[PATCH v20210616 31/36] tools: add --max_iters to libxl_domain_suspend

[Olaf Hering <olaf@xxxxxxxxx>]

Migrating a large, and potentially busy, domU will take more
time than neccessary due to excessive number of copying iterations.

Allow to host admin to control the number of iterations which
copy cumulated domU dirty pages to the target host.

The default remains 5, which means one initial iteration to copy the
entire domU memory, and up to 4 additional iterations to copy dirty
memory from the still running domU. After the given number of iterations
the domU is suspended, remaining dirty memory is copied and the domU is
finally moved to the target host.

This patch adjusts xl(1) and the libxl API.
External users check LIBXL_HAVE_DOMAIN_SUSPEND_PROPS for the availibility
of the new .max_iters property.

Signed-off-by: Olaf Hering <olaf@xxxxxxxxx>
---
 docs/man/xl.1.pod.in              |  4 ++++
 tools/include/libxl.h             |  1 +
 tools/libs/light/libxl_dom_save.c |  2 +-
 tools/libs/light/libxl_domain.c   |  1 +
 tools/libs/light/libxl_internal.h |  1 +
 tools/xl/xl_cmdtable.c            |  3 ++-
 tools/xl/xl_migrate.c             | 10 +++++++++-
 7 files changed, 19 insertions(+), 3 deletions(-)

diff --git a/docs/man/xl.1.pod.in b/docs/man/xl.1.pod.in
index 70a6ebf438..594387bcf4 100644
--- a/docs/man/xl.1.pod.in
+++ b/docs/man/xl.1.pod.in
@@ -494,6 +494,10 @@ such that it will be identical on the destination host, 
unless that
 configuration is overridden using the B<-C> option. Note that it is not
 possible to use this option for a 'localhost' migration.
 
+=item B<--max_iters> I<iterations>
+
+Number of copy iterations before final suspend+move (default: 5)
+
 =back
 
 =item B<remus> [I<OPTIONS>] I<domain-id> I<host>
diff --git a/tools/include/libxl.h b/tools/include/libxl.h
index 9a4d7514ed..bf77da0524 100644
--- a/tools/include/libxl.h
+++ b/tools/include/libxl.h
@@ -1714,6 +1714,7 @@ static inline int 
libxl_retrieve_domain_configuration_0x041200(
 
 typedef struct {
     uint32_t flags; /* LIBXL_SUSPEND_* */
+    uint32_t max_iters;
 } libxl_domain_suspend_props;
 #define LIBXL_SUSPEND_DEBUG 1
 #define LIBXL_SUSPEND_LIVE 2
diff --git a/tools/libs/light/libxl_dom_save.c 
b/tools/libs/light/libxl_dom_save.c
index 3f3cff0342..938c0127f3 100644
--- a/tools/libs/light/libxl_dom_save.c
+++ b/tools/libs/light/libxl_dom_save.c
@@ -383,7 +383,7 @@ static int 
libxl__domain_save_precopy_policy(precopy_stats_t stats, void *user)
          stats.iteration, stats.dirty_count, stats.total_written);
     if (stats.dirty_count >= 0 && stats.dirty_count < 
LIBXL_XGS_POLICY_TARGET_DIRTY_COUNT)
         goto stop_copy;
-    if (stats.iteration >= LIBXL_XGS_POLICY_MAX_ITERATIONS)
+    if (stats.iteration >= dss->max_iters)
         goto stop_copy;
     return XGS_POLICY_CONTINUE_PRECOPY;
 
diff --git a/tools/libs/light/libxl_domain.c b/tools/libs/light/libxl_domain.c
index 5dbd27900f..9f98cd7f2b 100644
--- a/tools/libs/light/libxl_domain.c
+++ b/tools/libs/light/libxl_domain.c
@@ -527,6 +527,7 @@ int libxl_domain_suspend(libxl_ctx *ctx, uint32_t domid, 
int fd,
     dss->domid = domid;
     dss->fd = fd;
     dss->type = type;
+    dss->max_iters = props->max_iters ?: LIBXL_XGS_POLICY_MAX_ITERATIONS;
     dss->live = props->flags & LIBXL_SUSPEND_LIVE;
     dss->debug = props->flags & LIBXL_SUSPEND_DEBUG;
     dss->checkpointed_stream = LIBXL_CHECKPOINTED_STREAM_NONE;
diff --git a/tools/libs/light/libxl_internal.h 
b/tools/libs/light/libxl_internal.h
index 57d7e4b4b8..8cbcc5282c 100644
--- a/tools/libs/light/libxl_internal.h
+++ b/tools/libs/light/libxl_internal.h
@@ -3649,6 +3649,7 @@ struct libxl__domain_save_state {
     int live;
     int debug;
     int checkpointed_stream;
+    uint32_t max_iters;
     const libxl_domain_remus_info *remus;
     /* private */
     int rc;
diff --git a/tools/xl/xl_cmdtable.c b/tools/xl/xl_cmdtable.c
index ca1dfa3525..9b6b3c99aa 100644
--- a/tools/xl/xl_cmdtable.c
+++ b/tools/xl/xl_cmdtable.c
@@ -174,7 +174,8 @@ const struct cmd_spec cmd_table[] = {
       "                of the domain.\n"
       "--debug         Ignored.\n"
       "-p              Do not unpause domain after migrating it.\n"
-      "-D              Preserve the domain id"
+      "-D              Preserve the domain id\n"
+      "--max_iters N   Number of copy iterations before final stop+move"
     },
     { "restore",
       &main_restore, 0, 1,
diff --git a/tools/xl/xl_migrate.c b/tools/xl/xl_migrate.c
index 144890924f..af117d4d56 100644
--- a/tools/xl/xl_migrate.c
+++ b/tools/xl/xl_migrate.c
@@ -178,6 +178,7 @@ static void migrate_do_preamble(int send_fd, int recv_fd, 
pid_t child,
 
 static void migrate_domain(uint32_t domid, int preserve_domid,
                            const char *rune, int debug,
+                           uint32_t max_iters,
                            const char *override_config_file)
 {
     pid_t child = -1;
@@ -189,6 +190,7 @@ static void migrate_domain(uint32_t domid, int 
preserve_domid,
     int config_len;
     libxl_domain_suspend_props props = {
         .flags = LIBXL_SUSPEND_LIVE,
+        .max_iters = max_iters,
         };
 
     save_domain_core_begin(domid, preserve_domid, override_config_file,
@@ -542,8 +544,10 @@ int main_migrate(int argc, char **argv)
     char *host;
     int opt, daemonize = 1, monitor = 1, debug = 0, pause_after_migration = 0;
     int preserve_domid = 0;
+    uint32_t max_iters = 0;
     static struct option opts[] = {
         {"debug", 0, 0, 0x100},
+        {"max_iters", 1, 0, 0x101},
         {"live", 0, 0, 0x200},
         COMMON_LONG_OPTS
     };
@@ -571,6 +575,9 @@ int main_migrate(int argc, char **argv)
     case 0x100: /* --debug */
         debug = 1;
         break;
+    case 0x101: /* --max_iters */
+        max_iters = atoi(optarg);
+        break;
     case 0x200: /* --live */
         /* ignored for compatibility with xm */
         break;
@@ -605,7 +612,8 @@ int main_migrate(int argc, char **argv)
                   pause_after_migration ? " -p" : "");
     }
 
-    migrate_domain(domid, preserve_domid, rune, debug, config_filename);
+    migrate_domain(domid, preserve_domid, rune, debug,
+                   max_iters, config_filename);
     return EXIT_SUCCESS;
 }