Details
-
New Feature
-
Resolution: Fixed
-
Major
-
Lustre 2.4.0
-
16,900
-
4038
Description
Currently Lustre maximum buffer size for a RPC sending I/O is 1MB. This work looks to change the amount of data transfer to allow the data sent to be a size to achieve peak performance with large I/O transfers to the back end disk. Also an additional benefit is the reduction in the round trip time to send the data.
Attachments
Issue Links
- is related to
-
LU-4533 rpc_stats histogram does not support max_rpcs_in_flight greater than 31
- Open
-
LU-3308 large readdir chunk size slows unlink/"rm -r" performance
- Reopened
-
LU-2791 Stuck client on server OOM/lost message
- Resolved
-
LU-2816 sanity-benchmark test_bonnie slow after 4MB BRW RPC patch
- Resolved
-
LU-2598 obdfilter-survey LBUG ASSERTION( iobuf->dr_npages < iobuf->dr_max_pages ) failed
- Resolved
-
LU-2790 Failure to allocated osd keys leads to ofd_intent_policy()) ASSERTION( res_lvb != ((void *)0) ) failed
- Resolved
-
LU-3438 replay-ost-single test_5 failed with error int check_write_rcs() "Unexpected # bytes transferred"
- Resolved
-
LU-2748 OSD uses kmalloc with high order to allocate a keys
- Resolved
-
LUDOC-80 4MB RPC Doc Changes
- Resolved
- is related to
-
LUDOC-80 4MB RPC Doc Changes
- Resolved
-
LU-2424 add memory limits for ptlrpc service
- Resolved
- Trackbacks
-
Lustre Community Development in Progress Features are being developed for future Lustre releases both at Whamcloud and by other organizations in the Lustre community. These will be eligible for inclusion in future Lustre releases as per our processes