...and time out after that. This will be needed because of an upcoming
change to passt-repair enabling it to start before passt is started,
on both source and target, by means of an inotify watch.
Once the inotify watch triggers, passt-repair will connect right away,
but we have no guarantees that the connection completes before we
start the migration process, so wait for it (for a reasonable amount
of time).
Signed-off-by: Stefano Brivio <sbrivio(a)redhat.com>
---
v2:
- Use 10 ms as timeout instead of 100 ms. Given that I'm unable to
migrate a simple guest with 256 MiB of memory and no storage other
than an initramfs in less than 4 milliseconds, at least on my test
system (rather fast CPU threads and memory interface), I think that
10 ms shouldn't make a big difference in case passt-repair is not
available for whatever reason
- Move the static assert next to the initialisation of 'tv'
flow.c | 20 ++++++++++++++++++++
repair.c | 31 +++++++++++++++++++++++++++++++
repair.h | 1 +
3 files changed, 52 insertions(+)
diff --git a/flow.c b/flow.c
index 749c498..5e64b79 100644
--- a/flow.c
+++ b/flow.c
@@ -911,6 +911,21 @@ static int flow_migrate_source_rollback(struct ctx *c, unsigned
bound, int ret)
return ret;
}
+/**
+ * flow_migrate_need_repair() - Do we need to set repair mode for any flow?
+ *
+ * Return: true if repair mode is needed, false otherwise
+ */
+static bool flow_migrate_need_repair(void)
+{
+ union flow *flow;
+
+ foreach_established_tcp_flow(flow)
+ return true;
+
+ return false;
+}
+
/**
* flow_migrate_repair_all() - Turn repair mode on or off for all flows
* @c: Execution context
@@ -966,6 +981,9 @@ int flow_migrate_source_pre(struct ctx *c, const struct migrate_stage
*stage,
(void)stage;
(void)fd;
+ if (flow_migrate_need_repair())
+ repair_wait(c);
+
if ((rc = flow_migrate_repair_all(c, true)))
return -rc;
@@ -1083,6 +1101,8 @@ int flow_migrate_target(struct ctx *c, const struct migrate_stage
*stage,
if (!count)
return 0;
+ repair_wait(c);
+
if ((rc = flow_migrate_repair_all(c, true)))
return -rc;
diff --git a/repair.c b/repair.c
index 3ee089f..ebeb248 100644
--- a/repair.c
+++ b/repair.c
@@ -27,6 +27,10 @@
#define SCM_MAX_FD 253 /* From Linux kernel (include/net/scm.h), not in UAPI */
+/* Wait for a while for TCP_REPAIR helper to connect if it's not there yet */
+#define REPAIR_ACCEPT_TIMEOUT_MS 10
+#define REPAIR_ACCEPT_TIMEOUT_US (REPAIR_ACCEPT_TIMEOUT_MS * 1000)
+
/* Pending file descriptors for next repair_flush() call, or command change */
static int repair_fds[SCM_MAX_FD];
@@ -138,6 +142,33 @@ void repair_handler(struct ctx *c, uint32_t events)
repair_close(c);
}
+/**
+ * repair_wait() - Wait (with timeout) for TCP_REPAIR helper to connect
+ * @c: Execution context
+ */
+void repair_wait(struct ctx *c)
+{
+ struct timeval tv = { .tv_sec = 0,
+ .tv_usec = (long)(REPAIR_ACCEPT_TIMEOUT_US) };
+ static_assert(REPAIR_ACCEPT_TIMEOUT_US < 1000 * 1000);
+
+ if (c->fd_repair >= 0 || c->fd_repair_listen == -1)
+ return;
+
+ if (setsockopt(c->fd_repair_listen, SOL_SOCKET, SO_RCVTIMEO,
+ &tv, sizeof(tv))) {
+ err_perror("Set timeout on TCP_REPAIR listening socket");
+ return;
+ }
+
+ repair_listen_handler(c, EPOLLIN);
+
+ tv.tv_usec = 0;
+ if (setsockopt(c->fd_repair_listen, SOL_SOCKET, SO_RCVTIMEO,
+ &tv, sizeof(tv)))
+ err_perror("Clear timeout on TCP_REPAIR listening socket");
+}
+
/**
* repair_flush() - Flush current set of sockets to helper, with current command
* @c: Execution context
diff --git a/repair.h b/repair.h
index de279d6..1d37922 100644
--- a/repair.h
+++ b/repair.h
@@ -10,6 +10,7 @@ void repair_sock_init(const struct ctx *c);
void repair_listen_handler(struct ctx *c, uint32_t events);
void repair_handler(struct ctx *c, uint32_t events);
void repair_close(struct ctx *c);
+void repair_wait(struct ctx *c);
int repair_flush(struct ctx *c);
int repair_set(struct ctx *c, int s, int cmd);
--
2.43.0