qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Zhang Chen <zhangckid@gmail.com>
To: qemu-devel@nongnu.org, Paolo Bonzini <pbonzini@redhat.com>,
	Juan Quintela <quintela@redhat.com>,
	"Dr . David Alan Gilbert" <dgilbert@redhat.com>,
	Jason Wang <jasowang@redhat.com>, Eric Blake <eblake@redhat.com>,
	Markus Armbruster <armbru@redhat.com>
Cc: Zhang Chen <zhangckid@gmail.com>,
	zhanghailiang <zhang.zhanghailiang@huawei.com>,
	Li Zhijian <lizhijian@cn.fujitsu.com>
Subject: [Qemu-devel] [PATCH V11 09/20] COLO: Flush memory data from ram cache
Date: Sun, 12 Aug 2018 04:59:13 +0800	[thread overview]
Message-ID: <20180811205924.4113-10-zhangckid@gmail.com> (raw)
In-Reply-To: <20180811205924.4113-1-zhangckid@gmail.com>

During the time of VM's running, PVM may dirty some pages, we will transfer
PVM's dirty pages to SVM and store them into SVM's RAM cache at next checkpoint
time. So, the content of SVM's RAM cache will always be same with PVM's memory
after checkpoint.

Instead of flushing all content of PVM's RAM cache into SVM's MEMORY,
we do this in a more efficient way:
Only flush any page that dirtied by PVM since last checkpoint.
In this way, we can ensure SVM's memory same with PVM's.

Besides, we must ensure flush RAM cache before load device state.

Signed-off-by: zhanghailiang <zhang.zhanghailiang@huawei.com>
Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
---
 migration/ram.c        | 37 +++++++++++++++++++++++++++++++++++++
 migration/trace-events |  2 ++
 2 files changed, 39 insertions(+)

diff --git a/migration/ram.c b/migration/ram.c
index 3dc403adb5..b4cbcf783f 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -3841,6 +3841,39 @@ static bool postcopy_is_running(void)
     return ps >= POSTCOPY_INCOMING_LISTENING && ps < POSTCOPY_INCOMING_END;
 }
 
+/*
+ * Flush content of RAM cache into SVM's memory.
+ * Only flush the pages that be dirtied by PVM or SVM or both.
+ */
+static void colo_flush_ram_cache(void)
+{
+    RAMBlock *block = NULL;
+    void *dst_host;
+    void *src_host;
+    unsigned long offset = 0;
+
+    trace_colo_flush_ram_cache_begin(ram_state->migration_dirty_pages);
+    rcu_read_lock();
+    block = QLIST_FIRST_RCU(&ram_list.blocks);
+
+    while (block) {
+        offset = migration_bitmap_find_dirty(ram_state, block, offset);
+
+        if (offset << TARGET_PAGE_BITS >= block->used_length) {
+            offset = 0;
+            block = QLIST_NEXT_RCU(block, next);
+        } else {
+            migration_bitmap_clear_dirty(ram_state, block, offset);
+            dst_host = block->host + (offset << TARGET_PAGE_BITS);
+            src_host = block->colo_cache + (offset << TARGET_PAGE_BITS);
+            memcpy(dst_host, src_host, TARGET_PAGE_SIZE);
+        }
+    }
+
+    rcu_read_unlock();
+    trace_colo_flush_ram_cache_end();
+}
+
 static int ram_load(QEMUFile *f, void *opaque, int version_id)
 {
     int flags = 0, ret = 0, invalid_flags = 0;
@@ -4017,6 +4050,10 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
     ret |= wait_for_decompress_done();
     rcu_read_unlock();
     trace_ram_load_complete(ret, seq_iter);
+
+    if (!ret  && migration_incoming_in_colo_state()) {
+        colo_flush_ram_cache();
+    }
     return ret;
 }
 
diff --git a/migration/trace-events b/migration/trace-events
index fa0ff3f3bf..bd2d0cd25a 100644
--- a/migration/trace-events
+++ b/migration/trace-events
@@ -102,6 +102,8 @@ ram_dirty_bitmap_sync_start(void) ""
 ram_dirty_bitmap_sync_wait(void) ""
 ram_dirty_bitmap_sync_complete(void) ""
 ram_state_resume_prepare(uint64_t v) "%" PRId64
+colo_flush_ram_cache_begin(uint64_t dirty_pages) "dirty_pages %" PRIu64
+colo_flush_ram_cache_end(void) ""
 
 # migration/migration.c
 await_return_path_close_on_source_close(void) ""
-- 
2.17.GIT

  parent reply	other threads:[~2018-08-11 21:00 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-08-11 20:59 [Qemu-devel] [PATCH V11 00/20] COLO: integrate colo frame with block replication and COLO proxy Zhang Chen
2018-08-11 20:59 ` [Qemu-devel] [PATCH V11 01/20] filter-rewriter: Add TCP state machine and fix memory leak in connection_track_table Zhang Chen
2018-08-11 20:59 ` [Qemu-devel] [PATCH V11 02/20] colo-compare: implement the process of checkpoint Zhang Chen
2018-08-11 20:59 ` [Qemu-devel] [PATCH V11 03/20] colo-compare: use notifier to notify packets comparing result Zhang Chen
2018-08-11 20:59 ` [Qemu-devel] [PATCH V11 04/20] COLO: integrate colo compare with colo frame Zhang Chen
2018-08-11 20:59 ` [Qemu-devel] [PATCH V11 05/20] COLO: Add block replication into colo process Zhang Chen
2018-08-17 11:04   ` Dr. David Alan Gilbert
2018-08-11 20:59 ` [Qemu-devel] [PATCH V11 06/20] COLO: Remove colo_state migration struct Zhang Chen
2018-08-11 20:59 ` [Qemu-devel] [PATCH V11 07/20] COLO: Load dirty pages into SVM's RAM cache firstly Zhang Chen
2018-08-11 20:59 ` [Qemu-devel] [PATCH V11 08/20] ram/COLO: Record the dirty pages that SVM received Zhang Chen
2018-08-11 20:59 ` Zhang Chen [this message]
2018-08-11 20:59 ` [Qemu-devel] [PATCH V11 10/20] qmp event: Add COLO_EXIT event to notify users while exited COLO Zhang Chen
2018-08-11 20:59 ` [Qemu-devel] [PATCH V11 11/20] qapi/migration.json: Rename COLO unknown mode to none mode Zhang Chen
2018-08-11 20:59 ` [Qemu-devel] [PATCH V11 12/20] qapi: Add new command to query colo status Zhang Chen
2018-08-11 20:59 ` [Qemu-devel] [PATCH V11 13/20] savevm: split the process of different stages for loadvm/savevm Zhang Chen
2018-08-11 20:59 ` [Qemu-devel] [PATCH V11 14/20] COLO: flush host dirty ram from cache Zhang Chen
2018-08-11 20:59 ` [Qemu-devel] [PATCH V11 15/20] net/net.c: Add net client type check function for COLO Zhang Chen
2018-08-21  3:26   ` Jason Wang
2018-08-21  9:26     ` Zhang Chen
2018-08-22  8:22       ` Jason Wang
2018-08-23  9:37         ` Zhang Chen
2018-08-11 20:59 ` [Qemu-devel] [PATCH V11 16/20] filter: Add handle_event method for NetFilterClass Zhang Chen
2018-08-21  3:30   ` Jason Wang
2018-08-21  9:25     ` Zhang Chen
2018-08-22  8:21       ` Jason Wang
2018-08-24  5:57         ` Zhang Chen
2018-08-28  7:19           ` Jason Wang
2018-08-30  5:56             ` Zhang Chen
2018-08-11 20:59 ` [Qemu-devel] [PATCH V11 17/20] filter-rewriter: handle checkpoint and failover event Zhang Chen
2018-08-21  3:40   ` Jason Wang
2018-08-21  9:51     ` Zhang Chen
2018-08-11 20:59 ` [Qemu-devel] [PATCH V11 18/20] COLO: notify net filters about checkpoint/failover event Zhang Chen
2018-08-11 20:59 ` [Qemu-devel] [PATCH V11 19/20] COLO: quick failover process by kick COLO thread Zhang Chen
2018-08-11 20:59 ` [Qemu-devel] [PATCH V11 20/20] docs: Add COLO status diagram to COLO-FT.txt Zhang Chen
2018-08-21  3:06 ` [Qemu-devel] [PATCH V11 00/20] COLO: integrate colo frame with block replication and COLO proxy Zhang Chen

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20180811205924.4113-10-zhangckid@gmail.com \
    --to=zhangckid@gmail.com \
    --cc=armbru@redhat.com \
    --cc=dgilbert@redhat.com \
    --cc=eblake@redhat.com \
    --cc=jasowang@redhat.com \
    --cc=lizhijian@cn.fujitsu.com \
    --cc=pbonzini@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=quintela@redhat.com \
    --cc=zhang.zhanghailiang@huawei.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).