I'm running open-iscsi-2.0.868 on a Linux 2.6.21 Xen DomU kernel. I
find that when doing heavy I/O, particularly between two iSCSI
targets, I receive the following messages in my kernel log:
Apr 10 10:23:07 mucilage BUG: scheduling while atomic:
scsi_wq_5/0x1001/7047
Apr 10 10:23:07 mucilage
Erez Zilber wrote:
> When a transport (e.g. iscsi_tcp, ib_iser) is unloaded, a notification
> must be sent to userspace. This will allow the userspace code to release
> all transport related resources.
>
Thanks for fixing this.
> +
> struct iscsi_uevent {
> uint32_t type; /* k/u events t
In RedHat 4, some OFED kernel modules (including open-iscsi modules)
use symbols that are encapsulated in ib_core (e.g. kfifo). ib_core
may not be unloaded before open-iscsi is unloaded. Therefore, disconnecting
from open-iscsi over iSER sessions is not suffiecient if the user tries to
stop openib
Some users may try to stop openibd while open-iscsi over iSER is
running. When stopping openibd, the script should check if there
are open-iscsi sessions that use the iSER transport and ask the
user to logout from these sessions before shutting down openibd.
Signed-off-by: Erez Zilber <[EMAIL PRO
The following series of patches fixes a bug that occurs when a user tries to
stop openibd while open-iscsi is running and there are active iSER sessions.
--~--~-~--~~~---~--~~
You received this message because you are subscribed to the Google Groups
"open-iscsi"
When a transport (e.g. iscsi_tcp, ib_iser) is unloaded, a notification
must be sent to userspace. This will allow the userspace code to release
all transport related resources.
Signed-off-by: Erez Zilber <[EMAIL PROTECTED]>
---
drivers/scsi/scsi_transport_iscsi.c | 31 +
When iscsid detects a new transport (e.g. iscsi_tcp, ib_iser), it
allocates an entry for it in the transport list. If the transport
is unloaded and then reloaded, iscsid would still use the old
transport entry. Therefore, the transport entry must be deleted
when the transport is unloaded.
Signed-
The following series of patches fixes a bug in iscsid: if a transport is
unloaded and then reloaded, the transport entry in iscsid is still the old one.
--~--~-~--~~~---~--~~
You received this message because you are subscribed to the Google Groups
"open-iscsi"