remus: blackhole replication target

The new --null option allows one to test and play with just the
memory checkpointing and network buffering aspect of remus, without
the need for a second host. The disk is not replicated. All replication
data is sent to /dev/null. This option is pretty handy when a user
wants to see the page churn for his workload or observe the latency hit
though the latter will not be accurate.

Signed-off-by: Shriram Rajagopalan <rshriram@cs.ubc.ca>
Committed-by: Ian Jackson <ian.jackson@eu.citrix.com>
xen-unstable changeset: 23196:29d81623dc14
Backport-requested-by: Shriram Rajagopalan <rshriram@gmail.com>
Committed-by: Ian Jackson <ian.jackson@eu.citrix.com>

diff --git a/tools/python/xen/remus/save.py b/tools/python/xen/remus/save.py
index 9858aec571cb5a214a2a1e752f79d1a84a9d22e7..0c86eeb55fa25d195ea1c8746c17d53c9fdeb2ef 100644 (file)
--- a/tools/python/xen/remus/save.py
+++ b/tools/python/xen/remus/save.py
@@ -95,6 +95,12 @@ class MigrationSocket(_proxy):
         self.sock = sock
         super(MigrationSocket, self).__init__(fd)
 
+class NullSocket(_proxy):
+    def __init__(self, address):
+        filedesc = os.open('/dev/null', 0666)
+        fd = os.fdopen(filedesc, 'w+')
+        super(NullSocket, self).__init__(fd)
+
 class Keepalive(object):
     "Call a keepalive method at intervals"
     def __init__(self, method, interval=0.1):

diff --git a/tools/remus/remus b/tools/remus/remus
index 11d83e418f6249dd5faea6230d61c9838d0f0a8a..93a7eb8415c8e6697f03b1775e314eac675b3513 100644 (file)
--- a/tools/remus/remus
+++ b/tools/remus/remus
@@ -21,6 +21,7 @@ class Cfg(object):
         self.domid = 0
 
         self.host = 'localhost'
+        self.nullremus = False
         self.port = XendOptions.instance().get_xend_relocation_port()
         self.interval = 200
         self.netbuffer = True
@@ -33,6 +34,8 @@ class Cfg(object):
                           help='checkpoint every MS milliseconds')
         parser.add_option('-p', '--port', dest='port', type='int',
                           help='send stream to port PORT', metavar='PORT')
+        parser.add_option('', '--blackhole', dest='nullremus', action='store_true',
+                          help='replicate to /dev/null (no disk checkpoints, only memory & net buffering)')
         parser.add_option('', '--no-net', dest='nonet', action='store_true',
                           help='run without net buffering (benchmark option)')
         parser.add_option('', '--timer', dest='timer', action='store_true',
@@ -49,6 +52,8 @@ class Cfg(object):
             self.interval = opts.interval
         if opts.port:
             self.port = opts.port
+        if opts.nullremus:
+            self.nullremus = True
         if opts.nonet:
             self.netbuffer = False
         if opts.timer:
@@ -107,18 +112,22 @@ def run(cfg):
     bufs = []
 
     # disks must commit before network can be released
-    for disk in dom.disks:
-        try:
-            bufs.append(ReplicatedDisk(disk))
-        except ReplicatedDiskException, e:
-            print e
-            continue
+    if not cfg.nullremus:
+        for disk in dom.disks:
+            try:
+                bufs.append(ReplicatedDisk(disk))
+            except ReplicatedDiskException, e:
+                print e
+                continue
 
     if cfg.netbuffer:
         for vif in dom.vifs:
             bufs.append(BufferedNIC(vif))
 
-    fd = save.MigrationSocket((cfg.host, cfg.port))
+    if cfg.nullremus:
+        fd = save.NullSocket((cfg.host, cfg.port))
+    else:
+        fd = save.MigrationSocket((cfg.host, cfg.port))
 
     def postsuspend():
         'Begin external checkpointing after domain has paused'