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 v2 44/45] libxl/colo: setup and control disk replication for blktap2 backends
Date: Fri, 8 Aug 2014 15:01:43 +0800 [thread overview]
Message-ID: <1407481305-19808-45-git-send-email-wency@cn.fujitsu.com> (raw)
In-Reply-To: <1407481305-19808-1-git-send-email-wency@cn.fujitsu.com>
This patch adds the machinery required for protecting a guest's
disk state, when the guest disk uses a blktap2 disk backend.
1. COLO blktap2 disk device: Implements the interfaces required by the
checkpoint abstract device layer. A note about the implementation:
a) setup() is called for each disk attached to the guest.
During setup():
i) perform the sanity check: backend type should be LIBXL_DISK_BACKEND_TAP
and format should be LIBXL_DISK_FORMAT_COLO.
ii) connect to the control socket: /var/run/tap/colo_xxx, xxx is
"host:port"(The character ':/' will be changed to '_').
b) The postsuspend callback() will write "flush" to this socket
c) The commit callback() will wait and read "done" from this socket
Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
---
tools/libxl/Makefile | 2 +-
tools/libxl/libxl_colo_save.c | 5 +-
tools/libxl/libxl_colo_save_disk_blktap2.c | 216 +++++++++++++++++++++++++++++
tools/libxl/libxl_create.c | 7 +
tools/libxl/libxl_noblktap2.c | 29 ++++
5 files changed, 257 insertions(+), 2 deletions(-)
create mode 100644 tools/libxl/libxl_colo_save_disk_blktap2.c
diff --git a/tools/libxl/Makefile b/tools/libxl/Makefile
index 1c32ae2..b4755c8 100644
--- a/tools/libxl/Makefile
+++ b/tools/libxl/Makefile
@@ -45,7 +45,7 @@ LIBXLU_LIBS =
LIBXL_OBJS-y = osdeps.o libxl_paths.o libxl_bootloader.o flexarray.o
ifeq ($(LIBXL_BLKTAP),y)
-LIBXL_OBJS-y += libxl_blktap2.o
+LIBXL_OBJS-y += libxl_blktap2.o libxl_colo_save_disk_blktap2.o
else
LIBXL_OBJS-y += libxl_noblktap2.o
endif
diff --git a/tools/libxl/libxl_colo_save.c b/tools/libxl/libxl_colo_save.c
index 75d83c8..b7070b2 100644
--- a/tools/libxl/libxl_colo_save.c
+++ b/tools/libxl/libxl_colo_save.c
@@ -18,7 +18,10 @@
#include "libxl_internal.h"
#include "libxl_colo.h"
+extern const libxl__checkpoint_device_subkind_ops colo_save_device_blktap2_disk;
+
static const libxl__checkpoint_device_subkind_ops *colo_ops[] = {
+ &colo_save_device_blktap2_disk,
NULL,
};
@@ -49,7 +52,7 @@ void libxl__colo_save_setup(libxl__egc *egc, libxl__colo_save_state *css)
css->svm_running = false;
/* TODO: disk/nic support */
- cds->device_kind_flags = 0;
+ cds->device_kind_flags = LIBXL__CHECKPOINT_DEVICE_DISK;
cds->ops = colo_ops;
cds->callback = colo_save_setup_done;
cds->ao = ao;
diff --git a/tools/libxl/libxl_colo_save_disk_blktap2.c b/tools/libxl/libxl_colo_save_disk_blktap2.c
new file mode 100644
index 0000000..1c35971
--- /dev/null
+++ b/tools/libxl/libxl_colo_save_disk_blktap2.c
@@ -0,0 +1,216 @@
+/*
+ * 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 <string.h>
+#include <sys/un.h>
+
+#define BLKTAP2_REQUEST "flush"
+#define BLKTAP2_RESPONSE "done"
+#define BLKTAP_CTRL_DIR "/var/run/tap"
+
+typedef struct libxl__colo_blktap2_disk {
+ char *name;
+ char *ctl_socket_path;
+ int fd;
+ libxl__ev_fd ev;
+ libxl__checkpoint_device *dev;
+}libxl__colo_blktap2_disk;
+
+/* ========== init() and cleanup() ========== */
+static int blktap2_colo_init(libxl__checkpoint_devices_state *cds)
+{
+ return 0;
+}
+
+static void blktap2_colo_cleanup(libxl__checkpoint_devices_state *cds)
+{
+}
+
+/* ========== setup() and teardown() ========== */
+static int blktap2_control_connect(libxl__gc *gc,
+ libxl__colo_blktap2_disk *blktap2_disk)
+{
+ struct sockaddr_un saddr;
+ int fd, err;
+
+ fd = socket(AF_UNIX, SOCK_STREAM, 0);
+ if (fd < 0) {
+ LOG(ERROR, "cannot creating socket fd");
+ return ERROR_FAIL;
+ }
+
+ memset(&saddr, 0, sizeof(saddr));
+ saddr.sun_family = AF_UNIX;
+ strcpy(saddr.sun_path, blktap2_disk->ctl_socket_path);
+
+ err = connect(fd, (const struct sockaddr *)&saddr, sizeof(saddr));
+ if (err) {
+ LOG(ERROR, "cannot connecte to %s", blktap2_disk->ctl_socket_path);
+ close(fd);
+ return ERROR_FAIL;
+ }
+
+ blktap2_disk->fd = fd;
+ return 0;
+}
+
+static void blktap2_colo_setup(libxl__checkpoint_device *dev)
+{
+ const libxl_device_disk *disk = dev->backend_dev;
+ libxl__colo_blktap2_disk *blktap2_disk;
+ int rc;
+ char *type;
+ int i, l;
+
+ STATE_AO_GC(dev->cds->ao);
+
+ if (disk->backend != LIBXL_DISK_BACKEND_TAP ||
+ disk->format != LIBXL_DISK_FORMAT_COLO) {
+ rc = ERROR_CHECKPOINT_DEVOPS_DOES_NOT_MATCH;
+ goto out;
+ }
+
+ dev->set_up = 1;
+ GCNEW(blktap2_disk);
+ dev->concrete_data = blktap2_disk;
+ blktap2_disk->fd = -1;
+ blktap2_disk->dev = dev;
+
+ type = strchr(disk->pdev_path, '|');
+ if (!type) {
+ LOG(ERROR, "unexpected pdev_path: %s", disk->pdev_path);
+ rc = ERROR_FAIL;
+ goto out;
+ }
+ blktap2_disk->name = libxl__strndup(gc, disk->pdev_path,
+ type - disk->pdev_path);
+ blktap2_disk->ctl_socket_path = libxl__sprintf(gc, "%s/colo_%s",
+ BLKTAP_CTRL_DIR,
+ blktap2_disk->name);
+ /* scrub socket pathname */
+ l = strlen(blktap2_disk->ctl_socket_path);
+ for (i = strlen(BLKTAP_CTRL_DIR) + 1; i < l; i++) {
+ if (strchr(":/", blktap2_disk->ctl_socket_path[i]))
+ blktap2_disk->ctl_socket_path[i] = '_';
+ }
+
+ libxl__ev_fd_init(&blktap2_disk->ev);
+
+ rc = blktap2_control_connect(gc, blktap2_disk);
+
+out:
+ dev->aodev.rc = rc;
+ dev->aodev.callback(dev->cds->egc, &dev->aodev);
+}
+
+static void blktap2_colo_teardown(libxl__checkpoint_device *dev)
+{
+ libxl__colo_blktap2_disk *blktap2_disk = dev->concrete_data;
+
+ if (blktap2_disk->fd > 0) {
+ close(blktap2_disk->fd);
+ blktap2_disk->fd = -1;
+ }
+
+ dev->aodev.rc = 0;
+ dev->aodev.callback(dev->cds->egc, &dev->aodev);
+}
+
+/* ========== checkpointing APIs ========== */
+static void blktap2_control_readable(libxl__egc *egc, libxl__ev_fd *ev,
+ int fd, short events, short revents);
+
+static void blktap2_colo_postsuspend(libxl__checkpoint_device *dev)
+{
+ int ret;
+ libxl__colo_blktap2_disk *blktap2_disk = dev->concrete_data;
+ int rc = 0;
+
+ /* unit socket fd, so not block */
+ ret = write(blktap2_disk->fd, BLKTAP2_REQUEST, strlen(BLKTAP2_REQUEST));
+ if (ret < strlen(BLKTAP2_REQUEST))
+ rc = ERROR_FAIL;
+
+ dev->aodev.rc = rc;
+ dev->aodev.callback(dev->cds->egc, &dev->aodev);
+}
+
+static void blktap2_colo_commit(libxl__checkpoint_device *dev)
+{
+ libxl__colo_blktap2_disk *blktap2_disk = dev->concrete_data;
+ int rc;
+
+ /* Convenience aliases */
+ const int fd = blktap2_disk->fd;
+ libxl__ev_fd *const ev = &blktap2_disk->ev;
+
+ STATE_AO_GC(dev->cds->ao);
+
+ rc = libxl__ev_fd_register(gc, ev, blktap2_control_readable, fd, POLLIN);
+ if (rc) {
+ dev->aodev.rc = rc;
+ dev->aodev.callback(dev->cds->egc, &dev->aodev);
+ }
+}
+
+static void blktap2_control_readable(libxl__egc *egc, libxl__ev_fd *ev,
+ int fd, short events, short revents)
+{
+ libxl__colo_blktap2_disk *blktap2_disk =
+ CONTAINER_OF(ev, *blktap2_disk, ev);
+ int rc = 0, ret;
+ char response[5];
+
+ /* Convenience aliases */
+ libxl__checkpoint_device *const dev = blktap2_disk->dev;
+
+ EGC_GC;
+
+ libxl__ev_fd_deregister(gc, ev);
+
+ if (revents & ~POLLIN) {
+ LOG(ERROR, "unexpected poll event 0x%x (should be POLLIN)", revents);
+ rc = ERROR_FAIL;
+ goto out;
+ }
+
+ ret = read(blktap2_disk->fd, response, sizeof(response) - 1);
+ if (ret < sizeof(response) - 1) {
+ rc = ERROR_FAIL;
+ goto out;
+ }
+
+ response[4] = '\0';
+ if (strcmp(response, BLKTAP2_RESPONSE))
+ rc = ERROR_FAIL;
+
+out:
+ dev->aodev.rc = rc;
+ dev->aodev.callback(dev->cds->egc, &dev->aodev);
+}
+
+const libxl__checkpoint_device_subkind_ops colo_save_device_blktap2_disk = {
+ .kind = LIBXL__CHECKPOINT_DEVICE_DISK,
+ .init = blktap2_colo_init,
+ .cleanup = blktap2_colo_cleanup,
+ .setup = blktap2_colo_setup,
+ .teardown = blktap2_colo_teardown,
+ .postsuspend = blktap2_colo_postsuspend,
+ .commit = blktap2_colo_commit,
+};
diff --git a/tools/libxl/libxl_create.c b/tools/libxl/libxl_create.c
index 46bd02d..d1facef 100644
--- a/tools/libxl/libxl_create.c
+++ b/tools/libxl/libxl_create.c
@@ -831,6 +831,13 @@ static void initiate_domain_create(libxl__egc *egc,
for (i = 0; i < d_config->num_disks; i++) {
ret = libxl__device_disk_setdefault(gc, &d_config->disks[i]);
if (ret) goto error_out;
+
+ /* TODO: cleanup it when destroying the domain */
+ if (d_config->disks[i].backend == LIBXL_DISK_BACKEND_TAP &&
+ (d_config->disks[i].format == LIBXL_DISK_FORMAT_REMUS ||
+ d_config->disks[i].format == LIBXL_DISK_FORMAT_COLO))
+ libxl__blktap_devpath(gc, d_config->disks[i].pdev_path,
+ d_config->disks[i].format);
}
dcs->bl.ao = ao;
diff --git a/tools/libxl/libxl_noblktap2.c b/tools/libxl/libxl_noblktap2.c
index 38696ec..46207b3 100644
--- a/tools/libxl/libxl_noblktap2.c
+++ b/tools/libxl/libxl_noblktap2.c
@@ -39,6 +39,35 @@ libxl_disk_format libxl__blktap_get_real_format(const char *disk,
return format;
}
+static int blktap2_colo_init(libxl__checkpoint_device *cds)
+{
+ return 0;
+}
+
+static void blktap2_colo_cleanup(libxl__checkpoint_device *cds)
+{
+ return;
+}
+
+static void blktap2_colo_setup(libxl__checkpoint_device *cds)
+{
+ dev->aodev.rc = ERROR_FAIL;
+ dev->aodev.callback(dev->cds->egc, &dev->aodev);
+}
+
+static void blktap2_colo_teardown(libxl__checkpoint_device *cds)
+{
+ return;
+}
+
+const libxl__checkpoint_device_subkind_ops colo_save_device_blktap2_disk = {
+ .kind = LIBXL__CHECKPOINT_DEVICE_DISK,
+ .init = blktap2_colo_init,
+ .cleanup = blktap2_colo_cleanup,
+ .setup = blktap2_colo_setup,
+ .teardown = blktap2_colo_teardown,
+};
+
/*
* Local variables:
* mode: C
--
1.9.3
next prev parent reply other threads:[~2014-08-08 7:01 UTC|newest]
Thread overview: 64+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-08-08 7:00 [RFC Patch v2 00/45] COarse-grain LOck-stepping Virtual Machines for Non-stop Service Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 01/45] copy the correct page to memory Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 02/45] csum the correct page Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 03/45] don't zero out ioreq page Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 04/45] Refactor domain_suspend_callback_common() Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 05/45] Update libxl__domain_resume() for colo Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 06/45] Update libxl__domain_suspend_common_switch_qemu_logdirty() " Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 07/45] Introduce a new internal API libxl__domain_unpause() Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 08/45] Update libxl__domain_unpause() to support qemu-xen Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 09/45] support to resume uncooperative HVM guests Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 10/45] update datecopier to support sending data only Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 11/45] introduce a new API to aync read data from fd Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 12/45] move remus related codes to libxl_remus.c Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 13/45] rename remus device to checkpoint device Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 14/45] adjust the indentation Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 15/45] don't touch remus in checkpoint_device Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 16/45] Update libxl_save_msgs_gen.pl to support return data from xl to xc Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 17/45] Allow slave sends data to master Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 18/45] secondary vm suspend/resume/checkpoint code Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 19/45] primary vm suspend/get_dirty_pfn/resume/checkpoint code Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 20/45] xc_domain_save: flush cache before calling callbacks->postcopy() in colo mode Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 21/45] COLO: xc related codes Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 22/45] send store mfn and console mfn to xl before resuming secondary vm Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 23/45] implement the cmdline for COLO Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 24/45] HACK: do checkpoint per 20ms Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 25/45] colo: dynamic allocate aio_requests to avoid -EBUSY error Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 26/45] fix memory leak in block-remus Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 27/45] pass uuid to the callback td_open Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 28/45] return the correct dev path Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 29/45] blktap2: use correct way to get remus_image Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 30/45] don't call client_flush() when switching to unprotected mode Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 31/45] remus: fix bug in tdremus_close() Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 32/45] blktap2: use correct way to get free event id Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 33/45] blktap2: don't return negative " Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 34/45] blktap2: use correct way to define array Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 35/45] blktap2: connect to backup asynchronously Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 36/45] switch to unprotected mode before closing Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 37/45] blktap2: move async connect related codes to block-replication.c Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 38/45] blktap2: move ramdisk " Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 39/45] block-colo: implement colo disk replication Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 40/45] pass correct file to qemu if we use blktap2 Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 41/45] support blktap remus in xl Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 42/45] support blktap colo in xl: Wen Congyang
2014-08-08 7:01 ` [RFC Patch v2 43/45] update libxl__device_disk_from_xs_be() to support blktap device Wen Congyang
2014-08-08 7:01 ` Wen Congyang [this message]
2014-08-08 7:01 ` [RFC Patch v2 45/45] x86/hvm: Always set pending event injection when loading VMC[BS] state Wen Congyang
2014-08-08 7:24 ` Jan Beulich
2014-08-08 7:29 ` Wen Congyang
2014-08-26 16:02 ` Jan Beulich
2014-08-27 0:46 ` Wen Congyang
2014-08-27 14:58 ` Aravind Gopalakrishnan
2014-08-28 1:04 ` Wen Congyang
2014-08-28 8:54 ` Andrew Cooper
2014-08-28 11:17 ` Wen Congyang
2014-08-28 11:31 ` Paul Durrant
2014-08-29 5:59 ` Wen Congyang
2014-08-28 9:53 ` Tim Deegan
2014-08-27 23:24 ` Tian, Kevin
2014-08-27 15:02 ` Andrew Cooper
2014-08-08 7:01 ` [RFC Patch v2 46/45] Introduce "xen-load-devices-state" Wen Congyang
2014-08-08 7:19 ` [RFC Patch v2 00/45] COarse-grain LOck-stepping Virtual Machines for Non-stop Service Jan Beulich
2014-08-08 7:39 ` Wen Congyang
2014-08-08 8:21 ` Wen Congyang
2014-08-08 9:02 ` Jan Beulich
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=1407481305-19808-45-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).