Details
-
New Feature
-
Resolution: Duplicate
-
Major
-
None
-
None
-
None
-
9223372036854775807
Description
On machines with slow single thread performance like KNL the bottleneck of I/O performance moved into code which just copy memory from one buffer to other (from user space to kernel or vice versa). In current Lustre implementation all I/O performs in single thread and this is become an issue for KNL. Significantly improve performance can be with solution which do parallel memory transfer of large buffers.
Attachments
Issue Links
- is duplicated by
-
LU-1056 Single-client, single-thread and single-file is limited at 1.5GB/s
- Resolved
- is related to
-
LU-11069 ifort lseek returns wrong position on lustre 2.10.3
- Resolved
-
LU-10367 FIO Fails to run with libaio
- Resolved
-
LU-9618 Connect readahead to prep_partial_page to improve small (< 1 page) write performance
- Resolved
-
LU-11825 Remove LU-8964/pio feature & supporting framework
- Resolved
-
LU-12043 improve Lustre single thread read performances
- Resolved
- is related to
-
LU-6658 single stream write performance improvement with worker threads in llite
- Resolved
-
LU-8709 parallel asynchronous readahead
- Resolved