migration/rdma.c | 1 + 1 file changed, 1 insertion(+)
backtrace:
'0x00007ffff5f44ec2 in __ibv_dereg_mr_1_1 (mr=0x7fff1007d390) at /home/lizhijian/rdma-core/libibverbs/verbs.c:478
478 void *addr = mr->addr;
(gdb) bt
#0 0x00007ffff5f44ec2 in __ibv_dereg_mr_1_1 (mr=0x7fff1007d390) at /home/lizhijian/rdma-core/libibverbs/verbs.c:478
#1 0x0000555555891fcc in rdma_delete_block (block=<optimized out>, rdma=0x7fff38176010) at ../migration/rdma.c:691
#2 qemu_rdma_cleanup (rdma=0x7fff38176010) at ../migration/rdma.c:2365
#3 0x00005555558925b0 in qio_channel_rdma_close_rcu (rcu=0x555556b8b6c0) at ../migration/rdma.c:3073
#4 0x0000555555d652a3 in call_rcu_thread (opaque=opaque@entry=0x0) at ../util/rcu.c:281
#5 0x0000555555d5edf9 in qemu_thread_start (args=0x7fffe88bb4d0) at ../util/qemu-thread-posix.c:541
#6 0x00007ffff54c73f9 in start_thread () at /lib64/libpthread.so.0
#7 0x00007ffff53f3b03 in clone () at /lib64/libc.so.6 '
Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
---
migration/rdma.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/migration/rdma.c b/migration/rdma.c
index b6cc4bef4a8..0f22b8227c0 100644
--- a/migration/rdma.c
+++ b/migration/rdma.c
@@ -1143,6 +1143,7 @@ static int qemu_rdma_reg_whole_ram_blocks(RDMAContext *rdma)
for (i--; i >= 0; i--) {
ibv_dereg_mr(local->block[i].mr);
+ local->block[i].mr = NULL;
rdma->total_registrations--;
}
--
2.30.2
* Li Zhijian (lizhijian@cn.fujitsu.com) wrote: > backtrace: > '0x00007ffff5f44ec2 in __ibv_dereg_mr_1_1 (mr=0x7fff1007d390) at /home/lizhijian/rdma-core/libibverbs/verbs.c:478 > 478 void *addr = mr->addr; > (gdb) bt > #0 0x00007ffff5f44ec2 in __ibv_dereg_mr_1_1 (mr=0x7fff1007d390) at /home/lizhijian/rdma-core/libibverbs/verbs.c:478 > #1 0x0000555555891fcc in rdma_delete_block (block=<optimized out>, rdma=0x7fff38176010) at ../migration/rdma.c:691 > #2 qemu_rdma_cleanup (rdma=0x7fff38176010) at ../migration/rdma.c:2365 > #3 0x00005555558925b0 in qio_channel_rdma_close_rcu (rcu=0x555556b8b6c0) at ../migration/rdma.c:3073 > #4 0x0000555555d652a3 in call_rcu_thread (opaque=opaque@entry=0x0) at ../util/rcu.c:281 > #5 0x0000555555d5edf9 in qemu_thread_start (args=0x7fffe88bb4d0) at ../util/qemu-thread-posix.c:541 > #6 0x00007ffff54c73f9 in start_thread () at /lib64/libpthread.so.0 > #7 0x00007ffff53f3b03 in clone () at /lib64/libc.so.6 ' > > Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com> Queued > --- > migration/rdma.c | 1 + > 1 file changed, 1 insertion(+) > > diff --git a/migration/rdma.c b/migration/rdma.c > index b6cc4bef4a8..0f22b8227c0 100644 > --- a/migration/rdma.c > +++ b/migration/rdma.c > @@ -1143,6 +1143,7 @@ static int qemu_rdma_reg_whole_ram_blocks(RDMAContext *rdma) > > for (i--; i >= 0; i--) { > ibv_dereg_mr(local->block[i].mr); > + local->block[i].mr = NULL; > rdma->total_registrations--; > } > > -- > 2.30.2 > > > > -- Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK
* Li Zhijian (lizhijian@cn.fujitsu.com) wrote: > backtrace: > '0x00007ffff5f44ec2 in __ibv_dereg_mr_1_1 (mr=0x7fff1007d390) at /home/lizhijian/rdma-core/libibverbs/verbs.c:478 > 478 void *addr = mr->addr; ANy idea why it deletes the same mr twice? What was your commandline? Dave > (gdb) bt > #0 0x00007ffff5f44ec2 in __ibv_dereg_mr_1_1 (mr=0x7fff1007d390) at /home/lizhijian/rdma-core/libibverbs/verbs.c:478 > #1 0x0000555555891fcc in rdma_delete_block (block=<optimized out>, rdma=0x7fff38176010) at ../migration/rdma.c:691 > #2 qemu_rdma_cleanup (rdma=0x7fff38176010) at ../migration/rdma.c:2365 > #3 0x00005555558925b0 in qio_channel_rdma_close_rcu (rcu=0x555556b8b6c0) at ../migration/rdma.c:3073 > #4 0x0000555555d652a3 in call_rcu_thread (opaque=opaque@entry=0x0) at ../util/rcu.c:281 > #5 0x0000555555d5edf9 in qemu_thread_start (args=0x7fffe88bb4d0) at ../util/qemu-thread-posix.c:541 > #6 0x00007ffff54c73f9 in start_thread () at /lib64/libpthread.so.0 > #7 0x00007ffff53f3b03 in clone () at /lib64/libc.so.6 ' > > Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com> > --- > migration/rdma.c | 1 + > 1 file changed, 1 insertion(+) > > diff --git a/migration/rdma.c b/migration/rdma.c > index b6cc4bef4a8..0f22b8227c0 100644 > --- a/migration/rdma.c > +++ b/migration/rdma.c > @@ -1143,6 +1143,7 @@ static int qemu_rdma_reg_whole_ram_blocks(RDMAContext *rdma) > > for (i--; i >= 0; i--) { > ibv_dereg_mr(local->block[i].mr); > + local->block[i].mr = NULL; > rdma->total_registrations--; > } > > -- > 2.30.2 > > > -- Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK
On 09/07/2021 03:11, Dr. David Alan Gilbert wrote: > * Li Zhijian (lizhijian@cn.fujitsu.com) wrote: >> backtrace: >> '0x00007ffff5f44ec2 in __ibv_dereg_mr_1_1 (mr=0x7fff1007d390) at /home/lizhijian/rdma-core/libibverbs/verbs.c:478 >> 478 void *addr = mr->addr; > ANy idea why it deletes the same mr twice? It's easy to reproduce it if we specify a nvdimm backing to a fsdax memory-backend-file which cannot support registering mr like: [root@iaas-rpma ~]# mount | grep pmem0 /dev/pmem0 on /mnt/pmem0 type ext4 (rw,relatime,seclabel,dax=always) [root@iaas-rpma ~]# ndctl list -n namespace0.0 [ { "dev":"namespace0.0", "mode":"fsdax", "map":"mem", "size":536870912, "sector_size":512, "blockdev":"pmem0" } ] `-object memory-backend-file,id=mem1,share=on,mem-path=/mnt/pmem0/nv-128m.img,size=128m,pmem=on,align=2m -device nvdimm,memdev=mem1,id=nv1` and then enable rdma-pin-all. (qemu) migrate_set_capability rdma-pin-all on (qemu) Now qemu has at least 2 ram block, pc.ram and mem1. the latter will be failed to register mr: `Failed to register local dest ram block! : Invalid argument ` in this case, the mr of pc.ram will be deleted twice. Thanks Li > > Dave > >> (gdb) bt >> #0 0x00007ffff5f44ec2 in __ibv_dereg_mr_1_1 (mr=0x7fff1007d390) at /home/lizhijian/rdma-core/libibverbs/verbs.c:478 >> #1 0x0000555555891fcc in rdma_delete_block (block=<optimized out>, rdma=0x7fff38176010) at ../migration/rdma.c:691 >> #2 qemu_rdma_cleanup (rdma=0x7fff38176010) at ../migration/rdma.c:2365 >> #3 0x00005555558925b0 in qio_channel_rdma_close_rcu (rcu=0x555556b8b6c0) at ../migration/rdma.c:3073 >> #4 0x0000555555d652a3 in call_rcu_thread (opaque=opaque@entry=0x0) at ../util/rcu.c:281 >> #5 0x0000555555d5edf9 in qemu_thread_start (args=0x7fffe88bb4d0) at ../util/qemu-thread-posix.c:541 >> #6 0x00007ffff54c73f9 in start_thread () at /lib64/libpthread.so.0 >> #7 0x00007ffff53f3b03 in clone () at /lib64/libc.so.6 ' >> >> Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com> >> --- >> migration/rdma.c | 1 + >> 1 file changed, 1 insertion(+) >> >> diff --git a/migration/rdma.c b/migration/rdma.c >> index b6cc4bef4a8..0f22b8227c0 100644 >> --- a/migration/rdma.c >> +++ b/migration/rdma.c >> @@ -1143,6 +1143,7 @@ static int qemu_rdma_reg_whole_ram_blocks(RDMAContext *rdma) >> >> for (i--; i >= 0; i--) { >> ibv_dereg_mr(local->block[i].mr); >> + local->block[i].mr = NULL; >> rdma->total_registrations--; >> } >> >> -- >> 2.30.2 >> >> >>
* lizhijian@fujitsu.com (lizhijian@fujitsu.com) wrote: > > > On 09/07/2021 03:11, Dr. David Alan Gilbert wrote: > > * Li Zhijian (lizhijian@cn.fujitsu.com) wrote: > >> backtrace: > >> '0x00007ffff5f44ec2 in __ibv_dereg_mr_1_1 (mr=0x7fff1007d390) at /home/lizhijian/rdma-core/libibverbs/verbs.c:478 > >> 478 void *addr = mr->addr; > > ANy idea why it deletes the same mr twice? > > It's easy to reproduce it if we specify a nvdimm backing to a fsdax memory-backend-file which cannot support registering mr like: > > [root@iaas-rpma ~]# mount | grep pmem0 > /dev/pmem0 on /mnt/pmem0 type ext4 (rw,relatime,seclabel,dax=always) > > [root@iaas-rpma ~]# ndctl list -n namespace0.0 > [ > { > "dev":"namespace0.0", > "mode":"fsdax", > "map":"mem", > "size":536870912, > "sector_size":512, > "blockdev":"pmem0" > } > ] > > > `-object memory-backend-file,id=mem1,share=on,mem-path=/mnt/pmem0/nv-128m.img,size=128m,pmem=on,align=2m -device nvdimm,memdev=mem1,id=nv1` > > and then enable rdma-pin-all. > > (qemu) migrate_set_capability rdma-pin-all on > (qemu) > > Now qemu has at least 2 ram block, pc.ram and mem1. the latter will be failed to register mr: > `Failed to register local dest ram block! : Invalid argument ` > > in this case, the mr of pc.ram will be deleted twice. Ah OK, that makes more sense - from your original description I hadn't noticed it was the failure path. Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com> > Thanks > Li > > > > Dave > > > >> (gdb) bt > >> #0 0x00007ffff5f44ec2 in __ibv_dereg_mr_1_1 (mr=0x7fff1007d390) at /home/lizhijian/rdma-core/libibverbs/verbs.c:478 > >> #1 0x0000555555891fcc in rdma_delete_block (block=<optimized out>, rdma=0x7fff38176010) at ../migration/rdma.c:691 > >> #2 qemu_rdma_cleanup (rdma=0x7fff38176010) at ../migration/rdma.c:2365 > >> #3 0x00005555558925b0 in qio_channel_rdma_close_rcu (rcu=0x555556b8b6c0) at ../migration/rdma.c:3073 > >> #4 0x0000555555d652a3 in call_rcu_thread (opaque=opaque@entry=0x0) at ../util/rcu.c:281 > >> #5 0x0000555555d5edf9 in qemu_thread_start (args=0x7fffe88bb4d0) at ../util/qemu-thread-posix.c:541 > >> #6 0x00007ffff54c73f9 in start_thread () at /lib64/libpthread.so.0 > >> #7 0x00007ffff53f3b03 in clone () at /lib64/libc.so.6 ' > >> > >> Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com> > >> --- > >> migration/rdma.c | 1 + > >> 1 file changed, 1 insertion(+) > >> > >> diff --git a/migration/rdma.c b/migration/rdma.c > >> index b6cc4bef4a8..0f22b8227c0 100644 > >> --- a/migration/rdma.c > >> +++ b/migration/rdma.c > >> @@ -1143,6 +1143,7 @@ static int qemu_rdma_reg_whole_ram_blocks(RDMAContext *rdma) > >> > >> for (i--; i >= 0; i--) { > >> ibv_dereg_mr(local->block[i].mr); > >> + local->block[i].mr = NULL; > >> rdma->total_registrations--; > >> } > >> > >> -- > >> 2.30.2 > >> > >> > >> -- Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK
© 2016 - 2024 Red Hat, Inc.