xen-devel.lists.xenproject.org archive mirror
 help / color / mirror / Atom feed
From: Yang Hongyang <yanghy@cn.fujitsu.com>
To: xen-devel@lists.xen.org
Cc: wei.liu2@citrix.com, ian.campbell@citrix.com,
	wency@cn.fujitsu.com, andrew.cooper3@citrix.com,
	yunhong.jiang@intel.com, eddie.dong@intel.com,
	guijianfeng@cn.fujitsu.com, rshriram@cs.ubc.ca,
	ian.jackson@eu.citrix.com
Subject: [PATCH v7 COLO 09/18] libxc/save: support COLO save
Date: Thu, 25 Jun 2015 14:31:03 +0800	[thread overview]
Message-ID: <1435213872-10698-10-git-send-email-yanghy@cn.fujitsu.com> (raw)
In-Reply-To: <1435213872-10698-1-git-send-email-yanghy@cn.fujitsu.com>

After suspend primary vm, get dirty bitmap on secondary vm,
and send pages both dirty on primary/secondary to secondary.

Signed-off-by: Yang Hongyang <yanghy@cn.fujitsu.com>
Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
CC: Andrew Cooper <andrew.cooper3@citrix.com>
---
 tools/libxc/xc_sr_common.h |   2 +
 tools/libxc/xc_sr_save.c   | 104 +++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 102 insertions(+), 4 deletions(-)

diff --git a/tools/libxc/xc_sr_common.h b/tools/libxc/xc_sr_common.h
index 01ee2e7..92d8da0 100644
--- a/tools/libxc/xc_sr_common.h
+++ b/tools/libxc/xc_sr_common.h
@@ -183,6 +183,8 @@ struct xc_sr_context
     {
         struct /* Save data. */
         {
+            int recv_fd;
+
             struct xc_sr_save_ops ops;
             struct save_callbacks *callbacks;
 
diff --git a/tools/libxc/xc_sr_save.c b/tools/libxc/xc_sr_save.c
index d12e5b1..6f13706 100644
--- a/tools/libxc/xc_sr_save.c
+++ b/tools/libxc/xc_sr_save.c
@@ -515,6 +515,58 @@ static int send_memory_live(struct xc_sr_context *ctx)
     return rc;
 }
 
+static int merge_secondary_dirty_bitmap(struct xc_sr_context *ctx)
+{
+    xc_interface *xch = ctx->xch;
+    struct xc_sr_record rec;
+    uint64_t *pfns = NULL;
+    uint64_t pfn;
+    unsigned count, i;
+    int rc;
+    DECLARE_HYPERCALL_BUFFER_SHADOW(unsigned long, dirty_bitmap,
+                                    &ctx->save.dirty_bitmap_hbuf);
+
+    rc = read_record(ctx, ctx->save.recv_fd, &rec);
+    if ( rc )
+        goto err;
+
+    if ( rec.type != REC_TYPE_DIRTY_BITMAP )
+    {
+        PERROR("Expect dirty bitmap record, but received %u", rec.type );
+        rc = -1;
+        goto err;
+    }
+
+    if ( rec.length % sizeof(*pfns) )
+    {
+        PERROR("Invalid dirty bitmap record length %u", rec.length );
+        rc = -1;
+        goto err;
+    }
+
+    count = rec.length / sizeof(*pfns);
+    pfns = rec.data;
+
+    for ( i = 0; i < count; i++ )
+    {
+        pfn = pfns[i];
+        if (pfn > ctx->save.p2m_size)
+        {
+            PERROR("Invalid pfn %#lx", pfn );
+            rc = -1;
+            goto err;
+        }
+
+        set_bit(pfn, dirty_bitmap);
+    }
+
+    rc = 0;
+
+ err:
+    free(rec.data);
+    return rc;
+}
+
 /*
  * Suspend the domain and send dirty memory.
  * This is the last iteration of the live migration and the
@@ -555,6 +607,16 @@ static int suspend_and_send_dirty(struct xc_sr_context *ctx)
 
     bitmap_or(dirty_bitmap, ctx->save.deferred_pages, ctx->save.p2m_size);
 
+    if ( !ctx->save.live && ctx->save.checkpointed == MIG_STREAM_COLO )
+    {
+        rc = merge_secondary_dirty_bitmap(ctx);
+        if ( rc )
+        {
+            PERROR("Failed to get secondary vm's dirty pages");
+            goto out;
+        }
+    }
+
     rc = send_dirty_pages(ctx, stats.dirty_count + ctx->save.nr_deferred_pages);
     if ( rc )
         goto out;
@@ -784,11 +846,42 @@ static int save(struct xc_sr_context *ctx, uint16_t guest_type)
             if ( rc )
                 goto err;
 
-            ctx->save.callbacks->postcopy(ctx->save.callbacks->data);
+            if ( ctx->save.checkpointed == MIG_STREAM_COLO )
+            {
+                rc = ctx->save.callbacks->checkpoint(ctx->save.callbacks->data);
+                if ( !rc )
+                {
+                    rc = -1;
+                    goto err;
+                }
+            }
 
-            rc = ctx->save.callbacks->checkpoint(ctx->save.callbacks->data);
-            if ( rc <= 0 )
-                ctx->save.checkpointed = false;
+            rc = ctx->save.callbacks->postcopy(ctx->save.callbacks->data);
+            if ( !rc )
+            {
+                rc = -1;
+                goto err;
+            }
+
+            if ( ctx->save.checkpointed == MIG_STREAM_COLO )
+            {
+                rc = ctx->save.callbacks->should_checkpoint(
+                                                    ctx->save.callbacks->data);
+                if ( rc <= 0 )
+                    ctx->save.checkpointed = false;
+            }
+            else if ( ctx->save.checkpointed == MIG_STREAM_REMUS )
+            {
+                rc = ctx->save.callbacks->checkpoint(ctx->save.callbacks->data);
+                if ( rc <= 0 )
+                    ctx->save.checkpointed = false;
+            }
+            else
+            {
+                ERROR("Unknown checkpointed stream");
+                rc = -1;
+                goto err;
+            }
         }
     } while ( ctx->save.checkpointed );
 
@@ -835,6 +928,7 @@ int xc_domain_save2(xc_interface *xch, int io_fd, uint32_t dom,
     ctx.save.live  = !!(flags & XCFLAGS_LIVE);
     ctx.save.debug = !!(flags & XCFLAGS_DEBUG);
     ctx.save.checkpointed = checkpointed_stream;
+    ctx.save.recv_fd = back_fd;
 
     /*
      * TODO: Find some time to better tweak the live migration algorithm.
@@ -850,6 +944,8 @@ int xc_domain_save2(xc_interface *xch, int io_fd, uint32_t dom,
         assert(callbacks->switch_qemu_logdirty);
     if ( ctx.save.checkpointed )
         assert(callbacks->checkpoint && callbacks->postcopy);
+    if ( ctx.save.checkpointed == MIG_STREAM_COLO )
+        assert(callbacks->should_checkpoint);
 
     IPRINTF("In experimental %s", __func__);
     DPRINTF("fd %d, dom %u, max_iters %u, max_factor %u, flags %u, hvm %d",
-- 
1.9.1

  parent reply	other threads:[~2015-06-25  6:31 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-06-25  6:30 [PATCH v7 COLO 00/18] COarse-grain LOck-stepping Virtual Machines for Non-stop Service Yang Hongyang
2015-06-25  6:30 ` [PATCH v7 COLO 01/18] docs: add colo readme Yang Hongyang
2015-07-14 15:15   ` Ian Campbell
2015-06-25  6:30 ` [PATCH v7 COLO 02/18] tools/libxl: handle colo_context records in a libxl migration v2 stream Yang Hongyang
2015-07-14 15:19   ` Ian Campbell
2015-07-15  0:34     ` Yang Hongyang
2015-06-25  6:30 ` [PATCH v7 COLO 03/18] tools/libxl: write colo_context records into the stream Yang Hongyang
2015-06-25  6:30 ` [PATCH v7 COLO 04/18] secondary vm suspend/resume/checkpoint code Yang Hongyang
2015-06-25  6:30 ` [PATCH v7 COLO 05/18] primary " Yang Hongyang
2015-06-25  6:31 ` [PATCH v7 COLO 06/18] libxc/restore: support COLO restore Yang Hongyang
2015-06-25  6:31 ` [PATCH v7 COLO 07/18] libxc/restore: send dirty bitmap to primary when checkpoint under colo Yang Hongyang
2015-06-25  6:31 ` [PATCH v7 COLO 08/18] send store mfn and console mfn to xl before resuming secondary vm Yang Hongyang
2015-06-25  6:31 ` Yang Hongyang [this message]
2015-06-25  6:31 ` [PATCH v7 COLO 10/18] implement the cmdline for COLO Yang Hongyang
2015-06-25  6:31 ` [PATCH v7 COLO 11/18] Support colo mode for qemu disk Yang Hongyang
2015-06-25  6:31 ` [PATCH v7 COLO 12/18] COLO: use qemu block replication Yang Hongyang
2015-06-25  6:31 ` [PATCH v7 COLO 13/18] COLO proxy: implement setup/teardown of COLO proxy module Yang Hongyang
2015-06-25  6:31 ` [PATCH v7 COLO 14/18] COLO proxy: preresume, postresume and checkpoint Yang Hongyang
2015-06-25  6:31 ` [PATCH v7 COLO 15/18] COLO nic: implement COLO nic subkind Yang Hongyang
2015-06-25  6:31 ` [PATCH v7 COLO 16/18] setup and control colo proxy on primary side Yang Hongyang
2015-06-25  6:31 ` [PATCH v7 COLO 17/18] setup and control colo proxy on secondary side Yang Hongyang
2015-06-25  6:31 ` [PATCH v7 COLO 18/18] cmdline switches and config vars to control colo-proxy Yang Hongyang
2015-07-14 15:55 ` [PATCH v7 COLO 00/18] COarse-grain LOck-stepping Virtual Machines for Non-stop Service Ian Campbell
2015-07-15  0:41   ` Yang Hongyang

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=1435213872-10698-10-git-send-email-yanghy@cn.fujitsu.com \
    --to=yanghy@cn.fujitsu.com \
    --cc=andrew.cooper3@citrix.com \
    --cc=eddie.dong@intel.com \
    --cc=guijianfeng@cn.fujitsu.com \
    --cc=ian.campbell@citrix.com \
    --cc=ian.jackson@eu.citrix.com \
    --cc=rshriram@cs.ubc.ca \
    --cc=wei.liu2@citrix.com \
    --cc=wency@cn.fujitsu.com \
    --cc=xen-devel@lists.xen.org \
    --cc=yunhong.jiang@intel.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).