From: Valeri G. <ga...@ki...> - 2016-04-27 20:37:13
|
Thank you, gentlemen! Valeri On Wed, April 27, 2016 1:44 pm, Piotr Robert Konopelko wrote: > Dear Valeri, > > I'd like to let you know, that we've just released MooseFS 2.0.89 with > fix. > > Corresponding commit: > https://github.com/moosefs/moosefs/commit/b0125cf44cb40cc48d5b730088180654a0c8329c > <https://github.com/moosefs/moosefs/commit/b0125cf44cb40cc48d5b730088180654a0c8329c> > > > You can download it as follows: > > Packages for FreeBSD - from our website: > https://moosefs.com/download/freebsd.html > <https://moosefs.com/download/freebsd.html> > Sources - from our website: https://moosefs.com/download/sources.html > <https://moosefs.com/download/sources.html> > Sources - from GitHub: https://github.com/moosefs/moosefs/tree/2.0.x > <https://github.com/moosefs/moosefs/tree/2.0.x> > > > I'm going to update official ports in FreeBSD ports collection today, so > they should be available in a few days. > > Best regards, > > -- > > <https://moosefs.com/> > Piotr Robert Konopelko > MooseFS Technical Support Engineer > e-mail : pio...@mo... <mailto:pio...@mo...> > www : https://moosefs.com <https://moosefs.com/> > <https://twitter.com/MooseFS> <https://www.facebook.com/moosefs> > <https://www.linkedin.com/company/moosefs> > <https://github.com/moosefs> > > This email and any files transmitted with it are confidential and intended > solely for the use of the individual or entity to whom they are addressed. > If you have received it by mistake, please let us know by e-mail reply and > delete it from your system; you may not copy this message or disclose its > contents to anyone. Finally, the recipient should check this email and any > attachments for the presence of viruses. Core Technology accepts no > liability for any damage caused by any virus transmitted by this email. > > >> On 27 Apr 2016, at 2:58 PM, Aleksander Wieliczko >> <ale...@mo...> wrote: >> >> Hi Valeri, >> >> I would like to tell you that this strange behaviour is connected with >> FreeBSD kernel not with MooseFS. >> >> Mainly FreeBSD kernel sending setattr command before first close. >> Today we will publish MooseFS 2.0.89 packages with fix for FreeBSD >> kernel. >> >> After upgrade please let us know if all is working correctly. >> >> Best regards >> Aleksander Wieliczko >> Technical Support Engineer >> MooseFS.com <x-msg://14/moosefs.com> >> >> >> >> On 04/25/2016 02:07 PM, Aleksander Wieliczko wrote: >>> Hi Valeri, >>> >>> Excuse me. >>> I missed you previous mail. >>> >>> Right now I will test this issue on FreeBSD 9.3 >>> >>> Best regards >>> Aleksander Wieliczko >>> Technical Support Engineer >>> MooseFS.com <x-msg://14/moosefs.com> >>> >>> On 04/25/2016 01:46 PM, Aleksander Wieliczko wrote: >>>> Hi Valeri, >>>> >>>> I would like to inform you that we have made simple test in our >>>> development environment, and we do not observe such a behaviour. >>>> This is what we have: >>>> >>>> FreeBSD 10.2 >>>> MFS version 2.0.88-1 >>>> FUSE library version: 2.9.5 >>>> >>>> root@freebsd:~ # stat /mnt/mfs/test/* >>>> 3976265473 8 -rw-r--r-- 1 root wheel 0 11 "Apr 25 13:19:41 2016" "Apr >>>> 25 13:19:41 2016" "Apr 25 13:19:41 2016" "Jan 1 00:59:59 1970" 4096 1 >>>> 0 /mnt/mfs/test/test1 >>>> 3976265473 9 -rw-r--r-- 1 root wheel 0 19 "Apr 25 13:23:26 2016" "Apr >>>> 25 13:23:26 2016" "Apr 25 13:23:26 2016" "Jan 1 00:59:59 1970" 4096 1 >>>> 0 /mnt/mfs/test/test2 >>>> 3976265473 10 -rw-r--r-- 1 root wheel 0 20 "Apr 25 13:23:50 2016" "Apr >>>> 25 13:23:50 2016" "Apr 25 13:23:50 2016" "Jan 1 00:59:59 1970" 4096 1 >>>> 0 /mnt/mfs/test/test3 >>>> 3976265473 11 -rw-r--r-- 1 root wheel 0 34 "Apr 25 13:23:58 2016" "Apr >>>> 25 13:23:58 2016" "Apr 25 13:23:58 2016" "Jan 1 00:59:59 1970" 4096 1 >>>> 0 /mnt/mfs/test/test4 >>>> 3976265473 12 -rw-r--r-- 1 root wheel 0 45 "Apr 25 13:24:07 2016" "Apr >>>> 25 13:24:07 2016" "Apr 25 13:24:07 2016" "Jan 1 00:59:59 1970" 4096 1 >>>> 0 /mnt/mfs/test/test5 >>>> >>>> root@freebsd:~ # rsync -avu /mnt/mfs/test /tmp/ >>>> >>>> root@freebsd:~ # stat /mnt/mfs/test/* >>>> 3976265473 8 -rw-r--r-- 1 root wheel 0 11 "Apr 25 13:31:36 2016" "Apr >>>> 25 13:19:41 2016" "Apr 25 13:19:41 2016" "Jan 1 00:59:59 1970" 4096 1 >>>> 0 /mnt/mfs/test/test1 >>>> 3976265473 9 -rw-r--r-- 1 root wheel 0 19 "Apr 25 13:31:36 2016" "Apr >>>> 25 13:23:26 2016" "Apr 25 13:23:26 2016" "Jan 1 00:59:59 1970" 4096 1 >>>> 0 /mnt/mfs/test/test2 >>>> 3976265473 10 -rw-r--r-- 1 root wheel 0 20 "Apr 25 13:31:36 2016" "Apr >>>> 25 13:23:50 2016" "Apr 25 13:23:50 2016" "Jan 1 00:59:59 1970" 4096 1 >>>> 0 /mnt/mfs/test/test3 >>>> 3976265473 11 -rw-r--r-- 1 root wheel 0 34 "Apr 25 13:31:36 2016" "Apr >>>> 25 13:23:58 2016" "Apr 25 13:23:58 2016" "Jan 1 00:59:59 1970" 4096 1 >>>> 0 /mnt/mfs/test/test4 >>>> 3976265473 12 -rw-r--r-- 1 root wheel 0 45 "Apr 25 13:31:36 2016" "Apr >>>> 25 13:24:07 2016" "Apr 25 13:24:07 2016" "Jan 1 00:59:59 1970" 4096 1 >>>> 0 /mnt/mfs/test/test5 >>>> >>>> You see, that only atime has been changed. >>>> >>>> Question is which FreeBSD version you have? >>>> >>>> I'm looking forward to hearing from you. >>>> Aleksander Wieliczko >>>> Technical Support Engineer >>>> MooseFS.com <x-msg://14/moosefs.com> >>>> >>>> >>>> On 04/22/2016 07:03 AM, Jakub Kruszona-Zawadzki wrote: >>>>> On 21 Apr, 2016, at 16:33, Valeri Galtsev <ga...@ki...> >>>>> <mailto:ga...@ki...> wrote: >>>>> >>>>>> Dear Experts, >>>>>> >>>>>> I have sort of weirdness I just stumbled over. >>>>>> >>>>>> I migrates some directories to moosefs (free opes source version, >>>>>> standard >>>>>> installation "by the book" on FreeBSD). At some point I decided to >>>>>> migrate >>>>>> the directory back to local (UFS) filesystem on the machine. Here is >>>>>> weirdness I observe: >>>>>> >>>>>> after i run >>>>>> >>>>>> rsync -avu /path/do/mfs/mount/directory /path/to/local/fs >>>>>> >>>>>> I do get the content of directory on local filesystem as expected >>>>>> with all >>>>>> correct file attributes (user/group ownership, creation time, >>>>>> content). >>>>>> However, the source files on moosefs change their time stamps, as if >>>>>> the >>>>>> report last access time instead of creation time. They were >>>>>> reporting >>>>>> correct creation times after they were rsync'ed from local >>>>>> filesystem to >>>>>> moosefs originally. This basically renders rsync command useless >>>>>> (and >>>>>> damaging if you care about file creation times) when you rsync from >>>>>> moosefs (elsewhere). >>>>>> >>>>>> What am I doing wrong? I've used Linux and Unix for over decade an a >>>>>> half, >>>>>> ans used rsync over comparable period of time. What I hit with >>>>>> moosefs >>>>>> gives me kind of shock, and I can't figure myself what could I be >>>>>> doing >>>>>> wrong. >>>>>> >>>>>> Thanks in advance for all your advices. >>>>>> >>>>>> Valeri >>>>> We have changed atime/mtime management in MooseFS recently (in >>>>> version 3.0.74), so the question is which version of MooseFS do you >>>>> use? >>>>> >>>>> It looks like a bug in MooseFS, so we need the version, because we >>>>> have two options here. >>>>> The bug was in previous atime/mtime mechanism (pre 3.0.74) or there >>>>> is a bug in current mechanism. >>>>> >>>> >>>> >>>> >>>> ------------------------------------------------------------------------------ >>>> Find and fix application performance issues faster with Applications >>>> Manager >>>> Applications Manager provides deep performance insights into multiple >>>> tiers of >>>> your business applications. It resolves application problems quickly >>>> and >>>> reduces your MTTR. Get your free trial! >>>> https://ad.doubleclick.net/ddm/clk/302982198;130105516;z >>>> <https://ad.doubleclick.net/ddm/clk/302982198;130105516;z> >>>> >>>> _________________________________________ >>>> moosefs-users mailing list >>>> moo...@li... >>>> <mailto:moo...@li...> >>>> https://lists.sourceforge.net/lists/listinfo/moosefs-users >>>> <https://lists.sourceforge.net/lists/listinfo/moosefs-users> >>> >>> >>> >>> ------------------------------------------------------------------------------ >>> Find and fix application performance issues faster with Applications >>> Manager >>> Applications Manager provides deep performance insights into multiple >>> tiers of >>> your business applications. It resolves application problems quickly >>> and >>> reduces your MTTR. Get your free trial! >>> https://ad.doubleclick.net/ddm/clk/302982198;130105516;z >>> <https://ad.doubleclick.net/ddm/clk/302982198;130105516;z> >>> >>> _________________________________________ >>> moosefs-users mailing list >>> moo...@li... >>> <mailto:moo...@li...> >>> https://lists.sourceforge.net/lists/listinfo/moosefs-users >>> <https://lists.sourceforge.net/lists/listinfo/moosefs-users> >> >> ------------------------------------------------------------------------------ >> Find and fix application performance issues faster with Applications >> Manager >> Applications Manager provides deep performance insights into multiple >> tiers of >> your business applications. It resolves application problems quickly and >> reduces your MTTR. Get your free trial! >> https://ad.doubleclick.net/ddm/clk/302982198;130105516;z_________________________________________ >> moosefs-users mailing list >> moo...@li... >> https://lists.sourceforge.net/lists/listinfo/moosefs-users > > ++++++++++++++++++++++++++++++++++++++++ Valeri Galtsev Sr System Administrator Department of Astronomy and Astrophysics Kavli Institute for Cosmological Physics University of Chicago Phone: 773-702-4247 ++++++++++++++++++++++++++++++++++++++++ |