From nobody Fri Mar 01 19:38:50 2024 X-Original-To: freebsd-stable@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 4Tmdgq0nxdz5CwjL for ; Fri, 1 Mar 2024 19:39:03 +0000 (UTC) (envelope-from juraj@lutter.sk) Received: from ns2.wilbury.net (ns2.wilbury.net [IPv6:2a01:b200:0:1:f816:3eff:fecd:13e6]) (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-signature ECDSA (P-256) client-digest SHA256) (Client CN "svc.wilbury.net", Issuer "R3" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 4Tmdgp2tjTz4lBf for ; Fri, 1 Mar 2024 19:39:02 +0000 (UTC) (envelope-from juraj@lutter.sk) Authentication-Results: mx1.freebsd.org; dkim=none; dmarc=pass (policy=none) header.from=lutter.sk; spf=pass (mx1.freebsd.org: domain of juraj@lutter.sk designates 2a01:b200:0:1:f816:3eff:fecd:13e6 as permitted sender) smtp.mailfrom=juraj@lutter.sk Received: from smtpclient.apple (gw-upc.owhome.net [188.167.168.254]) (Authenticated sender: juraj@lutter.sk) by svc.wilbury.net (Postfix) with ESMTPSA id 95B1261F91 for ; Fri, 1 Mar 2024 20:39:00 +0100 (CET) From: Juraj Lutter Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable List-Id: Production branch of FreeBSD source code List-Archive: https://lists.freebsd.org/archives/freebsd-stable List-Help: List-Post: List-Subscribe: List-Unsubscribe: Sender: owner-freebsd-stable@freebsd.org X-BeenThere: freebsd-stable@freebsd.org Mime-Version: 1.0 (Mac OS X Mail 16.0 \(3774.400.31\)) Subject: Re: CPU hog in vnlru and arc_prune on 13-STABLE Date: Fri, 1 Mar 2024 20:38:50 +0100 References: To: FreeBSD stable In-Reply-To: Message-Id: <71A074C6-6C33-45BA-A42C-B176DEF909EF@lutter.sk> X-Mailer: Apple Mail (2.3774.400.31) X-Spamd-Bar: --- X-Spamd-Result: default: False [-3.69 / 15.00]; NEURAL_HAM_LONG(-1.00)[-1.000]; NEURAL_HAM_MEDIUM(-1.00)[-1.000]; NEURAL_HAM_SHORT(-0.99)[-0.992]; DMARC_POLICY_ALLOW(-0.50)[lutter.sk,none]; R_SPF_ALLOW(-0.20)[+ip6:2a01:b200:0:1:f816:3eff:fecd:13e6:c]; ONCE_RECEIVED(0.10)[]; MIME_GOOD(-0.10)[text/plain]; ARC_NA(0.00)[]; ASN(0.00)[asn:44185, ipnet:2a01:b200::/32, country:SK]; MIME_TRACE(0.00)[0:+]; RCVD_COUNT_ONE(0.00)[1]; RCVD_VIA_SMTP_AUTH(0.00)[]; APPLE_MAILER_COMMON(0.00)[]; MID_RHS_MATCH_FROM(0.00)[]; R_DKIM_NA(0.00)[]; FROM_EQ_ENVFROM(0.00)[]; FROM_HAS_DN(0.00)[]; RCPT_COUNT_ONE(0.00)[1]; TO_MATCH_ENVRCPT_ALL(0.00)[]; TO_DN_ALL(0.00)[]; PREVIOUSLY_DELIVERED(0.00)[freebsd-stable@freebsd.org]; MLMMJ_DEST(0.00)[freebsd-stable@freebsd.org]; RCVD_TLS_ALL(0.00)[] X-Rspamd-Queue-Id: 4Tmdgp2tjTz4lBf > On 1 Mar 2024, at 20:19, Juraj Lutter wrote: >=20 > Hi, >=20 > I have a fresh (git b9880e247b26) 13.3-STABLE running in bhyve with 2 = vCPU and 10G of RAM. >=20 > I=E2=80=99ve put some load on it (building lang/rust from ports = outside poudriere, using make -j2) and the system > started to respond very slowly. >=20 > I did break the make process and I was able to look into top where = there was: >=20 > PID USERNAME PRI NICE SIZE RES STATE C TIME WCPU = COMMAND > 0 root -8 - 0B 1808K CPU1 1 35:53 99.79% = kernel{arc_prune} > 15 root 20 - 0B 16K RUN 0 34:19 99.35% = vnlru >=20 > The high CPU usage remains even after 30 minutes after the make was = stopped. >=20 > How can I narrow down the root cause? For the record, the kernel is = GENERIC. After manually issuing =E2=80=9Csync=E2=80=9D, the CPU hog stopped and = the machine is responding normally now. It still remains unclear to me why that situation could happen, though. =E2=80=94 Juraj Lutter XMPP: juraj (at) lutter.sk GSM: +421907986576