It shouldn't be a problem as max just restarted nfs - without user issues. I'm not changing any parms that will affect client mount options, only server scalability. ---- Daniel Murphy-Olson Systems Administrator Mathematics & Computer Science Division Argonne National Laboratory 630-252-0055 ----- Original Message ----- From: "Craig Stacey" <[email protected]> To: "Dan Olson" <[email protected]> Cc: [email protected] Sent: Wednesday, June 16, 2010 4:39:15 PM GMT -06:00 US/Canada Central Subject: Re: sto01 nfs tuning I'm generally cool about this with most services, but with NFS it can lead to stale NFS handles. Is that going to be an issue? On Jun 16, 2010, at 8:30 AM, Dan Olson wrote:
To clarify the nfs service needs to be restarted, not the server os.
---- Daniel Murphy-Olson Systems Administrator Mathematics & Computer Science Division Argonne National Laboratory 630-252-0055
----- Forwarded Message ----- From: [email protected] To: [email protected] Sent: Wednesday, June 16, 2010 8:21:55 AM GMT -06:00 US/Canada Central Subject: sto01 nfs tuning
I'm changing a few parms on the sto01 nfs server to improve performance. It needs to be restarted to take the new values. It should be down less than a minute. Anyone have any objections to doing it tonight around 9pm?
---- Daniel Murphy-Olson Systems Administrator Mathematics & Computer Science Division Argonne National Laboratory 630-252-0055
== Craig
Sounds good to me. On Jun 16, 2010, at 4:56 PM, [email protected] wrote:
It shouldn't be a problem as max just restarted nfs - without user issues. I'm not changing any parms that will affect client mount options, only server scalability.
---- Daniel Murphy-Olson Systems Administrator Mathematics & Computer Science Division Argonne National Laboratory 630-252-0055
----- Original Message ----- From: "Craig Stacey" <[email protected]> To: "Dan Olson" <[email protected]> Cc: [email protected] Sent: Wednesday, June 16, 2010 4:39:15 PM GMT -06:00 US/Canada Central Subject: Re: sto01 nfs tuning
I'm generally cool about this with most services, but with NFS it can lead to stale NFS handles. Is that going to be an issue?
On Jun 16, 2010, at 8:30 AM, Dan Olson wrote:
To clarify the nfs service needs to be restarted, not the server os.
---- Daniel Murphy-Olson Systems Administrator Mathematics & Computer Science Division Argonne National Laboratory 630-252-0055
----- Forwarded Message ----- From: [email protected] To: [email protected] Sent: Wednesday, June 16, 2010 8:21:55 AM GMT -06:00 US/Canada Central Subject: sto01 nfs tuning
I'm changing a few parms on the sto01 nfs server to improve performance. It needs to be restarted to take the new values. It should be down less than a minute. Anyone have any objections to doing it tonight around 9pm?
---- Daniel Murphy-Olson Systems Administrator Mathematics & Computer Science Division Argonne National Laboratory 630-252-0055
== Craig
== Craig
Dan and I talked about this last night before he left, the reason that there were no stale nfs handles last time was that t coincided with the building-wide power outage. All the hosts rebooted. I swear I had nothing to do with it. Swear. -- max On Jun 16, 2010, at 5:43 PM, Craig Stacey wrote:
Sounds good to me.
On Jun 16, 2010, at 4:56 PM, [email protected] wrote:
It shouldn't be a problem as max just restarted nfs - without user issues. I'm not changing any parms that will affect client mount options, only server scalability.
---- Daniel Murphy-Olson Systems Administrator Mathematics & Computer Science Division Argonne National Laboratory 630-252-0055
----- Original Message ----- From: "Craig Stacey" <[email protected]> To: "Dan Olson" <[email protected]> Cc: [email protected] Sent: Wednesday, June 16, 2010 4:39:15 PM GMT -06:00 US/Canada Central Subject: Re: sto01 nfs tuning
I'm generally cool about this with most services, but with NFS it can lead to stale NFS handles. Is that going to be an issue?
On Jun 16, 2010, at 8:30 AM, Dan Olson wrote:
To clarify the nfs service needs to be restarted, not the server os.
---- Daniel Murphy-Olson Systems Administrator Mathematics & Computer Science Division Argonne National Laboratory 630-252-0055
----- Forwarded Message ----- From: [email protected] To: [email protected] Sent: Wednesday, June 16, 2010 8:21:55 AM GMT -06:00 US/Canada Central Subject: sto01 nfs tuning
I'm changing a few parms on the sto01 nfs server to improve performance. It needs to be restarted to take the new values. It should be down less than a minute. Anyone have any objections to doing it tonight around 9pm?
---- Daniel Murphy-Olson Systems Administrator Mathematics & Computer Science Division Argonne National Laboratory 630-252-0055
== Craig
== Craig
participants (3)
-
Craig Stacey -
dolson＠mcs.anl.gov -
Max trefonides