Re: [PATCH 1/1] net/rds: suppress page allocation failure error in recv buffer refill

2020-10-05 Thread Manjunath Patil
Thanks David for your feedback. I will submit v3 of this patch removing the warning. -Manjunath On 10/3/2020 5:26 PM, David Miller wrote: From: Manjunath Patil Date: Fri, 2 Oct 2020 13:05:45 -0700 RDS/IB tries to refill the recv buffer in softirq context using GFP_NOWAIT flag. However alloc

Re: [PATCH 1/1] net/rds: suppress page allocation failure error in recv buffer refill

2020-10-03 Thread David Miller
From: Manjunath Patil Date: Fri, 2 Oct 2020 13:05:45 -0700 > RDS/IB tries to refill the recv buffer in softirq context using > GFP_NOWAIT flag. However alloc failure is handled by queueing a work to > refill the recv buffer with GFP_KERNEL flag. This means failure to > allocate with GFP_NOWAIT i

Re: [PATCH 1/1] net/rds: suppress page allocation failure error in recv buffer refill

2020-10-02 Thread Manjunath Patil
Thanks for ack'ing. Yeah, sorry about version. I had it in my mind to add it when I started, but forgot it at the last moment. -Thanks, Manjunath On 10/2/2020 1:10 PM, santosh.shilim...@oracle.com wrote: On 10/2/20 1:05 PM, Manjunath Patil wrote: RDS/IB tries to refill the recv buffer in sof

Re: [PATCH 1/1] net/rds: suppress page allocation failure error in recv buffer refill

2020-10-02 Thread santosh . shilimkar
On 10/2/20 1:05 PM, Manjunath Patil wrote: RDS/IB tries to refill the recv buffer in softirq context using GFP_NOWAIT flag. However alloc failure is handled by queueing a work to refill the recv buffer with GFP_KERNEL flag. This means failure to allocate with GFP_NOWAIT isn't fatal. Do not print

[PATCH 1/1] net/rds: suppress page allocation failure error in recv buffer refill

2020-10-02 Thread Manjunath Patil
RDS/IB tries to refill the recv buffer in softirq context using GFP_NOWAIT flag. However alloc failure is handled by queueing a work to refill the recv buffer with GFP_KERNEL flag. This means failure to allocate with GFP_NOWAIT isn't fatal. Do not print the PAF warnings if softirq context fails to

Re: [PATCH 1/1] net/rds: suppress page allocation failure error in recv buffer refill

2020-09-16 Thread Manjunath Patil
Hi Santosh, inline. On 9/16/2020 12:27 PM, santosh.shilim...@oracle.com wrote: On 9/16/20 12:08 PM, Manjunath Patil wrote: RDS/IB tries to refill the recv buffer in softirq context using GFP_NOWAIT flag. However alloc failure is handled by queueing a work to refill the recv buffer with GFP_KERN

Re: [PATCH 1/1] net/rds: suppress page allocation failure error in recv buffer refill

2020-09-16 Thread santosh . shilimkar
On 9/16/20 2:15 PM, Manjunath Patil wrote: Hi Santosh, inline. On 9/16/2020 12:27 PM, santosh.shilim...@oracle.com wrote: On 9/16/20 12:08 PM, Manjunath Patil wrote: RDS/IB tries to refill the recv buffer in softirq context using GFP_NOWAIT flag. However alloc failure is handled by queueing a

Re: [PATCH 1/1] net/rds: suppress page allocation failure error in recv buffer refill

2020-09-16 Thread Manjunath Patil
On 9/16/2020 2:25 PM, santosh.shilim...@oracle.com wrote: On 9/16/20 2:15 PM, Manjunath Patil wrote: Hi Santosh, inline. On 9/16/2020 12:27 PM, santosh.shilim...@oracle.com wrote: On 9/16/20 12:08 PM, Manjunath Patil wrote: RDS/IB tries to refill the recv buffer in softirq context using GFP_N

Re: [PATCH 1/1] net/rds: suppress page allocation failure error in recv buffer refill

2020-09-16 Thread santosh . shilimkar
On 9/16/20 12:08 PM, Manjunath Patil wrote: RDS/IB tries to refill the recv buffer in softirq context using GFP_NOWAIT flag. However alloc failure is handled by queueing a work to refill the recv buffer with GFP_KERNEL flag. This means failure to allocate with GFP_NOWAIT isn't fatal. Do not print

[PATCH 1/1] net/rds: suppress page allocation failure error in recv buffer refill

2020-09-16 Thread Manjunath Patil
RDS/IB tries to refill the recv buffer in softirq context using GFP_NOWAIT flag. However alloc failure is handled by queueing a work to refill the recv buffer with GFP_KERNEL flag. This means failure to allocate with GFP_NOWAIT isn't fatal. Do not print the PAF warnings if softirq context fails to