1
0
mirror of git://sourceware.org/git/lvm2.git synced 2024-12-22 17:35:59 +03:00
lvm2/lib/format_text/import.c

268 lines
6.9 KiB
C
Raw Normal View History

2001-12-17 22:46:10 +03:00
/*
2008-01-30 17:00:02 +03:00
* Copyright (C) 2001-2004 Sistina Software, Inc. All rights reserved.
2018-04-20 18:43:50 +03:00
* Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved.
2001-12-17 22:46:10 +03:00
*
2004-03-30 23:35:44 +04:00
* 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.
2004-03-30 23:35:44 +04:00
*
* You should have received a copy of the GNU Lesser General Public License
2004-03-30 23:35:44 +04:00
* along with this program; if not, write to the Free Software Foundation,
* Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
2001-12-17 22:46:10 +03:00
*/
#include "lib/misc/lib.h"
#include "lib/metadata/metadata.h"
#include "lib/commands/toolcontext.h"
2001-12-17 22:46:10 +03:00
#include "import-export.h"
2002-11-18 17:04:08 +03:00
/* FIXME Use tidier inclusion method */
static struct text_vg_version_ops *(_text_vsn_list[2]);
static int _text_import_initialised = 0;
static void _init_text_import(void)
{
if (_text_import_initialised)
return;
_text_vsn_list[0] = text_vg_vsn1_init();
_text_vsn_list[1] = NULL;
_text_import_initialised = 1;
}
/*
* Find out vgname on a given device.
*/
int text_read_metadata_summary(const struct format_type *fmt,
struct device *dev, dev_io_reason_t reason,
off_t offset, uint32_t size,
off_t offset2, uint32_t size2,
checksum_fn_t checksum_fn,
2018-04-20 18:43:50 +03:00
int checksum_only,
struct lvmcache_vgsummary *vgsummary)
{
2018-04-20 18:43:50 +03:00
struct dm_config_tree *cft;
struct text_vg_version_ops **vsn;
int r = 0;
_init_text_import();
2018-04-20 18:43:50 +03:00
if (!(cft = config_open(CONFIG_FILE_SPECIAL, NULL, 0)))
return_0;
if (dev) {
log_debug_metadata("Reading metadata summary from %s at %llu size %d (+%d)",
dev_name(dev), (unsigned long long)offset,
size, size2);
if (!config_file_read_fd(cft, dev, reason, offset, size,
2018-04-20 18:43:50 +03:00
offset2, size2, checksum_fn,
vgsummary->mda_checksum,
checksum_only, 1)) {
improve reading and repairing vg metadata The fact that vg repair is implemented as a part of vg read has led to a messy and complicated implementation of vg_read, and limited and uncontrolled repair capability. This splits read and repair apart. Summary ------- - take all kinds of various repairs out of vg_read - vg_read no longer writes anything - vg_read now simply reads and returns vg metadata - vg_read ignores bad or old copies of metadata - vg_read proceeds with a single good copy of metadata - improve error checks and handling when reading - keep track of bad (corrupt) copies of metadata in lvmcache - keep track of old (seqno) copies of metadata in lvmcache - keep track of outdated PVs in lvmcache - vg_write will do basic repairs - new command vgck --updatemetdata will do all repairs Details ------- - In scan, do not delete dev from lvmcache if reading/processing fails; the dev is still present, and removing it makes it look like the dev is not there. Records are now kept about the problems with each PV so they be fixed/repaired in the appropriate places. - In scan, record a bad mda on failure, and delete the mda from mda in use list so it will not be used by vg_read or vg_write, only by repair. - In scan, succeed if any good mda on a device is found, instead of failing if any is bad. The bad/old copies of metadata should not interfere with normal usage while good copies can be used. - In scan, add a record of old mdas in lvmcache for later, do not repair them while reading, and do not let them prevent us from finding and using a good copy of metadata from elsewhere. One result is that "inconsistent metadata" is no longer a read error, but instead a record in lvmcache that can be addressed separate from the read. - Treat a dev with no good mdas like a dev with no mdas, which is an existing case we already handle. - Don't use a fake vg "handle" for returning an error from vg_read, or the vg_read_error function for getting that error number; just return null if the vg cannot be read or used, and an error_flags arg with flags set for the specific kind of error (which can be used later for determining the kind of repair.) - Saving an original copy of the vg metadata, for purposes of reverting a write, is now done explicitly in vg_read instead of being hidden in the vg_make_handle function. - When a vg is not accessible due to "access restrictions" but is otherwise fine, return the vg through the new error_vg arg so that process_each_pv can skip the PVs in the VG while processing. (This is a temporary accomodation for the way process_each_pv tracks which devs have been looked at, and can be dropped later when process_each_pv implementation dev tracking is changed.) - vg_read does not try to fix or recover a vg, but now just reads the metadata, checks access restrictions and returns it. (Checking access restrictions might be better done outside of vg_read, but this is a later improvement.) - _vg_read now simply makes one attempt to read metadata from each mda, and uses the most recent copy to return to the caller in the form of a 'vg' struct. (bad mdas were excluded during the scan and are not retried) (old mdas were not excluded during scan and are retried here) - vg_read uses _vg_read to get the latest copy of metadata from mdas, and then makes various checks against it to produce warnings, and to check if VG access is allowed (access restrictions include: writable, foreign, shared, clustered, missing pvs). - Things that were previously silently/automatically written by vg_read that are now done by vg_write, based on the records made in lvmcache during the scan and read: . clearing the missing flag . updating old copies of metadata . clearing outdated pvs . updating pv header flags - Bad/corrupt metadata are now repaired; they were not before. Test changes ------------ - A read command no longer writes the VG to repair it, so add a write command to do a repair. (inconsistent-metadata, unlost-pv) - When a missing PV is removed from a VG, and then the device is enabled again, vgck --updatemetadata is needed to clear the outdated PV before it can be used again, where it wasn't before. (lvconvert-repair-policy, lvconvert-repair-raid, lvconvert-repair, mirror-vgreduce-removemissing, pv-ext-flags, unlost-pv) Reading bad/old metadata ------------------------ - "bad metadata": the mda_header or metadata text has invalid fields or can't be parsed by lvm. This is a form of corruption that would not be caused by known failure scenarios. A checksum error is typically included among the errors reported. - "old metadata": a valid copy of the metadata that has a smaller seqno than other copies of the metadata. This can happen if the device failed, or io failed, or lvm failed while commiting new metadata to all the metadata areas. Old metadata on a PV that has been removed from the VG is the "outdated" case below. When a VG has some PVs with bad/old metadata, lvm can simply ignore the bad/old copies, and use a good copy. This is why there are multiple copies of the metadata -- so it's available even when some of the copies cannot be used. The bad/old copies do not have to be repaired before the VG can be used (the repair can happen later.) A PV with no good copies of the metadata simply falls back to being treated like a PV with no mdas; a common and harmless configuration. When bad/old metadata exists, lvm warns the user about it, and suggests repairing it using a new metadata repair command. Bad metadata in particular is something that users will want to investigate and repair themselves, since it should not happen and may indicate some other problem that needs to be fixed. PVs with bad/old metadata are not the same as missing devices. Missing devices will block various kinds of VG modification or activation, but bad/old metadata will not. Previously, lvm would attempt to repair bad/old metadata whenever it was read. This was unnecessary since lvm does not require every copy of the metadata to be used. It would also hide potential problems that should be investigated by the user. It was also dangerous in cases where the VG was on shared storage. The user is now allowed to investigate potential problems and decide how and when to repair them. Repairing bad/old metadata -------------------------- When label scan sees bad metadata in an mda, that mda is removed from the lvmcache info->mdas list. This means that vg_read will skip it, and not attempt to read/process it again. If it was the only in-use mda on a PV, that PV is treated like a PV with no mdas. It also means that vg_write will also skip the bad mda, and not attempt to write new metadata to it. The only way to repair bad metadata is with the metadata repair command. When label scan sees old metadata in an mda, that mda is kept in the lvmcache info->mdas list. This means that vg_read will read/process it again, and likely see the same mismatch with the other copies of the metadata. Like the label_scan, the vg_read will simply ignore the old copy of the metadata and use the latest copy. If the command is modifying the vg (e.g. lvcreate), then vg_write, which writes new metadata to every mda on info->mdas, will write the new metadata to the mda that had the old version. If successful, this will resolve the old metadata problem (without needing to run a metadata repair command.) Outdated PVs ------------ An outdated PV is a PV that has an old copy of VG metadata that shows it is a member of the VG, but the latest copy of the VG metadata does not include this PV. This happens if the PV is disconnected, vgreduce --removemissing is run to remove the PV from the VG, then the PV is reconnected. In this case, the outdated PV needs have its outdated metadata removed and the PV used flag needs to be cleared. This repair will be done by the subsequent repair command. It is also done if vgremove is run on the VG. MISSING PVs ----------- When a device is missing, most commands will refuse to modify the VG. This is the simple case. More complicated is when a command is allowed to modify the VG while it is missing a device. When a VG is written while a device is missing for one of it's PVs, the VG metadata is written to disk with the MISSING flag on the PV with the missing device. When the VG is next used, it is treated as if the PV with the MISSING flag still has a missing device, even if that device has reappeared. If all LVs that were using a PV with the MISSING flag are removed or repaired so that the MISSING PV is no longer used, then the next time the VG metadata is written, the MISSING flag will be dropped. Alternative methods of clearing the MISSING flag are: vgreduce --removemissing will remove PVs with missing devices, or PVs with the MISSING flag where the device has reappeared. vgextend --restoremissing will clear the MISSING flag on PVs where the device has reappeared, allowing the VG to be used normally. This must be done with caution since the reappeared device may have old data that is inconsistent with data on other PVs. Bad mda repair -------------- The new command: vgck --updatemetadata VG first uses vg_write to repair old metadata, and other basic issues mentioned above (old metadata, outdated PVs, pv_header flags, MISSING_PV flags). It will also go further and repair bad metadata: . text metadata that has a bad checksum . text metadata that is not parsable . corrupt mda_header checksum and version fields (To keep a clean diff, #if 0 is added around functions that are replaced by new code. These commented functions are removed by the following commit.)
2019-05-24 20:04:37 +03:00
log_warn("WARNING: invalid metadata text from %s at %llu.",
dev_name(dev), (unsigned long long)offset);
goto out;
}
} else {
if (!config_file_read(cft)) {
improve reading and repairing vg metadata The fact that vg repair is implemented as a part of vg read has led to a messy and complicated implementation of vg_read, and limited and uncontrolled repair capability. This splits read and repair apart. Summary ------- - take all kinds of various repairs out of vg_read - vg_read no longer writes anything - vg_read now simply reads and returns vg metadata - vg_read ignores bad or old copies of metadata - vg_read proceeds with a single good copy of metadata - improve error checks and handling when reading - keep track of bad (corrupt) copies of metadata in lvmcache - keep track of old (seqno) copies of metadata in lvmcache - keep track of outdated PVs in lvmcache - vg_write will do basic repairs - new command vgck --updatemetdata will do all repairs Details ------- - In scan, do not delete dev from lvmcache if reading/processing fails; the dev is still present, and removing it makes it look like the dev is not there. Records are now kept about the problems with each PV so they be fixed/repaired in the appropriate places. - In scan, record a bad mda on failure, and delete the mda from mda in use list so it will not be used by vg_read or vg_write, only by repair. - In scan, succeed if any good mda on a device is found, instead of failing if any is bad. The bad/old copies of metadata should not interfere with normal usage while good copies can be used. - In scan, add a record of old mdas in lvmcache for later, do not repair them while reading, and do not let them prevent us from finding and using a good copy of metadata from elsewhere. One result is that "inconsistent metadata" is no longer a read error, but instead a record in lvmcache that can be addressed separate from the read. - Treat a dev with no good mdas like a dev with no mdas, which is an existing case we already handle. - Don't use a fake vg "handle" for returning an error from vg_read, or the vg_read_error function for getting that error number; just return null if the vg cannot be read or used, and an error_flags arg with flags set for the specific kind of error (which can be used later for determining the kind of repair.) - Saving an original copy of the vg metadata, for purposes of reverting a write, is now done explicitly in vg_read instead of being hidden in the vg_make_handle function. - When a vg is not accessible due to "access restrictions" but is otherwise fine, return the vg through the new error_vg arg so that process_each_pv can skip the PVs in the VG while processing. (This is a temporary accomodation for the way process_each_pv tracks which devs have been looked at, and can be dropped later when process_each_pv implementation dev tracking is changed.) - vg_read does not try to fix or recover a vg, but now just reads the metadata, checks access restrictions and returns it. (Checking access restrictions might be better done outside of vg_read, but this is a later improvement.) - _vg_read now simply makes one attempt to read metadata from each mda, and uses the most recent copy to return to the caller in the form of a 'vg' struct. (bad mdas were excluded during the scan and are not retried) (old mdas were not excluded during scan and are retried here) - vg_read uses _vg_read to get the latest copy of metadata from mdas, and then makes various checks against it to produce warnings, and to check if VG access is allowed (access restrictions include: writable, foreign, shared, clustered, missing pvs). - Things that were previously silently/automatically written by vg_read that are now done by vg_write, based on the records made in lvmcache during the scan and read: . clearing the missing flag . updating old copies of metadata . clearing outdated pvs . updating pv header flags - Bad/corrupt metadata are now repaired; they were not before. Test changes ------------ - A read command no longer writes the VG to repair it, so add a write command to do a repair. (inconsistent-metadata, unlost-pv) - When a missing PV is removed from a VG, and then the device is enabled again, vgck --updatemetadata is needed to clear the outdated PV before it can be used again, where it wasn't before. (lvconvert-repair-policy, lvconvert-repair-raid, lvconvert-repair, mirror-vgreduce-removemissing, pv-ext-flags, unlost-pv) Reading bad/old metadata ------------------------ - "bad metadata": the mda_header or metadata text has invalid fields or can't be parsed by lvm. This is a form of corruption that would not be caused by known failure scenarios. A checksum error is typically included among the errors reported. - "old metadata": a valid copy of the metadata that has a smaller seqno than other copies of the metadata. This can happen if the device failed, or io failed, or lvm failed while commiting new metadata to all the metadata areas. Old metadata on a PV that has been removed from the VG is the "outdated" case below. When a VG has some PVs with bad/old metadata, lvm can simply ignore the bad/old copies, and use a good copy. This is why there are multiple copies of the metadata -- so it's available even when some of the copies cannot be used. The bad/old copies do not have to be repaired before the VG can be used (the repair can happen later.) A PV with no good copies of the metadata simply falls back to being treated like a PV with no mdas; a common and harmless configuration. When bad/old metadata exists, lvm warns the user about it, and suggests repairing it using a new metadata repair command. Bad metadata in particular is something that users will want to investigate and repair themselves, since it should not happen and may indicate some other problem that needs to be fixed. PVs with bad/old metadata are not the same as missing devices. Missing devices will block various kinds of VG modification or activation, but bad/old metadata will not. Previously, lvm would attempt to repair bad/old metadata whenever it was read. This was unnecessary since lvm does not require every copy of the metadata to be used. It would also hide potential problems that should be investigated by the user. It was also dangerous in cases where the VG was on shared storage. The user is now allowed to investigate potential problems and decide how and when to repair them. Repairing bad/old metadata -------------------------- When label scan sees bad metadata in an mda, that mda is removed from the lvmcache info->mdas list. This means that vg_read will skip it, and not attempt to read/process it again. If it was the only in-use mda on a PV, that PV is treated like a PV with no mdas. It also means that vg_write will also skip the bad mda, and not attempt to write new metadata to it. The only way to repair bad metadata is with the metadata repair command. When label scan sees old metadata in an mda, that mda is kept in the lvmcache info->mdas list. This means that vg_read will read/process it again, and likely see the same mismatch with the other copies of the metadata. Like the label_scan, the vg_read will simply ignore the old copy of the metadata and use the latest copy. If the command is modifying the vg (e.g. lvcreate), then vg_write, which writes new metadata to every mda on info->mdas, will write the new metadata to the mda that had the old version. If successful, this will resolve the old metadata problem (without needing to run a metadata repair command.) Outdated PVs ------------ An outdated PV is a PV that has an old copy of VG metadata that shows it is a member of the VG, but the latest copy of the VG metadata does not include this PV. This happens if the PV is disconnected, vgreduce --removemissing is run to remove the PV from the VG, then the PV is reconnected. In this case, the outdated PV needs have its outdated metadata removed and the PV used flag needs to be cleared. This repair will be done by the subsequent repair command. It is also done if vgremove is run on the VG. MISSING PVs ----------- When a device is missing, most commands will refuse to modify the VG. This is the simple case. More complicated is when a command is allowed to modify the VG while it is missing a device. When a VG is written while a device is missing for one of it's PVs, the VG metadata is written to disk with the MISSING flag on the PV with the missing device. When the VG is next used, it is treated as if the PV with the MISSING flag still has a missing device, even if that device has reappeared. If all LVs that were using a PV with the MISSING flag are removed or repaired so that the MISSING PV is no longer used, then the next time the VG metadata is written, the MISSING flag will be dropped. Alternative methods of clearing the MISSING flag are: vgreduce --removemissing will remove PVs with missing devices, or PVs with the MISSING flag where the device has reappeared. vgextend --restoremissing will clear the MISSING flag on PVs where the device has reappeared, allowing the VG to be used normally. This must be done with caution since the reappeared device may have old data that is inconsistent with data on other PVs. Bad mda repair -------------- The new command: vgck --updatemetadata VG first uses vg_write to repair old metadata, and other basic issues mentioned above (old metadata, outdated PVs, pv_header flags, MISSING_PV flags). It will also go further and repair bad metadata: . text metadata that has a bad checksum . text metadata that is not parsable . corrupt mda_header checksum and version fields (To keep a clean diff, #if 0 is added around functions that are replaced by new code. These commented functions are removed by the following commit.)
2019-05-24 20:04:37 +03:00
log_warn("WARNING: invalid metadata text from file.");
goto out;
}
}
2018-04-20 18:43:50 +03:00
if (checksum_only) {
/* Checksum matches already-cached content - no need to reparse. */
log_debug_metadata("Skipped parsing metadata on %s", dev_name(dev));
2018-04-20 18:43:50 +03:00
r = 1;
goto out;
}
2008-01-30 17:00:02 +03:00
/*
* Find a set of version functions that can read this file
*/
for (vsn = &_text_vsn_list[0]; *vsn; vsn++) {
2018-04-20 18:43:50 +03:00
if (!(*vsn)->check_version(cft))
continue;
2018-04-20 18:43:50 +03:00
if (!(*vsn)->read_vgsummary(fmt, cft, vgsummary))
goto_out;
2018-04-20 18:43:50 +03:00
r = 1;
break;
}
2018-04-20 18:43:50 +03:00
out:
config_destroy(cft);
return r;
}
2018-04-20 18:43:50 +03:00
struct cached_vg_fmtdata {
uint32_t cached_mda_checksum;
size_t cached_mda_size;
};
struct volume_group *text_read_metadata(struct format_instance *fid,
2002-11-18 17:04:08 +03:00
const char *file,
struct cached_vg_fmtdata **vg_fmtdata,
unsigned *use_previous_vg,
struct device *dev, int primary_mda,
2002-11-18 17:04:08 +03:00
off_t offset, uint32_t size,
off_t offset2, uint32_t size2,
checksum_fn_t checksum_fn,
2018-04-20 18:43:50 +03:00
uint32_t checksum,
2002-11-18 17:04:08 +03:00
time_t *when, char **desc)
{
2018-04-20 18:43:50 +03:00
struct volume_group *vg = NULL;
struct dm_config_tree *cft;
struct text_vg_version_ops **vsn;
int skip_parse;
/*
* This struct holds the checksum and size of the VG metadata
* that was read from a previous device. When we read the VG
* metadata from this device, we can skip parsing it into a
* cft (saving time) if the checksum of the metadata buffer
* we read from this device matches the size/checksum saved in
* the mda_header/rlocn struct on this device, and matches the
* size/checksum from the previous device.
*/
if (vg_fmtdata && !*vg_fmtdata &&
!(*vg_fmtdata = dm_pool_zalloc(fid->mem, sizeof(**vg_fmtdata)))) {
log_error("Failed to allocate VG fmtdata for text format.");
return NULL;
}
_init_text_import();
2018-04-20 18:43:50 +03:00
*desc = NULL;
*when = 0;
2018-04-20 18:43:50 +03:00
if (!(cft = config_open(CONFIG_FILE_SPECIAL, file, 0)))
2006-05-10 21:51:02 +04:00
return_NULL;
/* Does the metadata match the already-cached VG? */
2018-04-20 18:43:50 +03:00
skip_parse = vg_fmtdata &&
((*vg_fmtdata)->cached_mda_checksum == checksum) &&
((*vg_fmtdata)->cached_mda_size == (size + size2));
if (dev) {
log_debug_metadata("Reading metadata from %s at %llu size %d (+%d)",
dev_name(dev), (unsigned long long)offset,
size, size2);
if (!config_file_read_fd(cft, dev, MDA_CONTENT_REASON(primary_mda), offset, size,
2018-04-20 18:43:50 +03:00
offset2, size2, checksum_fn, checksum,
skip_parse, 1)) {
log_warn("WARNING: couldn't read volume group metadata from %s.", dev_name(dev));
goto out;
}
} else {
if (!config_file_read(cft)) {
log_warn("WARNING: couldn't read volume group metadata from file.");
goto out;
}
}
2018-04-20 18:43:50 +03:00
if (skip_parse) {
if (use_previous_vg)
*use_previous_vg = 1;
log_debug_metadata("Skipped parsing metadata on %s", dev_name(dev));
2018-04-20 18:43:50 +03:00
goto out;
}
/*
* Find a set of version functions that can read this file
*/
for (vsn = &_text_vsn_list[0]; *vsn; vsn++) {
if (!(*vsn)->check_version(cft))
continue;
if (!(vg = (*vsn)->read_vg(fid->fmt->cmd, fid->fmt, fid, cft)))
2018-04-20 18:43:50 +03:00
goto_out;
(*vsn)->read_desc(vg->vgmem, cft, when, desc);
vg->committed_cft = cft; /* Reuse CFT for recreation of committed VG */
vg->buffer_size_hint = size + size2;
cft = NULL;
2018-04-20 18:43:50 +03:00
break;
}
if (vg && vg_fmtdata && *vg_fmtdata) {
(*vg_fmtdata)->cached_mda_size = (size + size2);
(*vg_fmtdata)->cached_mda_checksum = checksum;
2001-12-17 22:46:10 +03:00
}
2018-04-20 18:43:50 +03:00
if (use_previous_vg)
*use_previous_vg = 0;
2018-04-20 18:43:50 +03:00
out:
if (cft)
config_destroy(cft);
2018-04-20 18:43:50 +03:00
return vg;
2001-12-17 22:46:10 +03:00
}
struct volume_group *text_read_metadata_file(struct format_instance *fid,
2002-11-18 17:04:08 +03:00
const char *file,
time_t *when, char **desc)
{
return text_read_metadata(fid, file, NULL, NULL, NULL, 0,
(off_t)0, 0, (off_t)0, 0, NULL, 0,
when, desc);
2001-12-17 22:46:10 +03:00
}
static struct volume_group *_import_vg_from_config_tree(struct cmd_context *cmd,
struct format_instance *fid,
const struct dm_config_tree *cft)
{
struct volume_group *vg = NULL;
struct text_vg_version_ops **vsn;
int vg_missing;
_init_text_import();
for (vsn = &_text_vsn_list[0]; *vsn; vsn++) {
if (!(*vsn)->check_version(cft))
continue;
/*
* The only path to this point uses cached vgmetadata,
* so it can use cached PV state too.
*/
if (!(vg = (*vsn)->read_vg(cmd, fid->fmt, fid, cft)))
stack;
else {
set_pv_devices(fid, vg);
if ((vg_missing = vg_missing_pv_count(vg)))
log_verbose("There are %d physical volumes missing.", vg_missing);
vg_mark_partial_lvs(vg, 1);
/* FIXME: move this code inside read_vg() */
}
break;
}
return vg;
}
struct volume_group *import_vg_from_config_tree(struct cmd_context *cmd,
struct format_instance *fid,
const struct dm_config_tree *cft)
{
return _import_vg_from_config_tree(cmd, fid, cft);
}
struct volume_group *vg_from_config_tree(struct cmd_context *cmd, const struct dm_config_tree *cft)
{
static struct text_vg_version_ops *ops;
_init_text_import();
ops = _text_vsn_list[0];
return ops->read_vg(cmd, cmd->fmt, NULL, cft);
}