Back to bug 1380602
| Who | When | What | Removed | Added |
|---|---|---|---|---|
| Mike Christie | 2016-09-30 05:23:13 UTC | Summary | RHEL 7.3.z: have rbd multipathd checker set lock_on_read rbd map setting | RHEL 7.3: have rbd multipathd checker set lock_on_read rbd map setting |
| Mike Christie | 2016-09-30 05:23:33 UTC | CC | mchristi | |
| Mike Christie | 2016-09-30 05:25:31 UTC | Blocks | 1379890 | |
| Ben Marzinski | 2016-09-30 15:35:44 UTC | Status | NEW | ASSIGNED |
| Jonathan Earl Brassow | 2016-09-30 20:18:49 UTC | CC | jbrassow | |
| Flags | needinfo?(mchristi) | |||
| Mike Christie | 2016-09-30 21:36:13 UTC | Flags | needinfo?(mchristi) | |
| Jonathan Earl Brassow | 2016-09-30 21:43:26 UTC | Keywords | ZStream | |
| Assignee | lvm-team | bmarzins | ||
| Mark Thacker | 2016-10-11 00:26:08 UTC | CC | mthacker | |
| Ken Dreyer (Red Hat) | 2016-10-12 21:09:40 UTC | Blocks | 1378186 | |
| Zhang Yi | 2016-10-17 23:55:50 UTC | CC | yizhan | |
| Ben Marzinski | 2016-11-09 19:27:23 UTC | Status | ASSIGNED | MODIFIED |
| Fixed In Version | device-mapper-multipath-0.4.9-100.el7 | |||
| Doc Type | If docs needed, set a value | Bug Fix | ||
| Ben Marzinski | 2016-11-09 19:28:26 UTC | Flags | needinfo?(mchristi) | |
| Marcel Kolaja | 2016-11-10 08:21:12 UTC | CC | mkolaja, snagar | |
| Flags | needinfo?(snagar) | |||
| Mike Christie | 2016-11-10 19:30:22 UTC | Doc Text | Cause: When a Ceph rbd image is exported through multiple iSCSI targets, the rbd kernel module will grab the exclusive lock when it receives a write request. Consequence: If a write request is hung in the rbd module, and the iSCSI initiator and multipath layer decide to fail the request to the application, read requests sent after the failure may not reflect the state of the write. Fix: The rbd module will grab the exclusive lock for both reads and writes. This will cause hung writes to be flushed and or failed before executing reads. Result: Read requests sent after failed writes will always return the same data. | |
| Flags | needinfo?(mchristi) needinfo?(snagar) | |||
| Jonathan Earl Brassow | 2016-11-15 14:25:44 UTC | Keywords | ZStream | |
| Siddharth Nagar | 2016-11-15 14:48:45 UTC | Priority | unspecified | high |
| Marcel Kolaja | 2016-11-15 16:11:51 UTC | Blocks | 1395298 | |
| Marcel Kolaja | 2016-11-15 16:12:38 UTC | Keywords | ZStream | |
| Lin Li | 2016-12-08 07:24:53 UTC | CC | lilin | |
| QA Contact | storage-qe | lilin | ||
| errata-xmlrpc | 2017-02-17 18:58:12 UTC | Status | MODIFIED | ON_QA |
| Lenka Špačková | 2017-04-11 16:08:36 UTC | Docs Contact | slevine | |
| Steven J. Levine | 2017-05-05 21:42:55 UTC | Doc Text | Cause: When a Ceph rbd image is exported through multiple iSCSI targets, the rbd kernel module will grab the exclusive lock when it receives a write request. Consequence: If a write request is hung in the rbd module, and the iSCSI initiator and multipath layer decide to fail the request to the application, read requests sent after the failure may not reflect the state of the write. Fix: The rbd module will grab the exclusive lock for both reads and writes. This will cause hung writes to be flushed and or failed before executing reads. Result: Read requests sent after failed writes will always return the same data. | Read requests sent after failed writes will always return the same data on multipath devices Previously, if a write request wass hung in the `rbd` module, and the iSCSI initiator and multipath layer decided to fail the request to the application, read requests sent after the failure may not have reflected the state of the write. This was because When a Ceph `rbd` image is exported through multiple iSCSI targets, the `rbd` kernel module will grab the exclusive lock when it receives a write request. With this fix, The `rbd` module will grab the exclusive lock for both reads and writes. This will cause hung writes to be flushed and or failed before executing reads. As a result, read requests sent after failed writes will always return the same data. |
| Flags | needinfo?(bmarzins) | |||
| Ben Marzinski | 2017-05-08 16:44:46 UTC | Flags | needinfo?(bmarzins) | |
| Lin Li | 2017-06-07 05:28:48 UTC | CC | ceph-qe-bugs | |
| Flags | needinfo?(ceph-qe-bugs) | |||
| Lin Li | 2017-06-13 09:13:02 UTC | Flags | needinfo?(ceph-qe-bugs) | |
| Lin Li | 2017-06-20 05:19:42 UTC | Status | ON_QA | VERIFIED |
| Parikshith | 2017-06-20 05:26:04 UTC | CC | pbyregow | |
| Ian Colle | 2017-07-10 17:12:38 UTC | CC | icolle | |
| Flags | needinfo?(ceph-qe-bugs) needinfo?(ceph-qe-bugs) | |||
| errata-xmlrpc | 2017-08-01 16:34:26 UTC | Status | VERIFIED | CLOSED |
| Resolution | --- | ERRATA | ||
| Last Closed | 2017-08-01 12:34:26 UTC | |||
| Pasi Karkkainen | 2017-08-02 08:13:17 UTC | CC | pasik | |
| Pavel Najman | 2021-09-03 12:10:25 UTC | Pool ID | sst_platform_storage_rhel_7 | sst_logical_storage_rhel_7 |
Back to bug 1380602