Ricardo,
Your --mgsnode specification with all commas implies that you have four
NIDs on a single host. But the rest of your writeup indicates two hosts.
>From the Lustre manual, "13.12. Specifying NIDs and Failover":
> Where multiple NIDs are specified separated by commas (for example,
> 10.67
On Thu, Aug 5, 2021 at 3:23 PM Andreas Dilger wrote:
> On Aug 5, 2021, at 13:29, Nathan Dauchy wrote:
>
> Andreas, thanks as always for your insight. Comments inline...
>
> On Thu, Aug 5, 2021 at 10:48 AM Andreas Dilger
> wrote:
>
>> On Aug 5, 2021, at 09:28, Nathan Dauchy via lustre-discuss <
Andreas, thanks as always for your insight. Comments inline...
On Thu, Aug 5, 2021 at 10:48 AM Andreas Dilger
wrote:
> On Aug 5, 2021, at 09:28, Nathan Dauchy via lustre-discuss <
> lustre-discuss@lists.lustre.org> wrote:
>
> Question: Is it possible that a flash journal device on an ext4
> fi
Greetings ext4 and flash storage experts!
Motivation: We have ldiskfs OSTs that are primarily HDDs and use a Flash
device for an external journal device. Recent IOR benchmarks showed that
write performance dropped (suddenly?) to about 25% of the original
baseline, yet read performance remains fi
On Tue, Feb 16, 2021 at 9:46 AM Kurt Strosahl wrote:
> During a maintenance window today I revooted the OSS that OST had been
> mounted on, after it came up the usage dropped significantly
>
Kurt,
That behavior you describe sounds a bit like issues reported on this list a
while back:
Data migr
Andreas, thanks for the insight and advice. Followup details inline
below...
On Thu, Jan 7, 2021 at 9:56 PM Andreas Dilger wrote:
> On Jan 7, 2021, at 08:54, Nathan Dauchy - NOAA Affiliate wrote:
>
> I am looking for assistance on how to improve file create rate, as
> measured
Greetings Lustre Experts!
I am looking for assistance on how to improve file create rate, as measured
with MDtest.
In particular, this is for filesystems with (4) MDTs that use progressive
file layouts (PFL) to place the first part of each file on one of the (2)
Flash OSTs, with the remainder of
On Tue, Dec 8, 2020 at 11:46 AM Kevin M. Hildebrand wrote:
> We appear to be tripping over the same issues reported recently by
> Tung-Han Hsieh and Simon Guilbault, namely that cur_grant_bytes is being
> reduced to a very small value and causing abysmal performance.
>
I'm curious if anyone enco
Simon, Tung-Han,
You may also want to watch these tickets that seem to be related to the
issue you describe:
https://jira.whamcloud.com/browse/LU-14124
https://jira.whamcloud.com/browse/LU-14125
-Nathan
On Mon, Nov 2, 2020 at 7:18 AM Simon Guilbault <
simon.guilba...@calculquebec.ca> wrote:
>
On Thu, Feb 20, 2020 at 11:47 AM Konzem, Kevin P <
kkon...@contractor.usgs.gov> wrote:
> test this by running 'while [ true ];do /bin/df -TP /performance;done' on
> two sessions on the same client. As soon as I start the second while loop,
> the outputs go from:
> Filesystem Type
On Wed, Nov 13, 2019 at 4:28 AM Thomas Roth wrote:
> Hi all,
>
> we keep hitting LU-10697, which makes the users' experience quite painful.
> There was a related issue in Lustre 2.12/2.13 which is also unresolved -
> can't find the LU- at the moment.
>
>
Thomas,
Perhaps you are looking for LU-12
On Wed, Jul 3, 2019 at 2:15 PM Kurt Strosahl wrote:
>
> Hopefully a simple question... If I run lctl lfsck_start is there a place
> where I can get a list of what it did?
>
>
Kurt,
As far as I know, this is still an open feature request...
https://jira.whamcloud.com/browse/LU-5202 (LFSCK 5: LFSC
On Mon, Apr 15, 2019 at 9:18 PM Jacek Tomaka wrote:
>
> >signal_cache should have one entry for each process (or thread-group).
>
> That is what i thought as well, looking at the kernel source, allocations
> from
> signal_cache happen only during fork.
>
>
I was recently chasing an issue with cli
0552/
?
Thanks,
Nathan
On Wed, May 18, 2016 at 1:30 PM, Dilger, Andreas
wrote:
>
> Cheers, Andreas
> --
> Andreas Dilger
> Lustre Principal Architect
> Intel High Performance Data Division
>
> On 2016/05/18, 11:22, "Nathan Dauchy - NOAA Affiliate" <
> nath
Andreas,
Thanks very much for your comments...
On Wed, May 18, 2016 at 1:30 PM, Dilger, Andreas
wrote:
>
> On 2016/05/18, 11:22, "Nathan Dauchy - NOAA Affiliate" <
> nathan.dau...@noaa.gov> wrote:
>
> I'm looking for your experience and perhaps some
On Wed, May 18, 2016 at 2:04 PM, Mohr Jr, Richard Frank (Rick Mohr) <
rm...@utk.edu> wrote:
>
> 2) Use some sort of formula (like ORNL’s “file_size/100GB” or even your
> log function)
>
> Since I mainly care about striping for large files and I want the stripe
> count to increase as file size grow
to understand the application access pattern. I can't see another way to
> do that goal justice. (The Lustre ADIO in the MPI I/O library does this,
> partly by controlling the I/O pattern through I/O aggregation for
> collective I/Os.)
>
> So I think your tool can definitely
Greetings All,
I'm looking for your experience and perhaps some lively discussion
regarding "best practices" for choosing a file stripe count. The Lustre
manual has good tips on "Choosing a Stripe Size", and in practice the
default 1M rarely causes problems on our systems. Stripe Count on the oth
On Mon, Dec 14, 2015 at 9:08 AM, Scott Nolin
wrote:
>
> On 12/14/2015 12:43 AM, Dilger, Andreas wrote:
> ...
>
>> Is this a tool that you are using? IIRC, there wasn't a particular reason
>> that it was removed, except that when we asked LLNL (the authors) they
>> said they were no longer using
19 matches
Mail list logo