qemu-kvm/SOURCES/kvm-migration-Rate-limit-in...

173 lines
6.5 KiB
Diff

From 8e8f421cce99543081f225acf46541312cfbc371 Mon Sep 17 00:00:00 2001
From: Laurent Vivier <lvivier@redhat.com>
Date: Tue, 17 Mar 2020 17:05:18 +0000
Subject: [PATCH 1/2] migration: Rate limit inside host pages
RH-Author: Laurent Vivier <lvivier@redhat.com>
Message-id: <20200317170518.9303-1-lvivier@redhat.com>
Patchwork-id: 94374
O-Subject: [RHEL-AV-8.2.0 qemu-kvm PATCH] migration: Rate limit inside host pages
Bugzilla: 1814336
RH-Acked-by: Peter Xu <peterx@redhat.com>
RH-Acked-by: Juan Quintela <quintela@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
When using hugepages, rate limiting is necessary within each huge
page, since a 1G huge page can take a significant time to send, so
you end up with bursty behaviour.
Fixes: 4c011c37ecb3 ("postcopy: Send whole huge pages")
Reported-by: Lin Ma <LMa@suse.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit 97e1e06780e70f6e98a0d2df881e0c0927d3aeb6)
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
BZ: https://bugzilla.redhat.com/show_bug.cgi?id=1814336
BRANCH: rhel-av-8.2.0
UPSTREAM: Merged
BREW: https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=27283241
TESTED: Tested that the migration abort doesn't trigger an error message in
the kernel logs on P9
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
migration/migration.c | 57 ++++++++++++++++++++++++++++----------------------
migration/migration.h | 1 +
migration/ram.c | 2 ++
migration/trace-events | 4 ++--
4 files changed, 37 insertions(+), 27 deletions(-)
diff --git a/migration/migration.c b/migration/migration.c
index ed18c59..e31d0f5 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -3253,6 +3253,37 @@ void migration_consume_urgent_request(void)
qemu_sem_wait(&migrate_get_current()->rate_limit_sem);
}
+/* Returns true if the rate limiting was broken by an urgent request */
+bool migration_rate_limit(void)
+{
+ int64_t now = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
+ MigrationState *s = migrate_get_current();
+
+ bool urgent = false;
+ migration_update_counters(s, now);
+ if (qemu_file_rate_limit(s->to_dst_file)) {
+ /*
+ * Wait for a delay to do rate limiting OR
+ * something urgent to post the semaphore.
+ */
+ int ms = s->iteration_start_time + BUFFER_DELAY - now;
+ trace_migration_rate_limit_pre(ms);
+ if (qemu_sem_timedwait(&s->rate_limit_sem, ms) == 0) {
+ /*
+ * We were woken by one or more urgent things but
+ * the timedwait will have consumed one of them.
+ * The service routine for the urgent wake will dec
+ * the semaphore itself for each item it consumes,
+ * so add this one we just eat back.
+ */
+ qemu_sem_post(&s->rate_limit_sem);
+ urgent = true;
+ }
+ trace_migration_rate_limit_post(urgent);
+ }
+ return urgent;
+}
+
/*
* Master migration thread on the source VM.
* It drives the migration and pumps the data down the outgoing channel.
@@ -3319,8 +3350,6 @@ static void *migration_thread(void *opaque)
trace_migration_thread_setup_complete();
while (migration_is_active(s)) {
- int64_t current_time;
-
if (urgent || !qemu_file_rate_limit(s->to_dst_file)) {
MigIterateState iter_state = migration_iteration_run(s);
if (iter_state == MIG_ITERATE_SKIP) {
@@ -3347,29 +3376,7 @@ static void *migration_thread(void *opaque)
update_iteration_initial_status(s);
}
- current_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
-
- migration_update_counters(s, current_time);
-
- urgent = false;
- if (qemu_file_rate_limit(s->to_dst_file)) {
- /* Wait for a delay to do rate limiting OR
- * something urgent to post the semaphore.
- */
- int ms = s->iteration_start_time + BUFFER_DELAY - current_time;
- trace_migration_thread_ratelimit_pre(ms);
- if (qemu_sem_timedwait(&s->rate_limit_sem, ms) == 0) {
- /* We were worken by one or more urgent things but
- * the timedwait will have consumed one of them.
- * The service routine for the urgent wake will dec
- * the semaphore itself for each item it consumes,
- * so add this one we just eat back.
- */
- qemu_sem_post(&s->rate_limit_sem);
- urgent = true;
- }
- trace_migration_thread_ratelimit_post(urgent);
- }
+ urgent = migration_rate_limit();
}
trace_migration_thread_after_loop();
diff --git a/migration/migration.h b/migration/migration.h
index a2b2336..a15e8d8 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -347,5 +347,6 @@ extern bool migrate_pre_2_2;
void migration_make_urgent_request(void);
void migration_consume_urgent_request(void);
+bool migration_rate_limit(void);
#endif
diff --git a/migration/ram.c b/migration/ram.c
index 3891eff..5344c7d 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -2661,6 +2661,8 @@ static int ram_save_host_page(RAMState *rs, PageSearchStatus *pss,
pages += tmppages;
pss->page++;
+ /* Allow rate limiting to happen in the middle of huge pages */
+ migration_rate_limit();
} while ((pss->page & (pagesize_bits - 1)) &&
offset_in_ramblock(pss->block, pss->page << TARGET_PAGE_BITS));
diff --git a/migration/trace-events b/migration/trace-events
index 6dee7b5..2f9129e 100644
--- a/migration/trace-events
+++ b/migration/trace-events
@@ -138,12 +138,12 @@ migrate_send_rp_recv_bitmap(char *name, int64_t size) "block '%s' size 0x%"PRIi6
migration_completion_file_err(void) ""
migration_completion_postcopy_end(void) ""
migration_completion_postcopy_end_after_complete(void) ""
+migration_rate_limit_pre(int ms) "%d ms"
+migration_rate_limit_post(int urgent) "urgent: %d"
migration_return_path_end_before(void) ""
migration_return_path_end_after(int rp_error) "%d"
migration_thread_after_loop(void) ""
migration_thread_file_err(void) ""
-migration_thread_ratelimit_pre(int ms) "%d ms"
-migration_thread_ratelimit_post(int urgent) "urgent: %d"
migration_thread_setup_complete(void) ""
open_return_path_on_source(void) ""
open_return_path_on_source_continue(void) ""
--
1.8.3.1