Comments on: GlusterFS tcp_nodelay patch update http://northernmost.org/blog/glusterfs-tcp_nodelay-patch-update/ Just another manic Monday Wed, 04 Jan 2012 14:30:53 +0000 hourly 1 http://wordpress.org/?v=3.3.1 By: admin http://northernmost.org/blog/glusterfs-tcp_nodelay-patch-update/comment-page-1/#comment-664 admin Tue, 22 Dec 2009 20:55:10 +0000 http://northernmost.org/blog/?p=202#comment-664 Hi, Unfortunately I don't know. FUSE is quite alright performance wise, but of course there's always drawbackcs. However, for a lot of workloads, you hit other bottlenecks before kernel/fuse becomes one. Hi,

Unfortunately I don’t know. FUSE is quite alright performance wise, but of course there’s always drawbackcs. However, for a lot of workloads, you hit other bottlenecks before kernel/fuse becomes one.

]]> By: darlfader http://northernmost.org/blog/glusterfs-tcp_nodelay-patch-update/comment-page-1/#comment-662 darlfader Fri, 04 Dec 2009 20:01:21 +0000 http://northernmost.org/blog/?p=202#comment-662 Hi, if I may ask an uninformed question... do you know if gluster at some point will offer a more kernel-internal implementation without FUSE? I might be wrong but my feeling says there would be certain performance benefits if it ran from the kernel, right next to the network/IB drivers ;) Hi,

if I may ask an uninformed question…

do you know if gluster at some point will offer a more kernel-internal implementation without FUSE?

I might be wrong but my feeling says there would be certain performance benefits if it ran from the kernel, right next to the network/IB drivers ;)

]]> By: Jonas http://northernmost.org/blog/glusterfs-tcp_nodelay-patch-update/comment-page-1/#comment-660 Jonas Tue, 06 Oct 2009 10:11:51 +0000 http://northernmost.org/blog/?p=202#comment-660 Nice one! Nice one!

]]>