Re: [PATCH] tcp: set SOCK_NOSPACE under memory presure

From: Jason Baron jba...@akamai.com Date: Thu, 30 Apr 2015 10:34:17 -0400 Just curious if anybody had any further reaction on this issue. I think making the epoll edge trigger case, as least match what we are seeing for poll()/select()/epoll() level trigger seems reasonable here. Ok Jason I

Re: [PATCH] tcp: set SOCK_NOSPACE under memory presure

From: Jason Baron jba...@akamai.com Date: Thu, 30 Apr 2015 10:34:17 -0400 Just curious if anybody had any further reaction on this issue. I think making the epoll edge trigger case, as least match what we are seeing for poll()/select()/epoll() level trigger seems reasonable here. It's in my

Re: [PATCH] tcp: set SOCK_NOSPACE under memory presure

On 04/21/2015 05:33 PM, David Miller wrote: From: Jason Baron jba...@akamai.com Date: Mon, 20 Apr 2015 20:05:13 + (GMT) Under tcp memory pressure, calling epoll_wait() in edge triggered mode after -EAGAIN, can result in an indefinite hang in epoll_wait(), even when there is suffcient

[PATCH] tcp: set SOCK_NOSPACE under memory presure

Under tcp memory pressure, calling epoll_wait() in edge triggered mode after -EAGAIN, can result in an indefinite hang in epoll_wait(), even when there is suffcient memory available to continue making progress. The problem is that __sk_mem_schedule() can return 0, under memory pressure without

Re: [PATCH] tcp: set SOCK_NOSPACE under memory presure

From: Jason Baron jba...@akamai.com Date: Mon, 20 Apr 2015 20:05:13 + (GMT) Under tcp memory pressure, calling epoll_wait() in edge triggered mode after -EAGAIN, can result in an indefinite hang in epoll_wait(), even when there is suffcient memory available to continue making progress.