All of lore.kernel.org
 help / color / mirror / Atom feed
From: Peter Xu <peterx@redhat.com>
To: qemu-devel@nongnu.org
Cc: Andrea Arcangeli <aarcange@redhat.com>,
	"Daniel P . Berrange" <berrange@redhat.com>,
	Juan Quintela <quintela@redhat.com>,
	Alexey Perevalov <a.perevalov@samsung.com>,
	"Dr . David Alan Gilbert" <dgilbert@redhat.com>,
	peterx@redhat.com
Subject: [Qemu-devel] [PATCH v5 07/28] migration: allow src return path to pause
Date: Tue,  5 Dec 2017 14:52:46 +0800	[thread overview]
Message-ID: <20171205065307.21853-8-peterx@redhat.com> (raw)
In-Reply-To: <20171205065307.21853-1-peterx@redhat.com>

Let the thread pause for network issues.

Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
---
 migration/migration.c  | 35 +++++++++++++++++++++++++++++++++--
 migration/migration.h  |  1 +
 migration/trace-events |  2 ++
 3 files changed, 36 insertions(+), 2 deletions(-)

diff --git a/migration/migration.c b/migration/migration.c
index 6f0d48bbed..0dfbbe5673 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -1689,6 +1689,18 @@ static void migrate_handle_rp_req_pages(MigrationState *ms, const char* rbname,
     }
 }
 
+/* Return true to retry, false to quit */
+static bool postcopy_pause_return_path_thread(MigrationState *s)
+{
+    trace_postcopy_pause_return_path();
+
+    qemu_sem_wait(&s->postcopy_pause_rp_sem);
+
+    trace_postcopy_pause_return_path_continued();
+
+    return true;
+}
+
 /*
  * Handles messages sent on the return path towards the source VM
  *
@@ -1705,6 +1717,8 @@ static void *source_return_path_thread(void *opaque)
     int res;
 
     trace_source_return_path_thread_entry();
+
+retry:
     while (!ms->rp_state.error && !qemu_file_get_error(rp) &&
            migration_is_setup_or_active(ms->state)) {
         trace_source_return_path_thread_loop_top();
@@ -1796,13 +1810,28 @@ static void *source_return_path_thread(void *opaque)
             break;
         }
     }
-    if (qemu_file_get_error(rp)) {
+
+out:
+    res = qemu_file_get_error(rp);
+    if (res) {
+        if (res == -EIO) {
+            /*
+             * Maybe there is something we can do: it looks like a
+             * network down issue, and we pause for a recovery.
+             */
+            if (postcopy_pause_return_path_thread(ms)) {
+                /* Reload rp, reset the rest */
+                rp = ms->rp_state.from_dst_file;
+                ms->rp_state.error = false;
+                goto retry;
+            }
+        }
+
         trace_source_return_path_thread_bad_end();
         mark_source_rp_bad(ms);
     }
 
     trace_source_return_path_thread_end();
-out:
     ms->rp_state.from_dst_file = NULL;
     qemu_fclose(rp);
     return NULL;
@@ -2557,6 +2586,7 @@ static void migration_instance_finalize(Object *obj)
     g_free(params->tls_creds);
     qemu_sem_destroy(&ms->pause_sem);
     qemu_sem_destroy(&ms->postcopy_pause_sem);
+    qemu_sem_destroy(&ms->postcopy_pause_rp_sem);
 }
 
 static void migration_instance_init(Object *obj)
@@ -2587,6 +2617,7 @@ static void migration_instance_init(Object *obj)
     params->has_xbzrle_cache_size = true;
 
     qemu_sem_init(&ms->postcopy_pause_sem, 0);
+    qemu_sem_init(&ms->postcopy_pause_rp_sem, 0);
 }
 
 /*
diff --git a/migration/migration.h b/migration/migration.h
index 55894ecb79..ebb049f692 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -162,6 +162,7 @@ struct MigrationState
 
     /* Needed by postcopy-pause state */
     QemuSemaphore postcopy_pause_sem;
+    QemuSemaphore postcopy_pause_rp_sem;
 };
 
 void migrate_set_state(int *state, int old_state, int new_state);
diff --git a/migration/trace-events b/migration/trace-events
index bed1646cd6..a4031cfe00 100644
--- a/migration/trace-events
+++ b/migration/trace-events
@@ -99,6 +99,8 @@ migration_thread_setup_complete(void) ""
 open_return_path_on_source(void) ""
 open_return_path_on_source_continue(void) ""
 postcopy_start(void) ""
+postcopy_pause_return_path(void) ""
+postcopy_pause_return_path_continued(void) ""
 postcopy_pause_continued(void) ""
 postcopy_pause_incoming(void) ""
 postcopy_pause_incoming_continued(void) ""
-- 
2.14.3

  parent reply	other threads:[~2017-12-05  6:53 UTC|newest]

Thread overview: 43+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-12-05  6:52 [Qemu-devel] [PATCH v5 00/28] Migration: postcopy failure recovery Peter Xu
2017-12-05  6:52 ` [Qemu-devel] [PATCH v5 01/28] migration: better error handling with QEMUFile Peter Xu
2017-12-05 11:40   ` Dr. David Alan Gilbert
2017-12-05  6:52 ` [Qemu-devel] [PATCH v5 02/28] migration: reuse mis->userfault_quit_fd Peter Xu
2017-12-05  6:52 ` [Qemu-devel] [PATCH v5 03/28] migration: provide postcopy_fault_thread_notify() Peter Xu
2017-12-05  6:52 ` [Qemu-devel] [PATCH v5 04/28] migration: new postcopy-pause state Peter Xu
2017-12-05  6:52 ` [Qemu-devel] [PATCH v5 05/28] migration: implement "postcopy-pause" src logic Peter Xu
2017-12-05  6:52 ` [Qemu-devel] [PATCH v5 06/28] migration: allow dst vm pause on postcopy Peter Xu
2017-12-14 13:10   ` Dr. David Alan Gilbert
2017-12-05  6:52 ` Peter Xu [this message]
2017-12-05  6:52 ` [Qemu-devel] [PATCH v5 08/28] migration: allow send_rq to fail Peter Xu
2017-12-14 13:21   ` Dr. David Alan Gilbert
2017-12-05  6:52 ` [Qemu-devel] [PATCH v5 09/28] migration: allow fault thread to pause Peter Xu
2017-12-05  6:52 ` [Qemu-devel] [PATCH v5 10/28] qmp: hmp: add migrate "resume" option Peter Xu
2017-12-05  6:52 ` [Qemu-devel] [PATCH v5 11/28] migration: pass MigrationState to migrate_init() Peter Xu
2017-12-05  6:52 ` [Qemu-devel] [PATCH v5 12/28] migration: rebuild channel on source Peter Xu
2017-12-05  6:52 ` [Qemu-devel] [PATCH v5 13/28] migration: new state "postcopy-recover" Peter Xu
2017-12-05  6:52 ` [Qemu-devel] [PATCH v5 14/28] migration: wakeup dst ram-load-thread for recover Peter Xu
2017-12-05  6:52 ` [Qemu-devel] [PATCH v5 15/28] migration: new cmd MIG_CMD_RECV_BITMAP Peter Xu
2017-12-05  6:52 ` [Qemu-devel] [PATCH v5 16/28] migration: new message MIG_RP_MSG_RECV_BITMAP Peter Xu
2017-12-05  6:52 ` [Qemu-devel] [PATCH v5 17/28] migration: new cmd MIG_CMD_POSTCOPY_RESUME Peter Xu
2017-12-05  6:52 ` [Qemu-devel] [PATCH v5 18/28] migration: new message MIG_RP_MSG_RESUME_ACK Peter Xu
2017-12-05  6:52 ` [Qemu-devel] [PATCH v5 19/28] migration: introduce SaveVMHandlers.resume_prepare Peter Xu
2017-12-05  6:52 ` [Qemu-devel] [PATCH v5 20/28] migration: synchronize dirty bitmap for resume Peter Xu
2017-12-05  6:53 ` [Qemu-devel] [PATCH v5 21/28] migration: setup ramstate " Peter Xu
2017-12-05  6:53 ` [Qemu-devel] [PATCH v5 22/28] migration: final handshake for the resume Peter Xu
2017-12-05  6:53 ` [Qemu-devel] [PATCH v5 23/28] migration: free SocketAddress where allocated Peter Xu
2017-12-05  6:53 ` [Qemu-devel] [PATCH v5 24/28] migration: init dst in migration_object_init too Peter Xu
2017-12-05  6:53 ` [Qemu-devel] [PATCH v5 25/28] io: let watcher of the channel run in same ctx Peter Xu
2017-12-05  6:53 ` [Qemu-devel] [PATCH v5 26/28] migration: allow migrate_cancel to pause postcopy Peter Xu
2017-12-19 10:58   ` Dr. David Alan Gilbert
2018-01-24  8:28     ` Peter Xu
2018-01-24  9:06       ` Dr. David Alan Gilbert
2017-12-05  6:53 ` [Qemu-devel] [PATCH v5 27/28] qmp/migration: new command migrate-recover Peter Xu
2017-12-05  6:53 ` [Qemu-devel] [PATCH v5 28/28] hmp/migration: add migrate_recover command Peter Xu
2017-12-05  6:55 ` [Qemu-devel] [PATCH v5 00/28] Migration: postcopy failure recovery Peter Xu
2017-12-05 18:43 ` Dr. David Alan Gilbert
2017-12-06  2:39   ` Peter Xu
2018-01-11 16:59 ` Dr. David Alan Gilbert
2018-01-12  9:27   ` Peter Xu
2018-01-12 12:27     ` Dr. David Alan Gilbert
2018-01-24  6:19       ` Peter Xu
2018-01-24  9:05         ` 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=20171205065307.21853-8-peterx@redhat.com \
    --to=peterx@redhat.com \
    --cc=a.perevalov@samsung.com \
    --cc=aarcange@redhat.com \
    --cc=berrange@redhat.com \
    --cc=dgilbert@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 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.