Date: Tue, 24 Mar 2015 14:13:10 -0400 From: Michael Jung <mikej@paymentallianceintl.com> To: "jg@internetx.com" <jg@internetx.com>, FreeBSD FS <freebsd-fs@freebsd.org>, "freebsd-hardware@freebsd.org" <freebsd-hardware@freebsd.org> Subject: RE: Zoned Commands ZBC/ZAC, Shingled SMR drives, ZFS Message-ID: <9C91F97841BC4347910F206618BAA3BB096D453FB6@PAIMAIL.pai.local> In-Reply-To: <5511A204.7020705@internetx.com> References: <CAD2Ti2_kQhnDL9nvdCT-zMG1bPeLSqTHemn%2B9hueRDLotmsLmw@mail.gmail.com> <CAPLK-i9OSv4ng-6Bwqc%2Byne%2BimDx_veOkwZij=hC1jLrE_ZUJw@mail.gmail.com> <CAFHbX1KLSuES8rJ1Nzho7g8kj-mD_vRAuCyYvdEK9xpz49QBZA@mail.gmail.com> <02F3A553C174554DA1D5EC7CEE9BDDD7011BC3E42B@loki.lvc.com> <5511A204.7020705@internetx.com>
next in thread | previous in thread | raw e-mail | index | archive | help
I understand there to be three different types of SMR drives: Device manage= d, Host aware and Host managed.=20 It is my belief that only 'Device managed' drives are shipping which any file system can use, but the file system has no mechanisms to=20 leverage or control the drives behavior hence they are not good candidates= =20 for any RAID like system. 'host aware' or 'host managed' SMR drives open the real possibilities for u= se under ZFS and other file systems. =20 I found these links of interest. Tim Feldman - Host-Aware SMR - OpenZFS Dev Summit 2014 https://www.youtube.com/watch?v=3Db1yqjV8qemU http://open-zfs.org/w/images/2/2a/Host-Aware_SMR-Tim_Feldman.pdf http://www.snia.org/sites/default/files/Dunn-Feldman_SNIA_Tutorial_Shingled= _Magnetic_Recording-r7_Final.pdf --mikej -----Original Message----- From: owner-freebsd-fs@freebsd.org [mailto:owner-freebsd-fs@freebsd.org] On= Behalf Of InterNetX - Juergen Gotteswinter Sent: Tuesday, March 24, 2015 1:42 PM To: FreeBSD FS; freebsd-hardware@freebsd.org Subject: Re: Zoned Commands ZBC/ZAC, Shingled SMR drives, ZFS The HGST He8 HDDs completed its rebuild in 19 hours and 46 minutes. The Seagate Archive HDDs completed their rebuild in 57 hours and 13 minutes this is ... a feature. right? Am 24.03.2015 um 18:05 schrieb Dale Kline: > READ THE DOCUMENTATION THOROUGHLY on these SMR drives. There are seriou= s WRITE restrictions on these drives because of the overlapping (shingled) = tracks. I have read over several times and am still not sure of all of the= caveats. As Tom states below, they are to be used mainly in "WRITE ONCE,= READ MANY" environments. >=20 > -----Original Message----- > From: owner-freebsd-hardware@freebsd.org [mailto:owner-freebsd-hardware@f= reebsd.org] On Behalf Of Tom Evans > Sent: Tuesday, March 24, 2015 12:39 PM > To: Shehbaz Jaffer > Cc: FreeBSD FS; grarpamp; freebsd-hardware@freebsd.org > Subject: Re: Zoned Commands ZBC/ZAC, Shingled SMR drives, ZFS >=20 > On Tue, Mar 24, 2015 at 12:47 PM, Shehbaz Jaffer <shehbazjaffer007@gmail.= com> wrote: >> Hi, >> >> I was wondering what cost advantage do SMR drive provide as compared=20 >> to normal CMR drive? >> >> 8TB SMR drive - $ 260 >> 3TB CMR (Conventional Magnetic Recording drive) - $ 105 >> >=20 > Purchase price is not irrelevant, but the key benefits are increased capa= city per disk, and reduced power usage per disk and (multiplied by the incr= ease in capacity) per TB. In other words, they disks consume less power, yo= u need fewer of them, maybe allowing you to run fewer servers. >=20 > Of course, you also need a mainly read only workload. The RAID rebuild te= st from the linked review is *scary*. I wouldn't use these in ZFS raidz wit= hout plenty of disaster recovery testing - how long does it take to re-silv= er the pool when you lose a disk and what is the performance characteristic= s of the pool whilst it is doing so. >=20 > Cheers >=20 > Tom > _______________________________________________ > freebsd-hardware@freebsd.org mailing list http://lists.freebsd.org/mailma= n/listinfo/freebsd-hardware > To unsubscribe, send any mail to "freebsd-hardware-unsubscribe@freebsd.or= g" > _______________________________________________ > freebsd-fs@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-fs > To unsubscribe, send any mail to "freebsd-fs-unsubscribe@freebsd.org" >=20 _______________________________________________ freebsd-fs@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-fs To unsubscribe, send any mail to "freebsd-fs-unsubscribe@freebsd.org" =0A= GoPai.com | Facebook.com/PaymentAlliance =20 CONFIDENTIALITY NOTE: This message is intended only for the use of the individual or entity to whom it is addressed and may=20 contain information that is privileged, confidential, and=20 exempt from disclosure under applicable law. If the reader=20 of this message is not the intended recipient, you are hereby=20 notified that any dissemination, distribution or copying=20 of this communication is strictly prohibited. If you have=20 received this transmission in error, please notify us by=20 telephone at (502) 212-4001 or notify us at PAI , Dept. 99,=20 6060 Dutchmans Lane, Suite 320, Louisville, KY 40205
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?9C91F97841BC4347910F206618BAA3BB096D453FB6>