[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Xen-devel] [PATCH 1 of 2 V3] libxl: Remus - suspend/postflush/commit callbacks



# HG changeset patch
# User Shriram Rajagopalan <rshriram@xxxxxxxxx>
# Date 1328251593 28800
# Node ID 90e59c643c00c079996e13b75f89d1f0cd931a02
# Parent  c7abecc14cceb18140335ebe20faad826282cd1f
libxl: Remus - suspend/postflush/commit callbacks

 * Add libxl callback functions for Remus checkpoint suspend, postflush
   (aka resume) and checkpoint commit callbacks.
 * suspend callback is a stub that just bounces off
   libxl__domain_suspend_common_callback - which suspends the domain and
   saves the devices model state to a file.
 * resume callback currently just resumes the domain (and the device model).
 * commit callback just writes out the saved device model state to the
   network and sleeps for the checkpoint interval.
 * Introduce a new public API, libxl_domain_remus_start (currently a stub)
   that sets up the network and disk buffer and initiates continuous
   checkpointing.

 * Future patches will augument these callbacks/functions with more 
functionalities
   like issuing network buffer plug/unplug commands, disk checkpoint commands, 
etc.

Signed-off-by: Shriram Rajagopalan <rshriram@xxxxxxxxx>

diff -r c7abecc14cce -r 90e59c643c00 tools/libxl/libxl.c
--- a/tools/libxl/libxl.c       Thu Feb 02 22:46:33 2012 -0800
+++ b/tools/libxl/libxl.c       Thu Feb 02 22:46:33 2012 -0800
@@ -471,6 +471,41 @@ libxl_vminfo * libxl_list_vm(libxl_ctx *
     return ptr;
 }
 
+/* TODO: Explicit Checkpoint acknowledgements via recv_fd. */
+int libxl_domain_remus_start(libxl_ctx *ctx, libxl_domain_remus_info *info,
+                             uint32_t domid, int send_fd, int recv_fd)
+{
+    GC_INIT(ctx);
+    libxl_domain_type type = libxl__domain_type(gc, domid);
+    int rc = 0;
+
+    if (info == NULL) {
+        LIBXL__LOG(ctx, LIBXL__LOG_ERROR,
+                   "No remus_info structure supplied for domain %d", domid);
+        rc = ERROR_INVAL;
+        goto remus_fail;
+    }
+
+    /* TBD: Remus setup - i.e. attach qdisc, enable disk buffering, etc */
+
+    /* Point of no return */
+    rc = libxl__domain_suspend_common(gc, domid, send_fd, type, /* live */ 1,
+                                      /* debug */ 0, info);
+
+    /* 
+     * With Remus, if we reach this point, it means either
+     * backup died or some network error occurred preventing us
+     * from sending checkpoints.
+     */
+
+    /* TBD: Remus cleanup - i.e. detach qdisc, release other
+     * resources.
+     */
+ remus_fail:
+    GC_FREE;
+    return rc;
+}
+
 int libxl_domain_suspend(libxl_ctx *ctx, libxl_domain_suspend_info *info,
                          uint32_t domid, int fd)
 {
@@ -480,7 +515,9 @@ int libxl_domain_suspend(libxl_ctx *ctx,
     int debug = info != NULL && info->flags & XL_SUSPEND_DEBUG;
     int rc = 0;
 
-    rc = libxl__domain_suspend_common(gc, domid, fd, type, live, debug);
+    rc = libxl__domain_suspend_common(gc, domid, fd, type, live, debug,
+                                      /* No Remus */ NULL);
+
     if (!rc && type == LIBXL_DOMAIN_TYPE_HVM)
         rc = libxl__domain_save_device_model(gc, domid, fd);
     GC_FREE;
diff -r c7abecc14cce -r 90e59c643c00 tools/libxl/libxl.h
--- a/tools/libxl/libxl.h       Thu Feb 02 22:46:33 2012 -0800
+++ b/tools/libxl/libxl.h       Thu Feb 02 22:46:33 2012 -0800
@@ -266,6 +266,8 @@ typedef int (*libxl_console_ready)(libxl
 int libxl_domain_create_new(libxl_ctx *ctx, libxl_domain_config *d_config, 
libxl_console_ready cb, void *priv, uint32_t *domid);
 int libxl_domain_create_restore(libxl_ctx *ctx, libxl_domain_config *d_config, 
libxl_console_ready cb, void *priv, uint32_t *domid, int restore_fd);
 void libxl_domain_config_dispose(libxl_domain_config *d_config);
+int libxl_domain_remus_start(libxl_ctx *ctx, libxl_domain_remus_info *info,
+                             uint32_t domid, int send_fd, int recv_fd);
 int libxl_domain_suspend(libxl_ctx *ctx, libxl_domain_suspend_info *info,
                           uint32_t domid, int fd);
 
diff -r c7abecc14cce -r 90e59c643c00 tools/libxl/libxl_dom.c
--- a/tools/libxl/libxl_dom.c   Thu Feb 02 22:46:33 2012 -0800
+++ b/tools/libxl/libxl_dom.c   Thu Feb 02 22:46:33 2012 -0800
@@ -467,6 +467,8 @@ struct suspendinfo {
     int hvm;
     unsigned int flags;
     int guest_responded;
+    int save_fd; /* Migration stream fd (for Remus) */
+    int interval; /* checkpoint interval (for Remus) */
 };
 
 static int libxl__domain_suspend_common_switch_qemu_logdirty(int domid, 
unsigned int enable, void *data)
@@ -731,9 +733,43 @@ static int libxl__toolstack_save(uint32_
     return 0;
 }
 
+static int libxl__remus_domain_suspend_callback(void *data)
+{
+    /* TODO: Issue disk and network checkpoint reqs. */
+    return libxl__domain_suspend_common_callback(data);
+}
+
+static int libxl__remus_domain_resume_callback(void *data)
+{
+    struct suspendinfo *si = data;
+    libxl_ctx *ctx = libxl__gc_owner(si->gc);
+
+    /* Resumes the domain and the device model */
+    if (libxl_domain_resume(ctx, si->domid, /* Fast Suspend */1))
+        return 0;
+
+    /* TODO: Deal with disk. Start a new network output buffer */
+    return 1;
+}
+
+static int libxl__remus_domain_checkpoint_callback(void *data)
+{
+    struct suspendinfo *si = data;
+
+    /* This would go into tailbuf. */
+    if (si->hvm &&
+        libxl__domain_save_device_model(si->gc, si->domid, si->save_fd))
+        return 0;
+
+    /* TODO: Wait for disk and memory ack, release network buffer */
+    usleep(si->interval * 1000);
+    return 1;
+}
+
 int libxl__domain_suspend_common(libxl__gc *gc, uint32_t domid, int fd,
                                  libxl_domain_type type,
-                                 int live, int debug)
+                                 int live, int debug,
+                                 const libxl_domain_remus_info *r_info)
 {
     libxl_ctx *ctx = libxl__gc_owner(gc);
     int flags;
@@ -764,10 +800,20 @@ int libxl__domain_suspend_common(libxl__
         return ERROR_INVAL;
     }
 
+    memset(&si, 0, sizeof(si));
     flags = (live) ? XCFLAGS_LIVE : 0
           | (debug) ? XCFLAGS_DEBUG : 0
           | (hvm) ? XCFLAGS_HVM : 0;
 
+    if (r_info != NULL) {
+        si.interval = r_info->interval;
+        if (r_info->compression)
+            flags |= XCFLAGS_CHECKPOINT_COMPRESS;
+        si.save_fd = fd;
+    }
+    else
+        si.save_fd = -1;
+
     si.domid = domid;
     si.flags = flags;
     si.hvm = hvm;
@@ -791,7 +837,27 @@ int libxl__domain_suspend_common(libxl__
     }
 
     memset(&callbacks, 0, sizeof(callbacks));
-    callbacks.suspend = libxl__domain_suspend_common_callback;
+    if (r_info != NULL) {
+        /* save_callbacks:
+         * suspend - called after expiration of checkpoint interval,
+         *           to *suspend* the domain.
+         *
+         * postcopy - called after the domain's dirty pages have been
+         *            copied into an output buffer. We *resume* the domain
+         *            & the device model, return to the caller. Caller then
+         *            flushes the output buffer, while the domain continues to 
run.
+         *
+         * checkpoint - called after the memory checkpoint has been flushed out
+         *              into the network. Send the saved device state, *wait*
+         *              for checkpoint ack and *release* the network buffer 
(TBD).
+         *              Then *sleep* for the checkpoint interval.
+         */
+        callbacks.suspend = libxl__remus_domain_suspend_callback;
+        callbacks.postcopy = libxl__remus_domain_resume_callback;
+        callbacks.checkpoint = libxl__remus_domain_checkpoint_callback;
+    } else
+        callbacks.suspend = libxl__domain_suspend_common_callback;
+
     callbacks.switch_qemu_logdirty = 
libxl__domain_suspend_common_switch_qemu_logdirty;
     callbacks.toolstack_save = libxl__toolstack_save;
     callbacks.data = &si;
diff -r c7abecc14cce -r 90e59c643c00 tools/libxl/libxl_internal.h
--- a/tools/libxl/libxl_internal.h      Thu Feb 02 22:46:33 2012 -0800
+++ b/tools/libxl/libxl_internal.h      Thu Feb 02 22:46:33 2012 -0800
@@ -275,7 +275,8 @@ _hidden int libxl__domain_restore_common
                                          int fd);
 _hidden int libxl__domain_suspend_common(libxl__gc *gc, uint32_t domid, int fd,
                                          libxl_domain_type type,
-                                         int live, int debug);
+                                         int live, int debug,
+                                         const libxl_domain_remus_info 
*r_info);
 _hidden const char *libxl__device_model_savefile(libxl__gc *gc, uint32_t 
domid);
 _hidden int libxl__domain_suspend_device_model(libxl__gc *gc, uint32_t domid);
 _hidden int libxl__domain_resume_device_model(libxl__gc *gc, uint32_t domid);
diff -r c7abecc14cce -r 90e59c643c00 tools/libxl/libxl_types.idl
--- a/tools/libxl/libxl_types.idl       Thu Feb 02 22:46:33 2012 -0800
+++ b/tools/libxl/libxl_types.idl       Thu Feb 02 22:46:33 2012 -0800
@@ -397,3 +397,9 @@ libxl_sched_sedf = Struct("sched_sedf", 
     ("extratime", integer),
     ("weight", integer),
     ], dispose_fn=None)
+
+libxl_domain_remus_info = Struct("domain_remus_info",[
+    ("interval",     integer),
+    ("blackhole",    bool),
+    ("compression",  bool),
+    ])

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel


 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.