Mike Polek <[EMAIL PROTECTED]> writes: > Silly question... how many simultaneous file transfers can a 64M > memcache handle? And what parameters would affect that?
Just FYI, we tried throwing an extensive amount of load at the memory cache for extended periods (using it on www.stanford.edu) and found that disk cache was more reliable. We'd periodically see odd problems with memory cache (stale volumes, file servers marked incorrectly as down, that sort of thing). We didn't notice any real performance differences. Of course, if the system is diskless, this doesn't really help. :) This was back in the mid 1.2 days, so it may be that subsequent changes have made this information obsolete. -- Russ Allbery ([EMAIL PROTECTED]) <http://www.eyrie.org/~eagle/> _______________________________________________ OpenAFS-info mailing list OpenAFS-info@openafs.org https://lists.openafs.org/mailman/listinfo/openafs-info