osd: drop 'osd recovery max active' back to previous default (5)

Having this too large means that queues get too deep on the OSDs during
backfill and latency is very high.  In my tests, it also meant we generated
a lot of slow recovery messages just from the recovery ops themselves (no
client io).

Keeping this at the old default means we are no worse in this respect than
argonaut, which is a safe position to start from.

Signed-off-by: Sage Weil <sage@inktank.com>

diff --git a/src/common/config_opts.h b/src/common/config_opts.h
index 9c62c1958b33a5fd504ab33eaafbfa593af79c1d..55db517b055e85c1fbec71b3cef5b275eb1ecf08 100644 (file)
--- a/src/common/config_opts.h
+++ b/src/common/config_opts.h
@@ -337,7 +337,7 @@ OPTION(osd_default_data_pool_replay_window, OPT_INT, 45)
 OPTION(osd_preserve_trimmed_log, OPT_BOOL, false)
 OPTION(osd_auto_mark_unfound_lost, OPT_BOOL, false)
 OPTION(osd_recovery_delay_start, OPT_FLOAT, 15)
-OPTION(osd_recovery_max_active, OPT_INT, 20)
+OPTION(osd_recovery_max_active, OPT_INT, 5)
 OPTION(osd_recovery_max_chunk, OPT_U64, 8<<20)  // max size of push chunk
 OPTION(osd_recovery_forget_lost_objects, OPT_BOOL, false)   // off for now
 OPTION(osd_max_scrubs, OPT_INT, 1)