From mboxrd@z Thu Jan 1 00:00:00 1970 Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.remote-ip=100.103.45.18 ARC-Seal: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; cv=none; t=1794633579; b=H6YX1NE9aT+d1NMBmX9Fh7/dx8FauMvYkkJeIrUUzmdiPs/+M46EIDbWEiuc9Gqw4S4A hwN/GgkO9xFK/GY41Fpiau9QO2LTbceev9wsFWcFXfZByovfn+/X8hL8oGUXjTdh4fo6P 9b2Y581sWO5vBQnSMgrUs8UejuYOYBHX8VavBBq6PttgpJXZMdUWOcH6g53+BJBnrB54Z 51Pr3BUzNuesnmoGdv2hs88cSt7gTWNlWkIYKoYRDADn77mMeJ9aK79BUO+AVHxmov6xQ L2sKEAi4emzuI6sEgCJHzds8/HhGBgC03ctnEtE9+1wAPMnQ+jgUch3zQsFoJVehVoQ== ARC-Message-Signature: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; c=relaxed/relaxed; t=1794633579; h=Received:DKIM-Signature:Message-ID:From:Subject:Reply-To:To:Cc: In-Reply-To:References:Content-Type:Content-Transfer-Encoding:Date; bh=CqK6LAzEHR6m7cruH/u2MLgHblxMLPEfHrzXGmNuLVM=; b=l/4nYxl2vx1cM14YHW4s419mOMXBJh3+gH1Zdlc8mI5ROW4HY/XGn0Va44AARWtic67I 3oReB1Ik4aNpZ/JKjob76spXi95mF0rZrp+TN9h9J+38vSev5pBxRXnpZ1RlGrp+Zo5kc Bar4f4ZLC52e9Xq0KgCM7UCKDwEeM6ncjsc3DV7VXejKEvldqvLJPTUe1sFGsZMKlkzLW yCrYN/9kJFPnn/L7BJHXIdsnIlV/+YwiMii+oLXavQ8qgalX5eA4vqBO6+0EnRKHungO2 zKK75azx2Ix+U1OlYgWpweFBHOo/MY7eeVSJUF50nhInuRsloeXVL/QUV6cxoZszjjQ== ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass header.d=kernel.org header.i=@kernel.org header.a=rsa-sha256 header.s=k20260515 header.b=jsMRFNLe; arc=none smtp.remote-ip=100.103.45.18 Received: from smtp.kernel.org (quasi.space.kernel.org [100.103.45.18]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (prime256v1)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 5B08D606A329 for ; Sat, 14 Nov 2026 05:19:39 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.a=rsa-sha256 header.s=k20260515 header.b=jsMRFNLe Received: by smtp.kernel.org (Postfix) with ESMTPSA id C47F61F000C4; Sat, 14 Nov 2026 05:19:38 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel.org; s=k20260515; t=1794633578; bh=CqK6LAzEHR6m7cruH/u2MLgHblxMLPEfHrzXGmNuLVM=; h=From:Subject:Reply-To:To:Cc:In-Reply-To:References:Date; b=jsMRFNLe/btokCP+78+R1sa5zNETa9klFXsNpxhl/VribUCYWo2rUHnb4luES7ajE X/irLdHrc2Q+AzqaULmrM2ZvVujeIjXDoOvfrn2Bqk1FIidNP65gfSdvU2ZCCTnLu1 Wz2Gqy+/88ET2v7w3NpUS6C62MJsYvDi2p6CTTGv+jrYhxGVWhFVgV2M70llLcBuNN 99Wc3uJUlvYIZJKnQGI8H9hopNm5OhMhYTg7hf+yzFpWN7EZVymQq/eUxxPCheWvXP S2OO2Q1nmX+ThnYSD7XS5qJ3y7u206mrf+eK1R6oPimsT+2bNrXe/Y36APA3/PPDvZ 9Hfup/e0WXQMw== Message-ID: From: sashiko-bot@kernel.org Subject: Re: [PATCH v7 4/4] perf test: Test lazy symbol name loading Reply-To: sashiko-reviews@lists.linux.dev To: "Alireza Haghdoost" Cc: linux-perf-users@vger.kernel.org In-Reply-To: <20261113-perf-symbol-memory-send-v7-4-d992eced9f9c@uber.com> References: <20261113-perf-symbol-memory-send-v7-0-d992eced9f9c@uber.com> <20261113-perf-symbol-memory-send-v7-4-d992eced9f9c@uber.com> Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable Date: Sat, 14 Nov 2026 05:19:38 +0000 X-Mailing-List: linux-perf-users@vger.kernel.org List-Id: List-Post: List-Help: List-Subscribe: List-Unsubscribe: List-Owner: Precedence: list > From: Alireza Haghdoost >=20 > Add a "Lazy symbol loading" unit test suite. It covers duplicate > selection without names, lazy names that take one or more reads or > cannot be read at all, lookups from several threads while another one > walks the symbols, eager and lazy parity on a real DSO (perf itself, or > the one given with --dso), and a symbol table file that is replaced > after the first name was read. >=20 > Add two shell tests. lazy_load_symbols_parity.sh runs the parity test > on four small binaries built for the loader's corner cases: split > debuginfo whose function section is NOBITS in the debug file, a shared > library with .dynsym-only symbols and aliases, a stripped library with > .gnu_debugdata, and on x86_64 an IFUNC behind an IRELATIVE PLT slot. > script_lazy_load_symbols.sh records a small callchain profile and checks > that perf script prints the same output with and without > --lazy-load-symbols. As root, it also checks that names are read from > the build-id cache when the profiled process is in another mount > namespace. >=20 > Both shell tests skip a case, rather than fail it, when the toolchain > produced a file whose names perf loads eagerly anyway (PPC64 ELFv1 .opd, > .gnu_debugdata or a compressed .strtab). >=20 > Signed-off-by: Alireza Haghdoost Sashiko has reviewed this patch and found no issues. --=20 Sashiko AI review =C2=B7 https://sashiko.dev/#/patchset/20261113-perf-symbo= l-memory-send-v7-0-d992eced9f9c@uber.com?part=3D4