Re: High contention on the sk_buff_head.lock
From: Andi Kleen <hidden>
Date: 2009-03-19 13:45:28
Also in:
linux-rt-users, lkml
Possibly related (same subject, not in this thread)
- 2009-04-02 · Re: High contention on the sk_buff_head.lock · Herbert Xu <herbert@gondor.apana.org.au>
- 2009-04-02 · Re: High contention on the sk_buff_head.lock · Herbert Xu <herbert@gondor.apana.org.au>
- 2009-03-23 · Re: High contention on the sk_buff_head.lock · Jarek Poplawski <hidden>
- 2009-03-23 · Re: High contention on the sk_buff_head.lock · David Miller <davem@davemloft.net>
- 2009-03-23 · Re: High contention on the sk_buff_head.lock · Eric Dumazet <hidden>
Do we have to rule-out per-CPU queues, that aggregate into a master queue in a batch-wise manner?
TSO/GSO/USO is that actually in a very specific way. It batches packets into larger packets and then less per packet locks need to be taken. It was unclear if that was used in this workload or not. -Andi -- ak@linux.intel.com -- Speaking for myself only.