qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: mrhines@linux.vnet.ibm.com
To: qemu-devel@nongnu.org
Cc: GILR@il.ibm.com, SADEKJ@il.ibm.com, pbonzini@redhat.com,
	quintela@redhat.com, EREZH@il.ibm.com, owasserm@redhat.com,
	junqing.wang@cs2c.com.cn, onom@us.ibm.com, abali@us.ibm.com,
	isaku.yamahata@gmail.com, gokul@us.ibm.com, dbulkow@gmail.com,
	hinesmr@cn.ibm.com, BIRAN@il.ibm.com, lig.fnst@cn.fujitsu.com,
	"Michael R. Hines" <mrhines@us.ibm.com>
Subject: [Qemu-devel] [RFC PATCH v2 02/12] mc: timestamp migration_bitmap and KVM logdirty usage
Date: Tue, 18 Feb 2014 16:50:19 +0800	[thread overview]
Message-ID: <1392713429-18201-3-git-send-email-mrhines@linux.vnet.ibm.com> (raw)
In-Reply-To: <1392713429-18201-1-git-send-email-mrhines@linux.vnet.ibm.com>

From: "Michael R. Hines" <mrhines@us.ibm.com>

We also later export these statistics over QMP for better
monitoring of micro-checkpointing as the workload changes.

Signed-off-by: Michael R. Hines <mrhines@us.ibm.com>
---
 arch_init.c | 34 ++++++++++++++++++++++++++++------
 1 file changed, 28 insertions(+), 6 deletions(-)

diff --git a/arch_init.c b/arch_init.c
index 80574a0..b8364b0 100644
--- a/arch_init.c
+++ b/arch_init.c
@@ -193,6 +193,8 @@ typedef struct AccountingInfo {
     uint64_t skipped_pages;
     uint64_t norm_pages;
     uint64_t iterations;
+    uint64_t log_dirty_time;
+    uint64_t migration_bitmap_time;
     uint64_t xbzrle_bytes;
     uint64_t xbzrle_pages;
     uint64_t xbzrle_cache_miss;
@@ -201,7 +203,7 @@ typedef struct AccountingInfo {
 
 static AccountingInfo acct_info;
 
-static void acct_clear(void)
+void acct_clear(void)
 {
     memset(&acct_info, 0, sizeof(acct_info));
 }
@@ -236,6 +238,16 @@ uint64_t norm_mig_pages_transferred(void)
     return acct_info.norm_pages;
 }
 
+uint64_t norm_mig_log_dirty_time(void)
+{
+    return acct_info.log_dirty_time;
+}
+
+uint64_t norm_mig_bitmap_time(void)
+{
+    return acct_info.migration_bitmap_time;
+}
+
 uint64_t xbzrle_mig_bytes_transferred(void)
 {
     return acct_info.xbzrle_bytes;
@@ -426,27 +438,35 @@ static void migration_bitmap_sync(void)
     static int64_t num_dirty_pages_period;
     int64_t end_time;
     int64_t bytes_xfer_now;
+    int64_t begin_time;
+    int64_t dirty_time;
 
     if (!bytes_xfer_prev) {
         bytes_xfer_prev = ram_bytes_transferred();
     }
 
+    begin_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
     if (!start_time) {
         start_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
     }
-
     trace_migration_bitmap_sync_start();
     address_space_sync_dirty_bitmap(&address_space_memory);
 
+    dirty_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
+
     QTAILQ_FOREACH(block, &ram_list.blocks, next) {
         migration_bitmap_sync_range(block->mr->ram_addr, block->length);
     }
+
     trace_migration_bitmap_sync_end(migration_dirty_pages
                                     - num_dirty_pages_init);
     num_dirty_pages_period += migration_dirty_pages - num_dirty_pages_init;
     end_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
 
-    /* more than 1 second = 1000 millisecons */
+    acct_info.log_dirty_time += dirty_time - begin_time;
+    acct_info.migration_bitmap_time += end_time - dirty_time;
+
+    /* more than 1 second = 1000 milliseconds */
     if (end_time > start_time + 1000) {
         if (migrate_auto_converge()) {
             /* The following detection logic can be refined later. For now:
@@ -548,9 +568,11 @@ static int ram_save_block(QEMUFile *f, bool last_stage)
             /* XBZRLE overflow or normal page */
             if (bytes_sent == -1) {
                 bytes_sent = save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_PAGE);
-                qemu_put_buffer_async(f, p, TARGET_PAGE_SIZE);
-                bytes_sent += TARGET_PAGE_SIZE;
-                acct_info.norm_pages++;
+                if (ret != RAM_SAVE_CONTROL_DELAYED) {
+                    qemu_put_buffer_async(f, p, TARGET_PAGE_SIZE);
+                    bytes_sent += TARGET_PAGE_SIZE;
+                    acct_info.norm_pages++;
+                }
             }
 
             /* if page is unmodified, continue to the next */
-- 
1.8.1.2

  parent reply	other threads:[~2014-02-18  8:51 UTC|newest]

Thread overview: 68+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-02-18  8:50 [Qemu-devel] [RFC PATCH v2 00/12] mc: fault tolerante through micro-checkpointing mrhines
2014-02-18  8:50 ` [Qemu-devel] [RFC PATCH v2 01/12] mc: add documentation for micro-checkpointing mrhines
2014-02-18 12:45   ` Dr. David Alan Gilbert
2014-02-19  1:40     ` Michael R. Hines
2014-02-19 11:27       ` Dr. David Alan Gilbert
2014-02-20  1:17         ` Michael R. Hines
2014-02-20 10:09           ` Dr. David Alan Gilbert
2014-02-20 11:14             ` Li Guang
2014-02-20 14:58               ` Michael R. Hines
2014-02-20 14:57             ` Michael R. Hines
2014-02-20 16:32               ` Dr. David Alan Gilbert
2014-02-21  4:54                 ` Michael R. Hines
2014-02-21  9:44                   ` Dr. David Alan Gilbert
2014-03-03  6:08                     ` Michael R. Hines
2014-02-18  8:50 ` mrhines [this message]
2014-02-18 10:32   ` [Qemu-devel] [RFC PATCH v2 02/12] mc: timestamp migration_bitmap and KVM logdirty usage Dr. David Alan Gilbert
2014-02-19  1:42     ` Michael R. Hines
2014-03-11 21:31   ` Juan Quintela
2014-04-04  3:08     ` Michael R. Hines
2014-02-18  8:50 ` [Qemu-devel] [RFC PATCH v2 03/12] mc: introduce a 'checkpointing' status check into the VCPU states mrhines
2014-03-11 21:36   ` Juan Quintela
2014-04-04  3:11     ` Michael R. Hines
2014-03-11 21:40   ` Eric Blake
2014-04-04  3:12     ` Michael R. Hines
2014-02-18  8:50 ` [Qemu-devel] [RFC PATCH v2 04/12] mc: support custom page loading and copying mrhines
2014-02-18  8:50 ` [Qemu-devel] [RFC PATCH v2 05/12] rdma: accelerated memcpy() support and better external RDMA user interfaces mrhines
2014-02-18  8:50 ` [Qemu-devel] [RFC PATCH v2 06/12] mc: introduce state machine changes for MC mrhines
2014-02-19  1:00   ` Li Guang
2014-02-19  2:14     ` Michael R. Hines
2014-02-20  5:03     ` Michael R. Hines
2014-02-21  8:13     ` Michael R. Hines
2014-02-24  6:48       ` Li Guang
2014-02-26  2:52         ` Li Guang
2014-03-11 21:57   ` Juan Quintela
2014-04-04  3:50     ` Michael R. Hines
2014-02-18  8:50 ` [Qemu-devel] [RFC PATCH v2 07/12] mc: introduce additional QMP statistics for micro-checkpointing mrhines
2014-03-11 21:45   ` Eric Blake
2014-04-04  3:15     ` Michael R. Hines
2014-04-04  4:22       ` Eric Blake
2014-03-11 21:59   ` Juan Quintela
2014-04-04  3:55     ` Michael R. Hines
2014-02-18  8:50 ` [Qemu-devel] [RFC PATCH v2 08/12] mc: core logic mrhines
2014-02-19  1:07   ` Li Guang
2014-02-19  2:16     ` Michael R. Hines
2014-02-19  2:53       ` Li Guang
2014-02-19  4:27         ` Michael R. Hines
2014-02-18  8:50 ` [Qemu-devel] [RFC PATCH v2 09/12] mc: configure and makefile support mrhines
2014-02-18  8:50 ` [Qemu-devel] [RFC PATCH v2 10/12] mc: expose tunable parameter for checkpointing frequency mrhines
2014-03-11 21:49   ` Eric Blake
2014-03-11 22:15     ` Juan Quintela
2014-03-11 22:49       ` Eric Blake
2014-04-04  5:29         ` Michael R. Hines
2014-04-04 14:56           ` Eric Blake
2014-04-11  6:10             ` Michael R. Hines
2014-04-04 16:28           ` Dr. David Alan Gilbert
2014-04-04 16:35             ` Eric Blake
2014-04-04  3:29     ` Michael R. Hines
2014-02-18  8:50 ` [Qemu-devel] [RFC PATCH v2 11/12] mc: introduce new capabilities to control micro-checkpointing mrhines
2014-03-11 21:57   ` Eric Blake
2014-04-04  3:38     ` Michael R. Hines
2014-04-04  4:25       ` Eric Blake
2014-03-11 22:02   ` Juan Quintela
2014-03-11 22:07     ` Eric Blake
2014-04-04  3:57       ` Michael R. Hines
2014-04-04  3:56     ` Michael R. Hines
2014-02-18  8:50 ` [Qemu-devel] [RFC PATCH v2 12/12] mc: activate and use MC if requested mrhines
2014-02-18  9:28 ` [Qemu-devel] [RFC PATCH v2 00/12] mc: fault tolerante through micro-checkpointing Li Guang
2014-02-19  1:29   ` Michael R. Hines

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=1392713429-18201-3-git-send-email-mrhines@linux.vnet.ibm.com \
    --to=mrhines@linux.vnet.ibm.com \
    --cc=BIRAN@il.ibm.com \
    --cc=EREZH@il.ibm.com \
    --cc=GILR@il.ibm.com \
    --cc=SADEKJ@il.ibm.com \
    --cc=abali@us.ibm.com \
    --cc=dbulkow@gmail.com \
    --cc=gokul@us.ibm.com \
    --cc=hinesmr@cn.ibm.com \
    --cc=isaku.yamahata@gmail.com \
    --cc=junqing.wang@cs2c.com.cn \
    --cc=lig.fnst@cn.fujitsu.com \
    --cc=mrhines@us.ibm.com \
    --cc=onom@us.ibm.com \
    --cc=owasserm@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=quintela@redhat.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).