| Message ID | 99252a76de350c8123eebfe4fc01fc6a1c9b2383.1301354138.git.josh.durgin@dreamhost.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
Hi, 2011/3/29 Josh Durgin <josh.durgin@dreamhost.com>: > The new format is rbd:pool/image[@snapshot][:option1=value1[:option2=value2...]] > Each option is used to configure rados, and may be any Ceph option, or "conf". > The "conf" option specifies a Ceph configuration file to read. > > This allows rbd volumes from more than one Ceph cluster to be used by > specifying different monitor addresses, as well as having different > logging levels or locations for different volumes. > > Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> > --- > block/rbd.c | 119 ++++++++++++++++++++++++++++++++++++++++++++++++++-------- > 1 files changed, 102 insertions(+), 17 deletions(-) > > diff --git a/block/rbd.c b/block/rbd.c > index cb76dd3..bc3323d 100644 > --- a/block/rbd.c > +++ b/block/rbd.c > @@ -22,13 +22,17 @@ > /* > * When specifying the image filename use: > * > - * rbd:poolname/devicename > + * rbd:poolname/devicename[@snapshotname][:option1=value1[:option2=value2...]] I'm not sure IIUC, but currently this @snapshotname seems to be meaningless; it doesn't allow you to boot from a snapshot because it's read only. Am I misunderstanding or tested incorrectly? Yoshi > * > * poolname must be the name of an existing rados pool > * > * devicename is the basename for all objects used to > * emulate the raw device. > * > + * Each option given is used to configure rados, and may be > + * any Ceph option, or "conf". The "conf" option specifies > + * a Ceph configuration file to read. > + * > * Metadata information (image size, ...) is stored in an > * object with the name "devicename.rbd". > * > @@ -121,7 +125,8 @@ static int qemu_rbd_next_tok(char *dst, int dst_len, > static int qemu_rbd_parsename(const char *filename, > char *pool, int pool_len, > char *snap, int snap_len, > - char *name, int name_len) > + char *name, int name_len, > + char *conf, int conf_len) > { > const char *start; > char *p, *buf; > @@ -133,28 +138,84 @@ static int qemu_rbd_parsename(const char *filename, > > buf = qemu_strdup(start); > p = buf; > + *snap = '\0'; > + *conf = '\0'; > > ret = qemu_rbd_next_tok(pool, pool_len, p, '/', "pool name", &p); > if (ret < 0 || !p) { > ret = -EINVAL; > goto done; > } > - ret = qemu_rbd_next_tok(name, name_len, p, '@', "object name", &p); > - if (ret < 0) { > - goto done; > + > + if (strchr(p, '@')) { > + ret = qemu_rbd_next_tok(name, name_len, p, '@', "object name", &p); > + if (ret < 0) { > + goto done; > + } > + ret = qemu_rbd_next_tok(snap, snap_len, p, ':', "snap name", &p); > + } else { > + ret = qemu_rbd_next_tok(name, name_len, p, ':', "object name", &p); > } > - if (!p) { > - *snap = '\0'; > + if (ret < 0 || !p) { > goto done; > } > > - ret = qemu_rbd_next_tok(snap, snap_len, p, '\0', "snap name", &p); > + ret = qemu_rbd_next_tok(conf, conf_len, p, '\0', "configuration", &p); > > done: > qemu_free(buf); > return ret; > } > > +static int qemu_rbd_set_conf(rados_t cluster, const char *conf) > +{ > + char *p, *buf; > + char name[RBD_MAX_CONF_NAME_SIZE]; > + char value[RBD_MAX_CONF_VAL_SIZE]; > + int ret = 0; > + > + buf = qemu_strdup(conf); > + p = buf; > + > + while (p) { > + ret = qemu_rbd_next_tok(name, sizeof(name), p, > + '=', "conf option name", &p); > + if (ret < 0) { > + break; > + } > + > + if (!p) { > + error_report("conf option %s has no value", name); > + ret = -EINVAL; > + break; > + } > + > + ret = qemu_rbd_next_tok(value, sizeof(value), p, > + ':', "conf option value", &p); > + if (ret < 0) { > + break; > + } > + > + if (strncmp(name, "conf", strlen("conf"))) { > + ret = rados_conf_set(cluster, name, value); > + if (ret < 0) { > + error_report("invalid conf option %s", name); > + ret = -EINVAL; > + break; > + } > + } else { > + ret = rados_conf_read_file(cluster, value); > + if (ret < 0) { > + error_report("error reading conf file %s", value); > + break; > + } > + } > + } > + > + qemu_free(buf); > + return ret; > +} > + > static int qemu_rbd_create(const char *filename, QEMUOptionParameter *options) > { > int64_t bytes = 0; > @@ -163,6 +224,7 @@ static int qemu_rbd_create(const char *filename, QEMUOptionParameter *options) > char pool[RBD_MAX_POOL_NAME_SIZE]; > char name[RBD_MAX_IMAGE_NAME_SIZE]; > char snap_buf[RBD_MAX_SNAP_NAME_SIZE]; > + char conf[RBD_MAX_CONF_SIZE]; > char *snap = NULL; > rados_t cluster; > rados_ioctx_t io_ctx; > @@ -170,7 +232,8 @@ static int qemu_rbd_create(const char *filename, QEMUOptionParameter *options) > > if (qemu_rbd_parsename(filename, pool, sizeof(pool), > snap_buf, sizeof(snap_buf), > - name, sizeof(name)) < 0) { > + name, sizeof(name), > + conf, sizeof(conf)) < 0) { > return -EINVAL; > } > if (snap_buf[0] != '\0') { > @@ -203,8 +266,17 @@ static int qemu_rbd_create(const char *filename, QEMUOptionParameter *options) > return -EIO; > } > > - if (rados_conf_read_file(cluster, NULL) < 0) { > - error_report("error reading config file"); > + if (strstr(conf, "conf=") == NULL) { > + if (rados_conf_read_file(cluster, NULL) < 0) { > + error_report("error reading config file"); > + rados_shutdown(cluster); > + return -EIO; > + } > + } > + > + if (conf[0] != '\0' && > + qemu_rbd_set_conf(cluster, conf) < 0) { > + error_report("error setting config options"); > rados_shutdown(cluster); > return -EIO; > } > @@ -314,11 +386,13 @@ static int qemu_rbd_open(BlockDriverState *bs, const char *filename, int flags) > BDRVRBDState *s = bs->opaque; > char pool[RBD_MAX_POOL_NAME_SIZE]; > char snap_buf[RBD_MAX_SNAP_NAME_SIZE]; > + char conf[RBD_MAX_CONF_SIZE]; > int r; > > if (qemu_rbd_parsename(filename, pool, sizeof(pool), > snap_buf, sizeof(snap_buf), > - s->name, sizeof(s->name)) < 0) { > + s->name, sizeof(s->name), > + conf, sizeof(conf)) < 0) { > return -EINVAL; > } > s->snap = NULL; > @@ -332,11 +406,22 @@ static int qemu_rbd_open(BlockDriverState *bs, const char *filename, int flags) > return r; > } > > - r = rados_conf_read_file(s->cluster, NULL); > - if (r < 0) { > - error_report("error reading config file"); > - rados_shutdown(s->cluster); > - return r; > + if (strstr(conf, "conf=") == NULL) { > + r = rados_conf_read_file(s->cluster, NULL); > + if (r < 0) { > + error_report("error reading config file"); > + rados_shutdown(s->cluster); > + return r; > + } > + } > + > + if (conf[0] != '\0') { > + r = qemu_rbd_set_conf(s->cluster, conf); > + if (r < 0) { > + error_report("error setting config options"); > + rados_shutdown(s->cluster); > + return r; > + } > } > > r = rados_connect(s->cluster); > -- > 1.7.2.3 > > -- > To unsubscribe from this list: send the line "unsubscribe kvm" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html > -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Thu, Apr 07, 2011 at 10:14:03AM +0900, Yoshiaki Tamura wrote: > 2011/3/29 Josh Durgin <josh.durgin@dreamhost.com>: > > The new format is rbd:pool/image[@snapshot][:option1=value1[:option2=value2...]] > > Each option is used to configure rados, and may be any Ceph option, or "conf". > > The "conf" option specifies a Ceph configuration file to read. > > > > This allows rbd volumes from more than one Ceph cluster to be used by > > specifying different monitor addresses, as well as having different > > logging levels or locations for different volumes. > > > > Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> > > --- > > block/rbd.c | 119 ++++++++++++++++++++++++++++++++++++++++++++++++++-------- > > 1 files changed, 102 insertions(+), 17 deletions(-) > > > > diff --git a/block/rbd.c b/block/rbd.c > > index cb76dd3..bc3323d 100644 > > --- a/block/rbd.c > > +++ b/block/rbd.c > > @@ -22,13 +22,17 @@ > > /* > > * When specifying the image filename use: > > * > > - * rbd:poolname/devicename > > + * rbd:poolname/devicename[@snapshotname][:option1=value1[:option2=value2...]] > > I'm not sure IIUC, but currently this @snapshotname seems to be > meaningless; it doesn't allow you to boot from a snapshot because it's > read only. Am I misunderstanding or tested incorrectly? Read-only block devices are supported by QEMU and can be useful. Stefan -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
2011/4/7 Stefan Hajnoczi <stefanha@gmail.com>: > On Thu, Apr 07, 2011 at 10:14:03AM +0900, Yoshiaki Tamura wrote: >> 2011/3/29 Josh Durgin <josh.durgin@dreamhost.com>: >> > The new format is rbd:pool/image[@snapshot][:option1=value1[:option2=value2...]] >> > Each option is used to configure rados, and may be any Ceph option, or "conf". >> > The "conf" option specifies a Ceph configuration file to read. >> > >> > This allows rbd volumes from more than one Ceph cluster to be used by >> > specifying different monitor addresses, as well as having different >> > logging levels or locations for different volumes. >> > >> > Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> >> > --- >> > block/rbd.c | 119 ++++++++++++++++++++++++++++++++++++++++++++++++++-------- >> > 1 files changed, 102 insertions(+), 17 deletions(-) >> > >> > diff --git a/block/rbd.c b/block/rbd.c >> > index cb76dd3..bc3323d 100644 >> > --- a/block/rbd.c >> > +++ b/block/rbd.c >> > @@ -22,13 +22,17 @@ >> > /* >> > * When specifying the image filename use: >> > * >> > - * rbd:poolname/devicename >> > + * rbd:poolname/devicename[@snapshotname][:option1=value1[:option2=value2...]] >> >> I'm not sure IIUC, but currently this @snapshotname seems to be >> meaningless; it doesn't allow you to boot from a snapshot because it's >> read only. Am I misunderstanding or tested incorrectly? > > Read-only block devices are supported by QEMU and can be useful. I agree. My expectation was that @snapshotname is introduced to have writable snapshot. Yoshi > > Stefan > -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Thu, Apr 7, 2011 at 2:54 AM, Yoshiaki Tamura <tamura.yoshiaki@gmail.com> wrote: > 2011/4/7 Stefan Hajnoczi <stefanha@gmail.com>: >> On Thu, Apr 07, 2011 at 10:14:03AM +0900, Yoshiaki Tamura wrote: >>> 2011/3/29 Josh Durgin <josh.durgin@dreamhost.com>: >>> > The new format is rbd:pool/image[@snapshot][:option1=value1[:option2=value2...]] >>> > Each option is used to configure rados, and may be any Ceph option, or "conf". >>> > The "conf" option specifies a Ceph configuration file to read. >>> > >>> > This allows rbd volumes from more than one Ceph cluster to be used by >>> > specifying different monitor addresses, as well as having different >>> > logging levels or locations for different volumes. >>> > >>> > Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> >>> > --- >>> > block/rbd.c | 119 ++++++++++++++++++++++++++++++++++++++++++++++++++-------- >>> > 1 files changed, 102 insertions(+), 17 deletions(-) >>> > >>> > diff --git a/block/rbd.c b/block/rbd.c >>> > index cb76dd3..bc3323d 100644 >>> > --- a/block/rbd.c >>> > +++ b/block/rbd.c >>> > @@ -22,13 +22,17 @@ >>> > /* >>> > * When specifying the image filename use: >>> > * >>> > - * rbd:poolname/devicename >>> > + * rbd:poolname/devicename[@snapshotname][:option1=value1[:option2=value2...]] >>> >>> I'm not sure IIUC, but currently this @snapshotname seems to be >>> meaningless; it doesn't allow you to boot from a snapshot because it's >>> read only. Am I misunderstanding or tested incorrectly? >> >> Read-only block devices are supported by QEMU and can be useful. > > I agree. My expectation was that @snapshotname is introduced to have > writable snapshot. > The RADOS backend doesn't support writable snapshots. However, down the rbd roadmap we plan to have layering which in a sense is writable snapshots. The whole shift to librbd was done so that introducing such new functionality will be transparent and will not require much or any changes in the qemu code. Yehuda -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
2011/4/8 Yehuda Sadeh Weinraub <yehudasa@gmail.com>: > On Thu, Apr 7, 2011 at 2:54 AM, Yoshiaki Tamura > <tamura.yoshiaki@gmail.com> wrote: >> 2011/4/7 Stefan Hajnoczi <stefanha@gmail.com>: >>> On Thu, Apr 07, 2011 at 10:14:03AM +0900, Yoshiaki Tamura wrote: >>>> 2011/3/29 Josh Durgin <josh.durgin@dreamhost.com>: >>>> > The new format is rbd:pool/image[@snapshot][:option1=value1[:option2=value2...]] >>>> > Each option is used to configure rados, and may be any Ceph option, or "conf". >>>> > The "conf" option specifies a Ceph configuration file to read. >>>> > >>>> > This allows rbd volumes from more than one Ceph cluster to be used by >>>> > specifying different monitor addresses, as well as having different >>>> > logging levels or locations for different volumes. >>>> > >>>> > Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com> >>>> > --- >>>> > block/rbd.c | 119 ++++++++++++++++++++++++++++++++++++++++++++++++++-------- >>>> > 1 files changed, 102 insertions(+), 17 deletions(-) >>>> > >>>> > diff --git a/block/rbd.c b/block/rbd.c >>>> > index cb76dd3..bc3323d 100644 >>>> > --- a/block/rbd.c >>>> > +++ b/block/rbd.c >>>> > @@ -22,13 +22,17 @@ >>>> > /* >>>> > * When specifying the image filename use: >>>> > * >>>> > - * rbd:poolname/devicename >>>> > + * rbd:poolname/devicename[@snapshotname][:option1=value1[:option2=value2...]] >>>> >>>> I'm not sure IIUC, but currently this @snapshotname seems to be >>>> meaningless; it doesn't allow you to boot from a snapshot because it's >>>> read only. Am I misunderstanding or tested incorrectly? >>> >>> Read-only block devices are supported by QEMU and can be useful. >> >> I agree. My expectation was that @snapshotname is introduced to have >> writable snapshot. >> > The RADOS backend doesn't support writable snapshots. However, down > the rbd roadmap we plan to have layering which in a sense is writable > snapshots. The whole shift to librbd was done so that introducing such > new functionality will be transparent and will not require much or any > changes in the qemu code. Thanks. It made things clear :) I think it's a good move. Yoshi > > Yehuda > -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
diff --git a/block/rbd.c b/block/rbd.c index cb76dd3..bc3323d 100644 --- a/block/rbd.c +++ b/block/rbd.c @@ -22,13 +22,17 @@ /* * When specifying the image filename use: * - * rbd:poolname/devicename + * rbd:poolname/devicename[@snapshotname][:option1=value1[:option2=value2...]] * * poolname must be the name of an existing rados pool * * devicename is the basename for all objects used to * emulate the raw device. * + * Each option given is used to configure rados, and may be + * any Ceph option, or "conf". The "conf" option specifies + * a Ceph configuration file to read. + * * Metadata information (image size, ...) is stored in an * object with the name "devicename.rbd". * @@ -121,7 +125,8 @@ static int qemu_rbd_next_tok(char *dst, int dst_len, static int qemu_rbd_parsename(const char *filename, char *pool, int pool_len, char *snap, int snap_len, - char *name, int name_len) + char *name, int name_len, + char *conf, int conf_len) { const char *start; char *p, *buf; @@ -133,28 +138,84 @@ static int qemu_rbd_parsename(const char *filename, buf = qemu_strdup(start); p = buf; + *snap = '\0'; + *conf = '\0'; ret = qemu_rbd_next_tok(pool, pool_len, p, '/', "pool name", &p); if (ret < 0 || !p) { ret = -EINVAL; goto done; } - ret = qemu_rbd_next_tok(name, name_len, p, '@', "object name", &p); - if (ret < 0) { - goto done; + + if (strchr(p, '@')) { + ret = qemu_rbd_next_tok(name, name_len, p, '@', "object name", &p); + if (ret < 0) { + goto done; + } + ret = qemu_rbd_next_tok(snap, snap_len, p, ':', "snap name", &p); + } else { + ret = qemu_rbd_next_tok(name, name_len, p, ':', "object name", &p); } - if (!p) { - *snap = '\0'; + if (ret < 0 || !p) { goto done; } - ret = qemu_rbd_next_tok(snap, snap_len, p, '\0', "snap name", &p); + ret = qemu_rbd_next_tok(conf, conf_len, p, '\0', "configuration", &p); done: qemu_free(buf); return ret; } +static int qemu_rbd_set_conf(rados_t cluster, const char *conf) +{ + char *p, *buf; + char name[RBD_MAX_CONF_NAME_SIZE]; + char value[RBD_MAX_CONF_VAL_SIZE]; + int ret = 0; + + buf = qemu_strdup(conf); + p = buf; + + while (p) { + ret = qemu_rbd_next_tok(name, sizeof(name), p, + '=', "conf option name", &p); + if (ret < 0) { + break; + } + + if (!p) { + error_report("conf option %s has no value", name); + ret = -EINVAL; + break; + } + + ret = qemu_rbd_next_tok(value, sizeof(value), p, + ':', "conf option value", &p); + if (ret < 0) { + break; + } + + if (strncmp(name, "conf", strlen("conf"))) { + ret = rados_conf_set(cluster, name, value); + if (ret < 0) { + error_report("invalid conf option %s", name); + ret = -EINVAL; + break; + } + } else { + ret = rados_conf_read_file(cluster, value); + if (ret < 0) { + error_report("error reading conf file %s", value); + break; + } + } + } + + qemu_free(buf); + return ret; +} + static int qemu_rbd_create(const char *filename, QEMUOptionParameter *options) { int64_t bytes = 0; @@ -163,6 +224,7 @@ static int qemu_rbd_create(const char *filename, QEMUOptionParameter *options) char pool[RBD_MAX_POOL_NAME_SIZE]; char name[RBD_MAX_IMAGE_NAME_SIZE]; char snap_buf[RBD_MAX_SNAP_NAME_SIZE]; + char conf[RBD_MAX_CONF_SIZE]; char *snap = NULL; rados_t cluster; rados_ioctx_t io_ctx; @@ -170,7 +232,8 @@ static int qemu_rbd_create(const char *filename, QEMUOptionParameter *options) if (qemu_rbd_parsename(filename, pool, sizeof(pool), snap_buf, sizeof(snap_buf), - name, sizeof(name)) < 0) { + name, sizeof(name), + conf, sizeof(conf)) < 0) { return -EINVAL; } if (snap_buf[0] != '\0') { @@ -203,8 +266,17 @@ static int qemu_rbd_create(const char *filename, QEMUOptionParameter *options) return -EIO; } - if (rados_conf_read_file(cluster, NULL) < 0) { - error_report("error reading config file"); + if (strstr(conf, "conf=") == NULL) { + if (rados_conf_read_file(cluster, NULL) < 0) { + error_report("error reading config file"); + rados_shutdown(cluster); + return -EIO; + } + } + + if (conf[0] != '\0' && + qemu_rbd_set_conf(cluster, conf) < 0) { + error_report("error setting config options"); rados_shutdown(cluster); return -EIO; } @@ -314,11 +386,13 @@ static int qemu_rbd_open(BlockDriverState *bs, const char *filename, int flags) BDRVRBDState *s = bs->opaque; char pool[RBD_MAX_POOL_NAME_SIZE]; char snap_buf[RBD_MAX_SNAP_NAME_SIZE]; + char conf[RBD_MAX_CONF_SIZE]; int r; if (qemu_rbd_parsename(filename, pool, sizeof(pool), snap_buf, sizeof(snap_buf), - s->name, sizeof(s->name)) < 0) { + s->name, sizeof(s->name), + conf, sizeof(conf)) < 0) { return -EINVAL; } s->snap = NULL; @@ -332,11 +406,22 @@ static int qemu_rbd_open(BlockDriverState *bs, const char *filename, int flags) return r; } - r = rados_conf_read_file(s->cluster, NULL); - if (r < 0) { - error_report("error reading config file"); - rados_shutdown(s->cluster); - return r; + if (strstr(conf, "conf=") == NULL) { + r = rados_conf_read_file(s->cluster, NULL); + if (r < 0) { + error_report("error reading config file"); + rados_shutdown(s->cluster); + return r; + } + } + + if (conf[0] != '\0') { + r = qemu_rbd_set_conf(s->cluster, conf); + if (r < 0) { + error_report("error setting config options"); + rados_shutdown(s->cluster); + return r; + } } r = rados_connect(s->cluster);