View Issue Details

IDProjectCategoryView StatusLast Update
0016996CentOS-7kernelpublic2020-02-01 03:16
Reporterlccc7liu 
PrioritynormalSeverityminorReproducibilityalways
Status newResolutionopen 
Product Version7.6.1810 
Target VersionFixed in Version 
Summary0016996: SSD performance drop if FIO io queue depth bigger than SSD recommanded arbitration burst.
Descriptionfor SSD sequential read, base on SSD round robin arbitration, if host send io command size bigger than recommanded arbitration burst in each io queue, then will cause device handled LBA sequence is not sequential, thus, device sequential read performance will drop.
in Centos7, nvme driver can fetch recommanded arbitration burst value with SSD identify device command, but this value is not referenced in kernel, which may be caused by blk-mq feature porting.
so when we test SSD performance with FIO, if io queue depth is bigger than device recommanded arbitration burst, performan is not stable.
Steps To Reproduceinstall nvme-cli and FIO
fetch SSD recommanded arbitration burst value with nvme-cli
test SSD sequential read performance with io queue depth bigger than recommanded arbitration burst(libaio engine)
TagsNo tags attached.
abrt_hash
URL

Activities

There are no notes attached to this issue.

Issue History

Date Modified Username Field Change
2020-02-01 03:16 lccc7liu New Issue