Re: [Qemu-devel] [PATCH v9 4/4] block: Support GlusterFS as a QEMU block backend.

[Kevin Wolf <kwolf@redhat.com>]

Am 24.09.2012 11:13, schrieb Bharata B Rao:
> block: Support GlusterFS as a QEMU block backend.
> 
> From: Bharata B Rao <bharata@linux.vnet.ibm.com>
> 
> This patch adds gluster as the new block backend in QEMU. This gives
> QEMU the ability to boot VM images from gluster volumes. Its already
> possible to boot from VM images on gluster volumes using FUSE mount, but
> this patchset provides the ability to boot VM images from gluster volumes
> by by-passing the FUSE layer in gluster. This is made possible by
> using libgfapi routines to perform IO on gluster volumes directly.
> 
> VM Image on gluster volume is specified like this:
> 
> file=gluster[+transport]://[server[:port]]/volname/image[?socket=...]
> 
> 'gluster' is the protocol.
> 
> 'transport' specifies the transport type used to connect to gluster
> management daemon (glusterd). Valid transport types are
> tcp, unix and rdma. If a transport type isn't specified, then tcp
> type is assumed.
> 
> 'server' specifies the server where the volume file specification for
> the given volume resides. This can be either hostname, ipv4 address
> or ipv6 address. ipv6 address needs to be within square brackets [ ].
> If transport type is 'unix', then server field is ignored, but the
> 'socket' field needs to be populated with the path to unix domain
> socket.
> 
> 'port' is the port number on which glusterd is listening. This is optional
> and if not specified, QEMU will send 0 which will make gluster to use the
> default port. port is ignored for unix type of transport.
> 
> 'volname' is the name of the gluster volume which contains the VM image.
> 
> 'image' is the path to the actual VM image that resides on gluster volume.
> 
> Examples:
> 
> file=gluster://1.2.3.4/testvol/a.img
> file=gluster+tcp://1.2.3.4/testvol/a.img
> file=gluster+tcp://1.2.3.4:24007/testvol/dir/a.img
> file=gluster+tcp://[1:2:3:4:5:6:7:8]/testvol/dir/a.img
> file=gluster+tcp://[1:2:3:4:5:6:7:8]:24007/testvol/dir/a.img
> file=gluster+tcp://server.domain.com:24007/testvol/dir/a.img
> file=gluster+unix:///testvol/dir/a.img?socket=/tmp/glusterd.socket
> file=gluster+rdma://1.2.3.4:24007/testvol/a.img
> 
> Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com>
> ---
> 
>  block/Makefile.objs |    1 
>  block/gluster.c     |  642 +++++++++++++++++++++++++++++++++++++++++++++++++++
>  2 files changed, 643 insertions(+), 0 deletions(-)
>  create mode 100644 block/gluster.c
> 
> 
> diff --git a/block/Makefile.objs b/block/Makefile.objs
> index b5754d3..a1ae67f 100644
> --- a/block/Makefile.objs
> +++ b/block/Makefile.objs
> @@ -9,3 +9,4 @@ block-obj-$(CONFIG_POSIX) += raw-posix.o
>  block-obj-$(CONFIG_LIBISCSI) += iscsi.o
>  block-obj-$(CONFIG_CURL) += curl.o
>  block-obj-$(CONFIG_RBD) += rbd.o
> +block-obj-$(CONFIG_GLUSTERFS) += gluster.o
> diff --git a/block/gluster.c b/block/gluster.c
> new file mode 100644
> index 0000000..a2f8303
> --- /dev/null
> +++ b/block/gluster.c
> @@ -0,0 +1,642 @@
> +/*
> + * GlusterFS backend for QEMU
> + *
> + * Copyright (C) 2012 Bharata B Rao <bharata@linux.vnet.ibm.com>
> + *
> + * Pipe handling mechanism in AIO implementation is derived from
> + * block/rbd.c. Hence,
> + *
> + * Copyright (C) 2010-2011 Christian Brunner <chb@muc.de>,
> + *                         Josh Durgin <josh.durgin@dreamhost.com>
> + *
> + * This work is licensed under the terms of the GNU GPL, version 2.  See
> + * the COPYING file in the top-level directory.
> + *
> + * Contributions after 2012-01-13 are licensed under the terms of the
> + * GNU GPL, version 2 or (at your option) any later version.
> + */
> +#include <glusterfs/api/glfs.h>
> +#include "block_int.h"
> +#include "qemu_socket.h"
> +#include "uri.h"
> +
> +typedef struct GlusterAIOCB {
> +    BlockDriverAIOCB common;
> +    int64_t size;
> +    int ret;
> +    bool *finished;
> +    QEMUBH *bh;
> +} GlusterAIOCB;
> +
> +typedef struct BDRVGlusterState {
> +    struct glfs *glfs;
> +    int fds[2];
> +    struct glfs_fd *fd;
> +    int qemu_aio_count;
> +    int event_reader_pos;
> +    GlusterAIOCB *event_acb;
> +} BDRVGlusterState;
> +
> +#define GLUSTER_FD_READ  0
> +#define GLUSTER_FD_WRITE 1
> +
> +typedef struct GlusterConf {
> +    char *server;
> +    int port;
> +    char *volname;
> +    char *image;
> +    char *transport;
> +} GlusterConf;
> +
> +static void qemu_gluster_gconf_free(GlusterConf *gconf)
> +{
> +    g_free(gconf->server);
> +    g_free(gconf->volname);
> +    g_free(gconf->image);
> +    g_free(gconf->transport);
> +    g_free(gconf);
> +}
> +
> +static int parse_volume_options(GlusterConf *gconf, char *path)
> +{
> +    char *token, *saveptr;
> +
> +    /* volname */
> +    token = strtok_r(path, "/", &saveptr);
> +    if (!token) {
> +        return -EINVAL;
> +    }
> +    gconf->volname = g_strdup(token);
> +
> +    /* image */
> +    token = strtok_r(NULL, "?", &saveptr);

If I understand uri.c right, there is no ? in the path, so there's no
reason to call strtok. You could just use the rest of the string.

> +    if (!token) {
> +        return -EINVAL;
> +    }
> +    gconf->image = g_strdup(token);
> +    return 0;
> +}
> +
> +/*
> + * file=gluster[+transport]://[server[:port]]/volname/image[?socket=...]
> + *
> + * 'gluster' is the protocol.
> + *
> + * 'transport' specifies the transport type used to connect to gluster
> + * management daemon (glusterd). Valid transport types are
> + * tcp, unix and rdma. If a transport type isn't specified, then tcp
> + * type is assumed.
> + *
> + * 'server' specifies the server where the volume file specification for
> + * the given volume resides. This can be either hostname, ipv4 address
> + * or ipv6 address. ipv6 address needs to be within square brackets [ ].
> + * If transport type is 'unix', then server field is ignored, but the
> + * 'socket' field needs to be populated with the path to unix domain
> + * socket.
> + *
> + * 'port' is the port number on which glusterd is listening. This is optional
> + * and if not specified, QEMU will send 0 which will make gluster to use the
> + * default port. port is ignored for unix type of transport.
> + *
> + * 'volname' is the name of the gluster volume which contains the VM image.
> + *
> + * 'image' is the path to the actual VM image that resides on gluster volume.
> + *
> + * Examples:
> + *
> + * file=gluster://1.2.3.4/testvol/a.img
> + * file=gluster+tcp://1.2.3.4/testvol/a.img
> + * file=gluster+tcp://1.2.3.4:24007/testvol/dir/a.img
> + * file=gluster+tcp://[1:2:3:4:5:6:7:8]/testvol/dir/a.img
> + * file=gluster+tcp://[1:2:3:4:5:6:7:8]:24007/testvol/dir/a.img
> + * file=gluster+tcp://server.domain.com:24007/testvol/dir/a.img
> + * file=gluster+unix:///testvol/dir/a.img?socket=/tmp/glusterd.socket
> + * file=gluster+rdma://1.2.3.4:24007/testvol/a.img
> + */
> +static int qemu_gluster_parseuri(GlusterConf *gconf, const char *filename)
> +{
> +    URI *uri;
> +    QueryParams *qp = NULL;
> +    bool is_unix = false;
> +    int ret = 0;
> +    char *unescape_str = NULL;
> +
> +    uri = uri_parse(filename);
> +    if (!uri) {
> +        return -EINVAL;
> +    }
> +
> +    /* transport */
> +    if (!strcmp(uri->scheme, "gluster")) {
> +        gconf->transport = g_strdup("tcp");
> +    } else if (!strcmp(uri->scheme, "gluster+tcp")) {
> +        gconf->transport = g_strdup("tcp");
> +    } else if (!strcmp(uri->scheme, "gluster+unix")) {
> +        gconf->transport = g_strdup("unix");
> +        is_unix = true;
> +    } else if (!strcmp(uri->scheme, "gluster+rdma")) {
> +        gconf->transport = g_strdup("rdma");
> +    } else {
> +        ret = -EINVAL;
> +        goto out;
> +    }
> +
> +    ret = parse_volume_options(gconf, uri->path);
> +    if (ret < 0) {
> +        goto out;
> +    }
> +
> +    if (uri->query) {
> +        unescape_str = uri_string_unescape(uri->query, -1, NULL);
> +        if (!unescape_str) {
> +            ret = -EINVAL;
> +            goto out;
> +        }
> +    }

I agree with Paolo here, this need to go away.

The example that you posted ("gluster+unix:///b?c=d%26e=f") has indeed
only one argument with name 'c' and value 'd&e=f'. If you unescape here,
you would incorrectly require double escaping.

> +
> +    qp = query_params_parse(unescape_str);
> +    if (qp->n > 1 || (is_unix && !qp->n) || (!is_unix && qp->n)) {
> +        ret = -EINVAL;
> +        goto out;
> +    }
> +
> +    if (is_unix) {
> +        if (strcmp(qp->p[0].name, "socket")) {
> +            ret = -EINVAL;
> +            goto out;
> +        }
> +        gconf->server = g_strdup(qp->p[0].value);

Maybe add a check that uri->server is empty?

> +    } else {
> +        gconf->server = g_strdup(uri->server);
> +        gconf->port = uri->port;
> +    }
> +
> +out:
> +    if (qp) {
> +        query_params_free(qp);
> +    }
> +    g_free(unescape_str);
> +    uri_free(uri);
> +    return ret;
> +}
> +
> +static struct glfs *qemu_gluster_init(GlusterConf *gconf, const char *filename)
> +{
> +    struct glfs *glfs = NULL;
> +    int ret;
> +
> +    ret = qemu_gluster_parseuri(gconf, filename);
> +    if (ret < 0) {
> +        error_report("Usage: file=gluster[+transport]://[server[:port]]/"
> +            "volname/image[?socket=...]");
> +        errno = -ret;
> +        goto out;
> +    }
> +
> +    glfs = glfs_new(gconf->volname);
> +    if (!glfs) {
> +        goto out;
> +    }
> +
> +    ret = glfs_set_volfile_server(glfs, gconf->transport, gconf->server,
> +            gconf->port);
> +    if (ret < 0) {
> +        goto out;
> +    }
> +
> +    /*
> +     * TODO: Use GF_LOG_ERROR instead of hard code value of 4 here when
> +     * GlusterFS makes GF_LOG_* macros available to libgfapi users.
> +     */
> +    ret = glfs_set_logging(glfs, "-", 4);
> +    if (ret < 0) {
> +        goto out;
> +    }
> +
> +    ret = glfs_init(glfs);
> +    if (ret) {
> +        error_report("Gluster connection failed for server=%s port=%d "
> +             "volume=%s image=%s transport=%s\n", gconf->server, gconf->port,
> +             gconf->volname, gconf->image, gconf->transport);
> +        goto out;
> +    }
> +    return glfs;
> +
> +out:
> +    if (glfs) {
> +        glfs_fini(glfs);

Does this corrupt errno?

> +    }
> +    return NULL;
> +}
> +
> +static void qemu_gluster_complete_aio(GlusterAIOCB *acb, BDRVGlusterState *s)
> +{
> +    int ret;
> +    bool *finished = acb->finished;
> +    BlockDriverCompletionFunc *cb = acb->common.cb;
> +    void *opaque = acb->common.opaque;
> +
> +    if (!acb->ret || acb->ret == acb->size) {
> +        ret = 0; /* Success */
> +    } else if (acb->ret < 0) {
> +        ret = acb->ret; /* Read/Write failed */
> +    } else {
> +        ret = -EIO; /* Partial read/write - fail it */
> +    }
> +
> +    s->qemu_aio_count--;
> +    qemu_aio_release(acb);
> +    cb(opaque, ret);
> +    if (finished) {
> +        *finished = true;
> +    }
> +}
> +
> +static void qemu_gluster_aio_event_reader(void *opaque)
> +{
> +    BDRVGlusterState *s = opaque;
> +    ssize_t ret;
> +
> +    do {
> +        char *p = (char *)&s->event_acb;
> +
> +        ret = read(s->fds[GLUSTER_FD_READ], p + s->event_reader_pos,
> +                   sizeof(s->event_acb) - s->event_reader_pos);
> +        if (ret > 0) {
> +            s->event_reader_pos += ret;
> +            if (s->event_reader_pos == sizeof(s->event_acb)) {
> +                s->event_reader_pos = 0;
> +                qemu_gluster_complete_aio(s->event_acb, s);
> +            }
> +        }
> +    } while (ret < 0 && errno == EINTR);
> +}
> +
> +static int qemu_gluster_aio_flush_cb(void *opaque)
> +{
> +    BDRVGlusterState *s = opaque;
> +
> +    return (s->qemu_aio_count > 0);
> +}
> +
> +static int qemu_gluster_open(BlockDriverState *bs, const char *filename,
> +    int bdrv_flags)
> +{
> +    BDRVGlusterState *s = bs->opaque;
> +    int open_flags = 0;
> +    int ret = 0;
> +    GlusterConf *gconf = g_malloc0(sizeof(GlusterConf));
> +
> +    s->glfs = qemu_gluster_init(gconf, filename);
> +    if (!s->glfs) {
> +        ret = -errno;
> +        goto out;
> +    }
> +
> +    open_flags |=  O_BINARY;
> +    open_flags &= ~O_ACCMODE;

open_flags == O_BINARY here, so no O_ACCMODE bits to clear.

> +    if (bdrv_flags & BDRV_O_RDWR) {
> +        open_flags |= O_RDWR;
> +    } else {
> +        open_flags |= O_RDONLY;
> +    }
> +
> +    if ((bdrv_flags & BDRV_O_NOCACHE)) {
> +        open_flags |= O_DIRECT;
> +    }
> +
> +    s->fd = glfs_open(s->glfs, gconf->image, open_flags);
> +    if (!s->fd) {
> +        ret = -errno;
> +        goto out;
> +    }
> +
> +    ret = qemu_pipe(s->fds);
> +    if (ret < 0) {
> +        ret = -errno;
> +        goto out;
> +    }
> +    fcntl(s->fds[GLUSTER_FD_READ], F_SETFL, O_NONBLOCK);
> +    qemu_aio_set_fd_handler(s->fds[GLUSTER_FD_READ],
> +        qemu_gluster_aio_event_reader, NULL, qemu_gluster_aio_flush_cb, s);
> +
> +out:
> +    qemu_gluster_gconf_free(gconf);
> +    if (!ret) {
> +        return ret;
> +    }
> +    if (s->fd) {
> +        glfs_close(s->fd);
> +    }
> +    if (s->glfs) {
> +        glfs_fini(s->glfs);
> +    }
> +    return ret;
> +}
> +
> +static int qemu_gluster_create(const char *filename,
> +        QEMUOptionParameter *options)
> +{
> +    struct glfs *glfs;
> +    struct glfs_fd *fd;
> +    int ret = 0;
> +    int64_t total_size = 0;
> +    GlusterConf *gconf = g_malloc0(sizeof(GlusterConf));
> +
> +    glfs = qemu_gluster_init(gconf, filename);
> +    if (!glfs) {
> +        ret = -errno;
> +        goto out;
> +    }
> +
> +    while (options && options->name) {
> +        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
> +            total_size = options->value.n / BDRV_SECTOR_SIZE;
> +        }
> +        options++;
> +    }
> +
> +    fd = glfs_creat(glfs, gconf->image,
> +        O_WRONLY | O_CREAT | O_TRUNC | O_BINARY, S_IRUSR | S_IWUSR);
> +    if (!fd) {
> +        ret = -errno;
> +    } else {
> +        if (glfs_ftruncate(fd, total_size * BDRV_SECTOR_SIZE) != 0) {
> +            ret = -errno;
> +        }
> +        if (glfs_close(fd) != 0) {
> +            ret = -errno;
> +        }
> +    }
> +out:
> +    qemu_gluster_gconf_free(gconf);
> +    if (glfs) {
> +        glfs_fini(glfs);
> +    }
> +    return ret;
> +}
> +
> +static void qemu_gluster_aio_cancel(BlockDriverAIOCB *blockacb)
> +{
> +    GlusterAIOCB *acb = (GlusterAIOCB *)blockacb;
> +    bool finished = false;
> +
> +    acb->finished = &finished;
> +    while (!finished) {
> +        qemu_aio_wait();
> +    }
> +}
> +
> +static AIOPool gluster_aio_pool = {
> +    .aiocb_size = sizeof(GlusterAIOCB),
> +    .cancel = qemu_gluster_aio_cancel,
> +};
> +
> +static int qemu_gluster_send_pipe(BDRVGlusterState *s, GlusterAIOCB *acb)
> +{
> +    int ret = 0;
> +
> +    while (1) {
> +        int fd = s->fds[GLUSTER_FD_WRITE];
> +
> +        ret = write(fd, (void *)&acb, sizeof(acb));
> +        if (ret >= 0) {
> +            break;
> +        }
> +        if (errno == EINTR) {
> +            continue;
> +        }
> +        if (errno != EAGAIN) {
> +            break;
> +        }

Variatio delectat? ;-)

How about just do { ... } while (errno == EINTR || errno == EAGAIN); ?

> +    }
> +    return ret;
> +}

Kevin