Re: Progress on Bug#444271 / N2100 disk performance
On Fri, 2008-05-09 at 22:37 +0200, Martin Michlmayr wrote: * Markus Lindenberg [EMAIL PROTECTED] [2008-04-24 12:58]: i wonder if there's any progress on this one. i consider this a very limiting issue, as it renders my n2100 almost unusable regarding it's core purpose, being a high performance nas device in a gbit lan. even my slug seems to have a better disk performance. i know i could go back to thecus firmware if that's my main concern, but, you know, that's not an option either for obvious reasons. :-) Still no progress, but I just made 2.6.25 kernels available with the DMA patches applied. This kernel is largely untested, but it includes the same patch from Dan Williams that I tested before and that seems to work. Any feedback is welcome. Use at your own risk. http://merkel.debian.org/~tbm/tmp/n2100/dma/ I've been using this kernel for some time on my N2100 now, and the improvement in disk IO performance is substantial. I'd love to see this merged into lenny's kernel but I realise I should have sent this email a few weeks ago for that to be in any way possible... Ross -- Ross Burton mail: [EMAIL PROTECTED] jabber: [EMAIL PROTECTED] www: http://burtonini.com signature.asc Description: This is a digitally signed message part
Re: Progress on Bug#444271 / N2100 disk performance
Ross Burton wrote: I've been using this kernel for some time on my N2100 now, and the improvement in disk IO performance is substantial. I'd love to see this merged into lenny's kernel but I realise I should have sent this email a few weeks ago for that to be in any way possible... hedges.billgatliff.com/hedges.debian.org is an N2100. Might be another good place to try it out. I don't have root on hedges, and wouldn't use it even if I did--- it's debian's machine, after all. :) But I'm occasionally in physical proximity to the colo center that houses it, if necessary. Or, not. Not my call. :) b.g. -- Bill Gatliff [EMAIL PROTECTED] -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
RE: Progress on Bug#444271 / N2100 disk performance
Hi, is there any estimation, when changes will touch base in a regular kernel release? Regards Uwe On 11 Mai, 23:20, Martin Michlmayr [EMAIL PROTECTED] wrote: * Mikhail Gusarov [EMAIL PROTECTED] [2008-05-12 02:43]: MM Still no progress, but I just made 2.6.25 kernels available with MM the DMA patches applied. Can you publish source package too, to make it easier to build the kernel for armel? Download the linux-2.6 source from unstable (*) and applyhttp:// merkel.debian.org/~tbm/tmp/n2100/dma/patch-2.6.25-2iop1 (*) The 2.6.25-2 upload is still stuck in NEW, so for now you have to get the tar ball from unstable and the debian dir from svn://svn.debian.org/svn/kernel/dists/sid/linux-2.6/debian -- Martin Michlmayrhttp://www.cyrius.com/ -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: Progress on Bug#444271 / N2100 disk performance
* Uwe Holz [EMAIL PROTECTED] [2008-06-09 10:17]: is there any estimation, when changes will touch base in a regular kernel release? Probably not soon, if ever. These patches don't appear to be high priority for Intel, especially now that the IOP32x chip will reach its end of life at the end of this year. As I mentioned before, I think it needs a developer from the community to clean up the patches and submit them. -- Martin Michlmayr http://www.cyrius.com/ -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: Progress on Bug#444271 / N2100 disk performance
Martin Michlmayr [EMAIL PROTECTED] writes: Hi, * Uwe Holz [EMAIL PROTECTED] [2008-06-09 10:17]: is there any estimation, when changes will touch base in a regular kernel release? Probably not soon, if ever. These patches don't appear to be high priority for Intel, especially now that the IOP32x chip will reach its end of life at the end of this year. As I mentioned before, I think it needs a developer from the community to clean up the patches and submit them. imho, it's not only a matter of having someone from the community working on that. iirc, the patches were not really well perceived when sent to l-a-k. There was some hey' don't do that but nobody helped in finding a way to solve them. This is quite annoying as Dan was asking for help/advice. Arnaud -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: Progress on Bug#444271 / N2100 disk performance
* Arnaud Patard [EMAIL PROTECTED] [2008-06-09 13:57]: imho, it's not only a matter of having someone from the community working on that. iirc, the patches were not really well perceived when sent to l-a-k. There was some hey' don't do that but nobody helped in finding a way to solve them. This is quite annoying as Dan was asking for help/advice. You're of course right. Thanks for clarifying me overly simplied explanation. -- Martin Michlmayr http://www.cyrius.com/ -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: Progress on Bug#444271 / N2100 disk performance
Martin Michlmayr schrieb: * Tomasz Chmielewski [EMAIL PROTECTED] [2008-04-24 13:23]: Are these patches the same as those on http://sf.net/projects/xscaleiop or is it something different? Yeah, the patches are in there. Also look for Dan William's mail to linux-arm-kernel a few weeks ago where he submitted the DMA related patches. Last time I tried those patches on N4100, which should be similar, (2.6.23-iop series, and every earlier release) disk performance was still very poor. I didn't try 2.6.24-iop1 though. -- Tomasz Chmielewski http://wpkg.org -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: Progress on Bug#444271 / N2100 disk performance
* Tomasz Chmielewski [EMAIL PROTECTED] [2008-04-29 14:36]: Last time I tried those patches on N4100, which should be similar, (2.6.23-iop series, and every earlier release) disk performance was still very poor. Odd, they definitely sped up things here (on N2100). -- Martin Michlmayr http://www.cyrius.com/ -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: Progress on Bug#444271 / N2100 disk performance
Martin Michlmayr schrieb: * Tomasz Chmielewski [EMAIL PROTECTED] [2008-04-29 14:36]: Last time I tried those patches on N4100, which should be similar, (2.6.23-iop series, and every earlier release) disk performance was still very poor. Odd, they definitely sped up things here (on N2100). Could you send me your .config for N2100? -- Tomasz Chmielewski http://wpkg.org -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: Progress on Bug#444271 / N2100 disk performance
* Tomasz Chmielewski [EMAIL PROTECTED] [2008-04-29 14:56]: Odd, they definitely sped up things here (on N2100). Could you send me your .config for N2100? I've attached a config file, but basically, you just need to enable the DMA engine and the options that the patches add. -- Martin Michlmayr http://www.cyrius.com/ # # Automatically generated make config: don't edit # Linux kernel version: 2.6.24 # Mon Feb 18 18:53:23 2008 # CONFIG_ARM=y CONFIG_SYS_SUPPORTS_APM_EMULATION=y # CONFIG_GENERIC_GPIO is not set # CONFIG_GENERIC_TIME is not set # CONFIG_GENERIC_CLOCKEVENTS is not set CONFIG_MMU=y # CONFIG_NO_IOPORT is not set CONFIG_GENERIC_HARDIRQS=y CONFIG_STACKTRACE_SUPPORT=y CONFIG_LOCKDEP_SUPPORT=y CONFIG_TRACE_IRQFLAGS_SUPPORT=y CONFIG_HARDIRQS_SW_RESEND=y CONFIG_GENERIC_IRQ_PROBE=y CONFIG_RWSEM_GENERIC_SPINLOCK=y # CONFIG_ARCH_HAS_ILOG2_U32 is not set # CONFIG_ARCH_HAS_ILOG2_U64 is not set CONFIG_GENERIC_HWEIGHT=y CONFIG_GENERIC_CALIBRATE_DELAY=y CONFIG_ZONE_DMA=y CONFIG_VECTORS_BASE=0x CONFIG_DEFCONFIG_LIST=/lib/modules/$UNAME_RELEASE/.config # # General setup # CONFIG_EXPERIMENTAL=y CONFIG_BROKEN_ON_SMP=y CONFIG_INIT_ENV_ARG_LIMIT=32 CONFIG_LOCALVERSION= # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SWAP=y CONFIG_SYSVIPC=y CONFIG_SYSVIPC_SYSCTL=y CONFIG_POSIX_MQUEUE=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_BSD_PROCESS_ACCT_V3=y CONFIG_TASKSTATS=y CONFIG_TASK_DELAY_ACCT=y CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y # CONFIG_USER_NS is not set # CONFIG_PID_NS is not set CONFIG_AUDIT=y # CONFIG_IKCONFIG is not set CONFIG_LOG_BUF_SHIFT=14 CONFIG_CGROUPS=y # CONFIG_CGROUP_DEBUG is not set CONFIG_CGROUP_NS=y CONFIG_FAIR_GROUP_SCHED=y CONFIG_FAIR_USER_SCHED=y # CONFIG_FAIR_CGROUP_SCHED is not set CONFIG_CGROUP_CPUACCT=y CONFIG_SYSFS_DEPRECATED=y CONFIG_RELAY=y CONFIG_BLK_DEV_INITRD=y CONFIG_INITRAMFS_SOURCE= CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_SYSCTL=y # CONFIG_EMBEDDED is not set CONFIG_UID16=y CONFIG_SYSCTL_SYSCALL=y CONFIG_KALLSYMS=y # CONFIG_KALLSYMS_EXTRA_PASS is not set CONFIG_HOTPLUG=y CONFIG_PRINTK=y CONFIG_BUG=y CONFIG_ELF_CORE=y CONFIG_BASE_FULL=y CONFIG_FUTEX=y CONFIG_ANON_INODES=y CONFIG_EPOLL=y CONFIG_SIGNALFD=y CONFIG_EVENTFD=y CONFIG_SHMEM=y CONFIG_VM_EVENT_COUNTERS=y CONFIG_SLAB=y # CONFIG_SLUB is not set # CONFIG_SLOB is not set CONFIG_SLABINFO=y CONFIG_RT_MUTEXES=y # CONFIG_TINY_SHMEM is not set CONFIG_BASE_SMALL=0 CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_MODULE_FORCE_UNLOAD is not set CONFIG_MODVERSIONS=y # CONFIG_MODULE_SRCVERSION_ALL is not set CONFIG_KMOD=y CONFIG_BLOCK=y CONFIG_LBD=y # CONFIG_BLK_DEV_IO_TRACE is not set CONFIG_LSF=y # CONFIG_BLK_DEV_BSG is not set # # IO Schedulers # CONFIG_IOSCHED_NOOP=y CONFIG_IOSCHED_AS=y CONFIG_IOSCHED_DEADLINE=y CONFIG_IOSCHED_CFQ=y # CONFIG_DEFAULT_AS is not set # CONFIG_DEFAULT_DEADLINE is not set CONFIG_DEFAULT_CFQ=y # CONFIG_DEFAULT_NOOP is not set CONFIG_DEFAULT_IOSCHED=cfq # # System Type # # CONFIG_ARCH_AAEC2000 is not set # CONFIG_ARCH_INTEGRATOR is not set # CONFIG_ARCH_REALVIEW is not set # CONFIG_ARCH_VERSATILE is not set # CONFIG_ARCH_AT91 is not set # CONFIG_ARCH_CLPS7500 is not set # CONFIG_ARCH_CLPS711X is not set # CONFIG_ARCH_CO285 is not set # CONFIG_ARCH_EBSA110 is not set # CONFIG_ARCH_EP93XX is not set # CONFIG_ARCH_FOOTBRIDGE is not set # CONFIG_ARCH_NETX is not set # CONFIG_ARCH_H720X is not set # CONFIG_ARCH_IMX is not set # CONFIG_ARCH_IOP13XX is not set CONFIG_ARCH_IOP32X=y # CONFIG_ARCH_IOP33X is not set # CONFIG_ARCH_IXP23XX is not set # CONFIG_ARCH_IXP2000 is not set # CONFIG_ARCH_IXP4XX is not set # CONFIG_ARCH_L7200 is not set # CONFIG_ARCH_KS8695 is not set # CONFIG_ARCH_NS9XXX is not set # CONFIG_ARCH_MXC is not set # CONFIG_ARCH_PNX4008 is not set # CONFIG_ARCH_PXA is not set # CONFIG_ARCH_RPC is not set # CONFIG_ARCH_SA1100 is not set # CONFIG_ARCH_S3C2410 is not set # CONFIG_ARCH_SHARK is not set # CONFIG_ARCH_LH7A40X is not set # CONFIG_ARCH_DAVINCI is not set # CONFIG_ARCH_OMAP is not set # # IOP32x Implementation Options # # # IOP32x Platform Types # CONFIG_MACH_EP80219=y CONFIG_MACH_GLANTANK=y CONFIG_ARCH_IQ80321=y CONFIG_ARCH_IQ31244=y CONFIG_MACH_N2100=y CONFIG_IOP3XX_ATU=y # CONFIG_MACH_EM7210 is not set # # Boot options # # # Power management # CONFIG_PLAT_IOP=y # # Processor Type # CONFIG_CPU_32=y CONFIG_CPU_XSCALE=y CONFIG_CPU_32v5=y CONFIG_CPU_ABRT_EV5T=y CONFIG_CPU_CACHE_VIVT=y CONFIG_CPU_TLB_V4WBI=y CONFIG_CPU_CP15=y CONFIG_CPU_CP15_MMU=y # # Processor Features # # CONFIG_ARM_THUMB is not set # CONFIG_CPU_DCACHE_DISABLE is not set # CONFIG_OUTER_CACHE is not set # CONFIG_IWMMXT is not set CONFIG_XSCALE_PMU=y # # Bus support # CONFIG_PCI=y CONFIG_PCI_SYSCALL=y # CONFIG_ARCH_SUPPORTS_MSI is not set CONFIG_PCI_LEGACY=y # CONFIG_PCCARD is not set # # Kernel Features # # CONFIG_TICK_ONESHOT is not set # CONFIG_PREEMPT is not set # CONFIG_NO_IDLE_HZ is not set CONFIG_HZ=100 # CONFIG_AEABI is not set # CONFIG_ARCH_DISCONTIGMEM_ENABLE is not set CONFIG_SELECT_MEMORY_MODEL=y
Re: Progress on Bug#444271 / N2100 disk performance
Martin Michlmayr [EMAIL PROTECTED] writes: Hi, * Markus Lindenberg [EMAIL PROTECTED] [2008-04-24 12:58]: i wonder if there's any progress on this one. i consider this a very limiting issue, as it renders my n2100 almost unusable regarding it's core purpose, being a high performance nas device in a gbit lan. even my slug seems to have a better disk performance. No news I'm afraid. The patches appear to be stable now but have not received any comments from the wider kernel.org community, so I'm reluctant to put them into the Debian package. What is needed is an experienced developer who can take a look at the patches and push for upstream inclusion. Arnaud, did you have a chance to look at the patches recently? I must admit that last time I looked at them was when the patches were sent to l-a-k [1] but I plan to have a look at them Note also that they're not exactly the same version as the one available on sourceforge so some newer version exists somewhere. As some issues were raised, I'm not sure it's ready to be merged in the Debian kernel. Nevertheless, one can still use them on their own kernel and report bugs :) Arnaud [1] http://marc.info/?l=linux-arm-kernelm=120493107523366w=2 http://marc.info/?l=linux-arm-kernelm=120516121532622w=2 http://marc.info/?l=linux-arm-kernelm=120516134500498w=2 -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
