On 9/23/09 9:44 AM, "Eli Collins" <e...@cloudera.com> wrote: >> These values determine how much HDFS is *not* allowed to use. There is no >> limit on how much MR can take. This is exactly the opposite of what he and >> pretty much every other admin wants. [Negative math is fun! Or something.] > > Hey Allen -- is there a JIRA for this? A quick search didn't turn up > anything. Seems like there should be. Like many things, I think I probably skipped filing a specific JIRA after being unable to convince the HDFS team at Yahoo! that they were making my life unnecessarily hard. But HDFS-74 and its related JIRAs contain a lot of discussion around some of this.
- Re: local node Quotas (for an R&D cluster) Paul Smith
- Re: local node Quotas (for an R&D cluster... Ravi Phulari
- Program crashed when volume of data getting l... Kunsheng Chen
- Re: Program crashed when volume of data g... Chandraprakash Bhagtani
- RE: Program crashed when volume of data g... Amogh Vasekar
- Re: local node Quotas (for an R&D cluster) Allen Wittenauer
- Re: local node Quotas (for an R&D cluster... Edward Capriolo
- Re: local node Quotas (for an R&D cluster... Vinod KV
- Re: local node Quotas (for an R&D cluster... Eli Collins
- Re: local node Quotas (for an R&D clu... Paul Smith
- Re: local node Quotas (for an R&D clu... Allen Wittenauer
- Re: local node Quotas (for an R&D... Paul Smith
- Re: local node Quotas (for an R&a... Allen Wittenauer
- Re: local node Quotas (for a... Paul Smith
- Re: local node Quotas (for a... Steve Loughran
- Re: local node Quotas (for a... Paul Smith
- Re: local node Quotas (for a... Edward Capriolo
- Re: local node Quotas (for a... Steve Loughran
- Re: local node Quotas (for a... Allen Wittenauer
- Re: local node Quotas (for an R&D cluster) Paul Smith