[lustre-discuss] About Lustre small files performace(8k) improve

[Cameron Harr]

I'll assume here you're referring to MPI-IO, which is not really a 
"feature" but a way to perform parallel I/O using the message passing 
interface (MPI) stack. There can also be different interpretations of 
what MPI-IO exactly means: many HPC applications (and benchmarks such as 
IOR) use MPI and can write out data in parallel using various I/O APIs. 
One of those APIs for IOR is "mpiio", from the web page:

-a S api – API for I/O [POSIX|MPIIO|HDF5|HDFS|S3|S3_EMC|NCMPI|RADOS] In 
short, running parallel threads to write files will usually boost your 
IOPs to a point, though which API you choose should probably reflect 
what your real-life applications use. Cameron

On 3/18/23 2:44 AM, 王烁斌 via lustre-discuss wrote:
> Hi all,
>
> This is my Lustre FS.
> UUID                   1K-blocks        Used   Available Use% Mounted on
> ltfs-MDT0000_UUID      307826072       36904   281574768  1% 
> /mnt/lfs[MDT:0]
> ltfs-MDT0001_UUID      307826072       36452   281575220  1% 
> /mnt/lfs[MDT:1]
> ltfs-MDT0002_UUID      307826072       36600   281575072  1% 
> /mnt/lfs[MDT:2]
> ltfs-MDT0003_UUID      307826072       36300   281575372  1% 
> /mnt/lfs[MDT:3]
> ltfs-OST0000_UUID    15962575136     1027740 15156068868  1% 
> /mnt/lfs[OST:0]
> ltfs-OST0001_UUID    15962575136     1027780 15156067516  1% 
> /mnt/lfs[OST:1]
> ltfs-OST0002_UUID    15962575136     1027772 15156074212  1% 
> /mnt/lfs[OST:2]
> ltfs-OST0003_UUID    15962575136     1027756 15156067860  1% 
> /mnt/lfs[OST:3]
> ltfs-OST0004_UUID    15962575136     1027728 15156058224  1% 
> /mnt/lfs[OST:4]
> ltfs-OST0005_UUID    15962575136     1027772 15156057668  1% 
> /mnt/lfs[OST:5]
> ltfs-OST0006_UUID    15962575136     1027768 15156058568  1% 
> /mnt/lfs[OST:6]
> ltfs-OST0007_UUID    15962575136     1027792 15156056752  1% 
> /mnt/lfs[OST:7]
>
> filesystem_summary:  127700601088     8222108 121248509668   1% /mnt/lfs
>
> Structure ias flow:
>
> After testing, under the current structure, the write performance of 
> 500,000 "8k" small files is:
> NFSclient1——IOPS：28,000;  bandwidth——230MB
> NFSclient1——IOPS：27,500;  bandwidth——220MB
>
> Now I want to improve the performance of small files to a better 
> level，May I ask if there is a better way。
>
> I have noticed a feature called "MIP-IO" that can improve small file 
> performance, but I don't know how to deploy this feature. Is there any 
> way to improve small file performance？
>
>
>
>
> _______________________________________________
> lustre-discuss mailing list
> lustre-discuss at lists.lustre.org
> https://urldefense.us/v3/__http://lists.lustre.org/listinfo.cgi/lustre-discuss-lustre.org__;!!G2kpM7uM-TzIFchu!jpxmiee-6Txz4MkvTdXq-z7hM1I20qZ98shFSOwVie2UEZXxjo7aWF6Im3x0pik$  
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.lustre.org/pipermail/lustre-discuss-lustre.org/attachments/20230327/efe44249/attachment-0001.htm>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image.png
Type: image/png
Size: 52934 bytes
Desc: not available
URL: <http://lists.lustre.org/pipermail/lustre-discuss-lustre.org/attachments/20230327/efe44249/attachment-0001.png>