DPDK patches and discussions
 help / color / mirror / Atom feed
From: Shani Peretz <shperetz@nvidia.com>
To: <dev@dpdk.org>
Cc: <mb@smartsharesystems.com>, <stephen@networkplumber.org>,
	<bruce.richardson@intel.com>, <ajit.khaparde@broadcom.com>,
	<jerinj@marvell.com>, <konstantin.v.ananyev@yandex.ru>,
	<david.marchand@redhat.com>, <maxime.coquelin@redhat.com>,
	<gakhil@marvell.com>, <viacheslavo@nvidia.com>,
	<thomas@monjalon.net>, "Shani Peretz" <shperetz@nvidia.com>,
	Robin Jarry <rjarry@redhat.com>
Subject: [PATCH v2 4/4] usertool: add a script to parse mbuf history dump
Date: Tue, 16 Sep 2025 18:12:07 +0300	[thread overview]
Message-ID: <20250916151207.556618-5-shperetz@nvidia.com> (raw)
In-Reply-To: <20250916151207.556618-1-shperetz@nvidia.com>

Added a Python script that parses the history dump of a mbufs
generated by rte_mbuf_objects_dump and presents it in a human-readable
format.

If an operation ID is repeated, such as in the case of a double free,
it will be highlighted in red and listed at the end of the file.

Signed-off-by: Shani Peretz <shperetz@nvidia.com>
---
 usertools/dpdk-mbuf_history_parser.py | 173 ++++++++++++++++++++++++++
 1 file changed, 173 insertions(+)
 create mode 100755 usertools/dpdk-mbuf_history_parser.py

diff --git a/usertools/dpdk-mbuf_history_parser.py b/usertools/dpdk-mbuf_history_parser.py
new file mode 100755
index 0000000000..c39a796d5d
--- /dev/null
+++ b/usertools/dpdk-mbuf_history_parser.py
@@ -0,0 +1,173 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright (c) 2023 NVIDIA Corporation & Affiliates
+
+import sys
+import re
+import os
+import enum
+
+RED = "\033[91m"
+RESET = "\033[0m"
+ENUM_PATTERN = r'enum\s+rte_mbuf_history_op\s*{([^}]+)}'
+VALUE_PATTERN = r'([A-Z_]+)\s*=\s*(\d+),\s*(?:/\*\s*(.*?)\s*\*/)?'
+HEADER_FILE = os.path.join(
+    os.path.dirname(os.path.dirname(__file__)),
+    'lib/mbuf/rte_mbuf_history.h'
+)
+
+
+def print_history_sequence(address: str, sequence: list[str]):
+    max_op_width = max(
+        len(re.sub(r'\x1b\[[0-9;]*m', '', op)) for op in sequence
+    )
+    op_width = max_op_width
+    for i in range(0, len(sequence), 4):
+        chunk = sequence[i:i + 4]
+        formatted_ops = [f"{op:<{op_width}}" for op in chunk]
+        line = ""
+        for j, op in enumerate(formatted_ops):
+            line += op
+            if j < len(formatted_ops) - 1:
+                line += " -> "
+        if i + 4 < len(sequence):
+            line += " ->"
+        print(f"mbuf {address}: " + line)
+    print()
+
+
+def match_field(match: re.Match) -> tuple[int, str]:
+    name, value, _ = match.groups()
+    return (int(value), name.replace('RTE_MBUF_', ''))
+
+
+class HistoryEnum:
+    def __init__(self, ops: enum.Enum):
+        self.ops = ops
+
+    @staticmethod
+    def from_header(header_file: str) -> 'HistoryEnum':
+        with open(header_file, 'r') as f:
+            content = f.read()
+
+        # Extract each enum value and its comment
+        enum_content = re.search(ENUM_PATTERN, content, re.DOTALL).group(1)
+        fields = map(match_field, re.finditer(VALUE_PATTERN, enum_content))
+        fields = dict({v: k for k, v in fields})
+        return HistoryEnum(enum.Enum('HistoryOps', fields))
+
+
+class HistoryLine:
+    def __init__(self, address: str, ops: list):
+        self.address = address
+        self.ops = ops
+
+    def repeats(self) -> [list[str], str | None]:
+        repeated = None
+        sequence = []
+        for idx, op in enumerate(self.ops):
+            if idx > 0 and op == self.ops[idx - 1] and op.name != 'NEVER':
+                sequence[-1] = f"{RED}{op.name}{RESET}"
+                sequence.append(f"{RED}{op.name}{RESET}")
+                repeated = op.name
+            else:
+                sequence.append(op.name)
+        return sequence, repeated
+
+
+class HistoryMetrics:
+    def __init__(self, metrics: dict[str, int]):
+        self.metrics = metrics
+
+    def max_name_width(self) -> int:
+        return max(len(name) for name in self.metrics.keys())
+
+
+class HistoryParser:
+    def __init__(self):
+        self.history_enum = HistoryEnum.from_header(HEADER_FILE)
+
+    def parse(
+        self, dump_file: str
+    ) -> tuple[list[HistoryLine], 'HistoryMetrics']:
+        with open(dump_file, 'r') as f:
+            lines = [line for line in f.readlines() if line.strip()]
+            populated = next(line for line in lines if "Populated:" in line)
+            metrics_start = lines.index(populated)
+
+        history_lines = lines[3:metrics_start]
+        metrics_lines = lines[metrics_start:-1]
+        return (
+            self._parse_history(history_lines),
+            self._parse_metrics(metrics_lines)
+        )
+
+    def _parse_metrics(self, lines: list[str]) -> HistoryMetrics:
+        metrics = {}
+        for line in lines:
+            key, value = line.split(':', 1)
+            metrics[key] = int(value)
+        return HistoryMetrics(metrics)
+
+    def _parse_history(self, lines: list[str]) -> list[HistoryLine]:
+        # Parse the format "mbuf 0x1054b9980: 0000000000000065"
+        history_lines = []
+        for line in lines:
+            address = line.split(':')[0].split('mbuf ')[1]
+            history = line.split(':')[1]
+            history_lines.append(
+                HistoryLine(
+                    address=address,
+                    ops=self._parse(int(history, 16))
+                )
+            )
+        return history_lines
+
+    def _parse(self, history: int) -> list[str]:
+        ops = []
+        for _ in range(16):  # 64 bits / 4 bits = 16 possible operations
+            op = history & 0xF  # Extract lowest 4 bits
+            if op == 0:
+                break
+            ops.append(self.history_enum.ops(op))
+            history >>= 4
+
+        ops.reverse()
+        return ops
+
+
+def print_history_lines(history_lines: list[HistoryLine]):
+    lines = [
+        (line.address, line.repeats()) for line in history_lines
+    ]
+
+    for address, (sequence, _) in lines:
+        print_history_sequence(address, sequence)
+
+    print("=== Violations ===")
+    for address, (sequence, repeated) in lines:
+        if repeated:
+            print(f"mbuf {address} has repeated ops: {RED}{repeated}{RESET}")
+
+
+def print_metrics(metrics: HistoryMetrics):
+    print("=== Metrics Summary ===")
+    for name, value in metrics.metrics.items():
+        print(f"{name + ':':<{metrics.max_name_width() + 2}} {value}")
+
+
+def main():
+    if len(sys.argv) != 2:
+        print("Usage: {} <history_file>".format(sys.argv[0]))
+        sys.exit(1)
+
+    history_parser = HistoryParser()
+    history_lines, metrics = history_parser.parse(sys.argv[1])
+
+    print_history_lines(history_lines)
+    print()
+    print_metrics(metrics)
+
+
+if __name__ == "__main__":
+    main()
-- 
2.34.1


      parent reply	other threads:[~2025-09-16 15:13 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-06-16  7:29 [RFC PATCH 0/5] Introduce mempool object new debug capabilities Shani Peretz
2025-06-16  7:29 ` [RFC PATCH 1/5] mempool: record mempool objects operations history Shani Peretz
2025-06-16  7:29 ` [RFC PATCH 2/5] drivers: add mempool history compilation flag Shani Peretz
2025-06-16  7:29 ` [RFC PATCH 3/5] net/mlx5: mark an operation in mempool object's history Shani Peretz
2025-06-16  7:29 ` [RFC PATCH 4/5] app/testpmd: add testpmd command to dump mempool history Shani Peretz
2025-06-16  7:29 ` [RFC PATCH 5/5] usertool: add a script to parse mempool history dump Shani Peretz
2025-06-16 15:30 ` [RFC PATCH 0/5] Introduce mempool object new debug capabilities Stephen Hemminger
2025-06-19 12:57   ` Morten Brørup
2025-07-07  5:46     ` Shani Peretz
2025-07-07  5:45   ` Shani Peretz
2025-07-07 12:10     ` Morten Brørup
2025-07-19 14:39       ` Morten Brørup
2025-08-25 11:27         ` Slava Ovsiienko
2025-09-01 15:34           ` Morten Brørup
2025-09-16 15:12 ` [PATCH v2 0/4] add mbuf " Shani Peretz
2025-09-16 15:12   ` [PATCH v2 1/4] mbuf: record mbuf operations history Shani Peretz
2025-09-16 21:17     ` Stephen Hemminger
2025-09-16 21:33       ` Thomas Monjalon
2025-09-17  1:22         ` Morten Brørup
2025-09-16 15:12   ` [PATCH v2 2/4] net/mlx5: mark an operation in mbuf's history Shani Peretz
2025-09-16 21:14     ` Stephen Hemminger
2025-09-16 21:31       ` Thomas Monjalon
2025-09-16 15:12   ` [PATCH v2 3/4] app/testpmd: add testpmd command to dump mbuf history Shani Peretz
2025-09-16 15:12   ` Shani Peretz [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20250916151207.556618-5-shperetz@nvidia.com \
    --to=shperetz@nvidia.com \
    --cc=ajit.khaparde@broadcom.com \
    --cc=bruce.richardson@intel.com \
    --cc=david.marchand@redhat.com \
    --cc=dev@dpdk.org \
    --cc=gakhil@marvell.com \
    --cc=jerinj@marvell.com \
    --cc=konstantin.v.ananyev@yandex.ru \
    --cc=maxime.coquelin@redhat.com \
    --cc=mb@smartsharesystems.com \
    --cc=rjarry@redhat.com \
    --cc=stephen@networkplumber.org \
    --cc=thomas@monjalon.net \
    --cc=viacheslavo@nvidia.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).