Re: [OmniOS-discuss] OmniOS backup box hanging regularly
we’ve been using this, fired off by cron: https://github.com/MSU-iCER/puppet-zfs-auto-snapshot/blob/master/files/zfs-auto-snapshot.pl We manage it via puppet. It’s a bit of an older puppet module, but should still work. -Greg > On Oct 27, 2015, at 7:07 AM, Lauri Tirkkonen wrote: > > On Tue, Oct 27 2015 12:05:31 +0100, Jim Klimov wrote: >> Heh, in fact this OmniOS installation does not offer a time-slider, but >> rather the ksh93-based scripts for 'zfs/autosnapshot'. Now gotta verify what >> i run elsewhere;) > > I think OmniOS ships neither time-slider nor zfs-auto-snapshot. When we > used it I had to dig it out from somewhere in the interwebs and package > it :) > > -- > Lauri Tirkkonen | lotheac @ IRCnet > ___ > OmniOS-discuss mailing list > OmniOS-discuss@lists.omniti.com > http://lists.omniti.com/mailman/listinfo/omnios-discuss ___ OmniOS-discuss mailing list OmniOS-discuss@lists.omniti.com http://lists.omniti.com/mailman/listinfo/omnios-discuss
Re: [OmniOS-discuss] upgrade to 151014
> > The 1MB blocks are interesting to experiment with but I would not use them > without observing positive impact in real usage. > If you have an application that does IO in large blocks, the large block support in ZFS should make this faster. If your application only does small IOs (regardless of file size), then my recommendation would be to stick with the 128k record size. This was really added for things like Lustre on ZFS, which *really* likes 1MB IOs. Speaking as such a user, it is *awesome* and allows us to get much closer to the performance that the hardware is capable of. Large block sequential writes are massively improved when compared to ZFS with 128k record size. -Greg ___ OmniOS-discuss mailing list OmniOS-discuss@lists.omniti.com http://lists.omniti.com/mailman/listinfo/omnios-discuss
Re: [OmniOS-discuss] best or preferred 10g card for OmniOS
On Mar 26, 2015, at 12:24 PM, Doug Hughes wrote: > > any recommendations? We're having some pretty big problems with the > Solarflare card and driver dropping network under high load. We eliminated > LACP as a culprit, and the switch. > > Intel? Chelsio? other? I’ve had a pretty good experience with the Intel X520 cards, not really much I can complain about. -Greg ___ OmniOS-discuss mailing list OmniOS-discuss@lists.omniti.com http://lists.omniti.com/mailman/listinfo/omnios-discuss
Re: [OmniOS-discuss] Ang: Re: Ang: Re: infiniband
Enabling IB support for our ZFS-based filers is important enough to us that we have made the decision to migrate away from OmniOS/Illumos over to FreeBSD. FreeBSD 9 has a partial OFED stack, FreeBSD 10 is further along, and development continues for IB support in FreeBSD. I’ve successfully tested a Mellanox ConnectX-3 card on our FDR fabric on a FreeBSD 10.0-RELEASE system. This was with the subnet manager running on a Mellanox switch (which we regularly upgrade). If you’d like more details, please contact me off-list, I’m happy to share :) -Greg Greg Mason Michigan State University Institute for Cyber-Enabled Research High Performance Computing Center web: www.hpcc.msu.edu email: gma...@msu.edu > On Oct 24, 2014, at 11:35 AM, Ian Kaufman wrote: > > I wonder if Nexenta has added more/better support for IB? I believe > that Illumian 1.0 is finally out (after having run the Alpha for > years), and I know that they did have some interest in supporting IB > originally. If they have, then I would hope some of that support would > make it back upstream. > > Mayhaps I have an email to send out ... > > Ian > > On Fri, Oct 24, 2014 at 7:58 AM, Ian Kaufman wrote: >> I use a QLogic 12300 with SM built in. I haven't had any issues, >> saving my cluster frontend's cycles for other things. >> >> Ian >> >> On Fri, Oct 24, 2014 at 7:55 AM, Michael Rasmussen wrote: >>> On Fri, 24 Oct 2014 13:17:39 +0200 >>> Johan Kragsterman wrote: >>> >>>> >>>> Well, I can only find one person in that thread that BELIEVES that running >>>> SM on a switch is preferable to run OpenSM software. He hardly comes with >>>> any documentation of this, and I can't see any other that agrees... >>>> >>>> But of coarse, if you provide too little resources for OpenSM it will >>>> cause problems, or if you have any problems with the S/W or the >>>> configuration... >>>> >>> I think the issue here is that OpenSM is a single threaded application >>> so when the CPU which is assigned to it maxes out performance will >>> drop. So I guess it comes down to a trade-off between the >>> performance of the host CPU and the performance of the switch hardware. >>> >>> -- >>> Hilsen/Regards >>> Michael Rasmussen >>> >>> Get my public GnuPG keys: >>> michael rasmussen cc >>> http://pgp.mit.edu:11371/pks/lookup?op=get&search=0xD3C9A00E >>> mir datanom net >>> http://pgp.mit.edu:11371/pks/lookup?op=get&search=0xE501F51C >>> mir miras org >>> http://pgp.mit.edu:11371/pks/lookup?op=get&search=0xE3E80917 >>> -- >>> /usr/games/fortune -es says: >>> The default Magic Word, "Abracadabra", actually is a corruption of the >>> Hebrew phrase "ha-Bracha dab'ra" which means "pronounce the blessing". >>> >>> ___ >>> OmniOS-discuss mailing list >>> OmniOS-discuss@lists.omniti.com >>> http://lists.omniti.com/mailman/listinfo/omnios-discuss >>> >> >> >> >> -- >> Ian Kaufman >> Research Systems Administrator >> UC San Diego, Jacobs School of Engineering ikaufman AT ucsd DOT edu > > > > -- > Ian Kaufman > Research Systems Administrator > UC San Diego, Jacobs School of Engineering ikaufman AT ucsd DOT edu > ___ > OmniOS-discuss mailing list > OmniOS-discuss@lists.omniti.com > http://lists.omniti.com/mailman/listinfo/omnios-discuss ___ OmniOS-discuss mailing list OmniOS-discuss@lists.omniti.com http://lists.omniti.com/mailman/listinfo/omnios-discuss
Re: [OmniOS-discuss] OmniOS OpenSSL 1.0.1g and CVE-2014-0160
> > Theo, I am puzzled. I updated my box, and it did create a boot > environment with the fix in it, so I can't get it until I reboot... Maybe > I updated the wrong way? I did 'pkg image-update' which is how I usually > do things… Dan, If you simply do a “pkg install” or “pkg update” it will install the new OpenSSL package in the current BE. -Greg > > ___ > OmniOS-discuss mailing list > OmniOS-discuss@lists.omniti.com > http://lists.omniti.com/mailman/listinfo/omnios-discuss ___ OmniOS-discuss mailing list OmniOS-discuss@lists.omniti.com http://lists.omniti.com/mailman/listinfo/omnios-discuss
Re: [OmniOS-discuss] HCL: support Intel patsburg - C6xx - Sandy Bridge
I've been running some Sandy Bridge, Intel C602-based systems in production for a few months now. No issues, but I also am also only using LSI SAS2008-based HBAs, I'm not using the SATA or SAS ports provided by the chipset. Greg Mason HPC Systems Administrator Michigan State University High Performance Computing Center web: www.hpcc.msu.edu email: gma...@msu.edu aim: gma...@msu.edu phone: (517) 353-8666 On Mar 25, 2013, at 1:45 PM, srinivas jonn wrote: > > quick question on support for Intel sandy bridge chipsets: > > does anyone have success with running latest omniOS on Intel patsburg - ie > C6xx chipset? > > success has been reported against Intel C2xx - Cougar Point. > > Nexenta fully supports these, and Oracle Solaris 11 too > > but there is no mention in the official Illumos HCL > > the "device driver utility" on OI 151-A7 reported several unknown system > devices on Xeon E5-26xx server > > mostly the CPU QPI modules were reported "unknown" - does this mean any known > limitations? > > thank you. > ___ > OmniOS-discuss mailing list > OmniOS-discuss@lists.omniti.com > http://lists.omniti.com/mailman/listinfo/omnios-discuss ___ OmniOS-discuss mailing list OmniOS-discuss@lists.omniti.com http://lists.omniti.com/mailman/listinfo/omnios-discuss
