[Bug 205945] Re: [Hardy] Heavy I/O causes other processes to starve

2008-09-08 Thread Leann Ogasawara
Thanks for the update Tom. I think I'll just go ahead and close this report then. Thanks. ** Changed in: linux (Ubuntu) Status: Confirmed => Won't Fix -- [Hardy] Heavy I/O causes other processes to starve https://bugs.launchpad.net/bugs/205945 You received this bug notification because

[Bug 205945] Re: [Hardy] Heavy I/O causes other processes to starve

2008-08-29 Thread Tom Kirby
Hi Leann, Thank you for all your help with this issue. I'm sorry to say that I've upgraded my hard-drive since I reported the bug, and I'm no longer experiencing any problems with it. I'm now using the old hard-drive mounted in an external enclosure, connected via USB, and this setup doesn't show

[Bug 205945] Re: [Hardy] Heavy I/O causes other processes to starve

2008-08-28 Thread Leann Ogasawara
The Ubuntu Kernel Team is planning to move to the 2.6.27 kernel for the upcoming Intrepid Ibex 8.10 release. As a result, the kernel team would appreciate it if you could please test this newer 2.6.27 Ubuntu kernel. There are one of two ways you should be able to test: 1) If you are comfortable

[Bug 205945] Re: [Hardy] Heavy I/O causes other processes to starve

2008-06-06 Thread Leann Ogasawara
Hi Tom, Sorry for the inconvenience. It seems the kernel-ppa has removed the 2.6.25 images which used to be available. Currently the 2.6.26 images are being built (but appear to be experiencing some build failures). Hopefully this should be resolved in the next few days and you should be able to i

[Bug 205945] Re: [Hardy] Heavy I/O causes other processes to starve

2008-05-20 Thread Tom Kirby
Hi Leann, I added the "kernel-ppa.list" file as you described, with the appropriate entries in it, and then ran "sudo apt-get update". I then ran "sudo apt-get upgrade -s", but the only thing it would offer to upgrade was "linux-libc-dev", not "linux-image-2.6.25". I'm quite willing to help with t

[Bug 205945] Re: [Hardy] Heavy I/O causes other processes to starve

2008-05-18 Thread Leann Ogasawara
Hi Tom, Sorry for the extremely delayed response. Thanks for all the testing and the debugging output. I'm glad to hear there is at least a workaround. Just to see if it makes a difference, care to test the upcoming Intrepid Ibex 8.10 kernel which is currently being pulled together? It was most

[Bug 205945] Re: [Hardy] Heavy I/O causes other processes to starve

2008-04-11 Thread Tom Kirby
Thanks, Leann, the 'all_generic_ide' option fixes it for me. My HD still shows up as /dev/sda rather than /dev/hda (which isn't a problem in itself), but a 'cat /dev/urandom > ~/test' no longer clogs up the system. I'm attaching the dmesg that I get after I've booted with 'all_generic_ide', in case

[Bug 205945] Re: [Hardy] Heavy I/O causes other processes to starve

2008-04-11 Thread Tom Kirby
** Attachment added: "lspci-vvnn.log" http://launchpadlibrarian.net/13364125/lspci-vvnn.log -- [Hardy] Heavy I/O causes other processes to starve https://bugs.launchpad.net/bugs/205945 You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu.

[Bug 205945] Re: [Hardy] Heavy I/O causes other processes to starve

2008-04-11 Thread Tom Kirby
** Attachment added: "dmesg.log" http://launchpadlibrarian.net/13364119/dmesg.log -- [Hardy] Heavy I/O causes other processes to starve https://bugs.launchpad.net/bugs/205945 You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. -- ubuntu

[Bug 205945] Re: [Hardy] Heavy I/O causes other processes to starve

2008-04-11 Thread Tom Kirby
** Attachment added: "version.log" http://launchpadlibrarian.net/13364108/version.log -- [Hardy] Heavy I/O causes other processes to starve https://bugs.launchpad.net/bugs/205945 You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. -- ub

[Bug 205945] Re: [Hardy] Heavy I/O causes other processes to starve

2008-04-11 Thread Leann Ogasawara
Hi Tom, Per the kernel team's bug policy, can you please attach the following information. Please be sure to attach each file as a separate attachment. * cat /proc/version_signature > version.log * dmesg > dmesg.log * sudo lspci -vvnn > lspci-vvnn.log It also might be good to wait to capture yo

[Bug 205945] Re: [Hardy] Heavy I/O causes other processes to starve

2008-04-11 Thread Tom Kirby
Sorry, I mean a SCSI device. The HD is SATA. Under 2.6.22-14, it shows up as /dev/hda, but on 2.6.24-12 and onwards it becomes /dev/sda. -- [Hardy] Heavy I/O causes other processes to starve https://bugs.launchpad.net/bugs/205945 You received this bug notification because you are a member of Ubun

[Bug 205945] Re: [Hardy] Heavy I/O causes other processes to starve

2008-04-11 Thread Tom Kirby
Confirming that this problem shows up in 2.6.24-12 and onwards. I don't get the same problem with 2.6.22-14. I'm pretty sure it's to do with treating my HD as a SATA device. -- [Hardy] Heavy I/O causes other processes to starve https://bugs.launchpad.net/bugs/205945 You received this bug notific

[Bug 205945] Re: [Hardy] Heavy I/O causes other processes to starve

2008-04-05 Thread Tom Kirby
I don't get this problem if I boot with the "2.6.20-12-generic" kernel. It could be connected with libata (https://wiki.ubuntu.com/LibAtaForAtaDisks), as under 2.6.20-12 my SATA hd shows up as /dev/hda rather than /dev/sda like it does under 2.6.24-15. -- [Hardy] Heavy I/O causes other processes

[Bug 205945] Re: [Hardy] Heavy I/O causes other processes to starve

2008-04-05 Thread Tom Kirby
I think I'm correct in assigning this to "linux"... ** Changed in: linux (Ubuntu) Sourcepackagename: None => linux -- [Hardy] Heavy I/O causes other processes to starve https://bugs.launchpad.net/bugs/205945 You received this bug notification because you are a member of Ubuntu Bugs, which is sub

[Bug 205945] Re: [Hardy] Heavy I/O causes other processes to starve

2008-03-24 Thread Tom Kirby
I'm now pretty sure this is a disk access thing (it gets especially bad when I'm running a script that backs up my whole home directory with rsync), but fiddling with the script's i/o priority with 'ionice' doesn't really seem to help. -- [Hardy] Heavy I/O causes other processes to starve https:/