This has been rebased with the perf branch as well, upon which it was based (per CPU requirements).
On Mon, Dec 7, 2015 at 3:41 PM, Davide Libenzi <[email protected]> wrote: > The qpread code has been dropped, and the dual ended buffer has been added. > > $ cat \#arch/interrupts > IRQ[ 49] IRQ[240] > CPU[ 0] 55 1533 > CPU[ 1] 0 0 > CPU[ 2] 0 0 > CPU[ 3] 0 0 > CPU[ 4] 0 0 > CPU[ 5] 0 0 > CPU[ 6] 0 0 > CPU[ 7] 0 0 > > > On Thu, Dec 3, 2015 at 12:57 PM, Davide Libenzi <[email protected]> > wrote: > >> This is unfortunately on top of devarch_msr_perf (the perf one posted >> yesterday), since I needed per-CPU, which lives there. >> >> >> https://github.com/dlibenzi/akaros/compare/devarch_msr_perf...dlibenzi:interrupt_device >> >> BTW, there seem to be something wrong with block extra data. >> >> >> The following changes since commit >> 87782eff25975f0d52c3778ce93b0c496f653f83: >> >> Added new perf utility to access CPU counters from userspace >> (2015-12-02 16:13:50 -0800) >> >> are available in the git repository at: >> >> [email protected]:dlibenzi/akaros interrupt_device >> >> for you to fetch changes up to 23b44ab22a56704642d79f665cbca9cbc6b727e1: >> >> Added devarch interrupts device (2015-12-03 12:46:38 -0800) >> >> ---------------------------------------------------------------- >> Davide Libenzi (3): >> Added sizeof_field() macro >> Allows the queue data structure to use a minimum block size >> Added devarch interrupts device >> >> kern/arch/riscv/devarch.h | 8 +++ >> kern/arch/x86/devarch.c | 125 >> ++++++++++++++++++++++++++++++++++++++++++++++ >> kern/arch/x86/devarch.h | 1 + >> kern/arch/x86/trap.c | 3 ++ >> kern/include/ns.h | 4 +- >> kern/include/ros/common.h | 2 + >> kern/src/ns/qio.c | 71 ++++++++++++++++++++++---- >> 7 files changed, 203 insertions(+), 11 deletions(-) >> create mode 100644 kern/arch/riscv/devarch.h >> >> > -- You received this message because you are subscribed to the Google Groups "Akaros" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To post to this group, send email to [email protected]. For more options, visit https://groups.google.com/d/optout.
