qemu/block/throttle.c

279 lines
8.7 KiB
C
Raw Normal View History

/*
* QEMU block throttling filter driver infrastructure
*
* Copyright (c) 2017 Manos Pitsidianakis
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as
* published by the Free Software Foundation; either version 2 or
* (at your option) version 3 of the 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 General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
#include "qemu/osdep.h"
#include "block/throttle-groups.h"
#include "qemu/module.h"
#include "qemu/option.h"
#include "qemu/throttle-options.h"
#include "qapi/error.h"
static QemuOptsList throttle_opts = {
.name = "throttle",
.head = QTAILQ_HEAD_INITIALIZER(throttle_opts.head),
.desc = {
{
.name = QEMU_OPT_THROTTLE_GROUP_NAME,
.type = QEMU_OPT_STRING,
.help = "Name of the throttle group",
},
{ /* end of list */ }
},
};
/*
* If this function succeeds then the throttle group name is stored in
* @group and must be freed by the caller.
* If there's an error then @group remains unmodified.
*/
static int throttle_parse_options(QDict *options, char **group, Error **errp)
{
int ret;
const char *group_name;
QemuOpts *opts = qemu_opts_create(&throttle_opts, NULL, 0, &error_abort);
if (!qemu_opts_absorb_qdict(opts, options, errp)) {
ret = -EINVAL;
goto fin;
}
group_name = qemu_opt_get(opts, QEMU_OPT_THROTTLE_GROUP_NAME);
if (!group_name) {
error_setg(errp, "Please specify a throttle group");
ret = -EINVAL;
goto fin;
} else if (!throttle_group_exists(group_name)) {
error_setg(errp, "Throttle group '%s' does not exist", group_name);
ret = -EINVAL;
goto fin;
}
*group = g_strdup(group_name);
ret = 0;
fin:
qemu_opts_del(opts);
return ret;
}
static int throttle_open(BlockDriverState *bs, QDict *options,
int flags, Error **errp)
{
ThrottleGroupMember *tgm = bs->opaque;
char *group;
int ret;
bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds,
BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY,
false, errp);
if (!bs->file) {
return -EINVAL;
}
bs->supported_write_flags = bs->file->bs->supported_write_flags |
BDRV_REQ_WRITE_UNCHANGED;
bs->supported_zero_flags = bs->file->bs->supported_zero_flags |
BDRV_REQ_WRITE_UNCHANGED;
ret = throttle_parse_options(options, &group, errp);
if (ret == 0) {
/* Register membership to group with name group_name */
throttle_group_register_tgm(tgm, group, bdrv_get_aio_context(bs));
g_free(group);
}
return ret;
}
static void throttle_close(BlockDriverState *bs)
{
ThrottleGroupMember *tgm = bs->opaque;
throttle_group_unregister_tgm(tgm);
}
static int64_t throttle_getlength(BlockDriverState *bs)
{
return bdrv_getlength(bs->file->bs);
}
static int coroutine_fn throttle_co_preadv(BlockDriverState *bs,
block: use int64_t instead of uint64_t in driver read handlers We are generally moving to int64_t for both offset and bytes parameters on all io paths. Main motivation is realization of 64-bit write_zeroes operation for fast zeroing large disk chunks, up to the whole disk. We chose signed type, to be consistent with off_t (which is signed) and with possibility for signed return type (where negative value means error). So, convert driver read handlers parameters which are already 64bit to signed type. While being here, convert also flags parameter to be BdrvRequestFlags. Now let's consider all callers. Simple git grep '\->bdrv_\(aio\|co\)_preadv\(_part\)\?' shows that's there three callers of driver function: bdrv_driver_preadv() in block/io.c, passes int64_t, checked by bdrv_check_qiov_request() to be non-negative. qcow2_load_vmstate() does bdrv_check_qiov_request(). do_perform_cow_read() has uint64_t argument. And a lot of things in qcow2 driver are uint64_t, so converting it is big job. But we must not work with requests that don't satisfy bdrv_check_qiov_request(), so let's just assert it here. Still, the functions may be called directly, not only by drv->... Let's check: git grep '\.bdrv_\(aio\|co\)_preadv\(_part\)\?\s*=' | \ awk '{print $4}' | sed 's/,//' | sed 's/&//' | sort | uniq | \ while read func; do git grep "$func(" | \ grep -v "$func(BlockDriverState"; done The only one such caller: QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, &data, 1); ... ret = bdrv_replace_test_co_preadv(bs, 0, 1, &qiov, 0); in tests/unit/test-bdrv-drain.c, and it's OK obviously. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20210903102807.27127-4-vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> [eblake: fix typos] Signed-off-by: Eric Blake <eblake@redhat.com>
2021-09-03 18:27:59 +08:00
int64_t offset, int64_t bytes,
QEMUIOVector *qiov,
BdrvRequestFlags flags)
{
ThrottleGroupMember *tgm = bs->opaque;
throttle_group_co_io_limits_intercept(tgm, bytes, false);
return bdrv_co_preadv(bs->file, offset, bytes, qiov, flags);
}
static int coroutine_fn throttle_co_pwritev(BlockDriverState *bs,
block: use int64_t instead of uint64_t in driver write handlers We are generally moving to int64_t for both offset and bytes parameters on all io paths. Main motivation is realization of 64-bit write_zeroes operation for fast zeroing large disk chunks, up to the whole disk. We chose signed type, to be consistent with off_t (which is signed) and with possibility for signed return type (where negative value means error). So, convert driver write handlers parameters which are already 64bit to signed type. While being here, convert also flags parameter to be BdrvRequestFlags. Now let's consider all callers. Simple git grep '\->bdrv_\(aio\|co\)_pwritev\(_part\)\?' shows that's there three callers of driver function: bdrv_driver_pwritev() and bdrv_driver_pwritev_compressed() in block/io.c, both pass int64_t, checked by bdrv_check_qiov_request() to be non-negative. qcow2_save_vmstate() does bdrv_check_qiov_request(). Still, the functions may be called directly, not only by drv->... Let's check: git grep '\.bdrv_\(aio\|co\)_pwritev\(_part\)\?\s*=' | \ awk '{print $4}' | sed 's/,//' | sed 's/&//' | sort | uniq | \ while read func; do git grep "$func(" | \ grep -v "$func(BlockDriverState"; done shows several callers: qcow2: qcow2_co_truncate() write at most up to @offset, which is checked in generic qcow2_co_truncate() by bdrv_check_request(). qcow2_co_pwritev_compressed_task() pass the request (or part of the request) that already went through normal write path, so it should be OK qcow: qcow_co_pwritev_compressed() pass int64_t, it's updated by this patch quorum: quorum_co_pwrite_zeroes() pass int64_t and int - OK throttle: throttle_co_pwritev_compressed() pass int64_t, it's updated by this patch vmdk: vmdk_co_pwritev_compressed() pass int64_t, it's updated by this patch Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20210903102807.27127-5-vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Eric Blake <eblake@redhat.com>
2021-09-03 18:28:00 +08:00
int64_t offset, int64_t bytes,
QEMUIOVector *qiov,
BdrvRequestFlags flags)
{
ThrottleGroupMember *tgm = bs->opaque;
throttle_group_co_io_limits_intercept(tgm, bytes, true);
return bdrv_co_pwritev(bs->file, offset, bytes, qiov, flags);
}
static int coroutine_fn throttle_co_pwrite_zeroes(BlockDriverState *bs,
int64_t offset, int bytes,
BdrvRequestFlags flags)
{
ThrottleGroupMember *tgm = bs->opaque;
throttle_group_co_io_limits_intercept(tgm, bytes, true);
return bdrv_co_pwrite_zeroes(bs->file, offset, bytes, flags);
}
static int coroutine_fn throttle_co_pdiscard(BlockDriverState *bs,
int64_t offset, int bytes)
{
ThrottleGroupMember *tgm = bs->opaque;
throttle_group_co_io_limits_intercept(tgm, bytes, true);
return bdrv_co_pdiscard(bs->file, offset, bytes);
}
static int coroutine_fn throttle_co_pwritev_compressed(BlockDriverState *bs,
block: use int64_t instead of uint64_t in driver write handlers We are generally moving to int64_t for both offset and bytes parameters on all io paths. Main motivation is realization of 64-bit write_zeroes operation for fast zeroing large disk chunks, up to the whole disk. We chose signed type, to be consistent with off_t (which is signed) and with possibility for signed return type (where negative value means error). So, convert driver write handlers parameters which are already 64bit to signed type. While being here, convert also flags parameter to be BdrvRequestFlags. Now let's consider all callers. Simple git grep '\->bdrv_\(aio\|co\)_pwritev\(_part\)\?' shows that's there three callers of driver function: bdrv_driver_pwritev() and bdrv_driver_pwritev_compressed() in block/io.c, both pass int64_t, checked by bdrv_check_qiov_request() to be non-negative. qcow2_save_vmstate() does bdrv_check_qiov_request(). Still, the functions may be called directly, not only by drv->... Let's check: git grep '\.bdrv_\(aio\|co\)_pwritev\(_part\)\?\s*=' | \ awk '{print $4}' | sed 's/,//' | sed 's/&//' | sort | uniq | \ while read func; do git grep "$func(" | \ grep -v "$func(BlockDriverState"; done shows several callers: qcow2: qcow2_co_truncate() write at most up to @offset, which is checked in generic qcow2_co_truncate() by bdrv_check_request(). qcow2_co_pwritev_compressed_task() pass the request (or part of the request) that already went through normal write path, so it should be OK qcow: qcow_co_pwritev_compressed() pass int64_t, it's updated by this patch quorum: quorum_co_pwrite_zeroes() pass int64_t and int - OK throttle: throttle_co_pwritev_compressed() pass int64_t, it's updated by this patch vmdk: vmdk_co_pwritev_compressed() pass int64_t, it's updated by this patch Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20210903102807.27127-5-vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Eric Blake <eblake@redhat.com>
2021-09-03 18:28:00 +08:00
int64_t offset,
int64_t bytes,
QEMUIOVector *qiov)
{
return throttle_co_pwritev(bs, offset, bytes, qiov,
BDRV_REQ_WRITE_COMPRESSED);
}
static int throttle_co_flush(BlockDriverState *bs)
{
return bdrv_co_flush(bs->file->bs);
}
static void throttle_detach_aio_context(BlockDriverState *bs)
{
ThrottleGroupMember *tgm = bs->opaque;
throttle_group_detach_aio_context(tgm);
}
static void throttle_attach_aio_context(BlockDriverState *bs,
AioContext *new_context)
{
ThrottleGroupMember *tgm = bs->opaque;
throttle_group_attach_aio_context(tgm, new_context);
}
static int throttle_reopen_prepare(BDRVReopenState *reopen_state,
BlockReopenQueue *queue, Error **errp)
{
int ret;
char *group = NULL;
assert(reopen_state != NULL);
assert(reopen_state->bs != NULL);
ret = throttle_parse_options(reopen_state->options, &group, errp);
reopen_state->opaque = group;
return ret;
}
static void throttle_reopen_commit(BDRVReopenState *reopen_state)
{
BlockDriverState *bs = reopen_state->bs;
ThrottleGroupMember *tgm = bs->opaque;
char *group = reopen_state->opaque;
assert(group);
if (strcmp(group, throttle_group_get_name(tgm))) {
throttle_group_unregister_tgm(tgm);
throttle_group_register_tgm(tgm, group, bdrv_get_aio_context(bs));
}
g_free(reopen_state->opaque);
reopen_state->opaque = NULL;
}
static void throttle_reopen_abort(BDRVReopenState *reopen_state)
{
g_free(reopen_state->opaque);
reopen_state->opaque = NULL;
}
static void coroutine_fn throttle_co_drain_begin(BlockDriverState *bs)
{
ThrottleGroupMember *tgm = bs->opaque;
if (qatomic_fetch_inc(&tgm->io_limits_disabled) == 0) {
throttle_group_restart_tgm(tgm);
}
}
static void coroutine_fn throttle_co_drain_end(BlockDriverState *bs)
{
ThrottleGroupMember *tgm = bs->opaque;
assert(tgm->io_limits_disabled);
qatomic_dec(&tgm->io_limits_disabled);
}
static const char *const throttle_strong_runtime_opts[] = {
QEMU_OPT_THROTTLE_GROUP_NAME,
NULL
};
static BlockDriver bdrv_throttle = {
.format_name = "throttle",
.instance_size = sizeof(ThrottleGroupMember),
.bdrv_open = throttle_open,
.bdrv_close = throttle_close,
.bdrv_co_flush = throttle_co_flush,
.bdrv_child_perm = bdrv_default_perms,
.bdrv_getlength = throttle_getlength,
.bdrv_co_preadv = throttle_co_preadv,
.bdrv_co_pwritev = throttle_co_pwritev,
.bdrv_co_pwrite_zeroes = throttle_co_pwrite_zeroes,
.bdrv_co_pdiscard = throttle_co_pdiscard,
.bdrv_co_pwritev_compressed = throttle_co_pwritev_compressed,
.bdrv_attach_aio_context = throttle_attach_aio_context,
.bdrv_detach_aio_context = throttle_detach_aio_context,
.bdrv_reopen_prepare = throttle_reopen_prepare,
.bdrv_reopen_commit = throttle_reopen_commit,
.bdrv_reopen_abort = throttle_reopen_abort,
.bdrv_co_drain_begin = throttle_co_drain_begin,
.bdrv_co_drain_end = throttle_co_drain_end,
.is_filter = true,
.strong_runtime_opts = throttle_strong_runtime_opts,
};
static void bdrv_throttle_init(void)
{
bdrv_register(&bdrv_throttle);
}
block_init(bdrv_throttle_init);