aboutsummaryrefslogtreecommitdiff
path: root/migration
diff options
context:
space:
mode:
authorLidong Chen <jemmy858585@gmail.com>2018-05-30 17:43:31 +0800
committerJuan Quintela <quintela@redhat.com>2018-06-04 05:46:15 +0200
commitc5e76115ccb4979cec795a8ae38becd07c2fde9f (patch)
tree1ef10f398c10b6cfb09d3e947a5e136f27f88e62 /migration
parentf38f6d4155c0c5a3e96d81183362a40e2cc09b4c (diff)
downloadqemu-c5e76115ccb4979cec795a8ae38becd07c2fde9f.zip
qemu-c5e76115ccb4979cec795a8ae38becd07c2fde9f.tar.gz
qemu-c5e76115ccb4979cec795a8ae38becd07c2fde9f.tar.bz2
migration: not wait RDMA_CM_EVENT_DISCONNECTED event after rdma_disconnect
When cancel migration during RDMA precopy, the source qemu main thread hangs sometime. The backtrace is: (gdb) bt #0 0x00007f249eabd43d in write () from /lib64/libpthread.so.0 #1 0x00007f24a1ce98e4 in rdma_get_cm_event (channel=0x4675d10, event=0x7ffe2f643dd0) at src/cma.c:2189 #2 0x00000000007b6166 in qemu_rdma_cleanup (rdma=0x6784000) at migration/rdma.c:2296 #3 0x00000000007b7cae in qio_channel_rdma_close (ioc=0x3bfcc30, errp=0x0) at migration/rdma.c:2999 #4 0x00000000008db60e in qio_channel_close (ioc=0x3bfcc30, errp=0x0) at io/channel.c:273 #5 0x00000000007a8765 in channel_close (opaque=0x3bfcc30) at migration/qemu-file-channel.c:98 #6 0x00000000007a71f9 in qemu_fclose (f=0x527c000) at migration/qemu-file.c:334 #7 0x0000000000795b96 in migrate_fd_cleanup (opaque=0x3b46280) at migration/migration.c:1162 #8 0x000000000093a71b in aio_bh_call (bh=0x3db7a20) at util/async.c:90 #9 0x000000000093a7b2 in aio_bh_poll (ctx=0x3b121c0) at util/async.c:118 #10 0x000000000093f2ad in aio_dispatch (ctx=0x3b121c0) at util/aio-posix.c:436 #11 0x000000000093ab41 in aio_ctx_dispatch (source=0x3b121c0, callback=0x0, user_data=0x0) at util/async.c:261 #12 0x00007f249f73c7aa in g_main_context_dispatch () from /lib64/libglib-2.0.so.0 #13 0x000000000093dc5e in glib_pollfds_poll () at util/main-loop.c:215 #14 0x000000000093dd4e in os_host_main_loop_wait (timeout=28000000) at util/main-loop.c:263 #15 0x000000000093de05 in main_loop_wait (nonblocking=0) at util/main-loop.c:522 #16 0x00000000005bc6a5 in main_loop () at vl.c:1944 #17 0x00000000005c39b5 in main (argc=56, argv=0x7ffe2f6443f8, envp=0x3ad0030) at vl.c:4752 It does not get the RDMA_CM_EVENT_DISCONNECTED event after rdma_disconnect sometime. According to IB Spec once active side send DREQ message, it should wait for DREP message and only once it arrived it should trigger a DISCONNECT event. DREP message can be dropped due to network issues. For that case the spec defines a DREP_timeout state in the CM state machine, if the DREP is dropped we should get a timeout and a TIMEWAIT_EXIT event will be trigger. Unfortunately the current kernel CM implementation doesn't include the DREP_timeout state and in above scenario we will not get DISCONNECT or TIMEWAIT_EXIT events. So it should not invoke rdma_get_cm_event which may hang forever, and the event channel is also destroyed in qemu_rdma_cleanup. Signed-off-by: Lidong Chen <lidongchen@tencent.com> Reviewed-by: Juan Quintela <quintela@redhat.com> Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Signed-off-by: Juan Quintela <quintela@redhat.com>
Diffstat (limited to 'migration')
-rw-r--r--migration/rdma.c12
-rw-r--r--migration/trace-events1
2 files changed, 2 insertions, 11 deletions
diff --git a/migration/rdma.c b/migration/rdma.c
index 6077922..05aee3d 100644
--- a/migration/rdma.c
+++ b/migration/rdma.c
@@ -2267,8 +2267,7 @@ static int qemu_rdma_write(QEMUFile *f, RDMAContext *rdma,
static void qemu_rdma_cleanup(RDMAContext *rdma)
{
- struct rdma_cm_event *cm_event;
- int ret, idx;
+ int idx;
if (rdma->cm_id && rdma->connected) {
if ((rdma->error_state ||
@@ -2282,14 +2281,7 @@ static void qemu_rdma_cleanup(RDMAContext *rdma)
qemu_rdma_post_send_control(rdma, NULL, &head);
}
- ret = rdma_disconnect(rdma->cm_id);
- if (!ret) {
- trace_qemu_rdma_cleanup_waiting_for_disconnect();
- ret = rdma_get_cm_event(rdma->channel, &cm_event);
- if (!ret) {
- rdma_ack_cm_event(cm_event);
- }
- }
+ rdma_disconnect(rdma->cm_id);
trace_qemu_rdma_cleanup_disconnect();
rdma->connected = false;
}
diff --git a/migration/trace-events b/migration/trace-events
index 3c798dd..4a768ea 100644
--- a/migration/trace-events
+++ b/migration/trace-events
@@ -146,7 +146,6 @@ qemu_rdma_accept_pin_state(bool pin) "%d"
qemu_rdma_accept_pin_verbsc(void *verbs) "Verbs context after listen: %p"
qemu_rdma_block_for_wrid_miss(const char *wcompstr, int wcomp, const char *gcompstr, uint64_t req) "A Wanted wrid %s (%d) but got %s (%" PRIu64 ")"
qemu_rdma_cleanup_disconnect(void) ""
-qemu_rdma_cleanup_waiting_for_disconnect(void) ""
qemu_rdma_close(void) ""
qemu_rdma_connect_pin_all_requested(void) ""
qemu_rdma_connect_pin_all_outcome(bool pin) "%d"