[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [PULL 5/5] migration: not wait RDMA_CM_EVENT_DISCONNECTED e
From: |
Juan Quintela |
Subject: |
[Qemu-devel] [PULL 5/5] migration: not wait RDMA_CM_EVENT_DISCONNECTED event after rdma_disconnect |
Date: |
Mon, 4 Jun 2018 06:21:56 +0200 |
From: Lidong Chen <address@hidden>
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 <address@hidden>
Reviewed-by: Juan Quintela <address@hidden>
Reviewed-by: Dr. David Alan Gilbert <address@hidden>
Signed-off-by: Juan Quintela <address@hidden>
---
migration/rdma.c | 12 ++----------
migration/trace-events | 1 -
2 files changed, 2 insertions(+), 11 deletions(-)
diff --git a/migration/rdma.c b/migration/rdma.c
index 60779221b1..05aee3d591 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 3c798ddd11..4a768eaaeb 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"
--
2.17.0
- [Qemu-devel] [PULL 0/5] Migration pull request, Juan Quintela, 2018/06/04
- [Qemu-devel] [PULL 1/5] migration: introduce decompress-error-check, Juan Quintela, 2018/06/04
- [Qemu-devel] [PULL 2/5] migration: discard non-migratable RAMBlocks, Juan Quintela, 2018/06/04
- [Qemu-devel] [PULL 3/5] migration: Don't activate block devices if using -S, Juan Quintela, 2018/06/04
- [Qemu-devel] [PULL 4/5] migration: remove unnecessary variables len in QIOChannelRDMA, Juan Quintela, 2018/06/04
- [Qemu-devel] [PULL 5/5] migration: not wait RDMA_CM_EVENT_DISCONNECTED event after rdma_disconnect,
Juan Quintela <=
- Re: [Qemu-devel] [PULL 0/5] Migration pull request, no-reply, 2018/06/04
- Re: [Qemu-devel] [PULL 0/5] Migration pull request, Peter Maydell, 2018/06/04