Hi Rob, Okay; Sounds good to me. Right now, I will add the flag as an interim solution ... What is the time frame and/or objections to integrating Julian's hint patches to the system interface? thanks, murali
On Tue, 12 Sep 2006, Rob Ross wrote: > Sounds like a fine solution. Maybe could be integrated with the hints > that Julian wants to add (I know that complicates things a bit, but it > *is* a hint after all...)? > > Rob > > Murali Vilayannur wrote: > > Hi Rob, > > hehe :) > > Alright, I will change it then.. > > Just had a quick chat with Sam and RobL about this.. > > Are you ok with having a flag to the isys_fs_add and fs_add API that > > determines whether or not we should do these checks and have ping set the > > flag to 1 and client-core set to 0? > > thanks, > > Murali > > > > > > On Tue, 12 Sep 2006, Rob Ross wrote: > > > >> 80K clients... > >> > >> Murali Vilayannur wrote: > >>> Hi Rob, > >>> > >>>> Quick uneducated question: this isn't automatically done on *every* > >>>> mount, right? > >>> yeah, it is done automatically on every *new* mount upcall. Is this a > >>> problem? (I changed the code to this behavior y'day night) > >>> thanks, > >>> Murali > >>> > >>>> Rob > >>>> > >>>> Phil Carns wrote: > >>>>> Murali Vilayannur wrote: > >>>>>> Hi All, > >>>>>> Just a heads-up.. > >>>>>> I have checked in a patch that will allow the pvfs2-ping utility to > >>>>>> verify > >>>>>> if the fs.conf files obtained from all the servers for a given fsid > >>>>>> is the same by checking against their crypto check sum (SHA1 right now) > >>>>>> Please let me know if you have any serious objections to doing it the > >>>>>> way > >>>>>> I have done right now.. > >>>>>> Thanks, > >>>>>> Murali > >>>>> Hi Murali, > >>>>> > >>>>> This is integrated into fs_add so that the test is performed > >>>>> automatically at mount time now, correct? We had done something similar > >>>>> in the pvfs2-validate utility, but I think it will be good to have it > >>>>> integrated into the normal mount process. > >>>>> > >>>>> I haven't looked at the code, but I have a few functionality comments > >>>>> after playing with it this morning: > >>>>> > >>>>> - Is it possible to filter whitespace and comments out of the config > >>>>> file before gathering whatever information you need for comparison, or > >>>>> do you want to enforce that the fs.conf files be verbatim identical? > >>>>> > >>>>> - I ran one test where a server had an extra line in its configuration > >>>>> file, and that showed up fine as a mount error with information in the > >>>>> log files showing the size difference. However, I ran another test > >>>>> where I just changed the value of UnexpectedRequests from "50" to "51", > >>>>> and this did not generate any error. Is there anything in particular > >>>>> you have to do to enable the checksum tests in addition to the size > >>>>> tests? > >>>>> > >>>>> -Phil > >>>>> _______________________________________________ > >>>>> Pvfs2-developers mailing list > >>>>> [email protected] > >>>>> http://www.beowulf-underground.org/mailman/listinfo/pvfs2-developers > >>>>> > >> > > > > _______________________________________________ Pvfs2-developers mailing list [email protected] http://www.beowulf-underground.org/mailman/listinfo/pvfs2-developers
