[Devel] [PATCH RHEL COMMIT] ve/vfs: introduce "fs.odirect_enable" sysctl and disable it by default

Konstantin Khorenko khorenko at virtuozzo.com
Mon Oct 4 20:39:09 MSK 2021


The commit is pushed to "branch-rh9-5.14.vz9.1.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git
after ark-5.14
------>
commit 2731a47d966376ee02b038a3356ad3ec38243c8e
Author: Konstantin Khorenko <khorenko at virtuozzo.com>
Date:   Mon Oct 4 20:39:08 2021 +0300

    ve/vfs: introduce "fs.odirect_enable" sysctl and disable it by default
    
    We've observed a situation when in case of many Containers on a node
    even small direct disk io in each CT brings the whole node to knees
    (100 CTs, 5 lines of logs written each 20-30 seconds).
    The node had surely slow hdds.
    
    Note, that this significantly slows down async reads: they can be direct
    only, if they are called in cached mode, they effectively became
    synchronous in case > 1 writers.
    
    Example:
     # fio --randrepeat=1 --ioengine=libaio --direct=1 --gtod_reduce=1 \
       --name=test --filename=test --bs=4k --iodepth=64 --size=1G \
       --readwrite=randrw --rwmixread=75
    
    The vps here resulted in 20MB/s read and 6.8MB/s write, while other VPS
    (with O_DIRECT enabled) resulted in 230MB/s read and 76MB/s write.
    
    The root cause is known: libaio becomes synchronous in case of cached io.
    
    So the userspace is better check if underlying disk is fast enough and
    enable O_DIRECT in those cases.
    
    https://jira.sw.ru/browse/PSBM-53458
    https://jira.sw.ru/browse/PSBM-68005
    https://jira.sw.ru/browse/PSBM-68656
    https://jira.sw.ru/browse/PSBM-100671
    https://jira.sw.ru/browse/PSBM-104338
    
    Signed-off-by: Konstantin Khorenko <khorenko at virtuozzo.com>
    
    ===============================================================
    ===============================================================
    Original commit message:
    
     commit f5829bccbd390437013bd914d68caabf79d09b3e
     Author: Konstantin Khorenko <khorenko at virtuozzo.com>
     Date:   Mon Dec 11 23:00:45 2017 +0300
    
        ve/fs: introduce "fs.fsync-enable" and "fs.odirect_enable" sysctls
    
        ve/vfs: introduce "odirect_enable" sysctl and disable it by default
    
        khorenko@: we want to disable direct access from inside Container
                because this is limited numbers of direct requests available
                on the system (128), and in case they are busy next request
                is provided only after some requst is completed.
                There is no any scheduler at this level => DDoS is possible
                from inside a CT: just run _many_ processes writing with O_DIRECT.
    
        diff-vfs-odirect-enable && diff-vfs-odirect-enable-location-fix
    
        Signed-off-by: Kirill Tkhai <ktkhai at parallels.com>
    
        +++
        ve/fs: Port fs.fsync-enable and fs.odirect_enable sysctls
    
        This is a part of 74-diff-ve-mix-combined.
    
        https://jira.sw.ru/browse/PSBM-17903
    
        Signed-off-by: Kirill Tkhai <ktkhai at parallels.com>
    
        =====================================================
    
        ve/fs: check container odirect and fsync settings in __dentry_open
    
        sys_open for conventional filesystems doesn't call dentry_open,
        it calls __dentry_open (in nameidata_to_filp), so we have to move
        checks for odirect and fsync behaviour to __dentry_open
        to make them working on ploop containers.
    
        https://jira.sw.ru/browse/PSBM-17157
    
        Signed-off-by: Dmitry Guryanov <dguryanov at parallels.com>
    
        Acked-by: Dmitry Monakhov <dmonakhov at openvz.org>
        Signed-off-by: Dmitry Monakhov <dmonakhov at openvz.org>
    
        ================================================
    
        ve: initialize fsync_enable also for non ve0 environment
    
        Patchset description:
    
        ve: fix initialization and remove sysctl_fsync_enable
    
        v2:
        - initialize only on ve cgroup creation, remove get_ve_features
        - rename setup_iptables_mask into ve_setup_iptables_mask
    
        https://jira.sw.ru/browse/PSBM-34286
        https://jira.sw.ru/browse/PSBM-34285
    
        Pavel Tikhomirov (4):
          ve: remove sysctl_fsync_enable and use ve_fsync_behavior instead
          ve: initialize fsync_enable also for non ve0 environment
          ve: iptables: fix mask initialization and changing
          ve: cgroup: initialize odirect_enable, features and _randomize_va_space
    
        =====================================================================
        This patch description:
    
        v2: only on ve cgroup creation
    
        https://jira.sw.ru/browse/PSBM-34286
        Signed-off-by: Pavel Tikhomirov <ptikhomirov at virtuozzo.com>
        Acked-by: Dmitry Monakhov <dmonakhov at openvz.org>
    
    (cherry picked from vz8 commit 166db3147c1b29b4247e50eeae6c18f4ca88c162)
    Signed-off-by: Andrey Zhadchenko <andrey.zhadchenko at virtuozzo.com>
---
 fs/fcntl.c         | 30 ++++++++++++++++++++++++++++++
 fs/open.c          |  3 +++
 include/linux/fs.h |  2 ++
 include/linux/ve.h |  1 +
 kernel/sysctl.c    |  7 +++++++
 kernel/ve/ve.c     |  2 ++
 6 files changed, 45 insertions(+)

diff --git a/fs/fcntl.c b/fs/fcntl.c
index 714e7c9a5fc4..2e0c8515bd1a 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -26,6 +26,7 @@
 #include <linux/memfd.h>
 #include <linux/compat.h>
 #include <linux/mount.h>
+#include <linux/ve.h>
 
 #include <linux/poll.h>
 #include <asm/siginfo.h>
@@ -33,11 +34,40 @@
 
 #define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME)
 
+/*
+ * Host is always allowed to use O_DIRECT.
+ * Host's value of sysctl "fs.odirect_enable" might affect Containers only.
+ *
+ * Container's "fs.odirect_enable" sysctl value means:
+ *  0: Container ignores O_DIRECT flag
+ *  1: Container honors  O_DIRECT flag (in fact, any X>0 && X != 2)
+ *  2: Container checks the host's sysctl value and work according it
+ */
+int may_use_odirect(void)
+{
+	int may;
+
+	if (ve_is_super(get_exec_env()))
+		return 1;
+
+	may = capable(CAP_SYS_RAWIO);
+	if (!may) {
+		may = get_exec_env()->odirect_enable;
+		if (may == 2)
+			may = get_ve0()->odirect_enable;
+	}
+
+	return may;
+}
+
 static int setfl(int fd, struct file * filp, unsigned long arg)
 {
 	struct inode * inode = file_inode(filp);
 	int error = 0;
 
+	if (!may_use_odirect())
+		arg &= ~O_DIRECT;
+
 	/*
 	 * O_APPEND cannot be cleared if the file is marked as append-only
 	 * and the file is open for write.
diff --git a/fs/open.c b/fs/open.c
index 21c941193783..040df8bc6e76 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -782,6 +782,9 @@ static int do_dentry_open(struct file *f,
 	f->f_wb_err = filemap_sample_wb_err(f->f_mapping);
 	f->f_sb_err = file_sample_sb_err(f);
 
+	if (!may_use_odirect())
+		f->f_flags &= ~O_DIRECT;
+
 	if (unlikely(f->f_flags & O_PATH)) {
 		f->f_mode = FMODE_PATH | FMODE_OPENED;
 		f->f_op = &empty_fops;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index f4f31c29259f..8d772f6822bb 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -186,6 +186,8 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 /* File supports async buffered reads */
 #define FMODE_BUF_RASYNC	((__force fmode_t)0x40000000)
 
+extern int may_use_odirect(void);
+
 /*
  * Attribute flags.  These should be or-ed together to figure out what
  * has been changed!
diff --git a/include/linux/ve.h b/include/linux/ve.h
index bb4246147c0d..4ecfba601f45 100644
--- a/include/linux/ve.h
+++ b/include/linux/ve.h
@@ -55,6 +55,7 @@ struct ve_struct {
 #define VE_LOG_BUF_LEN		4096
 
 	struct kstat_lat_pcpu_struct    sched_lat_ve;
+	int			odirect_enable;
 
 #if IS_ENABLED(CONFIG_BINFMT_MISC)
 	struct binfmt_misc	*binfmt_misc;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 9321aa702a25..55054f136f68 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -3443,6 +3443,13 @@ static struct ctl_table fs_table[] = {
 		.child		= sysctl_mount_point,
 	},
 #endif
+	{
+		.procname	= "odirect_enable",
+		.data		= &ve0.odirect_enable,
+		.maxlen		= sizeof(int),
+		.mode		= 0644 | S_ISVTX,
+		.proc_handler	= proc_dointvec_virtual,
+	},
 	{
 		.procname	= "pipe-max-size",
 		.data		= &pipe_max_size,
diff --git a/kernel/ve/ve.c b/kernel/ve/ve.c
index a1888d6717f6..5822f74ea2a2 100644
--- a/kernel/ve/ve.c
+++ b/kernel/ve/ve.c
@@ -629,6 +629,8 @@ static struct cgroup_subsys_state *ve_create(struct cgroup_subsys_state *parent_
 
 	ve->meminfo_val = VE_MEMINFO_DEFAULT;
 
+	ve->odirect_enable = 2;
+
 	atomic_set(&ve->netns_avail_nr, NETNS_MAX_NR_DEFAULT);
 	ve->netns_max_nr = NETNS_MAX_NR_DEFAULT;
 


More information about the Devel mailing list