From d006b9dae589eb8f83626ce6ba84d7dc867335ec Mon Sep 17 00:00:00 2001 From: Shriram Rajagopalan Date: Mon, 25 Apr 2011 13:27:12 +0100 Subject: [PATCH] remus: proper cleanup on checkpoint failure. While running remus, when an error occurs during checkpointing (e.g., timeouts on primary, failing to checkpoint network buffer or disk or even communication failure) the domU is sometimes left in suspended state on primary. Instead of blindly closing the checkpoint file handle, attempt to resume the domain before the close. Signed-off-by: Shriram Rajagopalan Committed-by: Ian Jackson xen-unstable changeset: 23195:13ec53a59a42 xen-unstable date: Fri Apr 08 16:49:04 2011 +0100 --- tools/python/xen/lowlevel/checkpoint/checkpoint.c | 3 +++ tools/python/xen/remus/save.py | 6 +++++- 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/tools/python/xen/lowlevel/checkpoint/checkpoint.c b/tools/python/xen/lowlevel/checkpoint/checkpoint.c index 7545d7deb6..1581b64095 100644 --- a/tools/python/xen/lowlevel/checkpoint/checkpoint.c +++ b/tools/python/xen/lowlevel/checkpoint/checkpoint.c @@ -80,6 +80,9 @@ static PyObject* pycheckpoint_close(PyObject* obj, PyObject* args) { CheckpointObject* self = (CheckpointObject*)obj; + if (checkpoint_resume(&self->cps) < 0) + fprintf(stderr, "%s\n", checkpoint_error(&self->cps)); + checkpoint_close(&self->cps); Py_XDECREF(self->suspend_cb); diff --git a/tools/python/xen/remus/save.py b/tools/python/xen/remus/save.py index 71517da8c1..9858aec571 100644 --- a/tools/python/xen/remus/save.py +++ b/tools/python/xen/remus/save.py @@ -158,9 +158,13 @@ class Saver(object): self.checkpointer.open(self.vm.domid) self.checkpointer.start(self.fd, self.suspendcb, self.resumecb, self.checkpointcb, self.interval) - self.checkpointer.close() except xen.lowlevel.checkpoint.error, e: raise CheckpointError(e) + finally: + try: #errors in checkpoint close are not critical atm. + self.checkpointer.close() + except: + pass def _resume(self): """low-overhead version of XendDomainInfo.resumeDomain"""