From: Wen Congyang <wency@cn.fujitsu.com>
To: xen devel <xen-devel@lists.xen.org>
Cc: Ian Campbell <Ian.Campbell@citrix.com>,
Wen Congyang <wency@cn.fujitsu.com>,
Ian Jackson <Ian.Jackson@eu.citrix.com>,
Jiang Yunhong <yunhong.jiang@intel.com>,
Dong Eddie <eddie.dong@intel.com>,
Yang Hongyang <yanghy@cn.fujitsu.com>,
Lai Jiangshan <laijs@cn.fujitsu.com>
Subject: [RFC Patch 18/25] primary vm suspend/get_dirty_pfn/resume/checkpoint code
Date: Fri, 18 Jul 2014 19:39:03 +0800 [thread overview]
Message-ID: <1405683551-12579-19-git-send-email-wency@cn.fujitsu.com> (raw)
In-Reply-To: <1405683551-12579-1-git-send-email-wency@cn.fujitsu.com>
We will do the following things again and again:
1. Suspend primary vm
a. Suspend primary vm
b. do postsuspend
c. Read LIBXL_COLO_SVM_SUSPENDED to master
d. Read secondary vm's dirty page information to master(count + pfn list)
2. Get dirty pfn list
a. Return secondary vm's dirty pfn list
3. Resume primary vm
a. Read LIBXL_COLO_SVM_READY from slave
b. Do presume
c. Resume primary vm
d. Read LIBXL_COLO_SVM_RESUMED from slave
4. Wait a new checkpoint
a. Wait a new checkpoint(not implemented)
b. Send LIBXL_COLO_NEW_CHECKPOINT to slave
Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
---
tools/libxc/xenguest.h | 12 +
tools/libxl/Makefile | 2 +-
tools/libxl/libxl.c | 18 ++
tools/libxl/libxl_colo.h | 10 +
tools/libxl/libxl_colo_save.c | 585 +++++++++++++++++++++++++++++++++++++
tools/libxl/libxl_dom.c | 13 +-
tools/libxl/libxl_internal.h | 39 ++-
tools/libxl/libxl_save_msgs_gen.pl | 1 +
tools/libxl/libxl_types.idl | 1 +
9 files changed, 670 insertions(+), 11 deletions(-)
create mode 100644 tools/libxl/libxl_colo_save.c
diff --git a/tools/libxc/xenguest.h b/tools/libxc/xenguest.h
index d3061c7..1aeaad2 100644
--- a/tools/libxc/xenguest.h
+++ b/tools/libxc/xenguest.h
@@ -72,6 +72,18 @@ struct save_callbacks {
*/
int (*toolstack_save)(uint32_t domid, uint8_t **buf, uint32_t *len, void *data);
+ /* Called after the guest is suspended.
+ *
+ * returns the list of dirty pfn:
+ * struct {
+ * uint64_t count;
+ * uint64_t pfn[];
+ * };
+ *
+ * Note: the caller must free the return value.
+ */
+ uint8_t *(*get_dirty_pfn)(void *data);
+
/* to be provided as the last argument to each callback function */
void* data;
};
diff --git a/tools/libxl/Makefile b/tools/libxl/Makefile
index 9642500..6b01a94 100644
--- a/tools/libxl/Makefile
+++ b/tools/libxl/Makefile
@@ -57,7 +57,7 @@ LIBXL_OBJS-y += libxl_nonetbuffer.o
endif
LIBXL_OBJS-y += libxl_checkpoint_device.o libxl_remus_disk_drbd.o
-LIBXL_OBJS-y += libxl_colo_restore.o
+LIBXL_OBJS-y += libxl_colo_restore.o libxl_colo_save.o
LIBXL_OBJS-$(CONFIG_X86) += libxl_cpuid.o libxl_x86.o
LIBXL_OBJS-$(CONFIG_ARM) += libxl_nocpuid.o libxl_arm.o
diff --git a/tools/libxl/libxl.c b/tools/libxl/libxl.c
index 6e6781e..2ba6798 100644
--- a/tools/libxl/libxl.c
+++ b/tools/libxl/libxl.c
@@ -17,6 +17,7 @@
#include "libxl_osdeps.h"
#include "libxl_internal.h"
+#include "libxl_colo.h"
#define PAGE_TO_MEMKB(pages) ((pages) * 4)
#define BACKEND_STRING_SIZE 5
@@ -823,8 +824,25 @@ int libxl_domain_remus_start(libxl_ctx *ctx, libxl_domain_remus_info *info,
assert(info);
+ if (type != LIBXL_DOMAIN_TYPE_HVM && info->colo) {
+ /* colo only supports hvm now */
+ rc = ERROR_FAIL;
+ goto out;
+ }
+
/* Convenience aliases */
libxl__checkpoint_device_state *const cds = &dss->cds;
+ libxl__colo_save_state *const css = &dss->css;
+
+ if (info->colo) {
+ css->cds.ao = ao;
+ css->cds.domid = domid;
+ css->cds.saved_rc = 0;
+
+ /* Point of no return */
+ libxl__colo_save_setup(egc, css);
+ return AO_INPROGRESS;
+ }
if (info->netbuf) {
if (!libxl__netbuffer_enabled(gc)) {
diff --git a/tools/libxl/libxl_colo.h b/tools/libxl/libxl_colo.h
index 91df275..26a2563 100644
--- a/tools/libxl/libxl_colo.h
+++ b/tools/libxl/libxl_colo.h
@@ -35,4 +35,14 @@ extern void libxl__colo_restore_teardown(libxl__egc *egc,
libxl__colo_restore_state *crs,
int rc);
+extern void libxl__colo_save_domain_suspend_callback(void *data);
+extern void libxl__colo_save_domain_resume_callback(void *data);
+extern void libxl__colo_save_domain_checkpoint_callback(void *data);
+extern void libxl__colo_save_get_dirty_pfn_callback(void *data);
+extern void libxl__colo_save_setup(libxl__egc *egc,
+ libxl__colo_save_state *css);
+extern void libxl__colo_save_teardown(libxl__egc *egc,
+ libxl__colo_save_state *css,
+ int rc);
+
#endif
diff --git a/tools/libxl/libxl_colo_save.c b/tools/libxl/libxl_colo_save.c
new file mode 100644
index 0000000..aef6f97
--- /dev/null
+++ b/tools/libxl/libxl_colo_save.c
@@ -0,0 +1,585 @@
+/*
+ * Copyright (C) 2014 FUJITSU LIMITED
+ * Author: Wen Congyang <wency@cn.fujitsu.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published
+ * by the Free Software Foundation; version 2.1 only. with the special
+ * exception on linking described in file LICENSE.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU Lesser General Public License for more details.
+ */
+
+#include "libxl_osdeps.h" /* must come before any other headers */
+
+#include "libxl_internal.h"
+#include "libxl_colo.h"
+
+static const libxl__checkpoint_device_subkind_ops *colo_ops[] = {
+ NULL,
+};
+
+/* ================= colo: setup save environment ================= */
+static void colo_save_setup_done(libxl__egc *egc,
+ libxl__checkpoint_device_state *cds,
+ int rc);
+static void colo_save_setup_failed(libxl__egc *egc,
+ libxl__checkpoint_device_state *cds,
+ int rc);
+
+void libxl__colo_save_setup(libxl__egc *egc, libxl__colo_save_state *css)
+{
+ libxl__domain_suspend_state *dss = CONTAINER_OF(css, *dss, css);
+
+ css->send_fd = dss->fd;
+ css->recv_fd = dss->recv_fd;
+
+ /* TODO: disk/nic support */
+ css->cds.enabled_device_kinds = 0;
+ css->cds.ops = colo_ops;
+ css->cds.callback = colo_save_setup_done;
+ css->svm_running = false;
+
+ libxl__checkpoint_devices_setup(egc, &css->cds);
+}
+
+static void colo_save_setup_done(libxl__egc *egc,
+ libxl__checkpoint_device_state *cds,
+ int rc)
+{
+ libxl__colo_save_state *css = CONTAINER_OF(cds, *css, cds);
+ libxl__domain_suspend_state *dss = CONTAINER_OF(css, *dss, css);
+ STATE_AO_GC(cds->ao);
+
+ if (!rc) {
+ libxl__domain_suspend(egc, dss);
+ return;
+ }
+
+ LOG(ERROR, "COLO: failed to setup device for guest with domid %u",
+ dss->domid);
+ css->cds.saved_rc = rc;
+ css->cds.callback = colo_save_setup_failed;
+ libxl__checkpoint_devices_teardown(egc, &css->cds);
+}
+
+static void colo_save_setup_failed(libxl__egc *egc,
+ libxl__checkpoint_device_state *cds,
+ int rc)
+{
+ STATE_AO_GC(cds->ao);
+
+ libxl__ao_complete(egc, ao, rc);
+}
+
+
+/* ================= colo: teardown save environment ================= */
+static void colo_teardown_done(libxl__egc *egc,
+ libxl__checkpoint_device_state *cds,
+ int rc);
+
+void libxl__colo_save_teardown(libxl__egc *egc,
+ libxl__colo_save_state *css,
+ int rc)
+{
+ libxl__domain_suspend_state *dss = CONTAINER_OF(css, *dss, css);
+
+ dss->css.cds.saved_rc = rc;
+ dss->css.cds.callback = colo_teardown_done;
+ libxl__checkpoint_devices_teardown(egc, &dss->css.cds);
+ return;
+}
+
+static void colo_teardown_done(libxl__egc *egc,
+ libxl__checkpoint_device_state *cds,
+ int rc)
+{
+ libxl__colo_save_state *css = CONTAINER_OF(cds, *css, cds);
+ libxl__domain_suspend_state *dss = CONTAINER_OF(css, *dss, css);
+ dss->callback(egc, dss, rc);
+}
+
+/*
+ * checkpoint callbacks are called in the following order:
+ * 1. suspend
+ * 2. resume
+ * 3. checkpoint
+ */
+static void colo_common_read_done(libxl__egc *egc,
+ libxl__datareader_state *drs,
+ ssize_t real_size, int errnoval);
+/* ===================== colo: suspend primary vm ===================== */
+/*
+ * Do the following things when suspending primary vm:
+ * 1. suspend primary vm
+ * 2. do postsuspend
+ * 3. read LIBXL_COLO_SVM_SUSPENDED
+ * 4. read secondary vm's dirty pages
+ */
+static void colo_suspend_primary_vm_done(libxl__egc *egc,
+ libxl__domain_suspend_state2 *dss2,
+ int ok);
+static void colo_postsuspend_cb(libxl__egc *egc,
+ libxl__checkpoint_device_state *cds,
+ int rc);
+static void colo_read_pfn(libxl__egc *egc, libxl__colo_save_state *css);
+
+void libxl__colo_save_domain_suspend_callback(void *data)
+{
+ libxl__save_helper_state *shs = data;
+ libxl__egc *egc = shs->egc;
+ libxl__domain_suspend_state *dss = CONTAINER_OF(shs, *dss, shs);
+
+ /* Convenience aliases */
+ libxl__domain_suspend_state2 *dss2 = &dss->dss2;
+
+ dss2->callback_common_done = colo_suspend_primary_vm_done;
+ libxl__domain_suspend2(egc, dss2);
+}
+
+static void colo_suspend_primary_vm_done(libxl__egc *egc,
+ libxl__domain_suspend_state2 *dss2,
+ int ok)
+{
+ libxl__domain_suspend_state *dss = CONTAINER_OF(dss2, *dss, dss2);
+
+ STATE_AO_GC(dss2->ao);
+
+ if (!ok) {
+ LOG(ERROR, "cannot suspend primary vm");
+ goto out;
+ }
+
+ /* Convenience aliases */
+ libxl__checkpoint_device_state *const cds = &dss->css.cds;
+
+ cds->callback = colo_postsuspend_cb;
+ libxl__checkpoint_devices_postsuspend(egc, cds);
+ return;
+
+out:
+ libxl__xc_domain_saverestore_async_callback_done(egc, &dss->shs, ok);
+}
+
+static void colo_postsuspend_cb(libxl__egc *egc,
+ libxl__checkpoint_device_state *cds,
+ int rc)
+{
+ int ok = 0;
+ libxl__colo_save_state *css = CONTAINER_OF(cds, *css, cds);
+ libxl__domain_suspend_state *dss = CONTAINER_OF(css, *dss, css);
+
+ /* Convenience aliases */
+ libxl__datareader_state *const drs = &css->drs;
+
+ STATE_AO_GC(cds->ao);
+
+ if (rc) {
+ LOG(ERROR, "postsuspend fails");
+ goto out;
+ }
+
+ if (!css->svm_running) {
+ ok = 1;
+ goto out;
+ }
+
+ /*
+ * read LIBXL_COLO_SVM_SUSPENDED and the count of
+ * secondary vm's dirty pages.
+ */
+ memset(drs, 0, sizeof(*drs));
+ drs->ao = ao;
+ drs->readfd = css->recv_fd;
+ drs->readsize = sizeof(css->temp_buff);
+ drs->readwhat = "colo stream";
+ drs->callback = colo_common_read_done;
+ drs->buf = css->temp_buff;
+ css->callback = colo_read_pfn;
+
+ if (libxl__datareader_start(drs)) {
+ LOG(ERROR, "libxl__datareader_start() fails");
+ goto out;
+ }
+
+ return;
+
+out:
+ libxl__xc_domain_saverestore_async_callback_done(egc, &dss->shs, ok);
+}
+
+static void colo_read_pfn(libxl__egc *egc, libxl__colo_save_state *css)
+{
+ int ok = 0;
+ libxl__domain_suspend_state *dss = CONTAINER_OF(css, *dss, css);
+ STATE_AO_GC(css->cds.ao);
+
+ /* Convenience aliases */
+ libxl__datareader_state *const drs = &css->drs;
+
+ assert(!css->buff);
+ css->section = css->temp_buff[0];
+ css->count = *(uint64_t *)(&css->temp_buff[1]);
+
+ if (css->section != LIBXL_COLO_SVM_SUSPENDED) {
+ LOG(ERROR, "invalid section: %d, expected: %d",
+ css->section, LIBXL_COLO_SVM_SUSPENDED);
+ goto out;
+ }
+
+ css->buff = libxl__zalloc(NOGC, sizeof(uint64_t) * (css->count + 1));
+ css->buff[0] = css->count;
+
+ if (css->count == 0) {
+ /* no dirty pages */
+ ok = 1;
+ goto out;
+ }
+
+ /* read the pfn of secondary vm's dirty pages */
+ memset(drs, 0, sizeof(*drs));
+ drs->ao = ao;
+ drs->readfd = css->recv_fd;
+ drs->readsize = css->count * sizeof(uint64_t);
+ drs->readwhat = "colo stream";
+ drs->callback = colo_common_read_done;
+ drs->buf = css->buff + 1;
+ css->callback = NULL;
+
+ if (libxl__datareader_start(drs)) {
+ LOG(ERROR, "libxl__datareader_start() fails");
+ goto out;
+ }
+
+ return;
+
+out:
+ libxl__xc_domain_saverestore_async_callback_done(egc, &dss->shs, ok);
+}
+
+
+/* ===================== colo: get dirty pfn ===================== */
+void libxl__colo_save_get_dirty_pfn_callback(void *data)
+{
+ libxl__save_helper_state *shs = data;
+ libxl__egc *egc = shs->egc;
+ libxl__domain_suspend_state *dss = CONTAINER_OF(shs, *dss, shs);
+ uint64_t size;
+
+ /* Convenience aliases */
+ libxl__colo_save_state *const css = &dss->css;
+
+ assert(css->buff);
+ size = sizeof(uint64_t) * (css->count + 1);
+
+ libxl__xc_domain_saverestore_async_callback_done_with_data(egc, shs,
+ (uint8_t *)css->buff,
+ size);
+ free(css->buff);
+ css->buff = NULL;
+}
+
+
+/* ===================== colo: resume primary vm ===================== */
+/*
+ * Do the following things when resuming primary vm:
+ * 1. read LIBXL_COLO_SVM_READY
+ * 2. do preresume
+ * 3. resume primary vm
+ * 4. read LIBXL_COLO_SVM_RESUMED
+ */
+static void colo_preresume_dm_saved(libxl__egc *egc,
+ libxl__domain_suspend_state *dss, int rc);
+static void colo_read_svm_ready_done(libxl__egc *egc,
+ libxl__colo_save_state *css);
+static void colo_preresume_cb(libxl__egc *egc,
+ libxl__checkpoint_device_state *cds,
+ int rc);
+static void colo_read_svm_resumed_done(libxl__egc *egc,
+ libxl__colo_save_state *css);
+
+void libxl__colo_save_domain_resume_callback(void *data)
+{
+ libxl__save_helper_state *shs = data;
+ libxl__egc *egc = shs->egc;
+ libxl__domain_suspend_state *dss = CONTAINER_OF(shs, *dss, shs);
+
+ /* This would go into tailbuf. */
+ if (dss->hvm) {
+ libxl__domain_save_device_model(egc, dss, colo_preresume_dm_saved);
+ } else {
+ colo_preresume_dm_saved(egc, dss, 0);
+ }
+
+ return;
+}
+
+static void colo_preresume_dm_saved(libxl__egc *egc,
+ libxl__domain_suspend_state *dss, int rc)
+{
+ /* Convenience aliases */
+ libxl__colo_save_state *const css = &dss->css;
+ libxl__datareader_state *const drs = &css->drs;
+
+ STATE_AO_GC(css->cds.ao);
+
+ if (rc) {
+ LOG(ERROR, "Failed to save device model. Terminating COLO..");
+ goto out;
+ }
+
+ /* read LIBXL_COLO_SVM_READY */
+ memset(drs, 0, sizeof(*drs));
+ drs->ao = ao;
+ drs->readfd = css->recv_fd;
+ drs->readsize = sizeof(css->section);
+ drs->readwhat = "colo stream";
+ drs->callback = colo_common_read_done;
+ drs->buf = &css->section;
+ css->callback = colo_read_svm_ready_done;
+
+ if (libxl__datareader_start(drs)) {
+ LOG(ERROR, "libxl__datareader_start() fails");
+ goto out;
+ }
+
+ return;
+
+out:
+ libxl__xc_domain_saverestore_async_callback_done(egc, &dss->shs, 0);
+}
+
+static void colo_read_svm_ready_done(libxl__egc *egc,
+ libxl__colo_save_state *css)
+{
+ libxl__domain_suspend_state *dss = CONTAINER_OF(css, *dss, css);
+
+ STATE_AO_GC(css->cds.ao);
+
+ if (css->section != LIBXL_COLO_SVM_READY) {
+ LOG(ERROR, "invalid section: %d, expected: %d",
+ css->section, LIBXL_COLO_SVM_READY);
+ goto out;
+ }
+
+ css->svm_running = true;
+ css->cds.callback = colo_preresume_cb;
+ libxl__checkpoint_devices_preresume(egc, &css->cds);
+
+ return;
+
+out:
+ libxl__xc_domain_saverestore_async_callback_done(egc, &dss->shs, 0);
+}
+
+static void colo_preresume_cb(libxl__egc *egc,
+ libxl__checkpoint_device_state *cds,
+ int rc)
+{
+ libxl__colo_save_state *css = CONTAINER_OF(cds, *css, cds);
+ libxl__domain_suspend_state *dss = CONTAINER_OF(css, *dss, css);
+
+ /* Convenience aliases */
+ libxl__datareader_state *const drs = &css->drs;
+
+ STATE_AO_GC(cds->ao);
+
+ if (rc) {
+ LOG(ERROR, "preresume fails");
+ goto out;
+ }
+
+ /* Resumes the domain and the device model */
+ if (libxl__domain_resume(gc, dss->domid, /* Fast Suspend */1, 0)) {
+ LOG(ERROR, "cannot resume primary vm");
+ goto out;
+ }
+
+ /* read LIBXL_COLO_SVM_RESUMED */
+ memset(drs, 0, sizeof(*drs));
+ drs->ao = ao;
+ drs->readfd = css->recv_fd;
+ drs->readsize = sizeof(css->section);
+ drs->readwhat = "colo stream";
+ drs->callback = colo_common_read_done;
+ drs->buf = &css->section;
+ css->callback = colo_read_svm_resumed_done;
+
+ if (libxl__datareader_start(drs)) {
+ LOG(ERROR, "libxl__datareader_start() fails");
+ goto out;
+ }
+
+ return;
+
+out:
+ libxl__xc_domain_saverestore_async_callback_done(egc, &dss->shs, 0);
+}
+
+static void colo_read_svm_resumed_done(libxl__egc *egc,
+ libxl__colo_save_state *css)
+{
+ int ok = 0;
+ libxl__domain_suspend_state *dss = CONTAINER_OF(css, *dss, css);
+
+ STATE_AO_GC(css->cds.ao);
+
+ if (css->section != LIBXL_COLO_SVM_RESUMED) {
+ LOG(ERROR, "invalid section: %d, expected: %d",
+ css->section, LIBXL_COLO_SVM_RESUMED);
+ goto out;
+ }
+
+ ok = 1;
+
+out:
+ libxl__xc_domain_saverestore_async_callback_done(egc, &dss->shs, ok);
+}
+
+
+/* ===================== colo: wait new checkpoint ===================== */
+/*
+ * Do the following things:
+ * 1. do commit
+ * 2. wait for a new checkpoint
+ * 3. write LIBXL_COLO_NEW_CHECKPOINT
+ */
+static void colo_device_commit_cb(libxl__egc *egc,
+ libxl__checkpoint_device_state *cds,
+ int rc);
+static void colo_start_new_checkpoint(libxl__egc *egc,
+ libxl__checkpoint_device_state *cds,
+ int rc);
+static void colo_send_data_done(libxl__egc *egc,
+ libxl__datacopier_state *dc,
+ int onwrite, int errnoval);
+
+void libxl__colo_save_domain_checkpoint_callback(void *data)
+{
+ libxl__save_helper_state *shs = data;
+ libxl__domain_suspend_state *dss = CONTAINER_OF(shs, *dss, shs);
+ libxl__egc *egc = dss->shs.egc;
+
+ /* Convenience aliases */
+ libxl__checkpoint_device_state *const cds = &dss->css.cds;
+
+ cds->callback = colo_device_commit_cb;
+ libxl__checkpoint_devices_commit(egc, cds);
+}
+
+static void colo_device_commit_cb(libxl__egc *egc,
+ libxl__checkpoint_device_state *cds,
+ int rc)
+{
+ libxl__colo_save_state *css = CONTAINER_OF(cds, *css, cds);
+ libxl__domain_suspend_state *dss = CONTAINER_OF(css, *dss, css);
+
+ STATE_AO_GC(cds->ao);
+
+ if (rc) {
+ LOG(ERROR, "commit fails");
+ goto out;
+ }
+
+ /* TODO: wait a new checkpoint */
+ colo_start_new_checkpoint(egc, cds, 0);
+ return;
+
+out:
+ libxl__xc_domain_saverestore_async_callback_done(egc, &dss->shs, 0);
+}
+
+static void colo_start_new_checkpoint(libxl__egc *egc,
+ libxl__checkpoint_device_state *cds,
+ int rc)
+{
+ libxl__colo_save_state *css = CONTAINER_OF(cds, *css, cds);
+ libxl__domain_suspend_state *dss = CONTAINER_OF(css, *dss, css);
+ uint8_t section = LIBXL_COLO_NEW_CHECKPOINT;
+
+ /* Convenience aliases */
+ libxl__datacopier_state *const dc = &css->dc;
+
+ STATE_AO_GC(cds->ao);
+
+ if (rc)
+ goto out;
+
+ /* write LIBXL_COLO_NEW_CHECKPOINT */
+ memset(dc, 0, sizeof(*dc));
+ dc->ao = ao;
+ dc->readfd = -1;
+ dc->writefd = css->send_fd;
+ dc->maxsz = INT_MAX;
+ dc->copywhat = "new checkpoint is triggered";
+ dc->writewhat = "colo stream";
+ dc->callback = colo_send_data_done;
+
+ rc = libxl__datacopier_start(dc);
+ if (rc) {
+ LOG(ERROR, "libxl__datacopier_start() fails");
+ goto out;
+ }
+
+ /* tell slave that a new checkpoint is triggered */
+ libxl__datacopier_prefixdata(egc, dc, §ion, sizeof(section));
+ return;
+
+out:
+ libxl__xc_domain_saverestore_async_callback_done(egc, &dss->shs, 0);
+}
+
+static void colo_send_data_done(libxl__egc *egc,
+ libxl__datacopier_state *dc,
+ int onwrite, int errnoval)
+{
+ libxl__colo_save_state *css = CONTAINER_OF(dc, *css, dc);
+ libxl__domain_suspend_state *dss = CONTAINER_OF(css, *dss, css);
+ int ok;
+
+ STATE_AO_GC(dc->ao);
+
+ if (onwrite == -1 || errnoval) {
+ LOG(ERROR, "cannot start a new checkpoint");
+ ok = 0;
+ goto out;
+ }
+
+ /* Everything is OK */
+ ok = 1;
+
+out:
+ libxl__xc_domain_saverestore_async_callback_done(egc, &dss->shs, ok);
+}
+
+
+/* ===================== colo: common callback ===================== */
+static void colo_common_read_done(libxl__egc *egc,
+ libxl__datareader_state *drs,
+ ssize_t real_size, int errnoval)
+{
+ int ok = 0;
+ libxl__colo_save_state *css = CONTAINER_OF(drs, *css, drs);
+ libxl__domain_suspend_state *dss = CONTAINER_OF(css, *dss, css);
+ STATE_AO_GC(drs->ao);
+
+ if (real_size < drs->readsize) {
+ LOG(ERROR, "reading data fails: %lld", (long long)real_size);
+ goto out;
+ }
+
+ if (!css->callback) {
+ /* Everything is OK */
+ ok = 1;
+ goto out;
+ }
+
+ css->callback(egc, css);
+ return;
+
+out:
+ libxl__xc_domain_saverestore_async_callback_done(egc, &dss->shs, ok);
+}
diff --git a/tools/libxl/libxl_dom.c b/tools/libxl/libxl_dom.c
index 4ea2607..f51e701 100644
--- a/tools/libxl/libxl_dom.c
+++ b/tools/libxl/libxl_dom.c
@@ -19,6 +19,7 @@
#include "libxl_internal.h"
#include "libxl_arch.h"
+#include "libxl_colo.h"
#include <xc_dom.h>
#include <xen/hvm/hvm_info_table.h>
@@ -1747,7 +1748,12 @@ void libxl__domain_suspend(libxl__egc *egc, libxl__domain_suspend_state *dss)
}
memset(callbacks, 0, sizeof(*callbacks));
- if (r_info != NULL) {
+ if (r_info != NULL && r_info->colo) {
+ callbacks->suspend = libxl__colo_save_domain_suspend_callback;
+ callbacks->postcopy = libxl__colo_save_domain_resume_callback;
+ callbacks->checkpoint = libxl__colo_save_domain_checkpoint_callback;
+ callbacks->get_dirty_pfn = libxl__colo_save_get_dirty_pfn_callback;
+ } else if (r_info != NULL) {
callbacks->suspend = libxl__remus_domain_suspend_callback;
callbacks->postcopy = libxl__remus_domain_resume_callback;
callbacks->checkpoint = libxl__remus_domain_checkpoint_callback;
@@ -1911,7 +1917,10 @@ static void domain_suspend_done(libxl__egc *egc,
xc_suspend_evtchn_release(CTX->xch, CTX->xce, domid,
dss2->guest_evtchn.port, &dss2->guest_evtchn_lockfd);
- if (dss->remus) {
+ if (dss->remus && dss->remus->colo) {
+ libxl__colo_save_teardown(egc, &dss->css, rc);
+ return;
+ } else if (dss->remus) {
/*
* With Remus, if we reach this point, it means either
* backup died or some network error occurred preventing us
diff --git a/tools/libxl/libxl_internal.h b/tools/libxl/libxl_internal.h
index a1f3ec8..20f7da8 100644
--- a/tools/libxl/libxl_internal.h
+++ b/tools/libxl/libxl_internal.h
@@ -2690,6 +2690,25 @@ extern const libxl__checkpoint_device_subkind_ops remus_device_drbd_disk;
_hidden int libxl__netbuffer_enabled(libxl__gc *gc);
+/*----- colo related state structure -----*/
+typedef struct libxl__colo_save_state libxl__colo_save_state;
+struct libxl__colo_save_state {
+ libxl__checkpoint_device_state cds;
+ int send_fd;
+ int recv_fd;
+
+ /* private */
+ libxl__datacopier_state dc;
+ libxl__datareader_state drs;
+ uint8_t section;
+ uint64_t count;
+ uint64_t *buff;
+ /* read section and count, and then store it in temp_buff */
+ uint8_t temp_buff[9];
+ void (*callback)(libxl__egc *, libxl__colo_save_state *);
+ bool svm_running;
+};
+
/*----- Domain suspend (save) state structure -----*/
typedef struct libxl__domain_suspend_state libxl__domain_suspend_state;
@@ -2753,14 +2772,18 @@ struct libxl__domain_suspend_state {
libxl__domain_suspend_state2 dss2;
int hvm;
int xcflags;
- /* for Remus */
- struct {
- libxl__checkpoint_device_state cds;
- const char *netbufscript;
- /* used for Remus checkpoint */
- libxl__ev_time checkpoint_timeout;
- /* checkpoint interval */
- int interval;
+ union {
+ /* for Remus */
+ struct {
+ libxl__checkpoint_device_state cds;
+ const char *netbufscript;
+ /* used for Remus checkpoint */
+ libxl__ev_time checkpoint_timeout;
+ /* checkpoint interval */
+ int interval;
+ };
+ /* for COLO */
+ libxl__colo_save_state css;
};
libxl__save_helper_state shs;
libxl__logdirty_switch logdirty;
diff --git a/tools/libxl/libxl_save_msgs_gen.pl b/tools/libxl/libxl_save_msgs_gen.pl
index 0239cac..fbb2d67 100755
--- a/tools/libxl/libxl_save_msgs_gen.pl
+++ b/tools/libxl/libxl_save_msgs_gen.pl
@@ -36,6 +36,7 @@ our @msgs = (
'unsigned long', 'console_mfn'] ],
[ 9, 'srW', "complete", [qw(int retval
int errnoval)] ],
+ [ 10, 'scxAB', "get_dirty_pfn", [] ],
);
#----------------------------------------
diff --git a/tools/libxl/libxl_types.idl b/tools/libxl/libxl_types.idl
index 1e1a62e..6b21dcb 100644
--- a/tools/libxl/libxl_types.idl
+++ b/tools/libxl/libxl_types.idl
@@ -600,6 +600,7 @@ libxl_domain_remus_info = Struct("domain_remus_info",[
("netbuf", bool),
("netbufscript", string),
("diskbuf", bool),
+ ("colo", bool)
])
libxl_event_type = Enumeration("event_type", [
--
1.9.3
next prev parent reply other threads:[~2014-07-18 11:39 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-07-18 11:38 [RFC Patch 00/25] COarse-grain LOck-stepping Virtual Machines for Non-stop Service Wen Congyang
2014-07-18 11:38 ` [RFC Patch 01/25] copy the correct page to memory Wen Congyang
2014-07-18 11:38 ` [RFC Patch 02/25] csum the correct page Wen Congyang
2014-07-18 11:38 ` [RFC Patch 03/25] don't zero out ioreq page Wen Congyang
2014-07-18 11:38 ` [RFC Patch 04/25] don't touch remus in remus_device Wen Congyang
2014-07-18 11:38 ` [RFC Patch 05/25] rename remus device to checkpoint device Wen Congyang
2014-07-18 11:38 ` [RFC Patch 06/25] adjust the indentation Wen Congyang
2014-07-18 11:38 ` [RFC Patch 07/25] Refactor domain_suspend_callback_common() Wen Congyang
2014-07-18 11:38 ` [RFC Patch 08/25] Update libxl__domain_resume() for colo Wen Congyang
2014-07-18 11:38 ` [RFC Patch 09/25] Update libxl__domain_suspend_common_switch_qemu_logdirty() " Wen Congyang
2014-07-18 11:38 ` [RFC Patch 10/25] Introduce a new internal API libxl__domain_unpause() Wen Congyang
2014-07-18 11:38 ` [RFC Patch 11/25] Update libxl__domain_unpause() to support qemu-xen Wen Congyang
2014-07-18 11:38 ` [RFC Patch 12/25] support to resume uncooperative HVM guests Wen Congyang
2014-07-18 11:38 ` [RFC Patch 13/25] update datecopier to support sending data only Wen Congyang
2014-07-18 11:38 ` [RFC Patch 14/25] introduce a new API to aync read data from fd Wen Congyang
2014-07-18 11:39 ` [RFC Patch 15/25] Update libxl_save_msgs_gen.pl to support return data from xl to xc Wen Congyang
2014-07-18 11:39 ` [RFC Patch 16/25] Allow slave sends data to master Wen Congyang
2014-07-18 11:39 ` [RFC Patch 17/25] secondary vm suspend/resume/checkpoint code Wen Congyang
2014-07-18 11:39 ` Wen Congyang [this message]
2014-07-18 11:39 ` [RFC Patch 19/25] xc_domain_save: flush cache before calling callbacks->postcopy() in colo mode Wen Congyang
2014-07-18 11:39 ` [RFC Patch 20/25] COLO: xc related codes Wen Congyang
2014-07-18 11:39 ` [RFC Patch 21/25] send store mfn and console mfn to xl before resuming secondary vm Wen Congyang
2014-07-18 11:39 ` [RFC Patch 22/25] implement the cmdline for COLO Wen Congyang
2014-07-18 11:39 ` [RFC Patch 23/25] HACK: do checkpoint per 20ms Wen Congyang
2014-07-18 11:39 ` [RFC Patch 24/25] fix vm entry fail Wen Congyang
2014-07-24 10:40 ` Tim Deegan
2014-07-25 5:39 ` Wen Congyang
2014-08-07 6:52 ` Wen Congyang
2014-07-18 11:39 ` [RFC Patch 25/25] sync mmu before resuming secondary vm Wen Congyang
2014-07-24 10:59 ` Tim Deegan
2014-07-25 5:46 ` Wen Congyang
2014-08-07 7:46 ` Wen Congyang
2014-07-18 11:39 ` [RFC Patch 26/25] Introduce "xen-load-devices-state" Wen Congyang
2014-07-18 11:43 ` [RFC Patch 00/25] COarse-grain LOck-stepping Virtual Machines for Non-stop Service Wen Congyang
2014-07-18 14:18 ` Andrew Cooper
2014-07-18 14:30 ` Wen Congyang
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=1405683551-12579-19-git-send-email-wency@cn.fujitsu.com \
--to=wency@cn.fujitsu.com \
--cc=Ian.Campbell@citrix.com \
--cc=Ian.Jackson@eu.citrix.com \
--cc=eddie.dong@intel.com \
--cc=laijs@cn.fujitsu.com \
--cc=xen-devel@lists.xen.org \
--cc=yanghy@cn.fujitsu.com \
--cc=yunhong.jiang@intel.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).