From: Wen Congyang <wency@cn.fujitsu.com>
To: qemu devel <qemu-devel@nongnu.org>, Fam Zheng <famz@redhat.com>,
Max Reitz <mreitz@redhat.com>,
Paolo Bonzini <pbonzini@redhat.com>,
Stefan Hajnoczi <stefanha@redhat.com>
Cc: Kevin Wolf <kwolf@redhat.com>, Alberto Garcia <berto@igalia.com>,
qemu block <qemu-block@nongnu.org>,
Jiang Yunhong <yunhong.jiang@intel.com>,
Dong Eddie <eddie.dong@intel.com>,
"Dr. David Alan Gilbert" <dgilbert@redhat.com>,
"Michael R. Hines" <mrhines@linux.vnet.ibm.com>,
Gonglei <arei.gonglei@huawei.com>,
Yang Hongyang <yanghy@cn.fujitsu.com>,
zhanghailiang <zhang.zhanghailiang@huawei.com>
Subject: [Qemu-devel] [PATCH 06/16] quorum: allow ignoring child errors
Date: Wed, 2 Sep 2015 16:51:10 +0800 [thread overview]
Message-ID: <1441183880-26993-7-git-send-email-wency@cn.fujitsu.com> (raw)
In-Reply-To: <1441183880-26993-1-git-send-email-wency@cn.fujitsu.com>
If the child is not ready, read/write/getlength/flush will
return -errno. It is not critical error, and can be ignored:
1. read/write:
Just not report the error event.
2. getlength:
just ignore it. If all children's getlength return -errno,
and be ignored, return -EIO.
3. flush:
Just ignore it. If all children's getlength return -errno,
and be ignored, return 0.
Usage: children.x.ignore-errors=true
Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
Signed-off-by: zhanghailiang <zhang.zhanghailiang@huawei.com>
Signed-off-by: Gonglei <arei.gonglei@huawei.com>
Cc: Alberto Garcia <berto@igalia.com>
---
block/quorum.c | 94 ++++++++++++++++++++++++++++++++++++++++++++++++----
qapi/block-core.json | 5 ++-
2 files changed, 91 insertions(+), 8 deletions(-)
diff --git a/block/quorum.c b/block/quorum.c
index 8059861..f23dbb7 100644
--- a/block/quorum.c
+++ b/block/quorum.c
@@ -30,6 +30,7 @@
#define QUORUM_OPT_BLKVERIFY "blkverify"
#define QUORUM_OPT_REWRITE "rewrite-corrupted"
#define QUORUM_OPT_READ_PATTERN "read-pattern"
+#define QUORUM_CHILDREN_OPT_IGNORE_ERRORS "ignore-errors"
/* This union holds a vote hash value */
typedef union QuorumVoteValue {
@@ -65,6 +66,7 @@ typedef struct QuorumVotes {
/* the following structure holds the state of one quorum instance */
typedef struct BDRVQuorumState {
BlockDriverState **bs; /* children BlockDriverStates */
+ bool *ignore_errors; /* ignore children's error? */
int num_children; /* children count */
int max_children; /* The maximum children count, we need to reallocate
* bs if num_children will larger than maximum.
@@ -100,6 +102,7 @@ typedef struct QuorumChildRequest {
uint8_t *buf;
int ret;
QuorumAIOCB *parent;
+ int index;
} QuorumChildRequest;
/* Quorum will use the following structure to track progress of each read/write
@@ -212,6 +215,7 @@ static QuorumAIOCB *quorum_aio_get(BDRVQuorumState *s,
acb->qcrs[i].buf = NULL;
acb->qcrs[i].ret = 0;
acb->qcrs[i].parent = acb;
+ acb->qcrs[i].index = i;
}
return acb;
@@ -305,7 +309,7 @@ static void quorum_aio_cb(void *opaque, int ret)
acb->count++;
if (ret == 0) {
acb->success_count++;
- } else {
+ } else if (!s->ignore_errors[sacb->index]) {
quorum_report_bad(acb, sacb->aiocb->bs->node_name, ret);
}
assert(acb->count <= s->num_children);
@@ -716,19 +720,31 @@ static BlockAIOCB *quorum_aio_writev(BlockDriverState *bs,
static int64_t quorum_getlength(BlockDriverState *bs)
{
BDRVQuorumState *s = bs->opaque;
- int64_t result;
+ int64_t result = -EIO;
int i;
/* check that all file have the same length */
- result = bdrv_getlength(s->bs[0]);
- if (result < 0) {
- return result;
- }
- for (i = 1; i < s->num_children; i++) {
+ for (i = 0; i < s->num_children; i++) {
int64_t value = bdrv_getlength(s->bs[i]);
+
if (value < 0) {
return value;
}
+
+ if (value == 0 && s->ignore_errors[i]) {
+ /*
+ * If the child is not ready, it cannot return -errno,
+ * otherwise refresh_total_sectors() will fail when
+ * we open the child.
+ */
+ continue;
+ }
+
+ if (result == -EIO) {
+ result = value;
+ continue;
+ }
+
if (value != result) {
return -EIO;
}
@@ -766,6 +782,9 @@ static coroutine_fn int quorum_co_flush(BlockDriverState *bs)
for (i = 0; i < s->num_children; i++) {
result = bdrv_co_flush(s->bs[i]);
+ if (result < 0 && s->ignore_errors[i]) {
+ result = 0;
+ }
result_value.l = result;
quorum_count_vote(&error_votes, &result_value, i);
}
@@ -840,6 +859,19 @@ static QemuOptsList quorum_runtime_opts = {
},
};
+static QemuOptsList quorum_children_common_opts = {
+ .name = "quorum children",
+ .head = QTAILQ_HEAD_INITIALIZER(quorum_children_common_opts.head),
+ .desc = {
+ {
+ .name = QUORUM_CHILDREN_OPT_IGNORE_ERRORS,
+ .type = QEMU_OPT_BOOL,
+ .help = "ignore child I/O error",
+ },
+ { /* end of list */ }
+ },
+};
+
static int parse_read_pattern(const char *opt)
{
int i;
@@ -858,6 +890,37 @@ static int parse_read_pattern(const char *opt)
return -EINVAL;
}
+static int parse_children_options(BDRVQuorumState *s, QDict *options,
+ const char *indexstr, int index,
+ Error **errp)
+{
+ QemuOpts *children_opts = NULL;
+ Error *local_err = NULL;
+ int ret = 0;
+ bool value;
+
+ children_opts = qemu_opts_create(&quorum_children_common_opts, NULL, 0,
+ &error_abort);
+ qemu_opts_absorb_qdict_by_index(children_opts, options, indexstr,
+ &local_err);
+ if (local_err) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ value = qemu_opt_get_bool(children_opts, QUORUM_CHILDREN_OPT_IGNORE_ERRORS,
+ false);
+ s->ignore_errors[index] = value;
+
+out:
+ qemu_opts_del(children_opts);
+ /* propagate error */
+ if (local_err) {
+ error_propagate(errp, local_err);
+ }
+ return ret;
+}
+
static int quorum_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
@@ -929,12 +992,18 @@ static int quorum_open(BlockDriverState *bs, QDict *options, int flags,
s->bs = g_new0(BlockDriverState *, s->num_children);
opened = g_new0(bool, s->num_children);
s->max_children = s->num_children;
+ s->ignore_errors = g_new0(bool, s->num_children);
for (i = 0; i < s->num_children; i++) {
char indexstr[32];
ret = snprintf(indexstr, 32, "children.%d", i);
assert(ret < 32);
+ ret = parse_children_options(s, options, indexstr, i, &local_err);
+ if (ret < 0) {
+ goto close_exit;
+ }
+
ret = bdrv_open_image(&s->bs[i], NULL, options, indexstr, bs,
&child_format, false, &local_err);
if (ret < 0) {
@@ -976,6 +1045,7 @@ static void quorum_close(BlockDriverState *bs)
}
g_free(s->bs);
+ g_free(s->ignore_errors);
}
static void quorum_detach_aio_context(BlockDriverState *bs)
@@ -1014,10 +1084,18 @@ static void quorum_add_child(BlockDriverState *bs, QDict *options, Error **errp)
}
s->bs = g_renew(BlockDriverState *, s->bs, s->max_children + 1);
+ s->ignore_errors = g_renew(bool, s->ignore_errors, s->max_children + 1);
s->bs[s->num_children] = NULL;
s->max_children += 1;
}
+ ret = parse_children_options(s, options, "child", s->num_children,
+ &local_err);
+ if (ret < 0) {
+ error_propagate(errp, local_err);
+ return;
+ }
+
ret = bdrv_open_image(&s->bs[s->num_children], NULL, options, "child", bs,
&child_format, false, &local_err);
if (ret < 0) {
@@ -1058,6 +1136,8 @@ static void quorum_del_child(BlockDriverState *bs, BlockDriverState *child_bs,
bdrv_drain(bs);
/* We can safely remove this child now */
memmove(&s->bs[i], &s->bs[i+1], (s->num_children - i - 1) * sizeof(void *));
+ memmove(&s->ignore_errors[i], &s->ignore_errors[i+1],
+ (s->num_children - i - 1) * sizeof(bool));
s->num_children--;
s->bs[s->num_children] = NULL;
bdrv_unref(child_bs);
diff --git a/qapi/block-core.json b/qapi/block-core.json
index bf141a2..24099ef 100644
--- a/qapi/block-core.json
+++ b/qapi/block-core.json
@@ -1411,6 +1411,8 @@
# @allow-write-backing-file: #optional whether the backing file is opened in
# read-write mode. It is only for backing file
# (Since 2.5 default: false)
+# @ignore-errors: #options whether the child's I/O error should be ignored.
+# it is only for quorum's child.(Since 2.5 default: false)
#
# Since: 1.7
##
@@ -1425,7 +1427,8 @@
'*werror': 'BlockdevOnError',
'*read-only': 'bool',
'*detect-zeroes': 'BlockdevDetectZeroesOptions',
- '*allow-write-backing-file': 'bool' } }
+ '*allow-write-backing-file': 'bool',
+ '*ignore-errors': 'bool' } }
##
# @BlockdevOptionsFile
--
2.4.3
next prev parent reply other threads:[~2015-09-02 8:52 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-09-02 8:51 [Qemu-devel] [PATCH 00/16] Block replication for continuous checkpoints Wen Congyang
2015-09-02 8:51 ` [Qemu-devel] [PATCH 01/16] introduce a new API to enable/disable attach device model Wen Congyang
2015-09-02 15:37 ` Eric Blake
2015-09-07 1:27 ` Wen Congyang
2015-09-02 8:51 ` [Qemu-devel] [PATCH 02/16] introduce a new API to check if blk is attached Wen Congyang
2015-09-02 15:40 ` Eric Blake
2015-09-02 8:51 ` [Qemu-devel] [PATCH 03/16] allow writing to the backing file Wen Congyang
2015-09-02 16:06 ` Eric Blake
2015-09-09 9:19 ` Wen Congyang
2015-09-02 8:51 ` [Qemu-devel] [PATCH 04/16] block: Allow references for backing files Wen Congyang
2015-09-02 18:50 ` Eric Blake
2015-09-09 8:51 ` Wen Congyang
2015-09-02 8:51 ` [Qemu-devel] [PATCH 05/16] introduce a new API qemu_opts_absorb_qdict_by_index() Wen Congyang
2015-09-02 19:01 ` Eric Blake
2015-09-07 2:18 ` Wen Congyang
2015-09-02 8:51 ` Wen Congyang [this message]
2015-09-02 16:30 ` [Qemu-devel] [PATCH 06/16] quorum: allow ignoring child errors Eric Blake
2015-09-07 3:40 ` Wen Congyang
2015-09-07 16:56 ` Dr. David Alan Gilbert
2015-09-08 0:46 ` Wen Congyang
2015-09-02 8:51 ` [Qemu-devel] [PATCH 07/16] Backup: clear all bitmap when doing block checkpoint Wen Congyang
2015-09-02 14:10 ` Jeff Cody
2015-09-02 8:51 ` [Qemu-devel] [PATCH 08/16] block: make bdrv_put_ref_bh_schedule() as a public API Wen Congyang
2015-09-02 8:51 ` [Qemu-devel] [PATCH 09/16] Allow creating backup jobs when opening BDS Wen Congyang
2015-09-02 14:12 ` Jeff Cody
2015-09-02 8:51 ` [Qemu-devel] [PATCH 10/16] docs: block replication's description Wen Congyang
2015-09-02 20:41 ` Eric Blake
2015-09-09 8:22 ` Wen Congyang
2015-09-02 8:51 ` [Qemu-devel] [PATCH 11/16] Add new block driver interfaces to control block replication Wen Congyang
2015-09-02 16:33 ` Eric Blake
2015-09-09 9:24 ` Wen Congyang
2015-09-25 6:14 ` Wen Congyang
2015-09-02 8:51 ` [Qemu-devel] [PATCH 12/16] skip nbd_target when starting " Wen Congyang
2015-09-02 8:51 ` [Qemu-devel] [PATCH 13/16] quorum: implement block driver interfaces for " Wen Congyang
2015-09-02 8:51 ` [Qemu-devel] [PATCH 14/16] Implement new driver " Wen Congyang
2015-09-02 8:51 ` [Qemu-devel] [PATCH 15/16] support replication driver in blockdev-add Wen Congyang
2015-09-02 16:36 ` Eric Blake
2015-09-09 8:27 ` Wen Congyang
2015-09-02 8:51 ` [Qemu-devel] [PATCH 16/16] Add a new API to start/stop replication, do checkpoint to all BDSes 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=1441183880-26993-7-git-send-email-wency@cn.fujitsu.com \
--to=wency@cn.fujitsu.com \
--cc=arei.gonglei@huawei.com \
--cc=berto@igalia.com \
--cc=dgilbert@redhat.com \
--cc=eddie.dong@intel.com \
--cc=famz@redhat.com \
--cc=kwolf@redhat.com \
--cc=mreitz@redhat.com \
--cc=mrhines@linux.vnet.ibm.com \
--cc=pbonzini@redhat.com \
--cc=qemu-block@nongnu.org \
--cc=qemu-devel@nongnu.org \
--cc=stefanha@redhat.com \
--cc=yanghy@cn.fujitsu.com \
--cc=yunhong.jiang@intel.com \
--cc=zhang.zhanghailiang@huawei.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).