Bottlenecks with large number of relation segment files

Hello,

I am looking the effect of having large number of relation files under
$PGDATA/base/ (for example, in cases where I choose lower segment size
using --with-segsize). Consider a case where I am working with a large
database with large relations, for example a database similar in size
to what "pgbench -i -s 3500" would be.

May the routines in fd.c become bottleneck with a large number of
concurrent connections to above database, say something like "pgbench
-j 8 -c 128"? Is there any other place I should be paying attention
to?

--
Amit Langote