Note: This bug is displayed in read-only format because
the product is no longer active in Red Hat Bugzilla.
RHEL Engineering is moving the tracking of its product development work on RHEL 6 through RHEL 9 to Red Hat Jira (issues.redhat.com). If you're a Red Hat customer, please continue to file support cases via the Red Hat customer portal. If you're not, please head to the "RHEL project" in Red Hat Jira and file new tickets here. Individual Bugzilla bugs in the statuses "NEW", "ASSIGNED", and "POST" are being migrated throughout September 2023. Bugs of Red Hat partners with an assigned Engineering Partner Manager (EPM) are migrated in late September as per pre-agreed dates. Bugs against components "kernel", "kernel-rt", and "kpatch" are only migrated if still in "NEW" or "ASSIGNED". If you cannot log in to RH Jira, please consult article #7032570. That failing, please send an e-mail to the RH Jira admins at rh-issues@redhat.com to troubleshoot your issue as a user management inquiry. The email creates a ServiceNow ticket with Red Hat. Individual Bugzilla bugs that are migrated will be moved to status "CLOSED", resolution "MIGRATED", and set with "MigratedToJIRA" in "Keywords". The link to the successor Jira issue will be found under "Links", have a little "two-footprint" icon next to it, and direct you to the "RHEL project" in Red Hat Jira (issue links are of type "https://issues.redhat.com/browse/RHEL-XXXX", where "X" is a digit). This same link will be available in a blue banner at the top of the page informing you that that bug has been migrated.
DescriptionSweet Tea Dorminy
2017-12-07 13:43:04 UTC
Description of problem:
After 160 exabytes of data written to a VDO, the journal sequence number overflows one of the locations it is stored on disk, which is 48 bits. When this overflow happens, crash recovery has a strong possibility to corrupt data. This takes 4.5 years on theoretically ideal NVMe drives with an ideal write pattern, or on the Intel Optane 900p drive about 16 years with the same pattern.
(Math:
On theoretical NVMe drives, with latency of 2.8 microseconds, VDO
could (if not CPU bound, and having a fully allocated block map tree
in memory, and not memory latency bound) write 8M of zeroes in
5.6 microseconds, or 1.4 T/s. On such hardware, we could zero a
max-size 4P VDO in an hour. We could zero it 40 000 times in
approximately 4.5 years.
4P = (1<<40) blocks. 40000 is 40<<10. Each write makes two journal
entries. Therefore, this is 80<<50 journal entries; at 312 (~320) entries
per journal block, this is 1<<48 journal blocks.
)
Version-Release number of selected component (if applicable):
kmod-kvdo-6.1.0.81
How reproducible:
Always, given time.
Steps to Reproduce:
1. Write 160 exabytes.
2. Crash.
3. Validate your data.
Actual results:
Corruption.
Expected results:
Advance notice before crash that an upgrade to a version with a fix for this is necessary.
Additional info:
Since the problem described in this bug report should be
resolved in a recent advisory, it has been closed with a
resolution of ERRATA.
For information on the advisory, and where to find the updated
files, follow the link below.
If the solution does not work for you, open a new bug report.
https://access.redhat.com/errata/RHEA-2018:0900
Description of problem: After 160 exabytes of data written to a VDO, the journal sequence number overflows one of the locations it is stored on disk, which is 48 bits. When this overflow happens, crash recovery has a strong possibility to corrupt data. This takes 4.5 years on theoretically ideal NVMe drives with an ideal write pattern, or on the Intel Optane 900p drive about 16 years with the same pattern. (Math: On theoretical NVMe drives, with latency of 2.8 microseconds, VDO could (if not CPU bound, and having a fully allocated block map tree in memory, and not memory latency bound) write 8M of zeroes in 5.6 microseconds, or 1.4 T/s. On such hardware, we could zero a max-size 4P VDO in an hour. We could zero it 40 000 times in approximately 4.5 years. 4P = (1<<40) blocks. 40000 is 40<<10. Each write makes two journal entries. Therefore, this is 80<<50 journal entries; at 312 (~320) entries per journal block, this is 1<<48 journal blocks. ) Version-Release number of selected component (if applicable): kmod-kvdo-6.1.0.81 How reproducible: Always, given time. Steps to Reproduce: 1. Write 160 exabytes. 2. Crash. 3. Validate your data. Actual results: Corruption. Expected results: Advance notice before crash that an upgrade to a version with a fix for this is necessary. Additional info: