx,outdev=compare0 \ >>> -object iothread,id=iothread1 \ >>> -object colo-compare,id=comp0,primary_ >>> in=compare0-0,secondary_in=compare1,outdev=compare_out0,iothread=iothread1 >>> \ >>> -drive if=ide,id=colo-disk0,driver=qu >>> orum,read-pattern=fifo,vote-threshold=1,children.0.file.file >>> name=/var/lib/libvirt/images/1.raw,children.0.driver=raw -S >>> >>> Secondary: >>> sudo /home/lee/Documents/qemu/x86_64-softmmu/qemu-system-x86_64 >>> -boot c -m 2048 -smp 2 -qmp stdio -name secondary -enable-kvm -cpu >>> qemu64,+kvmclock \ >>> -device piix3-usb-uhci -device usb-tablet \ >>> -netdev tap,id=hn0,vhost=off,script=/e >>> tc/qemu-ifup,downscript=/etc/qemu-ifdown \ >>> -device rtl8139,netdev=hn0 \ >>> -chardev socket,id=red0,host=192.168.0.33,port=9003,reconnect=1 >>> \ >>> -chardev socket,id=red1,host=192.168.0.33,port=9004,reconnect=1 >>> \ >>> -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 \ >>> -drive if=none,id=colo-disk0,file.fil >>> ename=/var/lib/libvirt/images/2.raw,driver=raw,node-name=node0 \ >>> -drive if=ide,id=active-disk0,driver= >>> replication,mode=secondary,file.driver=qcow2,top-id=active- >>> disk0,file.file.filename=/mnt/ramfs/active_disk.img,file. >>> backing.driver=qcow2,file.backing.file.filename=/mnt/ >>> ramfs/hidden_disk.img,file.backing.backing=colo-disk0 \ >>> -incoming tcp:0:8888 >>> >>> Secondary: >>> {'execute':'qmp_capabilities'} >>> { 'execute': 'nbd-server-start', >>> 'arguments': {'addr': {'type': 'inet', 'data': {'host': >>> '192.168.0.33', 'port': '8889'} } } >>> } >>> {'execute': 'nbd-server-add', 'arguments': {'device': >>> 'colo-disk0', 'writable': true } } >>> {'execute': 'trace-event-set-state', 'arguments': {'name': >>> 'colo*', 'enable': true} } >>> >>> >>> Primary: >>> {'execute':'qmp_capabilities'} >>> { 'execute': 'human-monitor-command', >>> 'arguments': {'command-line': 'drive_add -n buddy >>> driver=replication,mode=primary,file.driver=nbd,file.host= >>> 192.168.0.33,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: >>> 192.168.0.33:8888 <http://192.168.0.33:8888>' } } >>> >>> Thanks >>> Suiheng >>> >>> -- >>> You received this bug notification because you are subscribed to the >>> bug >>> report. >>> https://bugs.launchpad.net/bugs/1754542 < >>> https://bugs.launchpad.net/bugs/1754542> >>> >>> Title: >>> colo: vm crash with segmentation fault >>> >>> Status in QEMU: >>> New >>> >>> Bug description: >>> I use Arch Linux x86_64 >>> Zhang Chen's(https://github.com/zhangckid/qemu/tree/qemu-colo-18ma >>> r10 <https://github.com/zhangckid/qemu/tree/qemu-colo-18mar10>) >>> >>> Following document 'COLO-FT.txt', >>> I test colo feature on my hosts >>> >>> I run this command >>> Primary: >>> sudo /usr/local/bin/qemu-system-x86_64 -enable-kvm -m 2048 -smp 2 >>> -qmp stdio -name primary \ >>> -device piix3-usb-uhci \ >>> -device usb-tablet -netdev tap,id=hn0,vhost=off \ >>> -device virtio-net-pci,id=net-pci0,netdev=hn0 \ >>> -drive if=virtio,id=primary-disk0,driver=quorum,read-pattern=fifo, >>> vote-threshold=1,\ >>> children.0.file.filename=/var/lib/libvirt/images/1.raw,\ >>> children.0.driver=raw -S >>> >>> Secondary: >>> sudo /usr/local/bin/qemu-system-x86_64 -enable-kvm -m 2048 -smp 2 >>> -qmp stdio -name secondary \ >>> -device piix3-usb-uhci \ >>> -device usb-tablet -netdev tap,id=hn0,vhost=off \ >>> -device virtio-net-pci,id=net-pci0,netdev=hn0 \ >>> -drive if=none,id=secondary-disk0,file.filename=/var/lib/libvirt/ >>> images/2.raw,driver=raw,node-name=node0 \ >>> -drive if=virtio,id=active-disk0,driv >>> er=replication,mode=secondary,\ >>> file.driver=qcow2,top-id=active-disk0,\ >>> file.file.filename=/mnt/ramfs/active_disk.img,\ >>> file.backing.driver=qcow2,\ >>> file.backing.file.filename=/mnt/ramfs/hidden_disk.img,\ >>> file.backing.backing=secondary-disk0 \ >>> -incoming tcp:0:8888 >>> >>> Secondary: >>> {'execute':'qmp_capabilities'} >>> { 'execute': 'nbd-server-start', >>> 'arguments': {'addr': {'type': 'inet', 'data': {'host': >>> '192.168.0.34', 'port': '8889'} } } >>> } >>> {'execute': 'nbd-server-add', 'arguments': {'device': >>> 'secondary-disk0', 'writable': true } } >>> >>> Primary: >>> {'execute':'qmp_capabilities'} >>> { 'execute': 'human-monitor-command', >>> 'arguments': {'command-line': 'drive_add -n buddy >>> driver=replication,mode=primary,file.driver=nbd,file.host= >>> 192.168.0.34,file.port=8889,file.export=secondary-disk0, >>> node-name=nbd_client0'}} >>> { 'execute':'x-blockdev-change', 'arguments':{'parent': >>> 'primary-disk0', 'node': 'nbd_client0' } } >>> { 'execute': 'migrate-set-capabilities', >>> 'arguments': {'capabilities': [ {'capability': 'x-colo', >>> 'state': true } ] } } >>> { 'execute': 'migrate', 'arguments': {'uri': 'tcp: >>> 192.168.0.34:8888 <http://192.168.0.34:8888>' } } >>> And two VM with cash >>> Primary: >>> {"timestamp": {"seconds": 1520763655, "microseconds": 511415}, >>> "event": "RESUME"} >>> [1] 329 segmentation fault sudo /usr/local/bin/qemu-system-x86_64 >>> -boot c -enable-kvm -m 2048 -smp 2 -qm >>> >>> Secondary: >>> {"timestamp": {"seconds": 1520763655, "microseconds": 510907}, >>> "event": "RESUME"} >>> [1] 367 segmentation fault sudo /usr/local/bin/qemu-system-x86_64 >>> -boot c -enable-kvm -m 2048 -smp 2 -qm >>> >>> To manage notifications about this bug go to: >>> https://bugs.launchpad.net/qemu/+bug/1754542/+subscriptions < >>> https://bugs.launchpad.net/qemu/+bug/1754542/+subscriptions> >>> >>> >>> >> > -- > Best regards. > Li Zhijian (8528) > > > >
>From ecb789cf7f383b112da3cce33eb9822a94b9497a Mon Sep 17 00:00:00 2001 From: Li Zhijian <lizhijian@cn.fujitsu.com> Date: Tue, 24 Mar 2015 21:53:26 -0400 Subject: [PATCH] check pc.ram block md5sum between migration Source and Destination Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com> --- savevm.c | 42 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) mode change 100644 => 100755 savevm.c diff --git a/savevm.c b/savevm.c old mode 100644 new mode 100755 index 3b0e222..3d431dc --- a/savevm.c +++ b/savevm.c @@ -51,6 +51,26 @@ #define ARP_PTYPE_IP 0x0800 #define ARP_OP_REQUEST_REV 0x3 +#include "qemu/rcu_queue.h" +#include <openssl/md5.h> + +static void check_host_md5(void) +{ + int i; + unsigned char md[MD5_DIGEST_LENGTH]; + MD5_CTX ctx; + RAMBlock *block = QLIST_FIRST_RCU(&ram_list.blocks);/* Only check 'pc.ram' block */ + + MD5_Init(&ctx); + MD5_Update(&ctx, (void *)block->host, block->used_length); + MD5_Final(md, &ctx); + printf("md_host : "); + for(i = 0; i < MD5_DIGEST_LENGTH; i++) { + fprintf(stderr, "%02x", md[i]); + } + fprintf(stderr, "\n"); +} + static int announce_self_create(uint8_t *buf, uint8_t *mac_addr) { @@ -741,7 +761,13 @@ void qemu_savevm_state_complete(QEMUFile *f) qemu_put_byte(f, QEMU_VM_SECTION_END); qemu_put_be32(f, se->section_id); + printf("before saving %s complete\n", se->idstr); + check_host_md5(); + ret = se->ops->save_live_complete(f, se->opaque); + printf("after saving %s complete\n", se->idstr); + check_host_md5(); + trace_savevm_section_end(se->idstr, se->section_id, ret); if (ret < 0) { qemu_file_set_error(f, ret); @@ -1007,6 +1033,13 @@ int qemu_loadvm_state(QEMUFile *f) QLIST_INSERT_HEAD(&loadvm_handlers, le, entry); ret = vmstate_load(f, le->se, le->version_id); +#if 0 + if (section_type == QEMU_VM_SECTION_FULL) { + printf("QEMU_VM_SECTION_FULL, after loading %s\n", le->se->idstr); + check_host_md5(); + } +#endif + if (ret < 0) { error_report("error while loading state for instance 0x%x of" " device '%s'", instance_id, idstr); @@ -1030,6 +1063,11 @@ int qemu_loadvm_state(QEMUFile *f) } ret = vmstate_load(f, le->se, le->version_id); + if (section_type == QEMU_VM_SECTION_END) { + printf("QEMU_VM_SECTION_END, after loading %s\n", le->se->idstr); + check_host_md5(); + } + if (ret < 0) { error_report("error while loading state section id %d(%s)", section_id, le->se->idstr); @@ -1061,7 +1099,11 @@ int qemu_loadvm_state(QEMUFile *f) g_free(buf); } + printf("after loading all vmstate\n"); + check_host_md5(); cpu_synchronize_all_post_init(); + printf("after cpu_synchronize_all_post_init\n"); + check_host_md5(); ret = 0; -- 1.7.12.4