git clone https://git.igankevich.com/hpcs-17-subord.git
Log | Files | Refs

commit 16308bcb1fb776d31e823d57f7458a5f4746baa3
parent e0481e7d595d587a7dd04044977d32a94a30a434
Author: Ivan Gankevich <igankevich@ya.ru>
Date:   Mon, 15 May 2017 13:44:08 +0300

Homogeneous architecture.

src/body.tex | 8+++++++-
1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/src/body.tex b/src/body.tex @@ -63,6 +63,11 @@ distribution, which, however, balances over time. Uneven load distribution does not cause node overload, since there is a kernel pool on each node that queues the kernels prior to execution. +Dynamic master/slave role distribution coupled with kernel distribution makes +overall distributed system architecture homogeneous within single cluster. On +every node the same daemon is run, and no configuration is needed to make a +hierarchy of daemons~--- it happens automatically. + \paragraph{Kernel layer} Consists of kernels and hierarchical (parent/child) logical links between them. The only purpose of kernel hierarchy is to provide fail over for kernels. @@ -318,7 +323,8 @@ generate wavy surface, parts of which are generated in parallel on all cluster nodes including the principal one. All generated parts are written in parallel to individual files. So, from computational point of view the programme is embarrassingly parallel with little synchronisation between concurrent -processes. +processes; the corresponding kernel hierarchy has one principal and $N$ +subordinates. All experiments were run on physical computer cluster consisting of 12 nodes. Wavy ocean surface parts were written to Network File System (NFS) which is