Messages in this thread | | | From | Zach Brown <> | Subject | Re: [PATCH 2/2] aio: propogate post-EIOCBQUEUED errors to completion event | Date | Tue, 20 Feb 2007 10:26:44 -0800 |
| |
On Feb 20, 2007, at 9:33 AM, Ananiev, Leonid I wrote:
> There is change in the patch which is uncommented in preface. > Now aio_ring_insert_entry() is not called if req->ki_users>=1. > Before was called. > Could you comment it?
It is described in the patch description, though perhaps not explicitly enough:
"To get this working we change the aio_complete() path so that the ring insertion is performed as the final iocb reference is dropped."
This stops an aio_complete() from generating a completion event before the submission path has had a chance to generate an error. This could happen if O_DIRECT bios completed very quickly before the submission path had a chance to return up and call ivalidate_inode_pages2_range().
- z
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |