Re: [PATCH] block: fix rdma queue mapping
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
- To: Sagi Grimberg <sagi@xxxxxxxxxxx>, <linux-block@xxxxxxxxxxxxxxx>, <linux-rdma@xxxxxxxxxxxxxxx>, <linux-nvme@xxxxxxxxxxxxxxxxxxx>
- Subject: Re: [PATCH] block: fix rdma queue mapping
- From: Max Gurtovoy <maxg@xxxxxxxxxxxx>
- Date: Sun, 19 Aug 2018 15:45:07 +0300
- Cc: Christoph Hellwig <hch@xxxxxx>, Steve Wise <swise@xxxxxxxxxxxxxxxxxxxxx>, Israel Rukshin <israelr@xxxxxxxxxxxx>
- In-reply-to: <20180817223823.19566-1-sagi@grimberg.me>
- References: <20180817223823.19566-1-sagi@grimberg.me>
- User-agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:52.0) Gecko/20100101 Thunderbird/52.9.1
Hi Sagi,
did you have a chance to look on Israel's and mine fixes that we
attached to the first thread ?
there are few issues with this approach. For example in case you don't
have a "free" cpu in the mask for Qi and you take cpu from Qi+j mask.
Also in case we have a non-symetrical affinity for 2 queues e.g. and the
system has 32 cpus, the mapping is 16 for each (and not according to the
user affinity...).
-Max.
[Index of Archives]
[Linux RAID]
[Linux SCSI]
[Linux ATA RAID]
[IDE]
[Linux Wireless]
[Linux Kernel]
[ATH6KL]
[Linux Bluetooth]
[Linux Netdev]
[Kernel Newbies]
[Security]
[Git]
[Netfilter]
[Bugtraq]
[Yosemite News]
[MIPS Linux]
[ARM Linux]
[Linux Security]
[Device Mapper]