Re: NFS regression between 5.17 and 5.18

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 




> On Apr 28, 2022, at 9:05 AM, Dennis Dalessandro <dennis.dalessandro@xxxxxxxxxxxxxxxxxxxx> wrote:
> 
> Hi NFS folks,
> 
> I've noticed a pretty nasty regression in our NFS capability between 5.17 and
> 5.18-rc1. I've tried to bisect but not having any luck. The problem I'm seeing
> is it takes 3 minutes to copy a file from NFS to the local disk. When it should
> take less than half a second, which it did up through 5.17.
> 
> It doesn't seem to be network related, but can't rule that out completely.
> 
> I tried to bisect but the problem can be intermittent. Some runs I'll see a
> problem in 3 out of 100 cycles, sometimes 0 out of 100. Sometimes I'll see it
> 100 out of 100.

It's not clear from your problem report whether the problem appears
when it's the server running v5.18-rc or the client.

It looks vaguely like a recent client issue where it encounters a
memory shortage while preparing an RPC and a delay is needed.


> The latest attempt I have is at 5.18-rc4 and here's what I see when I 1) create
> file with dd, 2) copy local disk to NFS mount, 3) copy NFS to local disk.
> 
> Test 2
> Creating /dev/shm/run_nfs_test.junk...
> 262144+0 records in
> 262144+0 records out
> 268435456 bytes (268 MB, 256 MiB) copied, 1.29037 s, 208 MB/s
> Done
> copy /dev/shm/run_nfs_test.junk to /mnt/nfs_test/run_nfs_test.junk...
> 
> real    0m0.502s
> user    0m0.001s
> sys     0m0.250s
> Done
> copy /mnt/nfs_test/run_nfs_test.junk to /dev/shm/run_nfs_test.tmp...
> 
> real    4m11.835s
> user    0m0.001s
> sys     0m0.277s
> Done
> Comparing files...
> Done
> Remove /dev/shm/run_nfs_test.tmp...
> 
> real    0m0.031s
> user    0m0.000s
> sys     0m0.031s
> Done
> Remove /dev/shm/run_nfs_test.junk...
> 
> real    0m0.031s
> user    0m0.001s
> sys     0m0.030s
> Done
> Remove /mnt/nfs_test/run_nfs_test.junk...
> 
> real    0m0.024s
> user    0m0.001s
> sys     0m0.022s
> Done
> 
> Create the server with a 4G RAM disk:
> mount -t tmpfs -o size=4096M tmpfs /mnt/nfs_test
> 
> exportfs -o fsid=0,rw,async,insecure,no_root_squash
> 192.168.254.0/255.255.255.0:/mnt/nfs_test
> 
> Mount on the client side with:
> mount -o rdma,port=20049 192.168.254.1:/mnt/nfs_test /mnt/nfs_test
> 
> Any advice on tracking this down further would be greatly appreciated.
> 
> Thanks
> 
> -Denny
> 

--
Chuck Lever







[Index of Archives]     [Linux Filesystem Development]     [Linux USB Development]     [Linux Media Development]     [Video for Linux]     [Linux NILFS]     [Linux Audio Users]     [Yosemite Info]     [Linux SCSI]

  Powered by Linux