40e5d4a0bc
Since ftl write buffers are associated with IO channels there can be situation that block that is being relocating could be still in cache. Such scenario is very likely when ftl is throttling user IO. l2p update should handle such situation when data is coming from relocation. Change-Id: Id0bb53d8ce45213b05bafa9ebcb843ce8eadbc7a Signed-off-by: Wojciech Malikowski <wojciech.malikowski@intel.com> Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1439 Tested-by: SPDK CI Jenkins <sys_sgci@intel.com> Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com> Reviewed-by: Jim Harris <james.r.harris@intel.com> Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com> |
||
---|---|---|
.. | ||
ftl_addr.h | ||
ftl_band.c | ||
ftl_band.h | ||
ftl_core.c | ||
ftl_core.h | ||
ftl_debug.c | ||
ftl_debug.h | ||
ftl_init.c | ||
ftl_io.c | ||
ftl_io.h | ||
ftl_reloc.c | ||
ftl_reloc.h | ||
ftl_restore.c | ||
ftl_trace.c | ||
ftl_trace.h | ||
Makefile | ||
spdk_ftl.map |