From owner-freebsd-dtrace@freebsd.org Fri Dec 7 13:09:48 2018 Return-Path: Delivered-To: freebsd-dtrace@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 4BFA3130D2DB for ; Fri, 7 Dec 2018 13:09:48 +0000 (UTC) (envelope-from eugene@zhegan.in) Received: from mailman.ysv.freebsd.org (mailman.ysv.freebsd.org [IPv6:2001:1900:2254:206a::50:5]) by mx1.freebsd.org (Postfix) with ESMTP id C439A8A77A for ; Fri, 7 Dec 2018 13:09:47 +0000 (UTC) (envelope-from eugene@zhegan.in) Received: by mailman.ysv.freebsd.org (Postfix) id 882F7130D2DA; Fri, 7 Dec 2018 13:09:47 +0000 (UTC) Delivered-To: dtrace@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 76A0B130D2D8 for ; Fri, 7 Dec 2018 13:09:47 +0000 (UTC) (envelope-from eugene@zhegan.in) Received: from elf.hq.norma.perm.ru (mail.norma.perm.ru [IPv6:2a00:7540:1::5]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client CN "mail.norma.perm.ru", Issuer "Vivat-Trade UNIX Root CA" (not verified)) by mx1.freebsd.org (Postfix) with ESMTPS id 9EF638A778 for ; Fri, 7 Dec 2018 13:09:43 +0000 (UTC) (envelope-from eugene@zhegan.in) Received: from bsdrookie.norma.com. (asterisk.enaza.ru [91.237.76.254] (may be forged)) by elf.hq.norma.perm.ru (8.15.2/8.15.2) with ESMTPS id wB7D9b1n071178 (version=TLSv1.2 cipher=DHE-RSA-AES128-SHA bits=128 verify=NO) for ; Fri, 7 Dec 2018 18:09:38 +0500 (+05) (envelope-from eugene@zhegan.in) To: dtrace@freebsd.org From: "Eugene M. Zheganin" Subject: iotop for iSCSI or zfs datasets Message-ID: <67bc8f0a-8702-c6ee-9d37-3a5064709126@zhegan.in> Date: Fri, 7 Dec 2018 18:09:37 +0500 User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:52.0) Gecko/20100101 Thunderbird/52.1.1 MIME-Version: 1.0 Content-Type: text/plain; charset=koi8-r; format=flowed Content-Transfer-Encoding: 7bit Content-Language: en-US X-Rspamd-Scan-Time: 0.76 X-Rspamd-Queue-Id: C439A8A77A X-Spamd-Result: default: False [-6.72 / 15.00]; ARC_NA(0.00)[]; R_SPF_FAIL(0.00)[-all]; RCVD_COUNT_FIVE(0.00)[5]; FORGED_RECIPIENTS_FORWARDING(0.00)[]; FROM_HAS_DN(0.00)[]; FORWARDED(0.00)[dtrace@mailman.ysv.freebsd.org]; NEURAL_HAM_MEDIUM(-1.00)[-1.000,0]; NEURAL_HAM_LONG(-1.00)[-1.000,0]; MIME_GOOD(-0.10)[text/plain]; TO_DN_NONE(0.00)[]; DMARC_NA(0.00)[zhegan.in]; SPF_FAIL_FORWARDING(0.00)[]; RCPT_COUNT_ONE(0.00)[1]; RCVD_IN_DNSWL_MED(-0.20)[5.0.0.0.0.5.0.0.0.0.0.0.0.0.0.0.a.6.0.2.4.5.2.2.0.0.9.1.1.0.0.2.list.dnswl.org : 127.0.9.2]; MX_GOOD(-0.01)[cached: mail-backup.zhegan.in]; NEURAL_HAM_SHORT(-0.97)[-0.965,0]; RCVD_NO_TLS_LAST(0.10)[]; FROM_EQ_ENVFROM(0.00)[]; R_DKIM_NA(0.00)[]; IP_SCORE(-3.55)[ip: (-9.87), ipnet: 2001:1900:2254::/48(-4.53), asn: 10310(-3.25), country: US(-0.09)]; ASN(0.00)[asn:10310, ipnet:2001:1900:2254::/48, country:US]; FORGED_RECIPIENTS(0.00)[dtrace@freebsd.org,freebsd-dtrace@freebsd.org]; MID_RHS_MATCH_FROM(0.00)[] X-Rspamd-Server: mx1.freebsd.org X-BeenThere: freebsd-dtrace@freebsd.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: "A discussion list for developers working on DTrace in FreeBSD." List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 07 Dec 2018 13:09:48 -0000 Hello, I have several iSCSI SAN systems running FreeBSD, and I need a tool to quickly determine which target/targets (and thus which initiator) are consuming most of iops. I can see that there are cfiscsi/iscsi probes in the FDT provider, and lots of zfs probes. Since my targets are using zvols as backends, both types will fir. I have some basic skills with dtrace, but in this case I totally lack documentation, so could you please point me to a direction (I'm not quite good at reading sources, but if that's the only way - you could point me to a specific part of the FreeBSD source tree I guess) to find the answer to a question "where can I find which probes/functions can I use to gather this data, including the argument list/types for them?" I was made aware that there's a ctlstat(8) utility, but it's not handy when it comes to hundreds of LUNs. I also can see the iotop in the context of network data transferred using trafshow, but this doesn't scale well to iops, and I would see reads/writes per second in terms that block devices use. Thanks. Eugene.