Andrew Cooper
2013-Oct-03 16:11 UTC
[PATCH v7] tools/migrate: Fix regression when migrating from older version of Xen
Commit 00a4b65f8534c9e6521eab2e6ce796ae36037774 Sep 7 2010
"libxc: provide notification of final checkpoint to restore end"
broke migration from any version of Xen using tools from prior to that commit
Older tools have no idea about an XC_SAVE_ID_LAST_CHECKPOINT, causing newer
tools xc_domain_restore() to start reading the qemu save record, as
ctx->last_checkpoint is 0.
The failure looks like:
xc: error: Max batch size exceeded (1970103633). Giving up.
where 1970103633 = 0x756d6551 = *(uint32_t*)"Qemu"
With this fix in place, the behaviour for normal migrations is reverted to how
it was before the regression; the migration is considered non-checkpointed
right from the start. A XC_SAVE_ID_LAST_CHECKPOINT chunk seen in the
migration stream is a nop. For checkpointed migrations the behaviour is
unchanged.
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
CC: Ian Campbell <Ian.Campbell@citrix.com>
CC: Ian Jackson <Ian.Jackson@eu.citrix.com>
CC: Shriram Rajagopalan <rshriram@cs.ubc.ca>
---
Changes in v7:
* Introduce the notion of LIBXL_ABI_VERSION 0x040400
* s/_FLAGS/_PARAMS/ for changes in libxl.h
---
tools/libxc/xc_domain_restore.c | 3 ++-
tools/libxc/xc_nomigrate.c | 2 +-
tools/libxc/xenguest.h | 3 ++-
tools/libxl/libxl.h | 33 ++++++++++++++++++++++++++++++-
tools/libxl/libxl_create.c | 11 +++++++----
tools/libxl/libxl_internal.h | 1 +
tools/libxl/libxl_save_callout.c | 2 +-
tools/libxl/libxl_save_helper.c | 3 ++-
tools/libxl/libxl_types.idl | 4 ++++
tools/libxl/xl_cmdimpl.c | 5 +++++
tools/python/xen/xend/XendCheckpoint.py | 2 +-
tools/xcutils/xc_restore.c | 14 ++++++++-----
12 files changed, 67 insertions(+), 16 deletions(-)
diff --git a/tools/libxc/xc_domain_restore.c b/tools/libxc/xc_domain_restore.c
index 939a76b..ecaf25d 100644
--- a/tools/libxc/xc_domain_restore.c
+++ b/tools/libxc/xc_domain_restore.c
@@ -1402,7 +1402,7 @@ int xc_domain_restore(xc_interface *xch, int io_fd,
uint32_t dom,
domid_t store_domid, unsigned int console_evtchn,
unsigned long *console_mfn, domid_t console_domid,
unsigned int hvm, unsigned int pae, int superpages,
- int no_incr_generationid,
+ int no_incr_generationid, int checkpointed_stream,
unsigned long *vm_generationid_addr,
struct restore_callbacks *callbacks)
{
@@ -1474,6 +1474,7 @@ int xc_domain_restore(xc_interface *xch, int io_fd,
uint32_t dom,
ctx->superpages = superpages;
ctx->hvm = hvm;
+ ctx->last_checkpoint = !checkpointed_stream;
ctxt = xc_hypercall_buffer_alloc(xch, ctxt, sizeof(*ctxt));
diff --git a/tools/libxc/xc_nomigrate.c b/tools/libxc/xc_nomigrate.c
index 73e7566..fb6d53e 100644
--- a/tools/libxc/xc_nomigrate.c
+++ b/tools/libxc/xc_nomigrate.c
@@ -35,7 +35,7 @@ int xc_domain_restore(xc_interface *xch, int io_fd, uint32_t
dom,
domid_t store_domid, unsigned int console_evtchn,
unsigned long *console_mfn, domid_t console_domid,
unsigned int hvm, unsigned int pae, int superpages,
- int no_incr_generationid,
+ int no_incr_generationid, int checkpointed_stream,
unsigned long *vm_generationid_addr,
struct restore_callbacks *callbacks)
{
diff --git a/tools/libxc/xenguest.h b/tools/libxc/xenguest.h
index c12091f..a0e30e1 100644
--- a/tools/libxc/xenguest.h
+++ b/tools/libxc/xenguest.h
@@ -114,6 +114,7 @@ struct restore_callbacks {
* @parm pae non-zero if this HVM domain has PAE support enabled
* @parm superpages non-zero to allocate guest memory with superpages
* @parm no_incr_generationid non-zero if generation id is NOT to be
incremented
+ * @parm checkpointed_stream non-zero if the far end of the stream is using
checkpointing
* @parm vm_generationid_addr returned with the address of the generation id
buffer
* @parm callbacks non-NULL to receive a callback to restore toolstack
* specific data
@@ -124,7 +125,7 @@ int xc_domain_restore(xc_interface *xch, int io_fd, uint32_t
dom,
domid_t store_domid, unsigned int console_evtchn,
unsigned long *console_mfn, domid_t console_domid,
unsigned int hvm, unsigned int pae, int superpages,
- int no_incr_generationid,
+ int no_incr_generationid, int checkpointed_stream,
unsigned long *vm_generationid_addr,
struct restore_callbacks *callbacks);
/**
diff --git a/tools/libxl/libxl.h b/tools/libxl/libxl.h
index 4cab294..0678e15 100644
--- a/tools/libxl/libxl.h
+++ b/tools/libxl/libxl.h
@@ -283,7 +283,8 @@
/* API compatibility. */
#ifdef LIBXL_API_VERSION
-#if LIBXL_API_VERSION != 0x040200 && LIBXL_API_VERSION != 0x040300
+#if LIBXL_API_VERSION != 0x040200 && LIBXL_API_VERSION != 0x040300
&& \
+ LIBXL_API_VERSION != 0x040400
#error Unknown LIBXL_API_VERSION
#endif
#endif
@@ -355,6 +356,14 @@
*/
#define LIBXL_HAVE_SPICE_VDAGENT 1
+/*
+ * LIBXL_HAVE_DOMAIN_CREATE_RESTORE_PARAMS 1
+ *
+ * If this is defined, libxl_domain_create_restore()''s API has changed
to
+ * include a params structure.
+ */
+#define LIBXL_HAVE_DOMAIN_CREATE_RESTORE_PARAMS 1
+
/* Functions annotated with LIBXL_EXTERNAL_CALLERS_ONLY may not be
* called from within libxl itself. Callers outside libxl, who
* do not #include libxl_internal.h, are fine. */
@@ -578,9 +587,31 @@ int libxl_domain_create_new(libxl_ctx *ctx,
libxl_domain_config *d_config,
LIBXL_EXTERNAL_CALLERS_ONLY;
int libxl_domain_create_restore(libxl_ctx *ctx, libxl_domain_config *d_config,
uint32_t *domid, int restore_fd,
+ const libxl_domain_restore_flags *flags,
const libxl_asyncop_how *ao_how,
const libxl_asyncprogress_how *aop_console_how)
LIBXL_EXTERNAL_CALLERS_ONLY;
+
+#if defined(LIBXL_API_VERSION) && LIBXL_API_VERSION < 0x040400
+
+int static inline libxl_domain_create_restore_0x040200(
+ libxl_ctx *ctx, libxl_domain_config *d_config,
+ uint32_t *domid, int restore_fd,
+ const libxl_asyncop_how *ao_how,
+ const libxl_asyncprogress_how *aop_console_how)
+ LIBXL_EXTERNAL_CALLERS_ONLY
+{
+ libxl_domain_restore_flags flags;
+ flags.checkpointed_stream = 0;
+
+ return libxl_domain_create_restore(
+ ctx, d_config, domid, restore_fd, &flags, ao_how, aop_console_how);
+}
+
+#define libxl_domain_create_restore libxl_domain_create_restore_0x040200
+
+#endif
+
/* A progress report will be made via ao_console_how, of type
* domain_create_console_available, when the domain''s primary
* console is available and can be connected to.
diff --git a/tools/libxl/libxl_create.c b/tools/libxl/libxl_create.c
index 7567238..4a6d4f6 100644
--- a/tools/libxl/libxl_create.c
+++ b/tools/libxl/libxl_create.c
@@ -1227,7 +1227,8 @@ static void domain_create_cb(libxl__egc *egc,
static int do_domain_create(libxl_ctx *ctx, libxl_domain_config *d_config,
uint32_t *domid,
- int restore_fd, const libxl_asyncop_how *ao_how,
+ int restore_fd, int checkpointed_stream,
+ const libxl_asyncop_how *ao_how,
const libxl_asyncprogress_how *aop_console_how)
{
AO_CREATE(ctx, 0, ao_how);
@@ -1238,6 +1239,7 @@ static int do_domain_create(libxl_ctx *ctx,
libxl_domain_config *d_config,
cdcs->dcs.guest_config = d_config;
cdcs->dcs.restore_fd = restore_fd;
cdcs->dcs.callback = domain_create_cb;
+ cdcs->dcs.checkpointed_stream = checkpointed_stream;
libxl__ao_progress_gethow(&cdcs->dcs.aop_console_how,
aop_console_how);
cdcs->domid_out = domid;
@@ -1264,17 +1266,18 @@ int libxl_domain_create_new(libxl_ctx *ctx,
libxl_domain_config *d_config,
const libxl_asyncop_how *ao_how,
const libxl_asyncprogress_how *aop_console_how)
{
- return do_domain_create(ctx, d_config, domid, -1,
+ return do_domain_create(ctx, d_config, domid, -1, 0,
ao_how, aop_console_how);
}
int libxl_domain_create_restore(libxl_ctx *ctx, libxl_domain_config *d_config,
uint32_t *domid, int restore_fd,
+ const libxl_domain_restore_flags *flags,
const libxl_asyncop_how *ao_how,
- const libxl_asyncprogress_how *aop_console_how)
+ const libxl_asyncprogress_how *aop_console_how)
{
return do_domain_create(ctx, d_config, domid, restore_fd,
- ao_how, aop_console_how);
+ flags->checkpointed_stream, ao_how,
aop_console_how);
}
/*
diff --git a/tools/libxl/libxl_internal.h b/tools/libxl/libxl_internal.h
index f051d91..4e15055 100644
--- a/tools/libxl/libxl_internal.h
+++ b/tools/libxl/libxl_internal.h
@@ -2514,6 +2514,7 @@ struct libxl__domain_create_state {
libxl_asyncprogress_how aop_console_how;
/* private to domain_create */
int guest_domid;
+ int checkpointed_stream;
libxl__domain_build_state build_state;
libxl__bootloader_state bl;
libxl__stub_dm_spawn_state dmss;
diff --git a/tools/libxl/libxl_save_callout.c b/tools/libxl/libxl_save_callout.c
index f164e98..6e45b2f 100644
--- a/tools/libxl/libxl_save_callout.c
+++ b/tools/libxl/libxl_save_callout.c
@@ -60,7 +60,7 @@ void libxl__xc_domain_restore(libxl__egc *egc,
libxl__domain_create_state *dcs,
state->store_domid, state->console_port,
state->console_domid,
hvm, pae, superpages, no_incr_generationid,
- cbflags,
+ cbflags, dcs->checkpointed_stream,
};
dcs->shs.ao = ao;
diff --git a/tools/libxl/libxl_save_helper.c b/tools/libxl/libxl_save_helper.c
index 772251a..880565e 100644
--- a/tools/libxl/libxl_save_helper.c
+++ b/tools/libxl/libxl_save_helper.c
@@ -252,6 +252,7 @@ int main(int argc, char **argv)
int superpages = strtoul(NEXTARG,0,10);
int no_incr_genidad = strtoul(NEXTARG,0,10);
unsigned cbflags = strtoul(NEXTARG,0,10);
+ int checkpointed = strtoul(NEXTARG,0,10);
assert(!*++argv);
helper_setcallbacks_restore(&helper_restore_callbacks, cbflags);
@@ -264,7 +265,7 @@ int main(int argc, char **argv)
r = xc_domain_restore(xch, io_fd, dom, store_evtchn, &store_mfn,
store_domid, console_evtchn, &console_mfn,
console_domid, hvm, pae, superpages,
- no_incr_genidad, &genidad,
+ no_incr_genidad, checkpointed, &genidad,
&helper_restore_callbacks);
helper_stub_restore_results(store_mfn,console_mfn,genidad,0);
complete(r);
diff --git a/tools/libxl/libxl_types.idl b/tools/libxl/libxl_types.idl
index 049dbb5..f9ad571 100644
--- a/tools/libxl/libxl_types.idl
+++ b/tools/libxl/libxl_types.idl
@@ -259,6 +259,10 @@ libxl_domain_create_info =
Struct("domain_create_info",[
("run_hotplug_scripts",libxl_defbool),
], dir=DIR_IN)
+libxl_domain_restore_flags = Struct("domain_restore_flags", [
+ ("checkpointed_stream", integer),
+ ])
+
MemKB = UInt(64, init_val = "LIBXL_MEMKB_DEFAULT")
libxl_domain_sched_params = Struct("domain_sched_params",[
diff --git a/tools/libxl/xl_cmdimpl.c b/tools/libxl/xl_cmdimpl.c
index a91b427..3ace31c 100644
--- a/tools/libxl/xl_cmdimpl.c
+++ b/tools/libxl/xl_cmdimpl.c
@@ -132,6 +132,7 @@ struct domain_create {
int vnc;
int vncautopass;
int console_autoconnect;
+ int checkpointed_stream;
const char *config_file;
const char *extra_config; /* extra config string */
const char *restore_file;
@@ -2064,8 +2065,11 @@ start:
}
if ( restoring ) {
+ libxl_domain_restore_flags flags;
+ flags.checkpointed_stream = dom_info->checkpointed_stream;
ret = libxl_domain_create_restore(ctx, &d_config,
&domid, restore_fd,
+ &flags,
0, autoconnect_console_how);
/*
* On subsequent reboot etc we should create the domain, not
@@ -3679,6 +3683,7 @@ static void migrate_receive(int debug, int daemonize, int
monitor,
dom_info.paused = 1;
dom_info.migrate_fd = recv_fd;
dom_info.migration_domname_r = &migration_domname;
+ dom_info.checkpointed_stream = remus;
rc = create_domain(&dom_info);
if (rc < 0) {
diff --git a/tools/python/xen/xend/XendCheckpoint.py
b/tools/python/xen/xend/XendCheckpoint.py
index fa09757..a433ffa 100644
--- a/tools/python/xen/xend/XendCheckpoint.py
+++ b/tools/python/xen/xend/XendCheckpoint.py
@@ -301,7 +301,7 @@ def restore(xd, fd, dominfo = None, paused = False,
relocating = False):
cmd = map(str, [xen.util.auxbin.pathTo(XC_RESTORE),
fd, dominfo.getDomid(),
- store_port, console_port, int(is_hvm), pae, apic,
superpages])
+ store_port, console_port, int(is_hvm), pae, apic,
superpages, 1])
log.debug("[xc_restore]: %s", string.join(cmd))
handler = RestoreInputHandler()
diff --git a/tools/xcutils/xc_restore.c b/tools/xcutils/xc_restore.c
index 35d725c..5ec90ac 100644
--- a/tools/xcutils/xc_restore.c
+++ b/tools/xcutils/xc_restore.c
@@ -19,7 +19,7 @@ int
main(int argc, char **argv)
{
unsigned int domid, store_evtchn, console_evtchn;
- unsigned int hvm, pae, apic, lflags;
+ unsigned int hvm, pae, apic, lflags, checkpointed;
xc_interface *xch;
int io_fd, ret;
int superpages;
@@ -27,9 +27,9 @@ main(int argc, char **argv)
xentoollog_level lvl;
xentoollog_logger *l;
- if ( (argc != 8) && (argc != 9) )
+ if ( !( argc >= 8 && argc <= 10) )
errx(1, "usage: %s iofd domid store_evtchn "
- "console_evtchn hvm pae apic [superpages]", argv[0]);
+ "console_evtchn hvm pae apic [superpages
[checkpointed]]", argv[0]);
lvl = XTL_DETAIL;
lflags = XTL_STDIOSTREAM_SHOW_PID | XTL_STDIOSTREAM_HIDE_PROGRESS;
@@ -45,14 +45,18 @@ main(int argc, char **argv)
hvm = atoi(argv[5]);
pae = atoi(argv[6]);
apic = atoi(argv[7]);
- if ( argc == 9 )
+ if ( argc >= 9 )
superpages = atoi(argv[8]);
else
superpages = !!hvm;
+ if ( argc >= 10 )
+ checkpointed = atoi(argv[9]);
+ else
+ checkpointed = 0;
ret = xc_domain_restore(xch, io_fd, domid, store_evtchn, &store_mfn, 0,
console_evtchn, &console_mfn, 0, hvm, pae,
superpages,
- 0, NULL, NULL);
+ 0, checkpointed, NULL, NULL);
if ( ret == 0 )
{
--
1.7.10.4
Shriram Rajagopalan
2013-Oct-07 03:00 UTC
Re: [PATCH v7] tools/migrate: Fix regression when migrating from older version of Xen
On Thu, Oct 3, 2013 at 9:11 AM, Andrew Cooper <andrew.cooper3@citrix.com>wrote:> Commit 00a4b65f8534c9e6521eab2e6ce796ae36037774 Sep 7 2010 > "libxc: provide notification of final checkpoint to restore end" > broke migration from any version of Xen using tools from prior to that > commit > > Older tools have no idea about an XC_SAVE_ID_LAST_CHECKPOINT, causing newer > tools xc_domain_restore() to start reading the qemu save record, as > ctx->last_checkpoint is 0. > > The failure looks like: > xc: error: Max batch size exceeded (1970103633). Giving up. > where 1970103633 = 0x756d6551 = *(uint32_t*)"Qemu" > > With this fix in place, the behaviour for normal migrations is reverted to > how > it was before the regression; the migration is considered non-checkpointed > right from the start. A XC_SAVE_ID_LAST_CHECKPOINT chunk seen in the > migration stream is a nop. For checkpointed migrations the behaviour is > unchanged. > > Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com> > CC: Ian Campbell <Ian.Campbell@citrix.com> > CC: Ian Jackson <Ian.Jackson@eu.citrix.com> > CC: Shriram Rajagopalan <rshriram@cs.ubc.ca> > >ack (as far as the remus bits are concerned). thanks shriram _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org http://lists.xen.org/xen-devel
Ian Campbell
2013-Oct-10 10:26 UTC
Re: [PATCH v7] tools/migrate: Fix regression when migrating from older version of Xen
On Thu, 2013-10-03 at 17:11 +0100, Andrew Cooper wrote:> + #define LIBXL_HAVE_DOMAIN_CREATE_RESTORE_PARAMS 1[...]> + const libxl_domain_restore_flags *flags,Looks like you forgot to change the type name...