Re: [Qemu-devel] [PATCH v6 15/15] translate-all: add tb hash bucket info to 'info jit' dump

[Sergey Fedorov]

On 25/05/16 04:13, Emilio G. Cota wrote:
> Examples:
>
> - Good hashing, i.e. tb_hash_func5(phys_pc, pc, flags):
> TB count            715135/2684354
> [...]
> TB hash buckets     388775/524288 (74.15% head buckets used)
> TB hash occupancy   33.04% avg chain occ. Histogram: [0,10)%|▆ █  
> ▅▁▃▁▁|[90,100]%
> TB hash avg chain   1.017 buckets. Histogram: 1|█▁▁|3
>
> - Not-so-good hashing, i.e. tb_hash_func5(phys_pc, pc, 0):
> TB count            712636/2684354
> [...]
> TB hash buckets     344924/524288 (65.79% head buckets used)
> TB hash occupancy   31.64% avg chain occ. Histogram: [0,10)%|█ ▆  
> ▅▁▃▁▂|[90,100]%
> TB hash avg chain   1.047 buckets. Histogram: 1|█▁▁▁|4
>
> - Bad hashing, i.e. tb_hash_func5(phys_pc, 0, 0):
> TB count            702818/2684354
> [...]
> TB hash buckets     112741/524288 (21.50% head buckets used)
> TB hash occupancy   10.15% avg chain occ. Histogram: [0,10)%|█ ▁  
> ▁▁▁▁▁|[90,100]%
> TB hash avg chain   2.107 buckets. Histogram: 
> [1.0,10.2)|█▁▁▁▁▁▁▁▁▁|[83.8,93.0]
>
> - Good hashing, but no auto-resize:
> TB count            715634/2684354
> TB hash buckets     8192/8192 (100.00% head buckets used)
> TB hash occupancy   98.30% avg chain occ. Histogram: 
> [95.3,95.8)%|▁▁▃▄▃▄▁▇▁█|[99.5,100.0]%
> TB hash avg chain   22.070 buckets. Histogram: 
> [15.0,16.7)|▁▂▅▄█▅▁▁▁▁|[30.3,32.0]

I personally don't see much use of the histogram labels. However,

Acked-by: Sergey Fedorov <address@hidden>

>
> Suggested-by: Richard Henderson <address@hidden>
> Reviewed-by: Richard Henderson <address@hidden>
> Signed-off-by: Emilio G. Cota <address@hidden>
> ---
>  translate-all.c | 36 ++++++++++++++++++++++++++++++++++++
>  1 file changed, 36 insertions(+)
>
> diff --git a/translate-all.c b/translate-all.c
> index 5357737..c8074cf 100644
> --- a/translate-all.c
> +++ b/translate-all.c
> @@ -1667,6 +1667,10 @@ void dump_exec_info(FILE *f, fprintf_function 
> cpu_fprintf)
>      int i, target_code_size, max_target_code_size;
>      int direct_jmp_count, direct_jmp2_count, cross_page;
>      TranslationBlock *tb;
> +    struct qht_stats hst;
> +    uint32_t hgram_opts;
> +    size_t hgram_bins;
> +    char *hgram;
>  
>      target_code_size = 0;
>      max_target_code_size = 0;
> @@ -1717,6 +1721,38 @@ void dump_exec_info(FILE *f, fprintf_function 
> cpu_fprintf)
>                  direct_jmp2_count,
>                  tcg_ctx.tb_ctx.nb_tbs ? (direct_jmp2_count * 100) /
>                          tcg_ctx.tb_ctx.nb_tbs : 0);
> +
> +    qht_statistics_init(&tcg_ctx.tb_ctx.htable, &hst);
> +
> +    cpu_fprintf(f, "TB hash buckets     %zu/%zu (%0.2f%% head buckets 
> used)\n",
> +                hst.used_head_buckets, hst.head_buckets,
> +                (double)hst.used_head_buckets / hst.head_buckets * 100);
> +
> +    hgram_opts =  QDIST_PR_BORDER | QDIST_PR_LABELS;
> +    hgram_opts |= QDIST_PR_100X   | QDIST_PR_PERCENT;
> +    if (qdist_xmax(&hst.occupancy) - qdist_xmin(&hst.occupancy) == 1) {
> +        hgram_opts |= QDIST_PR_NODECIMAL;
> +    }
> +    hgram = qdist_pr(&hst.occupancy, 10, hgram_opts);
> +    cpu_fprintf(f, "TB hash occupancy   %0.2f%% avg chain occ. Histogram: 
> %s\n",
> +                qdist_avg(&hst.occupancy) * 100, hgram);
> +    g_free(hgram);
> +
> +    hgram_opts = QDIST_PR_BORDER | QDIST_PR_LABELS;
> +    hgram_bins = qdist_xmax(&hst.chain) - qdist_xmin(&hst.chain);
> +    if (hgram_bins > 10) {
> +        hgram_bins = 10;
> +    } else {
> +        hgram_bins = 0;
> +        hgram_opts |= QDIST_PR_NODECIMAL | QDIST_PR_NOBINRANGE;
> +    }
> +    hgram = qdist_pr(&hst.chain, hgram_bins, hgram_opts);
> +    cpu_fprintf(f, "TB hash avg chain   %0.3f buckets. Histogram: %s\n",
> +                qdist_avg(&hst.chain), hgram);
> +    g_free(hgram);
> +
> +    qht_statistics_destroy(&hst);
> +
>      cpu_fprintf(f, "\nStatistics:\n");
>      cpu_fprintf(f, "TB flush count      %d\n", 
> tcg_ctx.tb_ctx.tb_flush_count);
>      cpu_fprintf(f, "TB invalidate count %d\n",