From patchwork Fri Jan 14 17:33:25 2011 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yoshiaki Tamura X-Patchwork-Id: 479621 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by demeter1.kernel.org (8.14.4/8.14.3) with ESMTP id p0EHxvlk018683 for ; Fri, 14 Jan 2011 18:00:03 GMT Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758031Ab1ANRe5 (ORCPT ); Fri, 14 Jan 2011 12:34:57 -0500 Received: from sh.osrg.net ([192.16.179.4]:44653 "EHLO sh.osrg.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1758018Ab1ANRew (ORCPT ); Fri, 14 Jan 2011 12:34:52 -0500 Received: from fs.osrg.net (postfix@fs.osrg.net [10.0.0.12]) by sh.osrg.net (8.14.3/8.14.3/OSRG-NET) with ESMTP id p0EHYI4O007430; Sat, 15 Jan 2011 02:34:18 +0900 Received: from localhost (hype-nh0.osrg.net [10.72.1.48]) by fs.osrg.net (Postfix) with ESMTP id C62B03E042C; Sat, 15 Jan 2011 02:34:14 +0900 (JST) From: Yoshiaki Tamura To: kvm@vger.kernel.org, qemu-devel@nongnu.org Cc: avi@redhat.com, anthony@codemonkey.ws, aliguori@us.ibm.com, mtosatti@redhat.com, dlaor@redhat.com, mst@redhat.com, kwolf@redhat.com, ananth@in.ibm.com, psuriset@linux.vnet.ibm.com, vatsa@linux.vnet.ibm.com, stefanha@linux.vnet.ibm.com, blauwirbel@gmail.com, ohmura.kei@lab.ntt.co.jp, Yoshiaki Tamura Subject: [PATCH 16/19] migration: introduce migrate_ft_trans_{put, get}_ready(), and modify migrate_fd_put_ready() when ft_mode is on. Date: Sat, 15 Jan 2011 02:33:25 +0900 Message-Id: <1295026408-11122-17-git-send-email-tamura.yoshiaki@lab.ntt.co.jp> X-Mailer: git-send-email 1.7.1.2 In-Reply-To: <1295026408-11122-1-git-send-email-tamura.yoshiaki@lab.ntt.co.jp> References: <1295026408-11122-1-git-send-email-tamura.yoshiaki@lab.ntt.co.jp> X-Dispatcher: imput version 20070423(IM149) Lines: 333 X-Greylist: IP, sender and recipient auto-whitelisted, not delayed by milter-greylist-4.2.6 (demeter1.kernel.org [140.211.167.41]); Fri, 14 Jan 2011 18:00:04 +0000 (UTC) X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-3.0 (sh.osrg.net [192.16.179.4]); Sat, 15 Jan 2011 02:34:20 +0900 (JST) X-Virus-Scanned: clamav-milter 0.96.5 at sh X-Virus-Status: Clean Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org diff --git a/migration.c b/migration.c index 9740cb6..fb73b2d 100644 --- a/migration.c +++ b/migration.c @@ -21,6 +21,7 @@ #include "qemu_socket.h" #include "block-migration.h" #include "qemu-objects.h" +#include "event-tap.h" //#define DEBUG_MIGRATION @@ -274,6 +275,14 @@ void migrate_fd_error(FdMigrationState *s) migrate_fd_cleanup(s); } +static void migrate_ft_trans_error(FdMigrationState *s) +{ + ft_mode = FT_ERROR; + qemu_savevm_state_cancel(s->mon, s->file); + migrate_fd_error(s); + event_tap_unregister(); +} + int migrate_fd_cleanup(FdMigrationState *s) { int ret = 0; @@ -309,6 +318,17 @@ void migrate_fd_put_notify(void *opaque) qemu_file_put_notify(s->file); } +static void migrate_fd_get_notify(void *opaque) +{ + FdMigrationState *s = opaque; + + qemu_set_fd_handler2(s->fd, NULL, NULL, NULL, NULL); + qemu_file_get_notify(s->file); + if (qemu_file_has_error(s->file)) { + migrate_ft_trans_error(s); + } +} + ssize_t migrate_fd_put_buffer(void *opaque, const void *data, size_t size) { FdMigrationState *s = opaque; @@ -343,6 +363,10 @@ int migrate_fd_get_buffer(void *opaque, uint8_t *data, int64_t pos, size_t size) ret = -(s->get_error(s)); } + if (ret == -EAGAIN) { + qemu_set_fd_handler2(s->fd, NULL, migrate_fd_get_notify, NULL, s); + } + return ret; } @@ -369,6 +393,234 @@ void migrate_fd_connect(FdMigrationState *s) migrate_fd_put_ready(s); } +static int migrate_ft_trans_commit(void *opaque) +{ + FdMigrationState *s = opaque; + int ret = -1; + + if (ft_mode != FT_TRANSACTION_COMMIT && ft_mode != FT_TRANSACTION_ATOMIC) { + fprintf(stderr, + "migrate_ft_trans_commit: invalid ft_mode %d\n", ft_mode); + goto out; + } + + do { + if (ft_mode == FT_TRANSACTION_ATOMIC) { + if (qemu_ft_trans_begin(s->file) < 0) { + fprintf(stderr, "qemu_ft_trans_begin failed\n"); + goto out; + } + + ret = qemu_savevm_trans_begin(s->mon, s->file, 0); + if (ret < 0) { + fprintf(stderr, "qemu_savevm_trans_begin failed\n"); + goto out; + } + + ft_mode = FT_TRANSACTION_COMMIT; + if (ret) { + /* don't proceed until if fd isn't ready */ + goto out; + } + } + + /* make the VM state consistent by flushing outstanding events */ + vm_stop(0); + + /* send at full speed */ + qemu_file_set_rate_limit(s->file, 0); + + ret = qemu_savevm_trans_complete(s->mon, s->file); + if (ret < 0) { + fprintf(stderr, "qemu_savevm_trans_complete failed\n"); + goto out; + } + + if (ret) { + /* don't proceed until if fd isn't ready */ + ret = 1; + goto out; + } + + ret = qemu_ft_trans_commit(s->file); + if (ret < 0) { + fprintf(stderr, "qemu_ft_trans_commit failed\n"); + goto out; + } + + if (ret) { + ft_mode = FT_TRANSACTION_RECV; + ret = 1; + goto out; + } + + /* flush and check if events are remaining */ + vm_start(); + ret = event_tap_flush_one(); + if (ret < 0) { + fprintf(stderr, "event_tap_flush_one failed\n"); + goto out; + } + + ft_mode = ret ? FT_TRANSACTION_BEGIN : FT_TRANSACTION_ATOMIC; + } while (ft_mode != FT_TRANSACTION_BEGIN); + + vm_start(); + ret = 0; + +out: + return ret; +} + +static int migrate_ft_trans_get_ready(void *opaque) +{ + FdMigrationState *s = opaque; + int ret = -1; + + if (ft_mode != FT_TRANSACTION_RECV) { + fprintf(stderr, + "migrate_ft_trans_get_ready: invalid ft_mode %d\n", ft_mode); + goto error_out; + } + + /* flush and check if events are remaining */ + vm_start(); + ret = event_tap_flush_one(); + if (ret < 0) { + fprintf(stderr, "event_tap_flush_one failed\n"); + goto error_out; + } + + if (ret) { + ft_mode = FT_TRANSACTION_BEGIN; + } else { + ft_mode = FT_TRANSACTION_ATOMIC; + + ret = migrate_ft_trans_commit(s); + if (ret < 0) { + goto error_out; + } + if (ret) { + goto out; + } + } + + vm_start(); + ret = 0; + goto out; + +error_out: + migrate_ft_trans_error(s); + +out: + return ret; +} + +static int migrate_ft_trans_put_ready(void) +{ + FdMigrationState *s = migrate_to_fms(current_migration); + int ret = -1, init = 0, timeout; + static int64_t start, now; + + switch (ft_mode) { + case FT_INIT: + init = 1; + ft_mode = FT_TRANSACTION_BEGIN; + case FT_TRANSACTION_BEGIN: + now = start = qemu_get_clock(vm_clock); + /* start transatcion at best effort */ + qemu_file_set_rate_limit(s->file, 1); + + if (qemu_ft_trans_begin(s->file) < 0) { + fprintf(stderr, "qemu_transaction_begin failed\n"); + goto error_out; + } + + vm_stop(0); + + ret = qemu_savevm_trans_begin(s->mon, s->file, init); + if (ret < 0) { + fprintf(stderr, "qemu_savevm_trans_begin\n"); + goto error_out; + } + + if (ret) { + ft_mode = FT_TRANSACTION_ITER; + vm_start(); + } else { + ft_mode = FT_TRANSACTION_COMMIT; + if (migrate_ft_trans_commit(s) < 0) { + goto error_out; + } + } + break; + + case FT_TRANSACTION_ITER: + now = qemu_get_clock(vm_clock); + timeout = ((now - start) >= max_downtime); + if (timeout || qemu_savevm_state_iterate(s->mon, s->file) == 1) { + DPRINTF("ft trans iter timeout %d\n", timeout); + + ft_mode = FT_TRANSACTION_COMMIT; + if (migrate_ft_trans_commit(s) < 0) { + goto error_out; + } + return 1; + } + + ft_mode = FT_TRANSACTION_ITER; + break; + + case FT_TRANSACTION_ATOMIC: + case FT_TRANSACTION_COMMIT: + if (migrate_ft_trans_commit(s) < 0) { + goto error_out; + } + break; + + default: + fprintf(stderr, + "migrate_ft_trans_put_ready: invalid ft_mode %d", ft_mode); + goto error_out; + } + + ret = 0; + goto out; + +error_out: + migrate_ft_trans_error(s); + +out: + return ret; +} + +static void migrate_ft_trans_connect(FdMigrationState *s, int old_vm_running) +{ + /* close buffered_file and open ft_trans_file + * NB: fd won't get closed, and reused by ft_trans_file + */ + qemu_fclose(s->file); + + s->file = qemu_fopen_ops_ft_trans(s, + migrate_fd_put_buffer, + migrate_fd_get_buffer, + migrate_ft_trans_put_ready, + migrate_ft_trans_get_ready, + migrate_fd_wait_for_unfreeze, + migrate_fd_close, + 1); + socket_set_nodelay(s->fd); + + /* events are tapped from now */ + if (event_tap_register(migrate_ft_trans_put_ready) < 0) { + migrate_ft_trans_error(s); + } + + if (old_vm_running) { + vm_start(); + } +} + void migrate_fd_put_ready(void *opaque) { FdMigrationState *s = opaque; @@ -394,6 +646,11 @@ void migrate_fd_put_ready(void *opaque) } else { state = MIG_STATE_COMPLETED; } + + if (ft_mode && state == MIG_STATE_COMPLETED) { + return migrate_ft_trans_connect(s, old_vm_running); + } + if (migrate_fd_cleanup(s) < 0) { if (old_vm_running) { vm_start(); @@ -420,8 +677,14 @@ void migrate_fd_cancel(MigrationState *mig_state) DPRINTF("cancelling migration\n"); s->state = MIG_STATE_CANCELLED; - qemu_savevm_state_cancel(s->mon, s->file); + if (ft_mode) { + qemu_ft_trans_cancel(s->file); + ft_mode = FT_OFF; + event_tap_unregister(); + } + + qemu_savevm_state_cancel(s->mon, s->file); migrate_fd_cleanup(s); }