* sk_stream_wait_memory: Query
@ 2009-08-26 13:44 Ravish Tayal
0 siblings, 0 replies; only message in thread
From: Ravish Tayal @ 2009-08-26 13:44 UTC (permalink / raw)
To: linux-arm, Kernel development list
Hi,
In " tcp_sendmsg" function in 2 situation, tcp code attempts to jump
to "wait_for_memory:
" case when
1. it fails to allocate to the new skb [sk_stream_alloc_pskb failure]
2. it fails to allocate new cache page.
and invokes the sk_stream_wait_memory function.
inside which it invokes the
sk_wait_event(sk, ¤t_timeo, sk_stream_memory_free(sk) &&
vm_wait);
in case if sk_stream_wait_memory is invoked due to skb allocation
failure, it would busy loop and would not relinquish the control.
[For non-preemptive kernel]
Is it fair expectation, or even this case it should let it current
task get scheduled and re try after timer expiry.
regards
Ravish Tayal
in the case if linux kernel is configured as non-premeptive
^ permalink raw reply [flat|nested] only message in thread
only message in thread, other threads:[~2009-08-26 13:52 UTC | newest]
Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2009-08-26 13:44 sk_stream_wait_memory: Query Ravish Tayal
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®