X-Git-Url: https://git.arvados.org/arvados.git/blobdiff_plain/2924f222d9efdb1b8776225d2d51bc8771d7b077..6d1c41d6fd83824669cd1a6d714ea6da1ae7ab4c:/services/fuse/arvados_fuse/command.py

diff --git a/services/fuse/arvados_fuse/command.py b/services/fuse/arvados_fuse/command.py
index 8cb0a0601b..c2242eb2bf 100644
--- a/services/fuse/arvados_fuse/command.py
+++ b/services/fuse/arvados_fuse/command.py
@@ -16,6 +16,7 @@ import signal
 import subprocess
 import sys
 import time
+import resource
 
 import arvados.commands._util as arv_cmd
 from arvados_fuse import crunchstat
@@ -133,6 +134,15 @@ class Mount(object):
         if self.args.logfile:
             self.args.logfile = os.path.realpath(self.args.logfile)
 
+        try:
+            nofile_limit = resource.getrlimit(resource.RLIMIT_NOFILE)
+            if nofile_limit[0] < 10240:
+                resource.setrlimit(resource.RLIMIT_NOFILE, (min(10240, nofile_limit[1]), nofile_limit[1]))
+        except Exception as e:
+            self.logger.warning("arv-mount: unable to adjust file handle limit: %s", e)
+
+        self.logger.debug("arv-mount: file handle limit is %s", resource.getrlimit(resource.RLIMIT_NOFILE))
+
         try:
             self._setup_logging()
             self._setup_api()
@@ -218,14 +228,28 @@ class Mount(object):
 
     def _setup_api(self):
         try:
+            # default value of file_cache is 0, this tells KeepBlockCache to
+            # choose a default based on whether disk_cache is enabled or not.
+
+            block_cache = arvados.keep.KeepBlockCache(cache_max=self.args.file_cache,
+                                                      disk_cache=self.args.disk_cache,
+                                                      disk_cache_dir=self.args.disk_cache_dir)
+
+            # If there's too many prefetch threads and you
+            # max out the CPU, delivering data to the FUSE
+            # layer actually ends up being slower.
+            # Experimentally, capping 7 threads seems to
+            # be a sweet spot.
+            prefetch_threads = min(max((block_cache.cache_max // (64 * 1024 * 1024)) - 1, 1), 7)
+
             self.api = arvados.safeapi.ThreadSafeApiCache(
                 apiconfig=arvados.config.settings(),
-                # default value of file_cache is 0, this tells KeepBlockCache to
-                # choose a default based on whether disk_cache is enabled or not.
+                api_params={
+                    'num_retries': self.args.retries,
+                },
                 keep_params={
-                    'block_cache': arvados.keep.KeepBlockCache(cache_max=self.args.file_cache,
-                                                               disk_cache=self.args.disk_cache,
-                                                               disk_cache_dir=self.args.disk_cache_dir),
+                    'block_cache': block_cache,
+                    'num_prefetch_threads': prefetch_threads,
                     'num_retries': self.args.retries,
                 },
                 version='v1',