github/open-cas-linux
2
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Set promote_on_threshold sequential cutoff flag

Browse Source 
Due to linux thread scheduling nature, we prefer to promote streams
as early as we reasonably can. One way to achieve that is to set
promotion count really low, which unfortunately significantly increases
number of accesses to shared structures. The other way is to promote
streams which reach cutoff threshold, as we can reasonably assume that
they are likely be continued after thread is rescheduled to another CPU.

Signed-off-by: Rafal Stefanowski <rafal.stefanowski@intel.com>
This commit is contained in:
Rafal Stefanowski 2021-11-09 13:41:49 +01:00
parent 259f9e3c58
commit 2097f8029b
2 changed files with 10 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
modules/cas_cache/layer_cache_management.c
View File

@ -1346,6 +1346,15 @@ int cache_mngt_add_core_to_cache(const char *cache_name, size_t name_len,
cfg->seq_cutoff_threshold = seq_cut_off_mb * MiB; cfg->seq_cutoff_threshold = seq_cut_off_mb * MiB;
cfg->seq_cutoff_promotion_count = 8; cfg->seq_cutoff_promotion_count = 8;
/* Due to linux thread scheduling nature, we prefer to promote streams
* as early as we reasonably can. One way to achieve that is to set
* promotion count really low, which unfortunately significantly increases
* number of accesses to shared structures. The other way is to promote
* streams which reach cutoff threshold, as we can reasonably assume that
* they are likely be continued after thread is rescheduled to another CPU.
*/
cfg->seq_cutoff_promote_on_threshold = true;
init_completion(&add_context.cmpl); init_completion(&add_context.cmpl);
add_context.core = &core; add_context.core = &core;
add_context.result = &result; add_context.result = &result;

2
ocf

@ -1 +1 @@
Subproject commit 12c8b4e333d7472f55f277195418db3df8ba6e2d Subproject commit f6e337ac79f0f016ee053b1fc6caf44abeb9cbf8