diff --git a/README b/README index c89941638dfe888d1c169b382937d067288f5126..7b4462c2092e6df07e93abef885fbc5e711c7bc0 100644 --- a/README +++ b/README @@ -16,6 +16,47 @@ Summary: Bio::EnsEMBL::Analysis::RunnableDB perl wrapper objects as nodes/blocks in the graphs but could be adapted more generally. +3 April, 2009 : Albert Vilella + + Added a new maximise_concurrency 1/0 option. When set to 1, it will + fetch jobs that need to be run in the adequate order as to maximise + the different number of analyses being run. This is useful for cases + where different analyses hit different tables and the overall sql + load can be kept higher without breaking the server, instead of + having lots of jobs for the same analysis trying to hit the same + tables. + + Added quick HIGHMEM option. This option is useful when a small + percent of jobs are too big and fail in normal conditions. The + runnable can check if it's the second time it's trying to run the + job, if it's because it contains big data (e.g. gene_count > 200) + and if it isn't already in HIGHMEM mode. Then, it will call + reset_highmem_job_by_dbID and quit: + + if ($self->input_job->retry_count == 1) { + if ($self->{'protein_tree'}->get_tagvalue('gene_count') > 200 && !defined($self->worker->{HIGHMEM})) { + $self->input_job->adaptor->reset_highmem_job_by_dbID($self->input_job->dbID); + $self->DESTROY; + throw("Alignment job too big: send to highmem and quit"); + } + } + + Assuming there is a + + beekeeper.pl -url <blah> -highmem -lsf_options "<lots of mem>" + + running, or a + + runWorker.pl <blah> -highmem 1 + + with lots of mem running, it will fetch the HIGHMEM jobs as if they + were "READY but needs HIGHMEM". + + Also added a modification to Queen that will not synchronize as + often when more than 450 jobs are running and the load is above + 0.9, so that the queries to analysis tables are not hitting the sql + server too much. + 23 July, 2008 : Will Spooner Removed remaining ensembl-pipeline dependencies.