]> git.baikalelectronics.ru Git - kernel.git/commit
rhashtable: better high order allocation attempts
authorDaniel Borkmann <daniel@iogearbox.net>
Thu, 19 Feb 2015 23:53:38 +0000 (00:53 +0100)
committerDavid S. Miller <davem@davemloft.net>
Fri, 20 Feb 2015 22:38:09 +0000 (17:38 -0500)
commit95d73ecc6962624a49f7a77ab45d257d10983e32
tree75f3fee2718ab7194dca0153ff765484b412401a
parent7a105662e06ec83037dafbc9076d13da604aca55
rhashtable: better high order allocation attempts

When trying to allocate future tables via bucket_table_alloc(), it seems
overkill on large table shifts that we probe for kzalloc() unconditionally
first, as it's likely to fail.

Only probe with kzalloc() for more reasonable table sizes and use vzalloc()
either as a fallback on failure or directly in case of large table sizes.

Fixes: 6b35a704d780 ("lib: Resizable, Scalable, Concurrent Hash Table")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
lib/rhashtable.c