|
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] [Xen-devel] [PATCH v18 08/11] xl/remus: cmdline switches and config vars to control network buffering
Add two members in libxl_domain_remus_info:
netbuf: whether netbuf is enabled
netbufscript: the path of the script which will be run to setup
and tear down the guest's interface.
Add cmdline switches to 'xl remus' command to enable or disable
network buffering and a domain-specific hotplug script to setup
network buffering.
Add a new config var 'remus.default.netbufscript' to xl.conf, that
allows the user to override the default global script used to
setup network buffering.
Note: Network buffering is enabled by default. Disabling network
buffering requires enabling unsafe mode.
Signed-off-by: Shriram Rajagopalan <rshriram@xxxxxxxxx>
Signed-off-by: Lai Jiangshan <laijs@xxxxxxxxxxxxxx>
Reviewed-by: Wen Congyang <wency@xxxxxxxxxxxxxx>
---
docs/man/xl.conf.pod.5 | 6 ++++++
docs/man/xl.pod.1 | 11 ++++++++++-
tools/libxl/libxl.c | 16 ++++++++++------
tools/libxl/libxl_netbuffer.c | 9 +++++++--
tools/libxl/libxl_types.idl | 2 ++
tools/libxl/xl.c | 4 ++++
tools/libxl/xl.h | 1 +
tools/libxl/xl_cmdimpl.c | 33 +++++++++++++++++++++++++--------
tools/libxl/xl_cmdtable.c | 7 +++++--
9 files changed, 70 insertions(+), 19 deletions(-)
diff --git a/docs/man/xl.conf.pod.5 b/docs/man/xl.conf.pod.5
index 7c43bde..8ae19bb 100644
--- a/docs/man/xl.conf.pod.5
+++ b/docs/man/xl.conf.pod.5
@@ -105,6 +105,12 @@ Configures the default gateway device to set for virtual
network devices.
Default: C<None>
+=item B<remus.default.netbufscript="PATH">
+
+Configures the default script used by Remus to setup network buffering.
+
+Default: C</etc/xen/scripts/remus-netbuf-setup>
+
=item B<output_format="json|sxp">
Configures the default output format used by xl when printing "machine
diff --git a/docs/man/xl.pod.1 b/docs/man/xl.pod.1
index 3aedead..2e5c36a 100644
--- a/docs/man/xl.pod.1
+++ b/docs/man/xl.pod.1
@@ -431,7 +431,7 @@ Enable Remus HA for domain. By default B<xl> relies on ssh
as a transport
mechanism between the two hosts.
N.B: Remus support in xl is still in experimental (proof-of-concept) phase.
- There is no support for network or disk buffering at the moment.
+ There is no support for disk buffering at the moment.
B<OPTIONS>
@@ -455,6 +455,11 @@ If empty, run <host> instead of ssh <host> xl
migrate-receive -r [-e].
On the new host, do not wait in the background (on <host>) for the death
of the domain. See the corresponding option of the I<create> subcommand.
+=item B<-N> I<netbufscript>
+
+Use <netbufscript> to setup network buffering instead of the
+default script (/etc/xen/scripts/remus-netbuf-setup).
+
=item B<-F>
Run Remus in unsafe mode. Use this option with caution as failover may
@@ -465,6 +470,10 @@ not work as intended.
Replicate memory checkpoints to /dev/null (blackhole).
Generally useful for debugging. Requires enabling unsafe mode.
+=item B<-n>
+
+Disable network output buffering. Requires enabling unsafe mode.
+
=back
=item B<pause> I<domain-id>
diff --git a/tools/libxl/libxl.c b/tools/libxl/libxl.c
index 6e488ca..b329a04 100644
--- a/tools/libxl/libxl.c
+++ b/tools/libxl/libxl.c
@@ -797,8 +797,9 @@ int libxl_domain_remus_start(libxl_ctx *ctx,
libxl_domain_remus_info *info,
libxl__domain_suspend_state *dss;
int rc;
- if (!info->unsafe && info->blackhole) {
- LOG(ERROR, "Unsafe mode must be enabled to replicate to /dev/null");
+ if (!info->unsafe && (info->blackhole || !info->netbuf)) {
+ LOG(ERROR, "Unsafe mode must be enabled to replicate to /dev/null and "
+ "disable network buffering");
goto out;
}
@@ -824,11 +825,14 @@ int libxl_domain_remus_start(libxl_ctx *ctx,
libxl_domain_remus_info *info,
/* Convenience aliases */
libxl__remus_devices_state *const rds = &dss->rds;
- if (!libxl__netbuffer_enabled(gc)) {
- LOG(ERROR, "Remus: No support for network buffering");
- goto out;
+ if (info->netbuf) {
+ if (!libxl__netbuffer_enabled(gc)) {
+ LOG(ERROR, "Remus: No support for network buffering");
+ goto out;
+ }
+ rds->device_kind_flags |= LIBXL__REMUS_DEVICE_NIC;
}
- rds->device_kind_flags |= LIBXL__REMUS_DEVICE_NIC;
+
rds->device_kind_flags |= LIBXL__REMUS_DEVICE_DISK;
rds->ao = ao;
diff --git a/tools/libxl/libxl_netbuffer.c b/tools/libxl/libxl_netbuffer.c
index 5093e0d..e1d02af 100644
--- a/tools/libxl/libxl_netbuffer.c
+++ b/tools/libxl/libxl_netbuffer.c
@@ -43,6 +43,7 @@ int libxl__netbuffer_enabled(libxl__gc *gc)
static int nic_init(libxl__remus_devices_state *rds)
{
int rc, ret;
+ libxl__domain_suspend_state *dss = CONTAINER_OF(rds, *dss, rds);
STATE_AO_GC(rds->ao);
@@ -70,8 +71,12 @@ static int nic_init(libxl__remus_devices_state *rds)
goto out;
}
- rds->netbufscript = GCSPRINTF("%s/remus-netbuf-setup",
- libxl__xen_script_dir_path());
+ if (dss->remus->netbufscript) {
+ rds->netbufscript = libxl__strdup(gc, dss->remus->netbufscript);
+ } else {
+ rds->netbufscript = GCSPRINTF("%s/remus-netbuf-setup",
+ libxl__xen_script_dir_path());
+ }
rc = 0;
diff --git a/tools/libxl/libxl_types.idl b/tools/libxl/libxl_types.idl
index f4cff51..78dcee6 100644
--- a/tools/libxl/libxl_types.idl
+++ b/tools/libxl/libxl_types.idl
@@ -591,6 +591,8 @@ libxl_domain_remus_info = Struct("domain_remus_info",[
("unsafe", bool),
("blackhole", bool),
("compression", bool),
+ ("netbuf", bool),
+ ("netbufscript", string),
])
libxl_event_type = Enumeration("event_type", [
diff --git a/tools/libxl/xl.c b/tools/libxl/xl.c
index 4c5a5ee..f014306 100644
--- a/tools/libxl/xl.c
+++ b/tools/libxl/xl.c
@@ -44,6 +44,7 @@ char *default_vifscript = NULL;
char *default_bridge = NULL;
char *default_gatewaydev = NULL;
char *default_vifbackend = NULL;
+char *default_remus_netbufscript = NULL;
enum output_format default_output_format = OUTPUT_FORMAT_JSON;
int claim_mode = 1;
bool progress_use_cr = 0;
@@ -176,6 +177,9 @@ static void parse_global_config(const char *configfile,
if (!xlu_cfg_get_long (config, "claim_mode", &l, 0))
claim_mode = l;
+ xlu_cfg_replace_string (config, "remus.default.netbufscript",
+ &default_remus_netbufscript, 0);
+
xlu_cfg_destroy(config);
}
diff --git a/tools/libxl/xl.h b/tools/libxl/xl.h
index 10a2e66..087eb8c 100644
--- a/tools/libxl/xl.h
+++ b/tools/libxl/xl.h
@@ -170,6 +170,7 @@ extern char *default_vifscript;
extern char *default_bridge;
extern char *default_gatewaydev;
extern char *default_vifbackend;
+extern char *default_remus_netbufscript;
extern char *blkdev_start;
enum output_format {
diff --git a/tools/libxl/xl_cmdimpl.c b/tools/libxl/xl_cmdimpl.c
index 3234d45..ea77116 100644
--- a/tools/libxl/xl_cmdimpl.c
+++ b/tools/libxl/xl_cmdimpl.c
@@ -7178,8 +7178,9 @@ int main_remus(int argc, char **argv)
r_info.unsafe = 0;
r_info.blackhole = 0;
r_info.compression = 1;
+ r_info.netbuf = 1;
- SWITCH_FOREACH_OPT(opt, "Fbui:s:e", NULL, "remus", 2) {
+ SWITCH_FOREACH_OPT(opt, "Fbuni:s:N:e", NULL, "remus", 2) {
case 'i':
r_info.interval = atoi(optarg);
break;
@@ -7192,6 +7193,12 @@ int main_remus(int argc, char **argv)
case 'u':
r_info.compression = 0;
break;
+ case 'n':
+ r_info.netbuf = 0;
+ break;
+ case 'N':
+ r_info.netbufscript = optarg;
+ break;
case 's':
ssh_command = optarg;
break;
@@ -7200,14 +7207,18 @@ int main_remus(int argc, char **argv)
break;
}
- if (!r_info.unsafe && r_info.blackhole) {
- perror("Unsafe mode must be enabled to replicate to /dev/null");
+ if (!r_info.unsafe && (r_info.blackhole || !r_info.netbuf)) {
+ perror("Unsafe mode must be enabled to replicate to /dev/null and "
+ "disable network buffering");
exit(-1);
}
domid = find_domain(argv[optind]);
host = argv[optind + 1];
+ if (!r_info.netbufscript)
+ r_info.netbufscript = default_remus_netbufscript;
+
if (r_info.blackhole) {
send_fd = open("/dev/null", O_RDWR, 0644);
if (send_fd < 0) {
@@ -7245,13 +7256,19 @@ int main_remus(int argc, char **argv)
/* Point of no return */
rc = libxl_domain_remus_start(ctx, &r_info, domid, send_fd, recv_fd, 0);
- /* If we are here, it means backup has failed/domain suspend failed.
- * Try to resume the domain and exit gracefully.
- * TODO: Split-Brain check.
+ /* check if the domain exists. User may have xl destroyed the
+ * domain to force failover
*/
- fprintf(stderr, "remus sender: libxl_domain_suspend failed"
- " (rc=%d)\n", rc);
+ if (libxl_domain_info(ctx, 0, domid)) {
+ fprintf(stderr, "Remus: Primary domain has been destroyed.\n");
+ close(send_fd);
+ return 0;
+ }
+ /* If we are here, it means remus setup/domain suspend/backup has
+ * failed. Try to resume the domain and exit gracefully.
+ * TODO: Split-Brain check.
+ */
if (rc == ERROR_GUEST_TIMEDOUT)
fprintf(stderr, "Failed to suspend domain at primary.\n");
else {
diff --git a/tools/libxl/xl_cmdtable.c b/tools/libxl/xl_cmdtable.c
index 1e24f1d..808f400 100644
--- a/tools/libxl/xl_cmdtable.c
+++ b/tools/libxl/xl_cmdtable.c
@@ -491,10 +491,13 @@ struct cmd_spec cmd_table[] = {
" ssh <host> xl migrate-receive -r [-e]\n"
"-e Do not wait in the background (on <host>) for
the death\n"
" of the domain.\n"
- "-F Enable unsafe configurations [-b flags]. Use
this option\n"
+ "-N <netbufscript> Use netbufscript to setup network buffering
instead of the\n"
+ " default script
(/etc/xen/scripts/remus-netbuf-setup).\n"
+ "-F Enable unsafe configurations [-b|-n flags]. Use
this option\n"
" with caution as failover may not work as
intended.\n"
"-b Replicate memory checkpoints to /dev/null
(blackhole).\n"
- " Works only in unsafe mode."
+ " Works only in unsafe mode.\n"
+ "-n Disable network output buffering. Works only in
unsafe mode."
},
#endif
{ "devd",
--
1.9.1
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel
|
 |
Lists.xenproject.org is hosted with RackSpace, monitoring our |