From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 48) id 773703858D38; Thu, 26 Jan 2023 07:07:01 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 773703858D38 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=sourceware.org; s=default; t=1674716821; bh=Bogud9B2k2s/sQRR4lKtOs80WtlZlp1zbO1vSAuq3+k=; h=From:To:Subject:Date:In-Reply-To:References:From; b=I+OJPaVCA1ksfRIyPeguXXScDMn8QPGXc0bx2OhWDrHUM8VvdJrznvFNQPd8Cwya2 /08udKirQ+pCA08aXWuG5HMR4yIWGYOE+kLuIWMbPllqsju9LvqZKwtYoe4T5FT9l6 VY+CfNWYVrRlc+4eQqE2LdyqBnfkSEIMLRKGK81U= From: "ville.heikkinen at nokia dot com" To: glibc-bugs@sourceware.org Subject: [Bug dynamic-link/27944] poor TLS performance in shared object after calling dlopen with another shared object that also contains TLS section Date: Thu, 26 Jan 2023 07:07:00 +0000 X-Bugzilla-Reason: CC X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: glibc X-Bugzilla-Component: dynamic-link X-Bugzilla-Version: 2.28 X-Bugzilla-Keywords: X-Bugzilla-Severity: normal X-Bugzilla-Who: ville.heikkinen at nokia dot com X-Bugzilla-Status: UNCONFIRMED X-Bugzilla-Resolution: X-Bugzilla-Priority: P2 X-Bugzilla-Assigned-To: unassigned at sourceware dot org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: cc Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable X-Bugzilla-URL: http://sourceware.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 List-Id: https://sourceware.org/bugzilla/show_bug.cgi?id=3D27944 Ville Heikkinen changed: What |Removed |Added ---------------------------------------------------------------------------- CC| |ville.heikkinen at nokia d= ot com --- Comment #2 from Ville Heikkinen --- I can confirm that we have hit this kind of issue while having a plugin interface that uses dlopen() to load dynamic libraries. This causes the TLS performance to degrade significantly. We've tested Dzmitry's patch and it s= eems to fix the issue. Could some of the maintainers check this bug and perhaps we could get the f= ix to the upstream? --=20 You are receiving this mail because: You are on the CC list for the bug.=