From ec60f44b6493abdde7bc765d7925fe2c8df3ec02 Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi@scylladb.com>
Date: Sun, 30 May 2021 15:02:52 +0300
Subject: [PATCH] main: improve process file limit handling

We check that the number of open files is sufficent for normal
work (with lots of connections and sstables), but we can improve
it a little. Systemd sets up a low file soft limit by default (so that
select() doesn't break on file descriptors larger than 1023) and
recommends[1] raising the soft limit to the more generous hard limit
if the application doesn't use select(), as ours does not.

Follow the recommendation and bump the limit. Note that this applies
only to scylla started from the command line, as systemd integration
already raises the soft limit.

[1] http://0pointer.net/blog/file-descriptor-limits.html

Closes #8756
---
 main.cc | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/main.cc b/main.cc
index b3d71a0f28..563bf0bf15 100644
--- a/main.cc
+++ b/main.cc
@@ -239,12 +239,24 @@ public:
 
 static
 void
-verify_rlimit(bool developer_mode) {
+adjust_and_verify_rlimit(bool developer_mode) {
     struct rlimit lim;
     int r = getrlimit(RLIMIT_NOFILE, &lim);
     if (r == -1) {
         throw std::system_error(errno, std::system_category());
     }
+
+    // First, try to increase the soft limit to the hard limit
+    // Ref: http://0pointer.net/blog/file-descriptor-limits.html
+
+    if (lim.rlim_cur < lim.rlim_max) {
+        lim.rlim_cur = lim.rlim_max;
+        r = setrlimit(RLIMIT_NOFILE, &lim);
+        if (r == -1) {
+            startlog.warn("adjusting RLIMIT_NOFILE failed with {}", std::system_error(errno, std::system_category()));
+        }
+    }
+
     auto recommended = 200'000U;
     auto min = 10'000U;
     if (lim.rlim_cur < min) {
@@ -566,7 +578,7 @@ int main(int ac, char** av) {
                 default_sg.set_shares(200);
             }).get();
 
-            verify_rlimit(cfg->developer_mode());
+            adjust_and_verify_rlimit(cfg->developer_mode());
             verify_adequate_memory_per_shard(cfg->developer_mode());
             if (cfg->partitioner() != "org.apache.cassandra.dht.Murmur3Partitioner") {
                 if (cfg->enable_deprecated_partitioners()) {