[RFC net-next PATCH V1 0/9] net: fragmentation performance scalability on NUMA/SMP systems · Jesper Dangaard Brouer <hidden> · 2012-11-23
[RFC net-next PATCH V1 7/9] net: frag queue locking per hash bucket · Jesper Dangaard Brouer <hidden> · 2012-11-23
Re: [RFC net-next PATCH V1 7/9] net: frag queue locking per hash bucket · Jesper Dangaard Brouer <hidden> · 2012-11-27
Re: [RFC net-next PATCH V1 7/9] net: frag queue locking per hash bucket · Jesper Dangaard Brouer <hidden> · 2012-11-27
[RFC net-next PATCH V1 8/9] net: increase frag queue hash size and cache-line · Jesper Dangaard Brouer <hidden> · 2012-11-23
[RFC net-next PATCH V1 9/9] net: frag remove readers-writer lock (hack) · Jesper Dangaard Brouer <hidden> · 2012-11-23
Re: [RFC net-next PATCH V1 9/9] net: frag remove readers-writer lock (hack) · Stephen Hemminger <hidden> · 2012-11-26
Re: [RFC net-next PATCH V1 9/9] net: frag remove readers-writer lock (hack) · Florian Westphal <fw@strlen.de> · 2012-11-26
[RFC net-next PATCH V1 2/9] net: frag cache line adjust inet_frag_queue.net · Jesper Dangaard Brouer <hidden> · 2012-11-23
[RFC net-next PATCH V1 4/9] net: frag helper functions for mem limit tracking · Jesper Dangaard Brouer <hidden> · 2012-11-23
Re: [RFC net-next PATCH V1 0/9] net: fragmentation performance scalability on NUMA/SMP systems · Eric Dumazet <hidden> · 2012-11-25
Re: [RFC net-next PATCH V1 0/9] net: fragmentation performance scalability on NUMA/SMP systems · Jesper Dangaard Brouer <hidden> · 2012-11-25
Re: [RFC net-next PATCH V1 0/9] net: fragmentation performance scalability on NUMA/SMP systems · Eric Dumazet <hidden> · 2012-11-25
Re: [RFC net-next PATCH V1 0/9] net: fragmentation performance scalability on NUMA/SMP systems · Jesper Dangaard Brouer <hidden> · 2012-11-26
Re: [RFC net-next PATCH V1 0/9] net: fragmentation performance scalability on NUMA/SMP systems · Eric Dumazet <hidden> · 2012-11-26
Re: [RFC net-next PATCH V1 0/9] net: fragmentation performance scalability on NUMA/SMP systems · Jesper Dangaard Brouer <hidden> · 2012-11-26

Re: [RFC net-next PATCH V1 0/9] net: fragmentation performance scalability on NUMA/SMP systems

From: Eric Dumazet <hidden>
Date: 2012-11-25 16:11:34

On Sun, 2012-11-25 at 09:53 +0100, Jesper Dangaard Brouer wrote:

Yes, for the default large 64k packets size, its just a "fake"
benchmark.  And notice with my fixes, we are even faster than the
none-frag/single-UDP packet case... but its because we are getting a
GSO/GRO effect.

Could you elaborate on this GSO/GRO effect ?

`h`	back out one level
`j`	next message in thread
`k`	previous message in thread
`l`	drill in
`Esc`	close help / fold thread tree
`?`	toggle this help