Back to bug 676753
| Who | When | What | Removed | Added |
|---|---|---|---|---|
| Amit Shah | 2011-02-11 05:29:08 UTC | CC | amit.shah | |
| Assignee | virt-maint | kwolf | ||
| Shirley Zhou | 2011-02-12 07:59:19 UTC | Priority | unspecified | medium |
| Severity | unspecified | medium | ||
| Nicole Dai | 2011-02-12 10:14:48 UTC | CC | ndai | |
| Min Deng | 2011-03-30 02:53:20 UTC | CC | mdeng | |
| juzhang | 2011-09-03 08:38:53 UTC | CC | juzhang | |
| Kevin Wolf | 2011-12-07 16:21:47 UTC | CC | wdai | |
| Ademar Reis | 2012-06-22 15:18:00 UTC | CC | areis | |
| Miroslav Rezanina | 2013-02-25 06:54:52 UTC | CC | mrezanin | |
| Ademar Reis | 2013-02-27 13:52:40 UTC | Status | NEW | CLOSED |
| Resolution | --- | WONTFIX | ||
| Doc Text | NOTE: this is a corner case which doesn't make sense in practice and should not be hit in the field unless the user makes a mistake. Cause: Qemu may hit timeouts when working with very large images (>= 2TiB) created with very small cluster sizes (512bytes). The default cluster size is 64KiB and we see no reason to use such small cluster size in such cases, as it hits performance in order to save a few bytes. Consequence: block I/O errors due to timeouts Workaround (if any): use standard cluster size or bigger (default of 64k works fine). Result: no block I/O error. | |||
| Doc Type | Bug Fix | Known Issue | ||
| Last Closed | 2013-02-27 08:52:40 UTC | |||
| Eliska Slobodova | 2013-09-20 15:18:44 UTC | Doc Text | NOTE: this is a corner case which doesn't make sense in practice and should not be hit in the field, unless the user makes a mistake. Cause: Qemu may hit timeouts when working with very large images (>= 2TiB) created with very small cluster sizes (512bytes). The default cluster size is 64KiB and we see no reason to use such small cluster size in such cases, as it hits performance in order to save a few bytes. Consequence: block I/O errors due to timeouts Workaround (if any): use standard cluster size or bigger (default of 64k works fine). Result: no block I/O error. | When working with very large images (larger than 2TB) created with very small cluster sizes (for example, 512bytes), block I/O errors can occur due to timeouts in qemu. To prevent this problem from occurring, use the default cluster size of 64KiB or larger. |
| John Skeoch | 2015-03-05 00:52:38 UTC | CC | mshao |
Back to bug 676753