Re: [Qemu-devel] [PATCH V6 08/10] migration: calculate vCPU blocktime on dst side

["Dr. David Alan Gilbert" <dgilbert@redhat.com>]

* Alexey Perevalov (a.perevalov@samsung.com) wrote:
> This patch provides blocktime calculation per vCPU,
> as a summary and as a overlapped value for all vCPUs.
> 
> This approach was suggested by Peter Xu, as an improvements of
> previous approch where QEMU kept tree with faulted page address and cpus bitmask
> in it. Now QEMU is keeping array with faulted page address as value and vCPU
> as index. It helps to find proper vCPU at UFFD_COPY time. Also it keeps
> list for blocktime per vCPU (could be traced with page_fault_addr)
> 
> Blocktime will not calculated if postcopy_blocktime field of
> MigrationIncomingState wasn't initialized.
> 
> Signed-off-by: Alexey Perevalov <a.perevalov@samsung.com>

<snip>

> +    if (dc->vcpu_addr[cpu] == 0) {
> +        atomic_inc(&dc->smp_cpus_down);
> +    }
> +
> +    atomic_xchg__nocheck(&dc->vcpu_addr[cpu], addr);

I was wondering if this could be done with atomic_cmpxchg with old=0,
but the behaviour would be different in the case where vcpu_addr[cpu]
wasn't zero  or the 'addr'; so I think allowing it to cope with that
case seems better.

Dave

> +    atomic_xchg__nocheck(&dc->last_begin, now_ms);
> +    atomic_xchg__nocheck(&dc->page_fault_vcpu_time[cpu], now_ms);
> +
> +    trace_mark_postcopy_blocktime_begin(addr, dc, dc->page_fault_vcpu_time[cpu],
> +            cpu);
> +}
> +
> +static void mark_postcopy_blocktime_end(uint64_t addr)
> +{
> +    MigrationIncomingState *mis = migration_incoming_get_current();
> +    PostcopyBlocktimeContext *dc = mis->blocktime_ctx;
> +    int i, affected_cpu = 0;
> +    int64_t now_ms;
> +    bool vcpu_total_blocktime = false;
> +    unsigned long int nr_bit;
> +
> +    if (!dc) {
> +        return;
> +    }
> +    /* mark that page as copied */
> +    nr_bit = get_copied_bit_offset(addr);
> +    set_bit_atomic(nr_bit, mis->copied_pages);
> +
> +    now_ms = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
> +
> +    /* lookup cpu, to clear it,
> +     * that algorithm looks straighforward, but it's not
> +     * optimal, more optimal algorithm is keeping tree or hash
> +     * where key is address value is a list of  */
> +    for (i = 0; i < smp_cpus; i++) {
> +        uint64_t vcpu_blocktime = 0;
> +        if (atomic_fetch_add(&dc->vcpu_addr[i], 0) != addr) {
> +            continue;
> +        }
> +        atomic_xchg__nocheck(&dc->vcpu_addr[i], 0);
> +        vcpu_blocktime = now_ms -
> +            atomic_fetch_add(&dc->page_fault_vcpu_time[i], 0);
> +        affected_cpu += 1;
> +        /* we need to know is that mark_postcopy_end was due to
> +         * faulted page, another possible case it's prefetched
> +         * page and in that case we shouldn't be here */
> +        if (!vcpu_total_blocktime &&
> +            atomic_fetch_add(&dc->smp_cpus_down, 0) == smp_cpus) {
> +            vcpu_total_blocktime = true;
> +        }
> +        /* continue cycle, due to one page could affect several vCPUs */
> +        dc->vcpu_blocktime[i] += vcpu_blocktime;
> +    }
> +
> +    atomic_sub(&dc->smp_cpus_down, affected_cpu);
> +    if (vcpu_total_blocktime) {
> +        dc->total_blocktime += now_ms - atomic_fetch_add(&dc->last_begin, 0);
> +    }
> +    trace_mark_postcopy_blocktime_end(addr, dc, dc->total_blocktime);
> +}
> +
>  /*
>   * Handle faults detected by the USERFAULT markings
>   */
> @@ -654,8 +750,11 @@ static void *postcopy_ram_fault_thread(void *opaque)
>          rb_offset &= ~(qemu_ram_pagesize(rb) - 1);
>          trace_postcopy_ram_fault_thread_request(msg.arg.pagefault.address,
>                                                  qemu_ram_get_idstr(rb),
> -                                                rb_offset);
> +                                                rb_offset,
> +                                                msg.arg.pagefault.feat.ptid);
>  
> +        mark_postcopy_blocktime_begin((uintptr_t)(msg.arg.pagefault.address),
> +                msg.arg.pagefault.feat.ptid, rb);
>          /*
>           * Send the request to the source - we want to request one
>           * of our host page sizes (which is >= TPS)
> @@ -750,6 +849,7 @@ int postcopy_place_page(MigrationIncomingState *mis, void *host, void *from,
>  
>          return -e;
>      }
> +    mark_postcopy_blocktime_end((uint64_t)(uintptr_t)host);
>  
>      trace_postcopy_place_page(host);
>      return 0;
> diff --git a/migration/trace-events b/migration/trace-events
> index 5b8ccf3..7bdadbb 100644
> --- a/migration/trace-events
> +++ b/migration/trace-events
> @@ -112,6 +112,8 @@ process_incoming_migration_co_end(int ret, int ps) "ret=%d postcopy-state=%d"
>  process_incoming_migration_co_postcopy_end_main(void) ""
>  migration_set_incoming_channel(void *ioc, const char *ioctype) "ioc=%p ioctype=%s"
>  migration_set_outgoing_channel(void *ioc, const char *ioctype, const char *hostname)  "ioc=%p ioctype=%s hostname=%s"
> +mark_postcopy_blocktime_begin(uint64_t addr, void *dd, int64_t time, int cpu) "addr 0x%" PRIx64 " dd %p time %" PRId64 " cpu %d"
> +mark_postcopy_blocktime_end(uint64_t addr, void *dd, int64_t time) "addr 0x%" PRIx64 " dd %p time %" PRId64
>  
>  # migration/rdma.c
>  qemu_rdma_accept_incoming_migration(void) ""
> @@ -188,7 +190,7 @@ postcopy_ram_enable_notify(void) ""
>  postcopy_ram_fault_thread_entry(void) ""
>  postcopy_ram_fault_thread_exit(void) ""
>  postcopy_ram_fault_thread_quit(void) ""
> -postcopy_ram_fault_thread_request(uint64_t hostaddr, const char *ramblock, size_t offset) "Request for HVA=%" PRIx64 " rb=%s offset=%zx"
> +postcopy_ram_fault_thread_request(uint64_t hostaddr, const char *ramblock, size_t offset, uint32_t pid) "Request for HVA=%" PRIx64 " rb=%s offset=%zx %u"
>  postcopy_ram_incoming_cleanup_closeuf(void) ""
>  postcopy_ram_incoming_cleanup_entry(void) ""
>  postcopy_ram_incoming_cleanup_exit(void) ""
> @@ -197,6 +199,7 @@ save_xbzrle_page_skipping(void) ""
>  save_xbzrle_page_overflow(void) ""
>  ram_save_iterate_big_wait(uint64_t milliconds, int iterations) "big wait: %" PRIu64 " milliseconds, %d iterations"
>  ram_load_complete(int ret, uint64_t seq_iter) "exit_code %d seq iteration %" PRIu64
> +get_mem_fault_cpu_index(uint32_t pid) "pid %u is not vCPU"
>  
>  # migration/exec.c
>  migration_exec_outgoing(const char *cmd) "cmd=%s"
> -- 
> 1.8.3.1
> 
--
Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK