Re: Need to enable caches in SMP ? (was Kernel 2.6 SMP very slow with ServerWorks LE Chipset)
Jeff V. Merkey wrote: Alan wrote: As per Alan's suggestion I decompressed the kernel source tree with the processes pegged to one CPU then the other, and as he predicted it took vastly longer on one CPU than the other, but I don't know what that implies, or how to fix it. From the timing it sounds like one processor cache is disabled which is a little peculiar to say the least. enable the L1 cache in the processor. BIOS settings, no doubt. Jeff The very spartan Phoenix BIOS doesn't have any options to enable or disable CPU Cache, which I know full well to enable, but it does have something rather vaguely called "Memory Caching" the enabling of which seems to have fixed the problem, it's strange it only disabled the cache on one CPU and only under 2.6, I'll investigate more in January. It's good to have the fix search able, this thread would have saved me from making an ass of myself. Thank you for your help. - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: Need to enable caches in SMP ? (was Kernel 2.6 SMP very slow with ServerWorks LE Chipset)
Jeff V. Merkey wrote: Alan wrote: As per Alan's suggestion I decompressed the kernel source tree with the processes pegged to one CPU then the other, and as he predicted it took vastly longer on one CPU than the other, but I don't know what that implies, or how to fix it. From the timing it sounds like one processor cache is disabled which is a little peculiar to say the least. enable the L1 cache in the processor. BIOS settings, no doubt. Jeff The very spartan Phoenix BIOS doesn't have any options to enable or disable CPU Cache, which I know full well to enable, but it does have something rather vaguely called Memory Caching the enabling of which seems to have fixed the problem, it's strange it only disabled the cache on one CPU and only under 2.6, I'll investigate more in January. It's good to have the fix search able, this thread would have saved me from making an ass of myself. Thank you for your help. - To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: Need to enable caches in SMP ? (was Kernel 2.6 SMP very slow with ServerWorks LE Chipset)
Alan wrote: As per Alan's suggestion I decompressed the kernel source tree with the processes pegged to one CPU then the other, and as he predicted it took vastly longer on one CPU than the other, but I don't know what that implies, or how to fix it. From the timing it sounds like one processor cache is disabled which is a little peculiar to say the least. Alan - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/ enable the L1 cache in the processor. BIOS settings, no doubt. Jeff - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Need to enable caches in SMP ? (was Kernel 2.6 SMP very slow with ServerWorks LE Chipset)
> As per Alan's suggestion I decompressed the kernel source tree with the > processes pegged to one CPU then the other, and as he predicted it took > vastly longer on one CPU than the other, but I don't know what that > implies, or how to fix it. >From the timing it sounds like one processor cache is disabled which is a little peculiar to say the least. Alan - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Need to enable caches in SMP ? (was Kernel 2.6 SMP very slow with ServerWorks LE Chipset)
As per Alan's suggestion I decompressed the kernel source tree with the processes pegged to one CPU then the other, and as he predicted it took vastly longer on one CPU than the other, but I don't know what that implies, or how to fix it. From the timing it sounds like one processor cache is disabled which is a little peculiar to say the least. Alan - To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: Need to enable caches in SMP ? (was Kernel 2.6 SMP very slow with ServerWorks LE Chipset)
Alan wrote: As per Alan's suggestion I decompressed the kernel source tree with the processes pegged to one CPU then the other, and as he predicted it took vastly longer on one CPU than the other, but I don't know what that implies, or how to fix it. From the timing it sounds like one processor cache is disabled which is a little peculiar to say the least. Alan - To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/ enable the L1 cache in the processor. BIOS settings, no doubt. Jeff - To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
