qdist: add module to represent frequency distributions of data

Sometimes it is useful to have a quick histogram to represent a certain
distribution -- for example, when investigating a performance regression
in a hash table due to inadequate hashing.

The appended allows us to easily represent a distribution using Unicode
characters. Further, the data structure keeping track of the distribution
is so simple that obtaining its values for off-line processing is trivial.

Example, taking the last 10 commits to QEMU:

 Characters in commit title  Count
-----------------------------------
                         39      1
                         48      1
                         53      1
                         54      2
                         57      1
                         61      1
                         67      1
                         78      1
                         80      1
qdist_init(&dist);
qdist_inc(&dist, 39);
[...]
qdist_inc(&dist, 80);

char *str = qdist_pr(&dist, 9, QDIST_PR_LABELS);
// -> [39.0,43.6)▂▂ █▂ ▂ ▄[75.4,80.0]
g_free(str);

char *str = qdist_pr(&dist, 4, QDIST_PR_LABELS);
// -> [39.0,49.2)▁█▁▁[69.8,80.0]
g_free(str);

Reviewed-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Emilio G. Cota <cota@braap.org>
Message-Id: <1465412133-3029-9-git-send-email-cota@braap.org>
Signed-off-by: Richard Henderson <rth@twiddle.net>

1 files changed, 63 insertions, 0 deletions

diff --git a/include/qemu/qdist.h b/include/qemu/qdist.h
new file mode 100644
index 0000000..f30050c
--- /dev/null
+++ b/include/qemu/qdist.h
@@ -0,0 +1,63 @@
+/*
+ * Copyright (C) 2016, Emilio G. Cota <cota@braap.org>
+ *
+ * License: GNU GPL, version 2 or later.
+ *   See the COPYING file in the top-level directory.
+ */
+#ifndef QEMU_QDIST_H
+#define QEMU_QDIST_H
+
+#include "qemu/osdep.h"
+#include "qemu-common.h"
+#include "qemu/bitops.h"
+
+/*
+ * Samples with the same 'x value' end up in the same qdist_entry,
+ * e.g. inc(0.1) and inc(0.1) end up as {x=0.1, count=2}.
+ *
+ * Binning happens only at print time, so that we retain the flexibility to
+ * choose the binning. This might not be ideal for workloads that do not care
+ * much about precision and insert many samples all with different x values;
+ * in that case, pre-binning (e.g. entering both 0.115 and 0.097 as 0.1)
+ * should be considered.
+ */
+struct qdist_entry {
+    double x;
+    unsigned long count;
+};
+
+struct qdist {
+    struct qdist_entry *entries;
+    size_t n;
+    size_t size;
+};
+
+#define QDIST_PR_BORDER     BIT(0)
+#define QDIST_PR_LABELS     BIT(1)
+/* the remaining options only work if PR_LABELS is set */
+#define QDIST_PR_NODECIMAL  BIT(2)
+#define QDIST_PR_PERCENT    BIT(3)
+#define QDIST_PR_100X       BIT(4)
+#define QDIST_PR_NOBINRANGE BIT(5)
+
+void qdist_init(struct qdist *dist);
+void qdist_destroy(struct qdist *dist);
+
+void qdist_add(struct qdist *dist, double x, long count);
+void qdist_inc(struct qdist *dist, double x);
+double qdist_xmin(const struct qdist *dist);
+double qdist_xmax(const struct qdist *dist);
+double qdist_avg(const struct qdist *dist);
+unsigned long qdist_sample_count(const struct qdist *dist);
+size_t qdist_unique_entries(const struct qdist *dist);
+
+/* callers must free the returned string with g_free() */
+char *qdist_pr_plain(const struct qdist *dist, size_t n_groups);
+
+/* callers must free the returned string with g_free() */
+char *qdist_pr(const struct qdist *dist, size_t n_groups, uint32_t opt);
+
+/* Only qdist code and test code should ever call this function */
+void qdist_bin__internal(struct qdist *to, const struct qdist *from, size_t n);
+
+#endif /* QEMU_QDIST_H */