[Bug 722101] New: "irq 10: nobody cared" problem with pata disks at promise ultra133tx2
https://bugzilla.novell.com/show_bug.cgi?id=722101 https://bugzilla.novell.com/show_bug.cgi?id=722101#c0 Summary: "irq 10: nobody cared" problem with pata disks at promise ultra133tx2 Classification: openSUSE Product: openSUSE 11.4 Version: Final Platform: x86 OS/Version: openSUSE 11.4 Status: NEW Severity: Critical Priority: P5 - None Component: Kernel AssignedTo: kernel-maintainers@forge.provo.novell.com ReportedBy: wefing@gmx.de QAContact: qa@suse.de Found By: --- Blocker: --- Created an attachment (id=454473) --> (http://bugzilla.novell.com/attachment.cgi?id=454473) output of hwinfo on the 11.4 rescue system User-Agent: Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.14) Gecko/2009090900 SUSE/3.0.14-0.1 Firefox/3.0.14 I'm running an old PC (PIII 700 MHz with two Samsung pata disks attached to a Promise Ultra133Tx2 PCI controller) under suse 10.3. Everything works as expected. Now I try to upgrade to suse 11.4. Before doing this, I boot into the rescue system of the 11.4 installation DVD in order to change the partitioning. This involves copying some 20 GB of data between several ext3 file systems residing on one of the two disks. It turned out that i/o performance during these operations was only 1/10 or worse of the performance observed under suse 10.3. Same result with "hdparm -t", which reports an i/o throughput of 5 MB/s under suse 11.4, but of 55MB/s under suse 10.3. In the suse 11.4 boot.msg file, I find the following message: 'irq 10: nobody cared (try booting with the "irqpoll" option)', see the attached hwinfo file. As /proc/interrupts reveals, irq 10 is associated with the pata disks. Booting with the irqpoll option does not make the diagnostic message disappear, "hdparm -t", however, now reports i/o throughputs ranging between 5MB/s and 55MB/s. Trying to copy data between partitions as described above leads to a system freeze after a minute or so. From this I conclude that using "irqpoll" is not an option here. I tried other boot options (acpi=off, noapic, nolapic, routeirq, assign-buses) without any success. Reproducible: Always Steps to Reproduce: 1. Boot into the rescue system of the suse 11.4 installation dvd. 2. hdparm -t <pata_disk_at_promise_controller> 3. Actual Results: hdparm reports an i/o throughput that is way below the maximal possible throughput, i.e., around 5MB/s. Expected Results: Expected throughput is 55MB/s. -- Configure bugmail: https://bugzilla.novell.com/userprefs.cgi?tab=email ------- You are receiving this mail because: ------- You are on the CC list for the bug.
https://bugzilla.novell.com/show_bug.cgi?id=722101 https://bugzilla.novell.com/show_bug.cgi?id=722101#c1 --- Comment #1 from Stephan Wefing <wefing@gmx.de> 2011-10-04 18:12:37 UTC --- Created an attachment (id=454476) --> (http://bugzilla.novell.com/attachment.cgi?id=454476) output of hwinfo under suse 10.3 (for comparison) -- Configure bugmail: https://bugzilla.novell.com/userprefs.cgi?tab=email ------- You are receiving this mail because: ------- You are on the CC list for the bug.
https://bugzilla.novell.com/show_bug.cgi?id=722101 https://bugzilla.novell.com/show_bug.cgi?id=722101#c2 --- Comment #2 from Stephan Wefing <wefing@gmx.de> 2011-10-04 18:40:27 UTC --- P.S.: Same low i/o performance for the rescue system from the suse 11.3 installation dvd. -- Configure bugmail: https://bugzilla.novell.com/userprefs.cgi?tab=email ------- You are receiving this mail because: ------- You are on the CC list for the bug.
https://bugzilla.novell.com/show_bug.cgi?id=722101 https://bugzilla.novell.com/show_bug.cgi?id=722101#c3 --- Comment #3 from Stephan Wefing <wefing@gmx.de> 2012-02-03 16:45:26 UTC --- Disk performance is normal for the rescue system of suse 11.2. This is the last system where the disk is associated with /dev/hd*; suse 11.3 and 11.4 use /dev/sd*. Unfortunately, I cannot use suse 12.1 either, see bug 739526. -- Configure bugmail: https://bugzilla.novell.com/userprefs.cgi?tab=email ------- You are receiving this mail because: ------- You are on the CC list for the bug.
https://bugzilla.novell.com/show_bug.cgi?id=722101 https://bugzilla.novell.com/show_bug.cgi?id=722101#c Jeff Mahoney <jeffm@suse.com> changed: What |Removed |Added ---------------------------------------------------------------------------- AssignedTo|kernel-maintainers@forge.pr |jlee@suse.com |ovo.novell.com | -- Configure bugmail: https://bugzilla.novell.com/userprefs.cgi?tab=email ------- You are receiving this mail because: ------- You are on the CC list for the bug.
https://bugzilla.novell.com/show_bug.cgi?id=722101 https://bugzilla.novell.com/show_bug.cgi?id=722101#c4 Jeff Mahoney <jeffm@suse.com> changed: What |Removed |Added ---------------------------------------------------------------------------- Status|NEW |RESOLVED CC| |jeffm@suse.com Resolution| |WONTFIX --- Comment #4 from Jeff Mahoney <jeffm@suse.com> 2012-08-02 11:54:00 EDT --- With the coming release of openSUSE 12.2, openSUSE kernel developers are focusing their efforts there. Reports against openSUSE 11.4 and prior will not get the attention needed to resolve them before openSUSE 12.2 is release and openSUSE 11.4 becomes unmaintained. Please re-test with openSUSE 12.1 or openSUSE RC2+ and re-open with an updated Product if you still encounter your issue. We apologize for this issue not getting the attention it deserves but we are focusing our resources in the area where they will have the most impact for our users. We're working hard to make openSUSE 12.2 the best openSUSE release yet! -- Configure bugmail: https://bugzilla.novell.com/userprefs.cgi?tab=email ------- You are receiving this mail because: ------- You are on the CC list for the bug.
participants (1)
-
bugzilla_noreply@novell.com