From: Gijsbert Wiesenekker (gijsbert.wiesenekker_at_gmail_dot_com)
Date: Fri May 02 2008 - 13:57:01 PDT
Paul, I have a question that I could not find easily in the documentation. When I checkpoint a task that uses almost all physical memory (8GB), taking a checkpoint takes about three hours (and the system becomes almost unusable). Obviously this is because taking the checkpoint pushes the system beyond it's memory limits. How much memory is needed to make a checkpoint? Regards, Gijsbert 2008/4/29 Paul H. Hargrove <PHHargrove_at_lbl_dot_gov>: > I am pleased to announce the availability of BLCR 0.7.0_beta1 from > http://mantis.lbl.gov/blcr-dist/ > Both source tarball and SRPM are available. The filenames and MD5 > checksums are: > 750edf8d3bf0b60cb710972aee1cdb1c blcr-0.7.0_b1-1.src.rpm > fe41c1a414233c779e3f391d078b4cdd blcr-0.7.0_b1.tar.gz > > Relative to the eventual 0.7.0 release, this Beta is lacking a few minor > features and I have not updated the NEWS file or HTML documentation (though > manpages and comments in libcr.h do reflect all new features). Based on our > in-house testing, this release is considered stable (though ARM and PPC64 > platforms are still designated as EXPERIMENTAL). > > If you have reported a bug recently, especially if you've been told to > expect a fix in 0.7.0, please try out this Beta release and let us know if > your problem is fixed and especially if it is not. > > Relative to the 0.6.x release series, BLCR is using a new configure and > build mechanism that should work correctly with Xen-enabled kernels and > other kernels that were problematic in previous releases. If you are unable > to configure or build this beta on any system where 0.6.x built > successfully, PLEASE let us know because the new configure/build mechanism > might be at fault. > > There will be at least one more Beta release prior to the full 0.7.0, to > include the minor features still not completed and to update the HTML docs > and NEWS file. > > -Paul > > PS > You are receiving this either because you are on the checkpoint_at_lbl_dot_gov > list, because you've recently sent email to the list (or me directly) > asking about BLCR status, or because our Bugzilla shows your interests in > a bug fixed in this beta. > > -- > Paul H. Hargrove PHHargrove_at_lbl_dot_gov > Future Technologies Group > HPC Research Department Tel: +1-510-495-2352 > Lawrence Berkeley National Laboratory Fax: +1-510-486-6900 >