From nobody Sat Dec 30 13:01:38 2023 X-Original-To: freebsd-fs@mlmmj.nyi.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1]) by mlmmj.nyi.freebsd.org (Postfix) with ESMTP id 4T2MrB51hpz558dV for ; Sat, 30 Dec 2023 13:03:38 +0000 (UTC) (envelope-from void@f-m.fm) Received: from wout3-smtp.messagingengine.com (wout3-smtp.messagingengine.com [64.147.123.19]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 4T2Mr95GYTz3LH7 for ; Sat, 30 Dec 2023 13:03:37 +0000 (UTC) (envelope-from void@f-m.fm) Authentication-Results: mx1.freebsd.org; dkim=pass header.d=f-m.fm header.s=fm2 header.b=H26TomIe; dkim=pass header.d=messagingengine.com header.s=fm2 header.b=Mbu3zUi5; spf=pass (mx1.freebsd.org: domain of void@f-m.fm designates 64.147.123.19 as permitted sender) smtp.mailfrom=void@f-m.fm; dmarc=pass (policy=none) header.from=f-m.fm Received: from compute6.internal (compute6.nyi.internal [10.202.2.47]) by mailout.west.internal (Postfix) with ESMTP id C50833200BE0 for ; Sat, 30 Dec 2023 08:03:35 -0500 (EST) Received: from imap46 ([10.202.2.96]) by compute6.internal (MEProxy); Sat, 30 Dec 2023 08:03:35 -0500 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=f-m.fm; h=cc :content-type:content-type:date:date:from:from:in-reply-to :in-reply-to:message-id:mime-version:references:reply-to:subject :subject:to:to; s=fm2; t=1703941415; x=1704027815; bh=5YvirWGhLB pVlAHRWhPk9Gmc42GTdoFxE9WeoyYGF/I=; b=H26TomIej+9/haHF/2Fb38ZRWm /xAmhZH08cIre/ZIETzAobkAnCn0s8zw044P7fVwBvB4BR2iT34YVWAkDilnf/iF jrR3ImRFzZ2VT5L9yOMwXXBwLP1ys0IO+H3rcchABEAL+/1NdrFDbiHRKTfRfHYr r99Dy7ZuZal8eI7tAxmkSGtJ6eJJsfURBCvh78JxnWcHQPz0qQbMBhlY08aGFGP6 ouTpVbF830zsuCvcbnmgNGHSxCEWLnKMdX18KJ1bg2gkY/b/waPkzKdqSklW2Y/8 jEvqkDxQbbesorNAfN8R1FLusmC54pChPnGgHJ9uO9Vo4CAasgCTpkT/GVYQ== DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=cc:content-type:content-type:date:date :feedback-id:feedback-id:from:from:in-reply-to:in-reply-to :message-id:mime-version:references:reply-to:subject:subject:to :to:x-me-proxy:x-me-proxy:x-me-sender:x-me-sender:x-sasl-enc; s= fm2; t=1703941415; x=1704027815; bh=5YvirWGhLBpVlAHRWhPk9Gmc42GT doFxE9WeoyYGF/I=; b=Mbu3zUi5p2R+fyJTvlWBxjZtTBZ658VxHODx6I5RbHtR daH1/wl/N/TixkSMhBMi6j6R1o36xXFJM5oCdxE3GY5Kpt0UIWLzFPmqPXRsNAZP QjKozF96fCshi9WIL7rBExkW9iWP/fORQfvVrpdqbE22/bl7Xj39YOVIdiweM5dF fi1C5gpZJuH73W1bd1ui1PDgZGQeebjJInbes18cNvIXyIbOf96YgOcu3j8iACk0 CUg/YCh9vGzN7W1rHVyxIA8KYUZTl0l1pTSZv53xaWGz5BjykltUOZ9CuYfqn692 K1CH+mvUIcQwEGbGaQmuPNUDubYxNrixKx9oLGdoDA== X-ME-Sender: X-ME-Proxy-Cause: gggruggvucftvghtrhhoucdtuddrgedvkedrvdefhedggeekucetufdoteggodetrfdotf fvucfrrhhofhhilhgvmecuhfgrshhtofgrihhlpdfqfgfvpdfurfetoffkrfgpnffqhgen uceurghilhhouhhtmecufedttdenucenucfjughrpefofgggkfgjfhffhffvufgtsehttd ertderredtnecuhfhrohhmpehvohhiugcuoehvohhiugesfhdqmhdrfhhmqeenucggtffr rghtthgvrhhnpeeiieehuedtudeikeduieekvdffgefgfeevvdefheffgedutdehtdetvd fhveekhfenucffohhmrghinhepfhhrvggvsghsugdrohhrghenucevlhhushhtvghrufhi iigvpedtnecurfgrrhgrmhepmhgrihhlfhhrohhmpehvohhiugesfhdqmhdrfhhm X-ME-Proxy: Feedback-ID: i2541463c:Fastmail Received: by mailuser.nyi.internal (Postfix, from userid 501) id 0BA022A2008B; Sat, 30 Dec 2023 08:03:35 -0500 (EST) X-Mailer: MessagingEngine.com Webmail Interface User-Agent: Cyrus-JMAP/3.9.0-alpha0-1364-ga51d5fd3b7-fm-20231219.001-ga51d5fd3 List-Id: Filesystems List-Archive: https://lists.freebsd.org/archives/freebsd-fs List-Help: List-Post: List-Subscribe: List-Unsubscribe: Sender: owner-freebsd-fs@freebsd.org MIME-Version: 1.0 Message-Id: In-Reply-To: <0D486016-8806-414F-B7F9-66519E8B0EBC@yahoo.com> References: <0D486016-8806-414F-B7F9-66519E8B0EBC.ref@yahoo.com> <0D486016-8806-414F-B7F9-66519E8B0EBC@yahoo.com> Date: Sat, 30 Dec 2023 13:01:38 +0000 From: void To: freebsd-fs Subject: Re: measuring swap partition speed Content-Type: text/plain X-Spamd-Result: default: False [-4.49 / 15.00]; NEURAL_HAM_MEDIUM(-1.00)[-1.000]; NEURAL_HAM_LONG(-1.00)[-1.000]; NEURAL_HAM_SHORT(-1.00)[-1.000]; DMARC_POLICY_ALLOW(-0.50)[f-m.fm,none]; RWL_MAILSPIKE_EXCELLENT(-0.40)[64.147.123.19:from]; R_DKIM_ALLOW(-0.20)[f-m.fm:s=fm2,messagingengine.com:s=fm2]; R_SPF_ALLOW(-0.20)[+ip4:64.147.123.19]; MIME_GOOD(-0.10)[text/plain]; RCVD_IN_DNSWL_LOW(-0.10)[64.147.123.19:from]; XM_UA_NO_VERSION(0.01)[]; TO_MATCH_ENVRCPT_ALL(0.00)[]; RCVD_TLS_LAST(0.00)[]; PREVIOUSLY_DELIVERED(0.00)[freebsd-fs@freebsd.org]; FROM_HAS_DN(0.00)[]; ARC_NA(0.00)[]; FREEMAIL_ENVFROM(0.00)[f-m.fm]; ASN(0.00)[asn:29838, ipnet:64.147.123.0/24, country:US]; TO_DN_ALL(0.00)[]; RCVD_COUNT_THREE(0.00)[3]; FREEMAIL_FROM(0.00)[f-m.fm]; DWL_DNSWL_NONE(0.00)[messagingengine.com:dkim]; DKIM_TRACE(0.00)[f-m.fm:+,messagingengine.com:+]; MIME_TRACE(0.00)[0:+]; FROM_EQ_ENVFROM(0.00)[]; RCPT_COUNT_ONE(0.00)[1]; MLMMJ_DEST(0.00)[freebsd-fs@freebsd.org] X-Rspamd-Queue-Id: 4T2Mr95GYTz3LH7 X-Spamd-Bar: ---- On Thu, 28 Dec 2023, at 14:07, Mark Millard wrote: > Could you produce the same sort of report (gstat -spod > and such included) for the arm64 context? The direct > (well matched) comparison/contrast to amd64 could prove > of interest to folks that work on arm64 support. Differences between last lot of tests and this lot: arm64 context stable/14-n266030-e615bcd32171 boots from microsd hd is ufs swap is an entire 12gb slice I noticed a couple of things additionally 1. when the 'swap slowdown' happened, in the gstat -spod output the % busy for da0 dropped to single figures. 2. when the test starts, it's as quick as can be expected. There's not much slowdown while git is 'receiving objects'. But in the next phase, when it's 'resolving deltas', the 'swap writing speed' drops from 10-15Mb/s to less than a tenth of that. It's the *degree* of slowdown that's the problem. Maybe 'resolving deltas' and 'find / blah' are analogous in terms of disk & swap reads/writes. Observation is that it's not heavy writes causing the problem, it's more like 'looking at files and comparing $something'. It makes no noticeable difference if atime is on or off. It was off on everything apart from /var/mail until wiping the system. At the moment, atime is however it defaults to. reasonably quick at first root@generic:~ # gstat -spod dT: 1.028s w: 1.000s L(q) ops/s r/s kB kBps ms/r w/s kB kBps ms/w d/s kB kBps ms/d o/s ms/o %busy Name 0 0 0 0 0 0.0 0 0 0 0.0 0 0 0 0.0 0 0.0 0.0| mmcsd0 1 1535 0 0 0 0.0 1535 11 17226 0.6 0 0 0 0.0 0 0.0 71.2| da0 root@generic:~ # dd if=/dev/urandom of=/dev/da0p2 bs=8k conv=sync status=progress ^C6489980928 bytes (6490 MB, 6189 MiB) transferred 532.008s, 12 MB/s 792389+0 records in 792388+0 records out 6491242496 bytes transferred in 532.733201 secs (12184791 bytes/sec) running the swapfile write test while 'resolving deltas' root@generic:~ # gstat -spod dT: 1.003s w: 1.000s L(q) ops/s r/s kB kBps ms/r w/s kB kBps ms/w d/s kB kBps ms/d o/s ms/o %busy Name 0 0 0 0 0 0.0 0 0 0 0.0 0 0 0 0.0 0 0.0 0.0| mmcsd0 0 45 0 0 0 0.0 45 8 359 0.5 0 0 0 0.0 0 0.0 2.1| da0 root@generic:~ # dd if=/dev/urandom of=/dev/da0p2 bs=8k conv=sync status=progress ^C2108448768 bytes (2108 MB, 2011 MiB) transferred 338.007s, 6238 kB/s 257380+0 records in 257379+0 records out 2108448768 bytes transferred in 338.032562 secs (6237413 bytes/sec) root@generic:~ # dd if=/dev/urandom of=/dev/da0p2 bs=8k conv=sync status=progress you have mail ^C317849600 bytes (318 MB, 303 MiB) transferred 336.036s, 946 kB/s 38907+0 records in 38906+0 records out 318717952 bytes transferred in 336.805322 secs (946297 bytes/sec) ############### root@generic:/mnt1-fbsd-ufs # date && time -l git clone https://git.freebsd.org/src.git Thu Dec 28 17:04:27 UTC 2023 Cloning into 'src'... remote: Enumerating objects: 4440009, done. remote: Counting objects: 100% (383231/383231), done. remote: Compressing objects: 100% (28796/28796), done. remote: Total 4440009 (delta 377522), reused 354435 (delta 354435), pack-reused 4056778 Receiving objects: 100% (4440009/4440009), 1.59 GiB | 3.38 MiB/s, done. Resolving deltas: 100% (3528665/3528665), done. Checking objects: 100% (16777216/16777216), done. Updating files: 100% (97320/97320), done. 2049.63 real 2210.75 user 178.10 sys 1077200 maximum resident set size 2333 average shared memory size 211 average unshared data size 128 average unshared stack size 470060 page reclaims 186 page faults 0 swaps 2176 block input operations 2747 block output operations 426413 messages sent 1188099 messages received 1978 signals received 1244606 voluntary context switches 6331454 involuntary context switches root@generic:/mnt1-fbsd-ufs # root@generic:/mnt1-fbsd-ufs # date && time -l git clone https://git.freebsd.org/ports.git you have mail Thu Dec 28 17:04:31 UTC 2023 Cloning into 'ports'... remote: Enumerating objects: 6048197, done. remote: Counting objects: 100% (961/961), done. remote: Compressing objects: 100% (144/144), done. remote: Total 6048197 (delta 926), reused 830 (delta 817), pack-reused 6047236 Receiving objects: 100% (6048197/6048197), 1.16 GiB | 3.11 MiB/s, done. Resolving deltas: 100% (3651525/3651525), done. Checking objects: 100% (16777216/16777216), done. Updating files: 100% (157074/157074), done. 3400.64 real 3584.20 user 191.39 sys 1265592 maximum resident set size 2373 average shared memory size 216 average unshared data size 128 average unshared stack size 890112 page reclaims 162 page faults 0 swaps 7535 block input operations 3006 block output operations 283569 messages sent 868282 messages received 3293 signals received 1670707 voluntary context switches 9390334 involuntary context switches root@generic:/mnt1-fbsd-ufs #