kernel oops in resched_task

2010-01-06 Thread Erez Zilber
Hi, I got this oops while running open-iscsi on a CentOS 5.3 machine (don't know how to recreate it). it crashes while trying to wake up the work queue after queuecommand was called. Has anyone seen something similar? Jan 2 22:24:27 172.16.9.55 RIP: 0010:[8008cccf] Jan 2 22:24:27

Re: kernel oops in resched_task

2010-01-06 Thread Pasi Kärkkäinen
On Wed, Jan 06, 2010 at 04:28:32PM +0200, Erez Zilber wrote: Hi, I got this oops while running open-iscsi on a CentOS 5.3 machine (don't know how to recreate it). it crashes while trying to wake up the work queue after queuecommand was called. Has anyone seen something similar? I'd

Re: iSCSI throughput drops as link rtt increases?

2010-01-06 Thread Jack Knight
Hi Pasi, Thank you very much for your reply. I was testing the performance of open-iscsi initiator with IET target over a 100Mbps Ethernet link with emulated rtt.  What I did was to do raw disk sequential write by $ dd if=/dev/zero of=/dev/sdb bs=1024 count=1048576 Did you also try

Re: developing prefetcher with open-iscsi

2010-01-06 Thread Mike Christie
On 12/21/2009 06:42 AM, nsabagwa mary wrote: Hi am new to linux kernel module development. been going through the open-iscsi code for some time now. i want to get and record memory page requests directed to the virtual disk files (read or write) which i want to later analyze and prefetch. this

Re: [PATCH] Use DESTDIR when generating an InitiatorName.

2010-01-06 Thread Mike Christie
On 12/21/2009 02:55 PM, philant...@exherbo.org wrote: From: Wulf C. Kruegerphilant...@exherbo.org For packaging, it's very useful to to check for /etc/iscsi/initiatorname.iscsi in the real filesystem but if we have to generate a new one, this should be done inside DESTDIR and not in the real

Re: iSCSI throughput drops as link rtt increases?

2010-01-06 Thread Mike Christie
On 01/04/2010 08:54 AM, Jack Z wrote: Then I used Wireshark to grab the traces of iSCSI and iperf and I found lots of iSCSI PDUs were divided into TCP segments of 1448 bytes but with iperf TCP segments could be as large as 65000+ bytes. I first thought this was because of the small default

Re: kernel oops in resched_task

2010-01-06 Thread Mike Christie
On 01/06/2010 08:28 AM, Erez Zilber wrote: Hi, I got this oops while running open-iscsi on a CentOS 5.3 machine (don't know how to recreate it). it crashes while trying to wake up the work queue after queuecommand was called. Has anyone seen something similar? I have not seen it. Are you

Re: Need help with multipath and iscsi in CentOS 5.4

2010-01-06 Thread Mike Christie
On 12/30/2009 11:48 AM, Kyle Schmitt wrote: On Wed, Dec 9, 2009 at 8:52 PM, Mike Christiemicha...@cs.wisc.edu wrote: So far single connections work: If I setup the box to use one NIC, I get one connection and can use it just fine. Could you send the /var/log/messages for when you run the

Re: Question about /sys/class/iscsi_connection

2010-01-06 Thread Mike Christie
On 01/02/2010 01:56 PM, Yangkook Kim wrote: Hi, Group, I am wondering why we have /sys/class/iscsi_connection for iscsi connection in sysfs filesystem. I understand that the one or more iscsi connection form a single iscsi session and, in this sense, iscsi connection subordinates to iscsi

Re: iSCSI throughput drops as link rtt increases?

2010-01-06 Thread Jack Z
Hi Mike, I use the default configuration of open-iscsi initiator and IET, except I change the NOP interval to 500s and the MaxRecvDataSegmentLength of IET to 262144 (default value is 8192). And the network I'm using is a straight-through cable between two laptops. I'm not sure whether the NICs

Re: iSCSI throughput drops as link rtt increases?

2010-01-06 Thread Jack Z
Hi Mike, I use the default configuration of open-iscsi initiator and IET, except I change the NOP interval to 500s and the MaxRecvDataSegmentLength of IET to 262144 (default value is 8192). And the network I'm using is a straight-through cable between two laptops. I'm not sure whether the NICs