1
0
mirror of git://sourceware.org/git/lvm2.git synced 2024-10-27 10:25:13 +03:00
lvm2/tools/vgmerge.c
David Teigland 8c87dda195 locking: unify global lock for flock and lockd
There have been two file locks used to protect lvm
"global state": "ORPHANS" and "GLOBAL".

Commands that used the ORPHAN flock in exclusive mode:
  pvcreate, pvremove, vgcreate, vgextend, vgremove,
  vgcfgrestore

Commands that used the ORPHAN flock in shared mode:
  vgimportclone, pvs, pvscan, pvresize, pvmove,
  pvdisplay, pvchange, fullreport

Commands that used the GLOBAL flock in exclusive mode:
  pvchange, pvscan, vgimportclone, vgscan

Commands that used the GLOBAL flock in shared mode:
  pvscan --cache, pvs

The ORPHAN lock covers the important cases of serializing
the use of orphan PVs.  It also partially covers the
reporting of orphan PVs (although not correctly as
explained below.)

The GLOBAL lock doesn't seem to have a clear purpose
(it may have eroded over time.)

Neither lock correctly protects the VG namespace, or
orphan PV properties.

To simplify and correct these issues, the two separate
flocks are combined into the one GLOBAL flock, and this flock
is used from the locking sites that are in place for the
lvmlockd global lock.

The logic behind the lvmlockd (distributed) global lock is
that any command that changes "global state" needs to take
the global lock in ex mode.  Global state in lvm is: the list
of VG names, the set of orphan PVs, and any properties of
orphan PVs.  Reading this global state can use the global lock
in sh mode to ensure it doesn't change while being reported.

The locking of global state now looks like:

lockd_global()
  previously named lockd_gl(), acquires the distributed
  global lock through lvmlockd.  This is unchanged.
  It serializes distributed lvm commands that are changing
  global state.  This is a no-op when lvmlockd is not in use.

lockf_global()
  acquires an flock on a local file.  It serializes local lvm
  commands that are changing global state.

lock_global()
  first calls lockf_global() to acquire the local flock for
  global state, and if this succeeds, it calls lockd_global()
  to acquire the distributed lock for global state.

Replace instances of lockd_gl() with lock_global(), so that the
existing sites for lvmlockd global state locking are now also
used for local file locking of global state.  Remove the previous
file locking calls lock_vol(GLOBAL) and lock_vol(ORPHAN).

The following commands which change global state are now
serialized with the exclusive global flock:

pvchange (of orphan), pvresize (of orphan), pvcreate, pvremove,
vgcreate, vgextend, vgremove, vgreduce, vgrename,
vgcfgrestore, vgimportclone, vgmerge, vgsplit

Commands that use a shared flock to read global state (and will
be serialized against the prior list) are those that use
process_each functions that are based on processing a list of
all VG names, or all PVs.  The list of all VGs or all PVs is
global state and the shared lock prevents those lists from
changing while the command is processing them.

The ORPHAN lock previously attempted to produce an accurate
listing of orphan PVs, but it was only acquired at the end of
the command during the fake vg_read of the fake orphan vg.
This is not when orphan PVs were determined; they were
determined by elimination beforehand by processing all real
VGs, and subtracting the PVs in the real VGs from the list
of all PVs that had been identified during the initial scan.
This is fixed by holding the single global lock in shared mode
while processing all VGs to determine the list of orphan PVs.
2019-04-29 13:01:05 -05:00

228 lines
5.9 KiB
C

/*
* Copyright (C) 2001-2004 Sistina Software, Inc. All rights reserved.
* Copyright (C) 2004-2009 Red Hat, Inc. All rights reserved.
*
* This file is part of LVM2.
*
* This copyrighted material is made available to anyone wishing to use,
* modify, copy, or redistribute it subject to the terms and conditions
* of the GNU Lesser General Public License v.2.1.
*
* You should have received a copy of the GNU Lesser General Public License
* along with this program; if not, write to the Free Software Foundation,
* Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include "tools.h"
static struct volume_group *_vgmerge_vg_read(struct cmd_context *cmd,
const char *vg_name)
{
struct volume_group *vg;
log_verbose("Checking for volume group \"%s\"", vg_name);
vg = vg_read_for_update(cmd, vg_name, NULL, 0, 0);
if (vg_read_error(vg)) {
release_vg(vg);
return NULL;
}
if (vg_is_shared(vg)) {
log_error("vgmerge not allowed for lock_type %s", vg->lock_type);
unlock_and_release_vg(cmd, vg, vg_name);
return NULL;
}
return vg;
}
/* Select bigger pool metadata spare volume */
static int _vgmerge_select_pool_metadata_spare(struct cmd_context *cmd,
struct volume_group *vg_to,
struct volume_group *vg_from)
{
struct volume_group *svg;
if (!vg_to->pool_metadata_spare_lv ||
!vg_from->pool_metadata_spare_lv)
return 1; /* no problem */
/* Drop smaller pool metadata spare */
svg = (vg_to->pool_metadata_spare_lv->le_count <
vg_from->pool_metadata_spare_lv->le_count) ? vg_to : vg_from;
vg_remove_pool_metadata_spare(svg);
/* Re-test lv name compatibility */
if (!vgs_are_compatible(cmd, vg_from, vg_to))
return_0;
return 1;
}
static int _vgmerge_single(struct cmd_context *cmd, const char *vg_name_to,
const char *vg_name_from)
{
struct pv_list *pvl, *tpvl;
struct volume_group *vg_to, *vg_from;
struct lv_list *lvl1, *lvl2;
int r = ECMD_FAILED;
int lock_vg_from_first = 0;
if (!strcmp(vg_name_to, vg_name_from)) {
log_error("Duplicate volume group name \"%s\"", vg_name_from);
return ECMD_FAILED;
}
lvmcache_label_scan(cmd);
if (strcmp(vg_name_to, vg_name_from) > 0)
lock_vg_from_first = 1;
if (lock_vg_from_first) {
if (!(vg_from = _vgmerge_vg_read(cmd, vg_name_from)))
return_ECMD_FAILED;
if (!(vg_to = _vgmerge_vg_read(cmd, vg_name_to))) {
unlock_and_release_vg(cmd, vg_from, vg_name_from);
return_ECMD_FAILED;
}
} else {
if (!(vg_to = _vgmerge_vg_read(cmd, vg_name_to)))
return_ECMD_FAILED;
if (!(vg_from = _vgmerge_vg_read(cmd, vg_name_from))) {
unlock_and_release_vg(cmd, vg_to, vg_name_to);
return_ECMD_FAILED;
}
}
if (!vgs_are_compatible(cmd, vg_from, vg_to))
goto_bad;
/* FIXME List arg: vg_show_with_pv_and_lv(vg_to); */
if (!archive(vg_from) || !archive(vg_to))
goto_bad;
if (!_vgmerge_select_pool_metadata_spare(cmd, vg_to, vg_from))
goto_bad;
/* Merge volume groups */
dm_list_iterate_items_safe(pvl, tpvl, &vg_from->pvs) {
del_pvl_from_vgs(vg_from, pvl);
add_pvl_to_vgs(vg_to, pvl);
pvl->pv->vg_name = dm_pool_strdup(cmd->mem, vg_to->name);
/* Mark the VGs that still hold metadata for the old VG */
log_debug_metadata("Marking PV %s as moved to VG %s", dev_name(pvl->pv->dev), vg_to->name);
pvl->pv->status |= PV_MOVED_VG;
}
/* Fix up LVIDs */
dm_list_iterate_items(lvl1, &vg_to->lvs) {
union lvid *lvid1 = &lvl1->lv->lvid;
char uuid[64] __attribute__((aligned(8)));
dm_list_iterate_items(lvl2, &vg_from->lvs) {
union lvid *lvid2 = &lvl2->lv->lvid;
if (id_equal(&lvid1->id[1], &lvid2->id[1])) {
if (!id_create(&lvid2->id[1])) {
log_error("Failed to generate new "
"random LVID for %s",
lvl2->lv->name);
goto bad;
}
if (!id_write_format(&lvid2->id[1], uuid,
sizeof(uuid)))
goto_bad;
log_verbose("Changed LVID for %s to %s",
lvl2->lv->name, uuid);
}
}
}
dm_list_iterate_items(lvl1, &vg_from->lvs) {
lvl1->lv->vg = vg_to;
lvl1->lv->lvid.id[0] = lvl1->lv->vg->id;
}
while (!dm_list_empty(&vg_from->lvs)) {
struct dm_list *lvh = vg_from->lvs.n;
dm_list_move(&vg_to->lvs, lvh);
}
while (!dm_list_empty(&vg_from->fid->metadata_areas_in_use)) {
struct dm_list *mdah = vg_from->fid->metadata_areas_in_use.n;
dm_list_move(&vg_to->fid->metadata_areas_in_use, mdah);
}
while (!dm_list_empty(&vg_from->fid->metadata_areas_ignored)) {
struct dm_list *mdah = vg_from->fid->metadata_areas_ignored.n;
dm_list_move(&vg_to->fid->metadata_areas_ignored, mdah);
}
if (!vg_to->pool_metadata_spare_lv)
vg_to->pool_metadata_spare_lv =
vg_from->pool_metadata_spare_lv;
vg_to->extent_count += vg_from->extent_count;
vg_to->free_count += vg_from->free_count;
/* Flag up that some PVs have moved from another VG */
vg_to->old_name = vg_from->name;
/* store it on disks */
log_verbose("Writing out updated volume group");
if (!vg_write(vg_to) || !vg_commit(vg_to))
goto_bad;
/* FIXME Remove /dev/vgfrom */
backup(vg_to);
log_print_unless_silent("Volume group \"%s\" successfully merged into \"%s\"",
vg_from->name, vg_to->name);
r = ECMD_PROCESSED;
bad:
/*
* Note: as vg_to is referencing moved elements from vg_from
* the order of release_vg calls is mandatory.
*/
unlock_and_release_vg(cmd, vg_to, vg_name_to);
unlock_and_release_vg(cmd, vg_from, vg_name_from);
return r;
}
int vgmerge(struct cmd_context *cmd, int argc, char **argv)
{
const char *vg_name_to, *vg_name_from;
int opt = 0;
int ret = 0, ret_max = 0;
if (argc < 2) {
log_error("Please enter 2 or more volume groups to merge");
return EINVALID_CMD_LINE;
}
if (!lock_global(cmd, "ex"))
return ECMD_FAILED;
clear_hint_file(cmd);
vg_name_to = skip_dev_dir(cmd, argv[0], NULL);
argc--;
argv++;
for (; opt < argc; opt++) {
vg_name_from = skip_dev_dir(cmd, argv[opt], NULL);
ret = _vgmerge_single(cmd, vg_name_to, vg_name_from);
if (ret > ret_max)
ret_max = ret;
}
return ret_max;
}