From nobody Wed Oct 29 17:12:38 2025 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) client-ip=208.118.235.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; spf=pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail(p=none dis=none) header.from=redhat.com Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 1524656295326877.8833847295258; Wed, 25 Apr 2018 04:38:15 -0700 (PDT) Received: from localhost ([::1]:35897 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fBIkS-0002aP-Hp for importer@patchew.org; Wed, 25 Apr 2018 07:38:08 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:34356) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fBIaW-00032q-0F for qemu-devel@nongnu.org; Wed, 25 Apr 2018 07:27:53 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1fBIaR-0005EP-Uh for qemu-devel@nongnu.org; Wed, 25 Apr 2018 07:27:52 -0400 Received: from mx3-rdu2.redhat.com ([66.187.233.73]:45570 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 1fBIaR-0005Dm-Oc for qemu-devel@nongnu.org; Wed, 25 Apr 2018 07:27:47 -0400 Received: from smtp.corp.redhat.com (int-mx06.intmail.prod.int.rdu2.redhat.com [10.11.54.6]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id 61BAA402314E for ; Wed, 25 Apr 2018 11:27:47 +0000 (UTC) Received: from secure.mitica (ovpn-117-169.ams2.redhat.com [10.36.117.169]) by smtp.corp.redhat.com (Postfix) with ESMTP id 57B08215CDC8; Wed, 25 Apr 2018 11:27:46 +0000 (UTC) From: Juan Quintela To: qemu-devel@nongnu.org Date: Wed, 25 Apr 2018 13:27:18 +0200 Message-Id: <20180425112723.1111-17-quintela@redhat.com> In-Reply-To: <20180425112723.1111-1-quintela@redhat.com> References: <20180425112723.1111-1-quintela@redhat.com> X-Scanned-By: MIMEDefang 2.78 on 10.11.54.6 X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.11.55.6]); Wed, 25 Apr 2018 11:27:47 +0000 (UTC) X-Greylist: inspected by milter-greylist-4.5.16 (mx1.redhat.com [10.11.55.6]); Wed, 25 Apr 2018 11:27:47 +0000 (UTC) for IP:'10.11.54.6' DOMAIN:'int-mx06.intmail.prod.int.rdu2.redhat.com' HELO:'smtp.corp.redhat.com' FROM:'quintela@redhat.com' RCPT:'' X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.2.x-3.x [generic] [fuzzy] X-Received-From: 66.187.233.73 Subject: [Qemu-devel] [PATCH v12 16/21] migration: Synchronize multifd threads with main thread X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: lvivier@redhat.com, dgilbert@redhat.com, peterx@redhat.com Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail: RSF_0 Z_629925259 SPT_0 Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" We synchronize all threads each RAM_SAVE_FLAG_EOS. Bitmap synchronizations don't happen inside a ram section, so we are safe about two channels trying to overwrite the same memory. Signed-off-by: Juan Quintela --- migration/ram.c | 118 +++++++++++++++++++++++++++++++++++++---- migration/trace-events | 6 +++ 2 files changed, 113 insertions(+), 11 deletions(-) diff --git a/migration/ram.c b/migration/ram.c index c4c185cc4c..398cb0af3b 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -405,6 +405,8 @@ static void compress_threads_save_setup(void) #define MULTIFD_MAGIC 0x11223344U #define MULTIFD_VERSION 1 =20 +#define MULTIFD_FLAG_SYNC (1 << 0) + typedef struct { uint32_t magic; uint32_t version; @@ -471,6 +473,8 @@ typedef struct { uint32_t num_packets; /* pages sent through this channel */ uint32_t num_pages; + /* syncs main thread and channels */ + QemuSemaphore sem_sync; } MultiFDSendParams; =20 typedef struct { @@ -507,6 +511,8 @@ typedef struct { uint32_t num_packets; /* pages sent through this channel */ uint32_t num_pages; + /* syncs main thread and channels */ + QemuSemaphore sem_sync; } MultiFDRecvParams; =20 static int multifd_send_initial_packet(MultiFDSendParams *p, Error **errp) @@ -682,6 +688,10 @@ struct { int count; /* array of pages to sent */ MultiFDPages_t *pages; + /* syncs main thread and channels */ + QemuSemaphore sem_sync; + /* global number of generated multifd packets */ + uint32_t seq; } *multifd_send_state; =20 static void multifd_send_terminate_threads(Error *err) @@ -727,6 +737,7 @@ int multifd_save_cleanup(Error **errp) p->c =3D NULL; qemu_mutex_destroy(&p->mutex); qemu_sem_destroy(&p->sem); + qemu_sem_destroy(&p->sem_sync); g_free(p->name); p->name =3D NULL; multifd_pages_clear(p->pages); @@ -735,6 +746,7 @@ int multifd_save_cleanup(Error **errp) g_free(p->packet); p->packet =3D NULL; } + qemu_sem_destroy(&multifd_send_state->sem_sync); g_free(multifd_send_state->params); multifd_send_state->params =3D NULL; multifd_pages_clear(multifd_send_state->pages); @@ -744,6 +756,33 @@ int multifd_save_cleanup(Error **errp) return ret; } =20 +static void multifd_send_sync_main(void) +{ + int i; + + if (!migrate_use_multifd()) { + return; + } + for (i =3D 0; i < migrate_multifd_channels(); i++) { + MultiFDSendParams *p =3D &multifd_send_state->params[i]; + + trace_multifd_send_sync_main_signal(p->id); + + qemu_mutex_lock(&p->mutex); + p->flags |=3D MULTIFD_FLAG_SYNC; + p->pending_job++; + qemu_mutex_unlock(&p->mutex); + qemu_sem_post(&p->sem); + } + for (i =3D 0; i < migrate_multifd_channels(); i++) { + MultiFDSendParams *p =3D &multifd_send_state->params[i]; + + trace_multifd_send_sync_main_wait(p->id); + qemu_sem_wait(&multifd_send_state->sem_sync); + } + trace_multifd_send_sync_main(multifd_send_state->seq); +} + static void *multifd_send_thread(void *opaque) { MultiFDSendParams *p =3D opaque; @@ -778,17 +817,20 @@ static void *multifd_send_thread(void *opaque) /* ToDo: send packet here */ =20 qemu_mutex_lock(&p->mutex); + p->flags =3D 0; p->pending_job--; qemu_mutex_unlock(&p->mutex); - continue; + + if (flags & MULTIFD_FLAG_SYNC) { + qemu_sem_post(&multifd_send_state->sem_sync); + } } else if (p->quit) { qemu_mutex_unlock(&p->mutex); break; + } else { + qemu_mutex_unlock(&p->mutex); + /* sometimes there are spurious wakeups */ } - qemu_mutex_unlock(&p->mutex); - /* this is impossible */ - error_setg(&local_err, "multifd_send_thread: Unknown command"); - break; } =20 out: @@ -840,12 +882,14 @@ int multifd_save_setup(void) multifd_send_state->params =3D g_new0(MultiFDSendParams, thread_count); atomic_set(&multifd_send_state->count, 0); multifd_pages_init(&multifd_send_state->pages, page_count); + qemu_sem_init(&multifd_send_state->sem_sync, 0); =20 for (i =3D 0; i < thread_count; i++) { MultiFDSendParams *p =3D &multifd_send_state->params[i]; =20 qemu_mutex_init(&p->mutex); qemu_sem_init(&p->sem, 0); + qemu_sem_init(&p->sem_sync, 0); p->quit =3D false; p->pending_job =3D 0; p->id =3D i; @@ -863,6 +907,10 @@ struct { MultiFDRecvParams *params; /* number of created threads */ int count; + /* syncs main thread and channels */ + QemuSemaphore sem_sync; + /* global number of generated multifd packets */ + uint32_t seq; } *multifd_recv_state; =20 static void multifd_recv_terminate_threads(Error *err) @@ -908,6 +956,7 @@ int multifd_load_cleanup(Error **errp) p->c =3D NULL; qemu_mutex_destroy(&p->mutex); qemu_sem_destroy(&p->sem); + qemu_sem_destroy(&p->sem_sync); g_free(p->name); p->name =3D NULL; multifd_pages_clear(p->pages); @@ -916,6 +965,7 @@ int multifd_load_cleanup(Error **errp) g_free(p->packet); p->packet =3D NULL; } + qemu_sem_destroy(&multifd_recv_state->sem_sync); g_free(multifd_recv_state->params); multifd_recv_state->params =3D NULL; g_free(multifd_recv_state); @@ -924,6 +974,42 @@ int multifd_load_cleanup(Error **errp) return ret; } =20 +static void multifd_recv_sync_main(void) +{ + int i; + + if (!migrate_use_multifd()) { + return; + } + for (i =3D 0; i < migrate_multifd_channels(); i++) { + MultiFDRecvParams *p =3D &multifd_recv_state->params[i]; + + trace_multifd_recv_sync_main_signal(p->id); + qemu_mutex_lock(&p->mutex); + p->pending_job =3D true; + qemu_mutex_unlock(&p->mutex); + } + for (i =3D 0; i < migrate_multifd_channels(); i++) { + MultiFDRecvParams *p =3D &multifd_recv_state->params[i]; + + trace_multifd_recv_sync_main_wait(p->id); + qemu_sem_wait(&multifd_recv_state->sem_sync); + qemu_mutex_lock(&p->mutex); + if (multifd_recv_state->seq < p->seq) { + multifd_recv_state->seq =3D p->seq; + } + qemu_mutex_unlock(&p->mutex); + } + for (i =3D 0; i < migrate_multifd_channels(); i++) { + MultiFDRecvParams *p =3D &multifd_recv_state->params[i]; + + trace_multifd_recv_sync_main_signal(p->id); + + qemu_sem_post(&p->sem_sync); + } + trace_multifd_recv_sync_main(multifd_recv_state->seq); +} + static void *multifd_recv_thread(void *opaque) { MultiFDRecvParams *p =3D opaque; @@ -933,9 +1019,8 @@ static void *multifd_recv_thread(void *opaque) trace_multifd_recv_thread_start(p->id); =20 while (true) { - qemu_sem_wait(&p->sem); qemu_mutex_lock(&p->mutex); - if (p->pending_job) { + if (true || p->pending_job) { uint32_t used; uint32_t flags; qemu_mutex_unlock(&p->mutex); @@ -956,14 +1041,18 @@ static void *multifd_recv_thread(void *opaque) p->num_packets++; p->num_pages +=3D used; qemu_mutex_unlock(&p->mutex); + + if (flags & MULTIFD_FLAG_SYNC) { + qemu_sem_post(&multifd_recv_state->sem_sync); + qemu_sem_wait(&p->sem_sync); + } } else if (p->quit) { qemu_mutex_unlock(&p->mutex); break; + } else { + qemu_mutex_unlock(&p->mutex); + /* sometimes there are spurious wakeups */ } - qemu_mutex_unlock(&p->mutex); - /* this is impossible */ - error_setg(&local_err, "multifd_recv_thread: Unknown command"); - break; } =20 if (local_err) { @@ -991,12 +1080,14 @@ int multifd_load_setup(void) multifd_recv_state =3D g_malloc0(sizeof(*multifd_recv_state)); multifd_recv_state->params =3D g_new0(MultiFDRecvParams, thread_count); atomic_set(&multifd_recv_state->count, 0); + qemu_sem_init(&multifd_recv_state->sem_sync, 0); =20 for (i =3D 0; i < thread_count; i++) { MultiFDRecvParams *p =3D &multifd_recv_state->params[i]; =20 qemu_mutex_init(&p->mutex); qemu_sem_init(&p->sem, 0); + qemu_sem_init(&p->sem_sync, 0); p->quit =3D false; p->pending_job =3D false; p->id =3D i; @@ -2695,6 +2786,7 @@ static int ram_save_setup(QEMUFile *f, void *opaque) ram_control_before_iterate(f, RAM_CONTROL_SETUP); ram_control_after_iterate(f, RAM_CONTROL_SETUP); =20 + multifd_send_sync_main(); qemu_put_be64(f, RAM_SAVE_FLAG_EOS); =20 return 0; @@ -2770,6 +2862,7 @@ static int ram_save_iterate(QEMUFile *f, void *opaque) */ ram_control_after_iterate(f, RAM_CONTROL_ROUND); =20 + multifd_send_sync_main(); out: qemu_put_be64(f, RAM_SAVE_FLAG_EOS); ram_counters.transferred +=3D 8; @@ -2823,6 +2916,7 @@ static int ram_save_complete(QEMUFile *f, void *opaqu= e) =20 rcu_read_unlock(); =20 + multifd_send_sync_main(); qemu_put_be64(f, RAM_SAVE_FLAG_EOS); =20 return 0; @@ -3253,6 +3347,7 @@ static int ram_load_postcopy(QEMUFile *f) break; case RAM_SAVE_FLAG_EOS: /* normal exit */ + multifd_recv_sync_main(); break; default: error_report("Unknown combination of migration flags: %#x" @@ -3438,6 +3533,7 @@ static int ram_load(QEMUFile *f, void *opaque, int ve= rsion_id) break; case RAM_SAVE_FLAG_EOS: /* normal exit */ + multifd_recv_sync_main(); break; default: if (flags & RAM_SAVE_FLAG_HOOK) { diff --git a/migration/trace-events b/migration/trace-events index 9eee048287..b0ab8e2d03 100644 --- a/migration/trace-events +++ b/migration/trace-events @@ -83,6 +83,12 @@ multifd_recv_thread_start(uint8_t id) "%d" multifd_recv_thread_end(uint8_t id, uint32_t packets, uint32_t pages) "cha= nnel %d packets %d pages %d" multifd_send(uint8_t id, uint32_t seq, uint32_t used, uint32_t flags) "cha= nnel %d seq number %d pages %d flags 0x%x" multifd_recv(uint8_t id, uint32_t seq, uint32_t used, uint32_t flags) "cha= nnel %d seq number %d pages %d flags 0x%x" +multifd_send_sync_main(uint32_t seq) "seq %d" +multifd_send_sync_main_signal(uint8_t id) "channel %d" +multifd_send_sync_main_wait(uint8_t id) "channel %d" +multifd_recv_sync_main(uint32_t seq) "seq %d" +multifd_recv_sync_main_signal(uint8_t id) "channel %d" +multifd_recv_sync_main_wait(uint8_t id) "channel %d" =20 # migration/migration.c await_return_path_close_on_source_close(void) "" --=20 2.17.0