[PATCH 4 of 5 V3] tools/libxl: Control network buffering in remus callbacks

[Shriram Rajagopalan <rshriram@cs.ubc.ca>]

# HG changeset patch
# User Shriram Rajagopalan <rshriram@cs.ubc.ca>
# Date 1382295546 25200
# Node ID a8deb9499e9dcce9869025fa1c02cf2e0d58612a
# Parent  d3f088236c550213fc04ed982df47b4771b28d2f
tools/libxl: Control network buffering in remus callbacks

This patch constitutes the core network buffering logic.
and does the following:
 a) create a new network buffer when the domain is suspended
    (remus_domain_suspend_callback)
 b) release the previous network buffer pertaining to the
    committed checkpoint (remus_domain_checkpoint_dm_saved)

Signed-off-by: Shriram Rajagopalan <rshriram@cs.ubc.ca>

diff -r d3f088236c55 -r a8deb9499e9d tools/libxl/libxl_dom.c
--- a/tools/libxl/libxl_dom.c	Sun Oct 20 11:54:26 2013 -0700
+++ b/tools/libxl/libxl_dom.c	Sun Oct 20 11:59:06 2013 -0700
@@ -1259,8 +1259,24 @@ void libxl__remus_teardown_done(libxl__e
 
 static int libxl__remus_domain_suspend_callback(void *data)
 {
-    /* REMUS TODO: Issue disk and network checkpoint reqs. */
-    return libxl__domain_suspend_common_callback(data);
+    /* REMUS TODO: Issue disk checkpoint reqs. */
+    libxl__save_helper_state *shs = data;
+    libxl__domain_suspend_state *dss = CONTAINER_OF(shs, *dss, shs);
+    libxl__remus_ctx *remus_ctx = dss->remus_ctx;
+    bool is_suspended;
+    STATE_AO_GC(dss->ao);
+
+    is_suspended = !!libxl__domain_suspend_common_callback(data);
+
+    if (!remus_ctx->netbuf_ctx) return is_suspended;
+
+    if (is_suspended) {
+        if (libxl__remus_netbuf_start_new_epoch(gc, dss->domid,
+                                                remus_ctx))
+            return !is_suspended;
+    }
+
+    return is_suspended;
 }
 
 static int libxl__remus_domain_resume_callback(void *data)
@@ -1273,7 +1289,7 @@ static int libxl__remus_domain_resume_ca
     if (libxl__domain_resume(gc, dss->domid, /* Fast Suspend */1))
         return 0;
 
-    /* REMUS TODO: Deal with disk. Start a new network output buffer */
+    /* REMUS TODO: Deal with disk. */
     return 1;
 }
 
@@ -1300,11 +1316,42 @@ static void libxl__remus_domain_checkpoi
 static void remus_checkpoint_dm_saved(libxl__egc *egc,
                                       libxl__domain_suspend_state *dss, int rc)
 {
-    /* REMUS TODO: Wait for disk and memory ack, release network buffer */
-    /* REMUS TODO: make this asynchronous */
-    assert(!rc); /* REMUS TODO handle this error properly */
-    usleep(dss->remus_ctx->interval * 1000);
-    libxl__xc_domain_saverestore_async_callback_done(egc, &dss->shs, 1);
+    /*
+     * REMUS TODO: Wait for disk and explicit memory ack (through restore
+     * callback from remote) before releasing network buffer.
+     */
+    libxl__remus_ctx *remus_ctx = dss->remus_ctx;
+    struct timespec epoch;
+    int do_next_iter = 0;
+    STATE_AO_GC(dss->ao);
+
+    if (rc) {
+        LOG(ERROR, "Failed to save device model. Terminating Remus..");
+        goto out;
+    }
+
+    if (remus_ctx->netbuf_ctx) {
+        rc = libxl__remus_netbuf_release_prev_epoch(gc, dss->domid,
+                                                     remus_ctx);
+        if (rc) {
+            LOG(ERROR, "Failed to release network buffer."
+                " Terminating Remus..");
+            goto out;
+        }
+    }
+
+    epoch.tv_sec = remus_ctx->interval / 1000; /* interval is in ms */
+    epoch.tv_nsec = remus_ctx->interval * 1000L * 1000L;
+    nanosleep(&epoch, 0);
+    /*
+     * Set return value to 1, so that the infinite checkpoint cycle
+     * continues. See xc_domain_save.c: xc_domain_save()
+     */
+    do_next_iter = 1;
+
+ out:
+    libxl__xc_domain_saverestore_async_callback_done(egc, &dss->shs,
+                                                     do_next_iter);
 }
 
 /*----- main code for suspending, in order of execution -----*/