From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by smtp.lore.kernel.org (Postfix) with ESMTP id 2FA93C02198 for ; Thu, 13 Feb 2025 02:57:36 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id 99F5C6B008C; Wed, 12 Feb 2025 21:57:35 -0500 (EST) Received: by kanga.kvack.org (Postfix, from userid 40) id 94C3F6B0092; Wed, 12 Feb 2025 21:57:35 -0500 (EST) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 813F56B0093; Wed, 12 Feb 2025 21:57:35 -0500 (EST) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (smtprelay0015.hostedemail.com [216.40.44.15]) by kanga.kvack.org (Postfix) with ESMTP id 6358E6B008C for ; Wed, 12 Feb 2025 21:57:35 -0500 (EST) Received: from smtpin04.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay02.hostedemail.com (Postfix) with ESMTP id E18C51201E1 for ; Thu, 13 Feb 2025 02:57:34 +0000 (UTC) X-FDA: 83113410828.04.366B08F Received: from out-175.mta1.migadu.com (out-175.mta1.migadu.com [95.215.58.175]) by imf10.hostedemail.com (Postfix) with ESMTP id E6057C0006 for ; Thu, 13 Feb 2025 02:57:32 +0000 (UTC) Authentication-Results: imf10.hostedemail.com; dkim=pass header.d=linux.dev header.s=key1 header.b=u1drbhpy; spf=pass (imf10.hostedemail.com: domain of yosry.ahmed@linux.dev designates 95.215.58.175 as permitted sender) smtp.mailfrom=yosry.ahmed@linux.dev; dmarc=pass (policy=none) header.from=linux.dev ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1739415453; h=from:from:sender:reply-to:subject:subject:date:date: message-id:message-id:to:to:cc:cc:mime-version:mime-version: content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references:dkim-signature; bh=NmWV5qLBGFJ380Q636JbOBAatzAC28wVNjP4Bc1s1jY=; b=jScYcbe4Ka55motkL0pU9CXjP8B4sVrPB80hTfQpiy33dCc1uDoRrmaFl/vnbQnRnkKiK8 OZilDKxEgGkF/R4Ef0ou0dBmLoI4/95sJJ0wkhL9EbipO7uz+5h9Es7WuisElQrDIpeUDa mRoQMd/blbbhe4P4khj+iRjQeEMs5T4= ARC-Authentication-Results: i=1; imf10.hostedemail.com; dkim=pass header.d=linux.dev header.s=key1 header.b=u1drbhpy; spf=pass (imf10.hostedemail.com: domain of yosry.ahmed@linux.dev designates 95.215.58.175 as permitted sender) smtp.mailfrom=yosry.ahmed@linux.dev; dmarc=pass (policy=none) header.from=linux.dev ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1739415453; a=rsa-sha256; cv=none; b=YALegAJB6Nl7/XWC18kmYUsQU3lCZArq/7UDeOUP4b4psv+zEIiX0IzzXif2BQkdSO5ILx 7kMlIYslzeC6xRUb6y1qvlBMJBr0tNIie6ELDLPIuwUDprF4HupmgryTRybTpUqmEf9rP7 QWpu4dcxnSX2LXVDhTOrm/E2UFS0D4g= MIME-Version: 1.0 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.dev; s=key1; t=1739415450; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=NmWV5qLBGFJ380Q636JbOBAatzAC28wVNjP4Bc1s1jY=; b=u1drbhpyXca+ZGXrN2eKhW797pCKeYFtckSmOgpaly4XqfrUi0RKF0Zi8FCQpWkVWcqLRG wOdHIVDU29LKTCRpasCW+6ns0+bLvOaOi7ssmTz9Aax8GpIqgTGkswExqdQMYk8dCeCo42 HxSa1vj8ZjeGQdz/cjFa6wCr/yF6J0o= Date: Thu, 13 Feb 2025 02:57:28 +0000 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable X-Report-Abuse: Please report any abuse attempt to abuse@migadu.com and include these headers. From: "Yosry Ahmed" Message-ID: <25268fbedb82a06ba0c13e2c490b164846ef508b@linux.dev> TLS-Required: No Subject: Re: [PATCHv4 14/17] zsmalloc: make zspage lock preemptible To: "Sergey Senozhatsky" Cc: "Sergey Senozhatsky" , "Andrew Morton" , "Minchan Kim" , linux-mm@kvack.org, linux-kernel@vger.kernel.org, "Kairui Song" In-Reply-To: References: <6vtpamir4bvn3snlj36tfmnmpcbd6ks6m3sdn7ewmoles7jhau@nbezqbnoukzv> <6uhsj4bckhursiblkxe54azfgyqal6tq2de3lpkxw6omkised6@uylodcjruuei> X-Migadu-Flow: FLOW_OUT X-Rspam-User: X-Rspamd-Server: rspam11 X-Rspamd-Queue-Id: E6057C0006 X-Stat-Signature: turxnwmkogxroahrj8euiitb9z9xxaci X-HE-Tag: 1739415452-482743 X-HE-Meta: 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 TP3nx6Uq pgf/9JqYI5ncG8GEaJVutGhXjRdUOunMaRnm0q0pAMEMVWUuVO2Z7ckKdqagwb4wPqiOOLFbo8sQOLqkBxg78RZA5LXfCd8EHXkoSFRPUb7g987wP09QFf0DVcgspnD8Guo9YvL4xbAOUMWIY3RuKd0cciutXGGpBQ/ZqVQtICDHT9YHoCr48Yhfln9tavk/NiHLcOAqrkBPWziU= X-Bogosity: Ham, tests=bogofilter, spamicity=0.000000, version=1.2.4 Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: List-Subscribe: List-Unsubscribe: February 12, 2025 at 6:18 PM, "Sergey Senozhatsky" wrote: >=20 >=20On (25/02/12 15:35), Yosry Ahmed wrote: >=20 >=20>=20 >=20> Difference at 95.0% confidence > >=20 >=20> -1.03219e+08 +/- 55308.7 > >=20 >=20> -27.9705% +/- 0.0149878% > >=20 >=20> (Student's t, pooled s =3D 58864.4) > >=20 >=20>=20=20 >=20>=20 >=20> Thanks for sharing these results, but I wonder if this will captur= e > >=20 >=20> regressions from locking changes (e.g. a lock being preemtible)? I= IUC > >=20 >=20> this is counting the instructions executed in these paths, and tha= t > >=20 >=20> won't change if the task gets preempted. Lock contention may be ca= ptured > >=20 >=20> as extra instructions, but I am not sure we'll directly see its ef= fect > >=20 >=20> in terms of serialization and delays. > >=20 >=20 > Yeah.. >=20 >=20>=20 >=20> I think we also need some high level testing (e.g. concurrent > >=20 >=20> swapins/swapouts) to find that out. I think that's what Kairui's t= esting > >=20 >=20> covers. > >=20 >=20 > I do a fair amount of high-level testing: heavy parallel (make -j36 and >=20 >=20parallel dd) workloads (multiple zram devices configuration - zram0 e= xt4, >=20 >=20zram1 writeback device, zram2 swap) w/ and w/o lockdep. In addition I= also >=20 >=20run these workloads under heavy memory pressure (a 4GB VM), when oom-= killer >=20 >=20starts to run around with a pair of scissors. But it's mostly regress= ion >=20 >=20testing. > If we can get some numbers from these parallel workloads that would be be= tter than the perf stats imo.