All of lore.kernel.org
 help / color / mirror / Atom feed
From: Lidong Chen <jemmy858585@gmail.com>
To: zhang.zhanghailiang@huawei.com, quintela@redhat.com,
	dgilbert@redhat.com, berrange@redhat.com, aviadye@mellanox.com,
	pbonzini@redhat.com
Cc: qemu-devel@nongnu.org, adido@mellanox.com,
	Lidong Chen <lidongchen@tencent.com>
Subject: [Qemu-devel] [PATCH v4 10/12] migration: create a dedicated thread to release rdma resource
Date: Wed, 30 May 2018 17:43:34 +0800	[thread overview]
Message-ID: <1527673416-31268-11-git-send-email-lidongchen@tencent.com> (raw)
In-Reply-To: <1527673416-31268-1-git-send-email-lidongchen@tencent.com>

ibv_dereg_mr wait for a long time for big memory size virtual server.

The test result is:
  10GB  326ms
  20GB  699ms
  30GB  1021ms
  40GB  1387ms
  50GB  1712ms
  60GB  2034ms
  70GB  2457ms
  80GB  2807ms
  90GB  3107ms
  100GB 3474ms
  110GB 3735ms
  120GB 4064ms
  130GB 4567ms
  140GB 4886ms

this will cause the guest os hang for a while when migration finished.
So create a dedicated thread to release rdma resource.

Signed-off-by: Lidong Chen <lidongchen@tencent.com>
---
 migration/rdma.c | 21 +++++++++++++++++----
 1 file changed, 17 insertions(+), 4 deletions(-)

diff --git a/migration/rdma.c b/migration/rdma.c
index dfa4f77..1b9e261 100644
--- a/migration/rdma.c
+++ b/migration/rdma.c
@@ -2979,12 +2979,12 @@ static void qio_channel_rdma_set_aio_fd_handler(QIOChannel *ioc,
     }
 }
 
-static int qio_channel_rdma_close(QIOChannel *ioc,
-                                  Error **errp)
+static void *qio_channel_rdma_close_thread(void *arg)
 {
-    QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(ioc);
+    QIOChannelRDMA *rioc = arg;
     RDMAContext *rdmain, *rdmaout;
-    trace_qemu_rdma_close();
+
+    rcu_register_thread();
 
     rdmain = rioc->rdmain;
     if (rdmain) {
@@ -3009,6 +3009,19 @@ static int qio_channel_rdma_close(QIOChannel *ioc,
     g_free(rdmain);
     g_free(rdmaout);
 
+    rcu_unregister_thread();
+    return NULL;
+}
+
+static int qio_channel_rdma_close(QIOChannel *ioc,
+                                  Error **errp)
+{
+    QemuThread t;
+    QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(ioc);
+    trace_qemu_rdma_close();
+
+    qemu_thread_create(&t, "rdma cleanup", qio_channel_rdma_close_thread,
+                           rioc, QEMU_THREAD_DETACHED);
     return 0;
 }
 
-- 
1.8.3.1

  parent reply	other threads:[~2018-05-30  9:44 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-05-30  9:43 [Qemu-devel] [PATCH v4 00/12] Enable postcopy RDMA live migration Lidong Chen
2018-05-30  9:43 ` [Qemu-devel] [PATCH v4 01/12] migration: disable RDMA WRITE after postcopy started Lidong Chen
2018-05-30  9:43 ` [Qemu-devel] [PATCH v4 02/12] migration: create a dedicated connection for rdma return path Lidong Chen
2018-05-30  9:43 ` [Qemu-devel] [PATCH v4 03/12] migration: remove unnecessary variables len in QIOChannelRDMA Lidong Chen
2018-05-30  9:43 ` [Qemu-devel] [PATCH v4 04/12] migration: avoid concurrent invoke channel_close by different threads Lidong Chen
2018-05-30 14:45   ` Dr. David Alan Gilbert
2018-05-31  7:07     ` 858585 jemmy
2018-05-31 10:52       ` Dr. David Alan Gilbert
2018-06-03 13:50         ` 858585 jemmy
2018-06-03 14:43           ` 858585 jemmy
2018-05-30  9:43 ` [Qemu-devel] [PATCH v4 05/12] migration: implement bi-directional RDMA QIOChannel Lidong Chen
2018-05-30  9:43 ` [Qemu-devel] [PATCH v4 06/12] migration: Stop rdma yielding during incoming postcopy Lidong Chen
2018-05-30  9:43 ` [Qemu-devel] [PATCH v4 07/12] migration: not wait RDMA_CM_EVENT_DISCONNECTED event after rdma_disconnect Lidong Chen
2018-05-30 12:24   ` Dr. David Alan Gilbert
2018-05-30  9:43 ` [Qemu-devel] [PATCH v4 08/12] migration: implement io_set_aio_fd_handler function for RDMA QIOChannel Lidong Chen
2018-05-30  9:43 ` [Qemu-devel] [PATCH v4 09/12] migration: invoke qio_channel_yield only when qemu_in_coroutine() Lidong Chen
2018-05-30  9:43 ` Lidong Chen [this message]
2018-05-30 16:50   ` [Qemu-devel] [PATCH v4 10/12] migration: create a dedicated thread to release rdma resource Dr. David Alan Gilbert
2018-05-31  7:25     ` 858585 jemmy
2018-05-31 10:55       ` Dr. David Alan Gilbert
2018-05-31 11:27         ` 858585 jemmy
2018-05-30  9:43 ` [Qemu-devel] [PATCH v4 11/12] migration: poll the cm event while wait RDMA work request completion Lidong Chen
2018-05-30 17:33   ` Dr. David Alan Gilbert
2018-05-31  7:36     ` 858585 jemmy
2018-06-03 15:04       ` Aviad Yehezkel
2018-06-05 14:26         ` 858585 jemmy
2018-05-30  9:43 ` [Qemu-devel] [PATCH v4 12/12] migration: implement the shutdown for RDMA QIOChannel Lidong Chen
2018-05-30 17:59   ` Dr. David Alan Gilbert

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=1527673416-31268-11-git-send-email-lidongchen@tencent.com \
    --to=jemmy858585@gmail.com \
    --cc=adido@mellanox.com \
    --cc=aviadye@mellanox.com \
    --cc=berrange@redhat.com \
    --cc=dgilbert@redhat.com \
    --cc=lidongchen@tencent.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.