From patchwork Mon May 31 19:31:40 2010 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Christian Brunner X-Patchwork-Id: 103316 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by demeter.kernel.org (8.14.3/8.14.3) with ESMTP id o4VJVlQ8014013 for ; Mon, 31 May 2010 19:31:47 GMT Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756893Ab0EaTbr (ORCPT ); Mon, 31 May 2010 15:31:47 -0400 Received: from mail-fx0-f46.google.com ([209.85.161.46]:62043 "EHLO mail-fx0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752929Ab0EaTbq (ORCPT ); Mon, 31 May 2010 15:31:46 -0400 Received: by fxm8 with SMTP id 8so363923fxm.19 for ; Mon, 31 May 2010 12:31:44 -0700 (PDT) Received: by 10.223.23.67 with SMTP id q3mr5968618fab.59.1275334304006; Mon, 31 May 2010 12:31:44 -0700 (PDT) Received: from chb-desktop (e181032174.adsl.alicedsl.de [85.181.32.174]) by mx.google.com with ESMTPS id g10sm42824889fai.12.2010.05.31.12.31.42 (version=SSLv3 cipher=RC4-MD5); Mon, 31 May 2010 12:31:43 -0700 (PDT) Date: Mon, 31 May 2010 21:31:40 +0200 From: Christian Brunner To: Kevin Wolf Cc: kvm@vger.kernel.org, qemu-devel@nongnu.org, ceph-devel@vger.kernel.org Subject: [PATCH] ceph/rbd block driver for qemu-kvm (v3) Message-ID: <20100531193140.GA13993@chb-desktop> MIME-Version: 1.0 Content-Disposition: inline User-Agent: Mutt/1.5.20 (2009-06-14) Sender: ceph-devel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: ceph-devel@vger.kernel.org X-Greylist: IP, sender and recipient auto-whitelisted, not delayed by milter-greylist-4.2.3 (demeter.kernel.org [140.211.167.41]); Mon, 31 May 2010 19:31:48 +0000 (UTC) diff --git a/Makefile.objs b/Makefile.objs index 1a942e5..08dc11f 100644 --- a/Makefile.objs +++ b/Makefile.objs @@ -18,6 +18,7 @@ block-nested-y += parallels.o nbd.o blkdebug.o block-nested-$(CONFIG_WIN32) += raw-win32.o block-nested-$(CONFIG_POSIX) += raw-posix.o block-nested-$(CONFIG_CURL) += curl.o +block-nested-$(CONFIG_RBD) += rbd.o block-obj-y += $(addprefix block/, $(block-nested-y)) diff --git a/block/rbd.c b/block/rbd.c new file mode 100644 index 0000000..4a60dda --- /dev/null +++ b/block/rbd.c @@ -0,0 +1,600 @@ +/* + * QEMU Block driver for RADOS (Ceph) + * + * Copyright (C) 2010 Christian Brunner + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include "qemu-common.h" +#include "qemu-error.h" +#include +#include + +#include + +#include "rbd_types.h" +#include "module.h" +#include "block_int.h" + +#include +#include +#include + +#include + +/* + * When specifying the image filename use: + * + * rbd:poolname/devicename + * + * poolname must be the name of an existing rados pool + * + * devicename is the basename for all objects used to + * emulate the raw device. + * + * Metadata information (image size, ...) is stored in an + * object with the name "devicename.rbd". + * + * The raw device is split into 4MB sized objects by default. + * The sequencenumber is encoded in a 12 byte long hex-string, + * and is attached to the devicename, separated by a dot. + * e.g. "devicename.1234567890ab" + * + */ + +#define OBJ_MAX_SIZE (1UL << OBJ_DEFAULT_OBJ_ORDER) + +typedef struct RBDAIOCB { + BlockDriverAIOCB common; + QEMUBH *bh; + int ret; + QEMUIOVector *qiov; + char *bounce; + int write; + int64_t sector_num; + int aiocnt; + int error; +} RBDAIOCB; + +typedef struct RADOSCB { + int rcbid; + RBDAIOCB *acb; + int done; + int64_t segsize; + char *buf; +} RADOSCB; + +typedef struct BDRVRBDState { + rados_pool_t pool; + char name[RBD_MAX_OBJ_NAME_SIZE]; + uint64_t size; + uint64_t objsize; +} BDRVRBDState; + +typedef struct rbd_obj_header_ondisk RbdHeader1; + +static int rbd_parsename(const char *filename, char *pool, char *name) +{ + const char *rbdname; + char *p; + int l; + + if (!strstart(filename, "rbd:", &rbdname)) { + return -EINVAL; + } + + pstrcpy(pool, 2 * RBD_MAX_SEG_NAME_SIZE, rbdname); + p = strchr(pool, '/'); + if (p == NULL) { + return -EINVAL; + } + + *p = '\0'; + + l = strlen(pool); + if(l >= RBD_MAX_SEG_NAME_SIZE) { + error_report("pool name to long"); + return -EINVAL; + } else if (l <= 0) { + error_report("pool name to short"); + return -EINVAL; + } + + l = strlen(++p); + if (l >= RBD_MAX_OBJ_NAME_SIZE) { + error_report("object name to long"); + return -EINVAL; + } else if (l <= 0) { + error_report("object name to short"); + return -EINVAL; + } + + strcpy(name, p); + + return l; +} + +static int create_tmap_op(uint8_t op, const char *name, char **tmap_desc) +{ + uint32_t len = strlen(name); + /* total_len = encoding op + name + empty buffer */ + uint32_t total_len = 1 + (sizeof(uint32_t) + len) + sizeof(uint32_t); + char *desc = NULL; + + qemu_malloc(total_len); + + *tmap_desc = desc; + + *desc = op; + desc++; + memcpy(desc, &len, sizeof(len)); + desc += sizeof(len); + memcpy(desc, name, len); + desc += len; + len = 0; + memcpy(desc, &len, sizeof(len)); + desc += sizeof(len); + + return desc - *tmap_desc; +} + +static void free_tmap_op(char *tmap_desc) +{ + qemu_free(tmap_desc); +} + +static int rbd_register_image(rados_pool_t pool, const char *name) +{ + char *tmap_desc; + const char *dir = RBD_DIRECTORY; + int ret; + + ret = create_tmap_op(CEPH_OSD_TMAP_SET, name, &tmap_desc); + if (ret < 0) { + return ret; + } + + ret = rados_tmap_update(pool, dir, tmap_desc, ret); + free_tmap_op(tmap_desc); + + return ret; +} + +static int rbd_create(const char *filename, QEMUOptionParameter *options) +{ + int64_t bytes = 0; + int64_t objsize; + uint64_t size; + time_t mtime; + uint8_t obj_order = RBD_DEFAULT_OBJ_ORDER; + char pool[RBD_MAX_SEG_NAME_SIZE]; + char n[RBD_MAX_SEG_NAME_SIZE]; + char name[RBD_MAX_SEG_NAME_SIZE]; + RbdHeader1 header; + rados_pool_t p; + int ret; + + if (rbd_parsename(filename, pool, name) < 0) { + return -EINVAL; + } + + snprintf(n, RBD_MAX_SEG_NAME_SIZE, "%s%s", name, RBD_SUFFIX); + + /* Read out options */ + while (options && options->name) { + if (!strcmp(options->name, BLOCK_OPT_SIZE)) { + bytes = options->value.n; + } else if (!strcmp(options->name, BLOCK_OPT_CLUSTER_SIZE)) { + if (options->value.n) { + objsize = options->value.n; + if ((objsize - 1) & objsize) { /* not a power of 2? */ + error_report("obj size needs to be power of 2"); + return -EINVAL; + } + if (objsize < 4096) { + error_report("obj size too small"); + return -EINVAL; + } + + for (obj_order = 0; obj_order < 64; obj_order++) { + if (objsize == 1) { + break; + } + objsize >>= 1; + } + } + } + options++; + } + + memset(&header, 0, sizeof(header)); + pstrcpy(header.text, sizeof(header.text), RBD_HEADER_TEXT); + pstrcpy(header.signature, sizeof(header.signature), RBD_HEADER_SIGNATURE); + pstrcpy(header.version, sizeof(header.version), RBD_HEADER_VERSION); + header.image_size = bytes; + cpu_to_le64s((uint64_t *) & header.image_size); + header.options.order = obj_order; + header.options.crypt_type = RBD_CRYPT_NONE; + header.options.comp_type = RBD_COMP_NONE; + header.snap_seq = 0; + header.snap_count = 0; + cpu_to_le32s(&header.snap_count); + + if (rados_initialize(0, NULL) < 0) { + error_report("error initializing"); + return -EIO; + } + + if (rados_open_pool(pool, &p)) { + error_report("error opening pool %s", pool); + rados_deinitialize(); + return -EIO; + } + + /* check for existing rbd header file */ + ret = rados_stat(p, n, &size, &mtime); + if (ret == 0) { + ret=-EEXIST; + goto done; + } + + /* create header file */ + ret = rados_write(p, n, 0, (const char *)&header, sizeof(header)); + if (ret < 0) { + goto done; + } + + ret = rbd_register_image(p, name); +done: + rados_close_pool(p); + rados_deinitialize(); + + return ret; +} + +static int rbd_open(BlockDriverState *bs, const char *filename, int flags) +{ + BDRVRBDState *s = bs->opaque; + char pool[RBD_MAX_SEG_NAME_SIZE]; + char n[RBD_MAX_SEG_NAME_SIZE]; + char hbuf[4096]; + int r; + + if (rbd_parsename(filename, pool, s->name) < 0) { + return -EINVAL; + } + snprintf(n, RBD_MAX_SEG_NAME_SIZE, "%s%s", s->name, RBD_SUFFIX); + + if ((r = rados_initialize(0, NULL)) < 0) { + error_report("error initializing"); + return r; + } + + if ((r = rados_open_pool(pool, &s->pool))) { + error_report("error opening pool %s", pool); + rados_deinitialize(); + return r; + } + + if ((r = rados_read(s->pool, n, 0, hbuf, 4096)) < 0) { + error_report("error reading header from %s", s->name); + goto failed; + } + + if (strncmp(hbuf + 64, RBD_HEADER_SIGNATURE, 4)) { + error_report("Invalid header signature %s", hbuf + 64); + r = -EMEDIUMTYPE; + goto failed; + } + + if (strncmp(hbuf + 68, RBD_HEADER_VERSION, 8)) { + error_report("Unknown image version %s", hbuf + 68); + r = -EMEDIUMTYPE; + goto failed; + } + + RbdHeader1 *header; + + header = (RbdHeader1 *) hbuf; + le64_to_cpus((uint64_t *) & header->image_size); + s->size = header->image_size; + s->objsize = 1 << header->options.order; + + return 0; + +failed: + rados_close_pool(s->pool); + rados_deinitialize(); + return r; +} + +static void rbd_close(BlockDriverState *bs) +{ + BDRVRBDState *s = bs->opaque; + + rados_close_pool(s->pool); + rados_deinitialize(); +} + +static int rbd_rw(BlockDriverState *bs, int64_t sector_num, + uint8_t *buf, int nb_sectors, int write) +{ + BDRVRBDState *s = bs->opaque; + char n[RBD_MAX_SEG_NAME_SIZE]; + + int64_t segnr, segoffs, segsize, r; + int64_t off, size; + + off = sector_num * BDRV_SECTOR_SIZE; + size = nb_sectors * BDRV_SECTOR_SIZE; + segnr = off / s->objsize; + segoffs = off % s->objsize; + segsize = s->objsize - segoffs; + + while (size > 0) { + if (size < segsize) { + segsize = size; + } + + snprintf(n, RBD_MAX_SEG_NAME_SIZE, "%s.%012" PRIx64, s->name, segnr); + + if (write) { + if ((r = rados_write(s->pool, n, segoffs, (const char *)buf, + segsize)) < 0) { + return r; + } + } else { + r = rados_read(s->pool, n, segoffs, (char *)buf, segsize); + if (r == -ENOENT) { + memset(buf, 0, segsize); + } else if (r < 0) { + return r; + } else if (r < segsize) { + memset(buf + r, 0, segsize - r); + } + } + + buf += segsize; + size -= segsize; + segoffs = 0; + segsize = s->objsize; + segnr++; + } + + return 0; +} + +static int rbd_read(BlockDriverState *bs, int64_t sector_num, + uint8_t *buf, int nb_sectors) +{ + return rbd_rw(bs, sector_num, buf, nb_sectors, 0); +} + +static int rbd_write(BlockDriverState *bs, int64_t sector_num, + const uint8_t *buf, int nb_sectors) +{ + return rbd_rw(bs, sector_num, (uint8_t *) buf, nb_sectors, 1); +} + +static void rbd_aio_cancel(BlockDriverAIOCB *blockacb) +{ + RBDAIOCB *acb = (RBDAIOCB *) blockacb; + qemu_bh_delete(acb->bh); + acb->bh = NULL; + qemu_aio_release(acb); +} + +static AIOPool rbd_aio_pool = { + .aiocb_size = sizeof(RBDAIOCB), + .cancel = rbd_aio_cancel, +}; + +/* This is the callback function for rados_aio_read and _write */ +static void rbd_finish_aiocb(rados_completion_t c, RADOSCB *rcb) +{ + RBDAIOCB *acb = rcb->acb; + int64_t r; + int i; + + acb->aiocnt--; + r = rados_aio_get_return_value(c); + rados_aio_release(c); + if (acb->write) { + if (r < 0) { + acb->ret = r; + acb->error = 1; + } else if (!acb->error) { + acb->ret += rcb->segsize; + } + } else { + if (r == -ENOENT) { + memset(rcb->buf, 0, rcb->segsize); + if (!acb->error) { + acb->ret += rcb->segsize; + } + } else if (r < 0) { + acb->ret = r; + acb->error = 1; + } else if (r < rcb->segsize) { + memset(rcb->buf + r, 0, rcb->segsize - r); + if (!acb->error) { + acb->ret += rcb->segsize; + } + } else if (!acb->error) { + acb->ret += r; + } + } + qemu_free(rcb); + i = 0; + if (!acb->aiocnt && acb->bh) { + qemu_bh_schedule(acb->bh); + } +} + +/* Callback when all queued rados_aio requests are complete */ +static void rbd_aio_bh_cb(void *opaque) +{ + RBDAIOCB *acb = opaque; + + if (!acb->write) { + qemu_iovec_from_buffer(acb->qiov, acb->bounce, acb->qiov->size); + } + qemu_vfree(acb->bounce); + acb->common.cb(acb->common.opaque, (acb->ret > 0 ? 0 : acb->ret)); + qemu_bh_delete(acb->bh); + acb->bh = NULL; + qemu_aio_release(acb); +} + +static BlockDriverAIOCB *rbd_aio_rw_vector(BlockDriverState *bs, + int64_t sector_num, + QEMUIOVector *qiov, + int nb_sectors, + BlockDriverCompletionFunc *cb, + void *opaque, int write) +{ + RBDAIOCB *acb; + RADOSCB *rcb; + rados_completion_t c; + char n[RBD_MAX_SEG_NAME_SIZE]; + int64_t segnr, segoffs, segsize, last_segnr; + int64_t off, size; + char *buf; + + BDRVRBDState *s = bs->opaque; + + acb = qemu_aio_get(&rbd_aio_pool, bs, cb, opaque); + acb->write = write; + acb->qiov = qiov; + acb->bounce = qemu_blockalign(bs, qiov->size); + acb->aiocnt = 0; + acb->ret = 0; + acb->error = 0; + + if (!acb->bh) { + acb->bh = qemu_bh_new(rbd_aio_bh_cb, acb); + } + + if (write) { + qemu_iovec_to_buffer(acb->qiov, acb->bounce); + } + + buf = acb->bounce; + + off = sector_num * BDRV_SECTOR_SIZE; + size = nb_sectors * BDRV_SECTOR_SIZE; + segnr = off / s->objsize; + segoffs = off % s->objsize; + segsize = s->objsize - segoffs; + + last_segnr = ((off + size - 1) / s->objsize); + acb->aiocnt = (last_segnr - segnr) + 1; + + while (size > 0) { + if (size < segsize) { + segsize = size; + } + + snprintf(n, RBD_MAX_SEG_NAME_SIZE, "%s.%012llx", s->name, + (long long unsigned int)segnr); + + rcb = qemu_malloc(sizeof(RADOSCB)); + rcb->done = 0; + rcb->acb = acb; + rcb->segsize = segsize; + rcb->buf = buf; + + if (write) { + rados_aio_create_completion(rcb, NULL, + (rados_callback_t) rbd_finish_aiocb, + &c); + rados_aio_write(s->pool, n, segoffs, buf, segsize, c); + } else { + rados_aio_create_completion(rcb, + (rados_callback_t) rbd_finish_aiocb, + NULL, &c); + rados_aio_read(s->pool, n, segoffs, buf, segsize, c); + } + + buf += segsize; + size -= segsize; + segoffs = 0; + segsize = s->objsize; + segnr++; + } + + return &acb->common; +} + +static BlockDriverAIOCB *rbd_aio_readv(BlockDriverState * bs, + int64_t sector_num, QEMUIOVector * qiov, + int nb_sectors, + BlockDriverCompletionFunc * cb, + void *opaque) +{ + return rbd_aio_rw_vector(bs, sector_num, qiov, nb_sectors, cb, opaque, 0); +} + +static BlockDriverAIOCB *rbd_aio_writev(BlockDriverState * bs, + int64_t sector_num, QEMUIOVector * qiov, + int nb_sectors, + BlockDriverCompletionFunc * cb, + void *opaque) +{ + return rbd_aio_rw_vector(bs, sector_num, qiov, nb_sectors, cb, opaque, 1); +} + +static int rbd_getinfo(BlockDriverState * bs, BlockDriverInfo * bdi) +{ + BDRVRBDState *s = bs->opaque; + bdi->cluster_size = s->objsize; + return 0; +} + +static int64_t rbd_getlength(BlockDriverState * bs) +{ + BDRVRBDState *s = bs->opaque; + + return s->size; +} + +static QEMUOptionParameter rbd_create_options[] = { + { + .name = BLOCK_OPT_SIZE, + .type = OPT_SIZE, + .help = "Virtual disk size" + }, + { + .name = BLOCK_OPT_CLUSTER_SIZE, + .type = OPT_SIZE, + .help = "RBD object size" + }, + {NULL} +}; + +static BlockDriver bdrv_rbd = { + .format_name = "rbd", + .instance_size = sizeof(BDRVRBDState), + .bdrv_file_open = rbd_open, + .bdrv_read = rbd_read, + .bdrv_write = rbd_write, + .bdrv_close = rbd_close, + .bdrv_create = rbd_create, + .bdrv_get_info = rbd_getinfo, + .create_options = rbd_create_options, + .bdrv_getlength = rbd_getlength, + .protocol_name = "rbd", + + .bdrv_aio_readv = rbd_aio_readv, + .bdrv_aio_writev = rbd_aio_writev, +}; + +static void bdrv_rbd_init(void) +{ + bdrv_register(&bdrv_rbd); +} + +block_init(bdrv_rbd_init); diff --git a/block/rbd_types.h b/block/rbd_types.h new file mode 100644 index 0000000..91ac4f9 --- /dev/null +++ b/block/rbd_types.h @@ -0,0 +1,64 @@ +/* + * Ceph - scalable distributed file system + * + * Copyright (C) 2004-2010 Sage Weil + * + * This is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License version 2.1, as published by the Free Software + * Foundation. See file COPYING. + * + */ + +#ifndef QEMU_BLOCK_RBD_TYPES_H +#define QEMU_BLOCK_RBD_TYPES_H + + +/* + * rbd image 'foo' consists of objects + * foo.rbd - image metadata + * foo.00000000 + * foo.00000001 + * ... - data + */ + +#define RBD_SUFFIX ".rbd" +#define RBD_DIRECTORY "rbd_directory" + +#define RBD_DEFAULT_OBJ_ORDER 22 /* 4MB */ + +#define RBD_MAX_OBJ_NAME_SIZE 96 +#define RBD_MAX_SEG_NAME_SIZE 128 + +#define RBD_COMP_NONE 0 +#define RBD_CRYPT_NONE 0 + +#define RBD_HEADER_TEXT "<<< Rados Block Device Image >>>\n" +#define RBD_HEADER_SIGNATURE "RBD" +#define RBD_HEADER_VERSION "001.004" + +struct rbd_obj_snap_ondisk { + uint64_t id; + uint64_t image_size; +} __attribute__((packed)); + +struct rbd_obj_header_ondisk { + char text[64]; + char signature[4]; + char version[8]; + struct { + uint8_t order; + uint8_t crypt_type; + uint8_t comp_type; + uint8_t unused; + } __attribute__((packed)) options; + uint64_t image_size; + uint64_t snap_seq; + uint32_t snap_count; + uint32_t reserved; + uint64_t snap_names_len; + struct rbd_obj_snap_ondisk snaps[0]; +} __attribute__((packed)); + + +#endif diff --git a/configure b/configure index 3cd2c5f..3f5c8ce 100755 --- a/configure +++ b/configure @@ -299,6 +299,7 @@ pkgversion="" check_utests="no" user_pie="no" zero_malloc="" +rbd="" # OS specific if check_define __linux__ ; then @@ -660,6 +661,10 @@ for opt do ;; --enable-vhost-net) vhost_net="yes" ;; + --disable-rbd) rbd="no" + ;; + --enable-rbd) rbd="yes" + ;; *) echo "ERROR: unknown option $opt"; show_help="yes" ;; esac @@ -826,6 +831,7 @@ echo " --enable-docs enable documentation build" echo " --disable-docs disable documentation build" echo " --disable-vhost-net disable vhost-net acceleration support" echo " --enable-vhost-net enable vhost-net acceleration support" +echo " --enable-rbd enable building the rados block device (rbd)" echo "" echo "NOTE: The object files are built at the place where configure is launched" exit 1 @@ -1579,6 +1585,27 @@ if test "$mingw32" != yes -a "$pthread" = no; then fi ########################################## +# rbd probe +if test "$rbd" != "no" ; then + cat > $TMPC < +#include +int main(void) { rados_initialize(0, NULL); return 0; } +EOF + rbd_libs="-lrados -lcrypto" + if compile_prog "" "$rbd_libs" ; then + rbd=yes + libs_tools="$rbd_libs $libs_tools" + libs_softmmu="$rbd_libs $libs_softmmu" + else + if test "$rbd" = "yes" ; then + feature_not_found "rados block device" + fi + rbd=no + fi +fi + +########################################## # linux-aio probe if test "$linux_aio" != "no" ; then @@ -2041,6 +2068,7 @@ echo "preadv support $preadv" echo "fdatasync $fdatasync" echo "uuid support $uuid" echo "vhost-net support $vhost_net" +echo "rbd support $rbd" if test $sdl_too_old = "yes"; then echo "-> Your SDL version is too old - please upgrade to have SDL support" @@ -2270,6 +2298,9 @@ echo "CONFIG_UNAME_RELEASE=\"$uname_release\"" >> $config_host_mak if test "$zero_malloc" = "yes" ; then echo "CONFIG_ZERO_MALLOC=y" >> $config_host_mak fi +if test "$rbd" = "yes" ; then + echo "CONFIG_RBD=y" >> $config_host_mak +fi # USB host support case "$usb" in