From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Jason@zx2c4.com Received: from krantz.zx2c4.com (localhost [127.0.0.1]) by krantz.zx2c4.com (ZX2C4 Mail Server) with ESMTP id c3464ab4 for ; Wed, 20 Jun 2018 23:42:32 +0000 (UTC) Received: from frisell.zx2c4.com (frisell.zx2c4.com [192.95.5.64]) by krantz.zx2c4.com (ZX2C4 Mail Server) with ESMTP id 9ae5d931 for ; Wed, 20 Jun 2018 23:42:32 +0000 (UTC) Received: by frisell.zx2c4.com (ZX2C4 Mail Server) with ESMTP id 2660062f for ; Wed, 20 Jun 2018 23:41:19 +0000 (UTC) Received: by frisell.zx2c4.com (ZX2C4 Mail Server) with ESMTPSA id 55f062b0 (TLSv1.2:ECDHE-RSA-AES128-GCM-SHA256:128:NO) for ; Wed, 20 Jun 2018 23:41:18 +0000 (UTC) Received: by mail-ot0-f179.google.com with SMTP id a5-v6so1475723otf.12 for ; Wed, 20 Jun 2018 16:47:22 -0700 (PDT) MIME-Version: 1.0 References: <8B706799-0A06-449B-960B-08C017C58412@lonnie.abelbeck.com> <981DB695-E660-431D-B5E9-ABD2D1352F9F@lonnie.abelbeck.com> In-Reply-To: <981DB695-E660-431D-B5E9-ABD2D1352F9F@lonnie.abelbeck.com> From: "Jason A. Donenfeld" Date: Thu, 21 Jun 2018 01:47:10 +0200 Message-ID: Subject: Re: [ANNOUNCE] WireGuard Snapshot `0.0.20180620` Available To: Lonnie Abelbeck Content-Type: text/plain; charset="UTF-8" Cc: WireGuard mailing list List-Id: Development discussion of WireGuard List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Hey Lonnie, Thanks for helping to debug this. On Thu, Jun 21, 2018 at 12:37 AM Lonnie Abelbeck wrote: > Hunk #1 only does the trick, though performance is ever so slightly slowe= r than before overall. It's good to hear that hunks #2 and #3 don't have much an effect, though it does still seem to have _some_ effect. Looks like hunk 1 is rather worrisome though. Can you try out https://=D7=90.cc/eaxxpxbB and let me know if it has any effect? > Is this issue because our project uses CONFIG_PREEMPT=3Dy ? Yes, generally, preemption is good for latency but bad for throughput. I was trying to make the queues a bit more preemption friendly, but this seemed to have killed performance, so I'll be revisiting this, because I don't want to make things worse than before. I find it very strange that 20180531 is still faster than the last patch I sent you. The only other difference along the hot path, besides the last patch I sent you, between the two snapshots is https://git.zx2c4.com/WireGuard/patch/?id=3Db7b193f499d4acd8a620163ec358c08= 30e856c9e and this is _removing_ code, so I'd think this would actually contribute to a speed increase, not a slight decrease. Are you sure the benchmark conditions were the same in other respects? Jason