From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:34801) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fDpIz-0006PH-Mi for qemu-devel@nongnu.org; Wed, 02 May 2018 06:48:14 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1fDpIy-0002no-I9 for qemu-devel@nongnu.org; Wed, 02 May 2018 06:48:13 -0400 Received: from mx3-rdu2.redhat.com ([66.187.233.73]:50596 helo=mx1.redhat.com) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1fDpIy-0002nU-9y for qemu-devel@nongnu.org; Wed, 02 May 2018 06:48:12 -0400 From: Peter Xu Date: Wed, 2 May 2018 18:47:22 +0800 Message-Id: <20180502104740.12123-7-peterx@redhat.com> In-Reply-To: <20180502104740.12123-1-peterx@redhat.com> References: <20180502104740.12123-1-peterx@redhat.com> Subject: [Qemu-devel] [PATCH v8 06/24] migration: allow fault thread to pause List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: qemu-devel@nongnu.org Cc: Alexey Perevalov , "Daniel P . Berrange" , Juan Quintela , Andrea Arcangeli , "Dr . David Alan Gilbert" , peterx@redhat.com Allows the fault thread to stop handling page faults temporarily. When network failure happened (and if we expect a recovery afterwards), we should not allow the fault thread to continue sending things to source, instead, it should halt for a while until the connection is rebuilt. When the dest main thread noticed the failure, it kicks the fault thread to switch to pause state. Reviewed-by: Dr. David Alan Gilbert Signed-off-by: Peter Xu --- migration/migration.h | 1 + migration/migration.c | 1 + migration/postcopy-ram.c | 54 ++++++++++++++++++++++++++++++++++++++++++++---- migration/savevm.c | 3 +++ migration/trace-events | 2 ++ 5 files changed, 57 insertions(+), 4 deletions(-) diff --git a/migration/migration.h b/migration/migration.h index db28a66a92..83ebc18b1e 100644 --- a/migration/migration.h +++ b/migration/migration.h @@ -76,6 +76,7 @@ struct MigrationIncomingState { /* notify PAUSED postcopy incoming migrations to try to continue */ QemuSemaphore postcopy_pause_sem_dst; + QemuSemaphore postcopy_pause_sem_fault; }; MigrationIncomingState *migration_incoming_get_current(void); diff --git a/migration/migration.c b/migration/migration.c index 09dbf5350c..9d184b3f36 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -160,6 +160,7 @@ MigrationIncomingState *migration_incoming_get_current(void) qemu_mutex_init(&mis_current.rp_mutex); qemu_event_init(&mis_current.main_thread_load_event, false); qemu_sem_init(&mis_current.postcopy_pause_sem_dst, 0); + qemu_sem_init(&mis_current.postcopy_pause_sem_fault, 0); init_dirty_bitmap_incoming_migration(); diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c index 8ceeaa2a93..658b750a8e 100644 --- a/migration/postcopy-ram.c +++ b/migration/postcopy-ram.c @@ -830,6 +830,17 @@ static void mark_postcopy_blocktime_end(uintptr_t addr) affected_cpu); } +static bool postcopy_pause_fault_thread(MigrationIncomingState *mis) +{ + trace_postcopy_pause_fault_thread(); + + qemu_sem_wait(&mis->postcopy_pause_sem_fault); + + trace_postcopy_pause_fault_thread_continued(); + + return true; +} + /* * Handle faults detected by the USERFAULT markings */ @@ -880,6 +891,22 @@ static void *postcopy_ram_fault_thread(void *opaque) break; } + if (!mis->to_src_file) { + /* + * Possibly someone tells us that the return path is + * broken already using the event. We should hold until + * the channel is rebuilt. + */ + if (postcopy_pause_fault_thread(mis)) { + mis->last_rb = NULL; + /* Continue to read the userfaultfd */ + } else { + error_report("%s: paused but don't allow to continue", + __func__); + break; + } + } + if (pfd[1].revents) { uint64_t tmp64 = 0; @@ -942,18 +969,37 @@ static void *postcopy_ram_fault_thread(void *opaque) (uintptr_t)(msg.arg.pagefault.address), msg.arg.pagefault.feat.ptid, rb); +retry: /* * Send the request to the source - we want to request one * of our host page sizes (which is >= TPS) */ if (rb != mis->last_rb) { mis->last_rb = rb; - migrate_send_rp_req_pages(mis, qemu_ram_get_idstr(rb), - rb_offset, qemu_ram_pagesize(rb)); + ret = migrate_send_rp_req_pages(mis, + qemu_ram_get_idstr(rb), + rb_offset, + qemu_ram_pagesize(rb)); } else { /* Save some space */ - migrate_send_rp_req_pages(mis, NULL, - rb_offset, qemu_ram_pagesize(rb)); + ret = migrate_send_rp_req_pages(mis, + NULL, + rb_offset, + qemu_ram_pagesize(rb)); + } + + if (ret) { + /* May be network failure, try to wait for recovery */ + if (ret == -EIO && postcopy_pause_fault_thread(mis)) { + /* We got reconnected somehow, try to continue */ + mis->last_rb = NULL; + goto retry; + } else { + /* This is a unavoidable fault */ + error_report("%s: migrate_send_rp_req_pages() get %d", + __func__, ret); + break; + } } } diff --git a/migration/savevm.c b/migration/savevm.c index 8ad99b1eaa..6ee69d8283 100644 --- a/migration/savevm.c +++ b/migration/savevm.c @@ -2083,6 +2083,9 @@ static bool postcopy_pause_incoming(MigrationIncomingState *mis) mis->to_src_file = NULL; qemu_mutex_unlock(&mis->rp_mutex); + /* Notify the fault thread for the invalidated file handle */ + postcopy_fault_thread_notify(mis); + error_report("Detected IO failure for postcopy. " "Migration paused."); diff --git a/migration/trace-events b/migration/trace-events index cd971bf9fe..7f836499d1 100644 --- a/migration/trace-events +++ b/migration/trace-events @@ -101,6 +101,8 @@ open_return_path_on_source_continue(void) "" postcopy_start(void) "" postcopy_pause_return_path(void) "" postcopy_pause_return_path_continued(void) "" +postcopy_pause_fault_thread(void) "" +postcopy_pause_fault_thread_continued(void) "" postcopy_pause_continued(void) "" postcopy_pause_incoming(void) "" postcopy_pause_incoming_continued(void) "" -- 2.14.3