From nobody Tue Mar 5 09:09:05 2024 X-Original-To: freebsd-hackers@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 4TpqWJ6Q8Vz5CF3C for ; Tue, 5 Mar 2024 09:09:16 +0000 (UTC) (envelope-from kpielorz_lst@tdx.co.uk) Received: from smtp.krpservers.com (smtp.krpservers.com [62.13.128.145]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client CN "*.krpservers.com", Issuer "RapidSSL TLS RSA CA G1" (not verified)) by mx1.freebsd.org (Postfix) with ESMTPS id 4TpqWH02fyz4PD2 for ; Tue, 5 Mar 2024 09:09:14 +0000 (UTC) (envelope-from kpielorz_lst@tdx.co.uk) Authentication-Results: mx1.freebsd.org; dkim=pass header.d=tdx.co.uk header.s=krpdkim header.b="oXFj9/5D"; dmarc=pass (policy=none) header.from=tdx.co.uk; spf=pass (mx1.freebsd.org: domain of kpielorz_lst@tdx.co.uk designates 62.13.128.145 as permitted sender) smtp.mailfrom=kpielorz_lst@tdx.co.uk Received: from [10.12.30.106] by smtp.krpservers.com (8.16.1/8.15.2) with ESMTPSA id 425995Ku044207 (version=TLSv1 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Tue, 5 Mar 2024 09:09:06 GMT DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=tdx.co.uk; s=krpdkim; t=1709629746; bh=QsMieM61cVTrtlgHWh8Op2TDKf1m3Jognn4jMHsBwVQ=; h=Date:From:To:Subject; b=oXFj9/5D1wUEfO5uuPpozYPlddyA0SJwyXu/3oG0Z7NCJoJ3Uy9fdGd9k31o4SipC 180sA5+TBnBKvZsUF6x2d/4MDuIgjWt7Ktl46QW+aWhygMG9xzAo+0fe/lEK2qDVW/ nwMZmCu4WYtMJMm+WucqWdyuKBjH931BIYraeunHY55mBm2wPlB/MzdIzxRaqgXCFu gUMaaPN18Gg0CwO/rUIGvOrNKPaQxLZ/RPvB+KIfxas9CUAOecmVd267RLc7/u19D1 8qULH/erFZl31e/RPc5X3GD5VJ1hwkiMnTjzDXs8v1IBSoEOAeo9D8snIN4hkGn2m/ VqmkM83wXuMfw== Date: Tue, 05 Mar 2024 09:09:05 +0000 From: Karl Pielorz To: Mark Millard , FreeBSD Hackers Subject: Re: ... was killed: a thread waited too long to allocate a page [actually: was killed: failed to reclaim memory problem] Message-ID: <6426C1F92FAEEB4E74A29F7D@[10.12.30.106]> In-Reply-To: References: X-Mailer: Mulberry/4.0.8 (Win32) List-Id: Technical discussions relating to FreeBSD List-Archive: https://lists.freebsd.org/archives/freebsd-hackers List-Help: List-Post: List-Subscribe: List-Unsubscribe: Sender: owner-freebsd-hackers@freebsd.org MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline X-Spamd-Bar: --- X-Spamd-Result: default: False [-3.40 / 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)[tdx.co.uk,none]; MID_RHS_IP_LITERAL(0.50)[]; R_SPF_ALLOW(-0.20)[+a:smtp.krpservers.com]; R_DKIM_ALLOW(-0.20)[tdx.co.uk:s=krpdkim]; MIME_GOOD(-0.10)[text/plain]; ONCE_RECEIVED(0.10)[]; ARC_NA(0.00)[]; MIME_TRACE(0.00)[0:+]; ASN(0.00)[asn:60969, ipnet:62.13.128.0/22, country:GB]; RCVD_COUNT_ONE(0.00)[1]; RCVD_VIA_SMTP_AUTH(0.00)[]; RCVD_TLS_ALL(0.00)[]; FREEMAIL_TO(0.00)[yahoo.com,freebsd.org]; MLMMJ_DEST(0.00)[freebsd-hackers@freebsd.org]; FROM_HAS_DN(0.00)[]; RCPT_COUNT_TWO(0.00)[2]; FROM_EQ_ENVFROM(0.00)[]; TO_DN_ALL(0.00)[]; TO_MATCH_ENVRCPT_SOME(0.00)[]; DKIM_TRACE(0.00)[tdx.co.uk:+] X-Rspamd-Queue-Id: 4TpqWH02fyz4PD2 --On 01 February 2024 08:30 -0800 Mark Millard wrote: > One direction of control is . . . > > What do you have for ( copied from my /boot/loader.conf ): > ># ># Delay when persistent low free RAM leads to ># Out Of Memory killing of processes: > vm.pageout_oom_seq=120 > > The default is 12 (last I knew, anyway). > > The 120 figure has allowed me and others to do buildworld, > buildkernel, and poudriere bulk runs on small arm boards > using all cores that otherwise got "failed to reclaim > memory" (to use the modern, improved [not misleading] > message text). Similarly for others that had other kinds > of contexts that got the message. Ok, as hopefully a final follow up after some weeks - thanks to those that posted replies, and having made the change above: vm.pageout_oom_seq=120 This seems to have cured the issue, at least for us. Reading through other replies / posts - it looks like most things these days, there's a number of different ways you could try and tackle this - but the above (as the first thing we did) seems to have fixed it. Slightly concerning that an otherwise 32G system w/ZFS, that I would call 'lightly loaded' can run into this issue (and only since going to 13.2) - but there you go :) I can't remember the last time I had to 'tweak' anything with FreeBSD - so I can't complain really. -Karl