[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [PATCH v2 30/45] translate-all: report correct avg host TB
From: |
Emilio G. Cota |
Subject: |
[Qemu-devel] [PATCH v2 30/45] translate-all: report correct avg host TB size |
Date: |
Sun, 16 Jul 2017 16:04:13 -0400 |
Since commit 6e3b2bfd6 ("tcg: allocate TB structs before the
corresponding translated code") we are not fully utilizing
code_gen_buffer for translated code, and therefore are
incorrectly reporting the amount of translated code as well as
the average host TB size. Address this by:
- Making the conscious choice of misreporting the total translated code;
doing otherwise would mislead users into thinking "-tb-size" is not
honoured.
- Expanding tb_tree_stats to accurately count the bytes of translated code on
the host, and using this for reporting the average tb host size,
as well as the expansion ratio.
In the future we might want to consider reporting the accurate numbers for
the total translated code, together with a "bookkeeping/overhead" field to
account for the TB structs.
Signed-off-by: Emilio G. Cota <address@hidden>
---
accel/tcg/translate-all.c | 32 +++++++++++++++++++++++---------
1 file changed, 23 insertions(+), 9 deletions(-)
diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c
index 7c6e401..b655931 100644
--- a/accel/tcg/translate-all.c
+++ b/accel/tcg/translate-all.c
@@ -923,6 +923,15 @@ static void page_flush_tb(void)
}
}
+static gboolean tb_host_size_iter(gpointer key, gpointer value, gpointer data)
+{
+ const TranslationBlock *tb = value;
+ size_t *size = data;
+
+ *size += tb->tc.size;
+ return false;
+}
+
/* flush all the translation blocks */
static void do_tb_flush(CPUState *cpu, run_on_cpu_data tb_flush_count)
{
@@ -937,11 +946,12 @@ static void do_tb_flush(CPUState *cpu, run_on_cpu_data
tb_flush_count)
if (DEBUG_TB_FLUSH_GATE) {
size_t nb_tbs = g_tree_nnodes(tcg_ctx.tb_ctx.tb_tree);
+ size_t host_size = 0;
- printf("qemu: flush code_size=%td nb_tbs=%zu avg_tb_size=%td\n",
+ g_tree_foreach(tcg_ctx.tb_ctx.tb_tree, tb_host_size_iter, &host_size);
+ printf("qemu: flush code_size=%td nb_tbs=%zu avg_tb_size=%zu\n",
tcg_ctx.code_gen_ptr - tcg_ctx.code_gen_buffer, nb_tbs,
- nb_tbs > 0 ?
- (tcg_ctx.code_gen_ptr - tcg_ctx.code_gen_buffer) / nb_tbs : 0);
+ nb_tbs > 0 ? host_size / nb_tbs : 0);
}
if ((unsigned long)(tcg_ctx.code_gen_ptr - tcg_ctx.code_gen_buffer)
> tcg_ctx.code_gen_buffer_size) {
@@ -1897,6 +1907,7 @@ static void print_qht_statistics(FILE *f,
fprintf_function cpu_fprintf,
}
struct tb_tree_stats {
+ size_t host_size;
size_t target_size;
size_t max_target_size;
size_t direct_jmp_count;
@@ -1909,6 +1920,7 @@ static gboolean tb_tree_stats_iter(gpointer key, gpointer
value, gpointer data)
const TranslationBlock *tb = value;
struct tb_tree_stats *tst = data;
+ tst->host_size += tb->tc.size;
tst->target_size += tb->size;
if (tb->size > tst->max_target_size) {
tst->max_target_size = tb->size;
@@ -1937,6 +1949,11 @@ void dump_exec_info(FILE *f, fprintf_function
cpu_fprintf)
g_tree_foreach(tcg_ctx.tb_ctx.tb_tree, tb_tree_stats_iter, &tst);
/* XXX: avoid using doubles ? */
cpu_fprintf(f, "Translation buffer state:\n");
+ /*
+ * Report total code size including the padding and TB structs;
+ * otherwise users might think "-tb-size" is not honoured.
+ * For avg host size we use the precise numbers from tb_tree_stats though.
+ */
cpu_fprintf(f, "gen code size %td/%zd\n",
tcg_ctx.code_gen_ptr - tcg_ctx.code_gen_buffer,
tcg_ctx.code_gen_highwater - tcg_ctx.code_gen_buffer);
@@ -1944,12 +1961,9 @@ void dump_exec_info(FILE *f, fprintf_function
cpu_fprintf)
cpu_fprintf(f, "TB avg target size %zu max=%zu bytes\n",
nb_tbs ? tst.target_size / nb_tbs : 0,
tst.max_target_size);
- cpu_fprintf(f, "TB avg host size %td bytes (expansion ratio: %0.1f)\n",
- nb_tbs ? (tcg_ctx.code_gen_ptr -
- tcg_ctx.code_gen_buffer) / nb_tbs : 0,
- tst.target_size ? (double) (tcg_ctx.code_gen_ptr -
- tcg_ctx.code_gen_buffer) /
- tst.target_size : 0);
+ cpu_fprintf(f, "TB avg host size %zu bytes (expansion ratio: %0.1f)\n",
+ nb_tbs ? tst.host_size / nb_tbs : 0,
+ tst.target_size ? (double)tst.host_size / tst.target_size : 0);
cpu_fprintf(f, "cross page TB count %zu (%zu%%)\n", tst.cross_page,
nb_tbs ? (tst.cross_page * 100) / nb_tbs : 0);
cpu_fprintf(f, "direct jump count %zu (%zu%%) (2 jumps=%zu %zu%%)\n",
--
2.7.4
- Re: [Qemu-devel] [PATCH v2 21/45] tcg: check CF_PARALLEL instead of parallel_cpus, (continued)
- [Qemu-devel] [PATCH v2 17/45] target/i386: check CF_PARALLEL instead of parallel_cpus, Emilio G. Cota, 2017/07/16
- [Qemu-devel] [PATCH v2 13/45] tcg: consolidate TB lookups in tb_lookup__cpu_state, Emilio G. Cota, 2017/07/16
- [Qemu-devel] [PATCH v2 41/45] translate-all: use qemu_protect_rwx/none helpers, Emilio G. Cota, 2017/07/16
- [Qemu-devel] [PATCH v2 44/45] translate-all: do not allocate a guard page for code_gen_buffer, Emilio G. Cota, 2017/07/16
- [Qemu-devel] [PATCH v2 28/45] translate-all: use a binary search tree to track TBs in TBContext, Emilio G. Cota, 2017/07/16
- [Qemu-devel] [PATCH v2 30/45] translate-all: report correct avg host TB size,
Emilio G. Cota <=
- [Qemu-devel] [PATCH v2 19/45] target/s390x: check CF_PARALLEL instead of parallel_cpus, Emilio G. Cota, 2017/07/16
- [Qemu-devel] [PATCH v2 27/45] exec-all: extract tb->tc_* into a separate struct tc_tb, Emilio G. Cota, 2017/07/16
- [Qemu-devel] [PATCH v2 45/45] tcg: enable multiple TCG contexts in softmmu, Emilio G. Cota, 2017/07/16
- [Qemu-devel] [PATCH v2 05/45] exec-all: fix typos in TranslationBlock's documentation, Emilio G. Cota, 2017/07/16