| Message ID | D3E216785288A145B7BC975F83A2ED103FEE66F7@szxeml556-mbx.china.huawei.com |
|---|---|
| State | New |
| Headers | show |
"Zhanghaoyu (A)" <haoyu.zhang@huawei.com> writes: > When network disconnection occurs during live migration, the migration thread will be stuck in the function sendmsg(), as the migration socket is in ~O_NONBLOCK mode now. > > Signed-off-by: Zeng Junliang <zengjunliang@huawei.com> Unconditionally setting an arbitrary timeout is a bad idea. Should we send a signal on cancel to break the migration thread out of sendmsg? Regards, Anthony Liguori > --- > include/migration/migration.h | 4 ++++ > migration-tcp.c | 23 ++++++++++++++++++++++- > 2 files changed, 26 insertions(+), 1 deletions(-) > > diff --git a/include/migration/migration.h b/include/migration/migration.h > index f0640e0..1a56248 100644 > --- a/include/migration/migration.h > +++ b/include/migration/migration.h > @@ -23,6 +23,8 @@ > #include "qapi-types.h" > #include "exec/cpu-common.h" > > +#define QEMU_MIGRATE_SOCKET_OP_TIMEOUT 60 > + > struct MigrationParams { > bool blk; > bool shared; > @@ -109,6 +111,8 @@ uint64_t xbzrle_mig_pages_transferred(void); > uint64_t xbzrle_mig_pages_overflow(void); > uint64_t xbzrle_mig_pages_cache_miss(void); > > +int tcp_migration_set_socket_timeout(int fd, int optname, int timeout_in_sec); > + > /** > * @migrate_add_blocker - prevent migration from proceeding > * > diff --git a/migration-tcp.c b/migration-tcp.c > index b20ee58..860238b 100644 > --- a/migration-tcp.c > +++ b/migration-tcp.c > @@ -29,11 +29,28 @@ > do { } while (0) > #endif > > +int tcp_migration_set_socket_timeout(int fd, int optname, int timeout_in_sec) > +{ > + struct timeval timeout; > + int ret = 0; > + > + if (fd < 0 || timeout_in_sec < 0 || > + (optname != SO_RCVTIMEO && optname != SO_SNDTIMEO)) > + return -1; > + > + timeout.tv_sec = timeout_in_sec; > + timeout.tv_usec = 0; > + > + ret = qemu_setsockopt(fd, SOL_SOCKET, optname, &timeout, sizeof(timeout)); > + > + return ret; > +} > + > static void tcp_wait_for_connect(int fd, void *opaque) > { > MigrationState *s = opaque; > > - if (fd < 0) { > + if (tcp_migration_set_socket_timeout(fd, SO_SNDTIMEO, QEMU_MIGRATE_SOCKET_OP_TIMEOUT) < 0) { > DPRINTF("migrate connect error\n"); > s->file = NULL; > migrate_fd_error(s); > @@ -76,6 +93,10 @@ static void tcp_accept_incoming_migration(void *opaque) > goto out; > } > > + if (tcp_migration_set_socket_timeout(c, SO_RCVTIMEO, QEMU_MIGRATE_SOCKET_OP_TIMEOUT) < 0) { > + fprintf(stderr, "set tcp migration socket receive timeout error\n"); > + goto out; > + } > process_incoming_migration(f); > return; > > -- > 1.7.3.1.msysgit.0
diff --git a/include/migration/migration.h b/include/migration/migration.h index f0640e0..1a56248 100644 --- a/include/migration/migration.h +++ b/include/migration/migration.h @@ -23,6 +23,8 @@ #include "qapi-types.h" #include "exec/cpu-common.h" +#define QEMU_MIGRATE_SOCKET_OP_TIMEOUT 60 + struct MigrationParams { bool blk; bool shared; @@ -109,6 +111,8 @@ uint64_t xbzrle_mig_pages_transferred(void); uint64_t xbzrle_mig_pages_overflow(void); uint64_t xbzrle_mig_pages_cache_miss(void); +int tcp_migration_set_socket_timeout(int fd, int optname, int timeout_in_sec); + /** * @migrate_add_blocker - prevent migration from proceeding * diff --git a/migration-tcp.c b/migration-tcp.c index b20ee58..860238b 100644 --- a/migration-tcp.c +++ b/migration-tcp.c @@ -29,11 +29,28 @@ do { } while (0) #endif +int tcp_migration_set_socket_timeout(int fd, int optname, int timeout_in_sec) +{ + struct timeval timeout; + int ret = 0; + + if (fd < 0 || timeout_in_sec < 0 || + (optname != SO_RCVTIMEO && optname != SO_SNDTIMEO)) + return -1; + + timeout.tv_sec = timeout_in_sec; + timeout.tv_usec = 0; + + ret = qemu_setsockopt(fd, SOL_SOCKET, optname, &timeout, sizeof(timeout)); + + return ret; +} + static void tcp_wait_for_connect(int fd, void *opaque) { MigrationState *s = opaque; - if (fd < 0) { + if (tcp_migration_set_socket_timeout(fd, SO_SNDTIMEO, QEMU_MIGRATE_SOCKET_OP_TIMEOUT) < 0) { DPRINTF("migrate connect error\n"); s->file = NULL; migrate_fd_error(s); @@ -76,6 +93,10 @@ static void tcp_accept_incoming_migration(void *opaque) goto out; } + if (tcp_migration_set_socket_timeout(c, SO_RCVTIMEO, QEMU_MIGRATE_SOCKET_OP_TIMEOUT) < 0) { + fprintf(stderr, "set tcp migration socket receive timeout error\n"); + goto out; + } process_incoming_migration(f); return;
When network disconnection occurs during live migration, the migration thread will be stuck in the function sendmsg(), as the migration socket is in ~O_NONBLOCK mode now. Signed-off-by: Zeng Junliang <zengjunliang@huawei.com> --- include/migration/migration.h | 4 ++++ migration-tcp.c | 23 ++++++++++++++++++++++- 2 files changed, 26 insertions(+), 1 deletions(-)