summaryrefslogtreecommitdiffstats
path: root/xlators/features/bit-rot/src/bitd/bit-rot-tbf.h
diff options
context:
space:
mode:
authorVenky Shankar <vshankar@redhat.com>2015-04-17 15:00:13 +0530
committerNiels de Vos <ndevos@redhat.com>2015-05-10 05:29:05 -0700
commit37bb956ee3d181314d487dfdabd9a1fd8b5f9d9c (patch)
treee0b8c2aefb19feb6654236ab71b5aa173db8acb6 /xlators/features/bit-rot/src/bitd/bit-rot-tbf.h
parent738620a5eeeee3802c09275831ac2b85d4ce91e5 (diff)
features/bit-rot: Token Bucket based throttling
BitRot daemons (signer & scrubber) are disk/cpu hoggers when left running full throttle. Checksum calculations (especially SHA family of hash routines) can be quite CPU intensive. Moreover periodic disk scans performed by scrubber followed by reading data blocks for hash calculation (which is also done by signer) generate lot of heavy IO request(s). This causes interference with actual client operations (be it a regular client or filesystems daemons such as self-heal, etc..) and results in degraded system performance. This patch introduces throttling based on Token Bucket Filtering[1]. It's a well known algorithm for checking (and ensuring) that data transmission conform to defined limits and generally used in packet switched networks. Linux control groups (Cgroups) uses a variant[2] of this algorithm to provide block device IO throttling (cgroup subsys "blkio": blk-iothrottle). So, why not just live with Cgroups? Cgroups is linux specific. We need to have a throttling mechanism for other supported UNIXes. Moreover, having our own implementation gives much more finer control in terms of tuning it for our needs (plus the simplicity of the alogorithm itself). Ideally, throttling should be a part of server stack (either as a separate translator or integrated with io-threads) since that's the point of entry for IO request(s) from *all* client(s). That way one could selectively throttle IO request(s) based on client PIDs (frame->root->pid), e.g., self-heal daemon, bitrot, etc.. (*actual* clients can run full throttle). This implementation avoids that deliberately (there needs to be a much more smarter queueing mechanism) and throttles CPU usage for hash calculations. This patch is just the infrastructure part with no interfaces exposed to set various throttling values. The tunable selected here (basically hardcoded) avoids 100% CPU usage during hash calculation (with some bursts cycles). We'd need much more intensive test(s) to assign values for various throttling options (lazy/normal/aggressive). [1] https://en.wikipedia.org/wiki/Token_bucket [2] http://en.wikipedia.org/wiki/Token_bucket#Hierarchical_token_bucket > Change-Id: Icc49af80eeab6adb60166d0810e69ef37cfe2fd8 > BUG: 1207020 > Signed-off-by: Venky Shankar <vshankar@redhat.com> > Reviewed-on: http://review.gluster.org/10307 > Reviewed-by: Vijay Bellur <vbellur@redhat.com> > Tested-by: Vijay Bellur <vbellur@redhat.com> Change-Id: I034ba1095aa3bfc3212a67a63ffb931431b372f6 Signed-off-by: Venky Shankar <vshankar@redhat.com> BUG: 1220041 Reviewed-on: http://review.gluster.org/10719 Tested-by: NetBSD Build System Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Gaurav Kumar Garg <ggarg@redhat.com>
Diffstat (limited to 'xlators/features/bit-rot/src/bitd/bit-rot-tbf.h')
-rw-r--r--xlators/features/bit-rot/src/bitd/bit-rot-tbf.h70
1 files changed, 70 insertions, 0 deletions
diff --git a/xlators/features/bit-rot/src/bitd/bit-rot-tbf.h b/xlators/features/bit-rot/src/bitd/bit-rot-tbf.h
new file mode 100644
index 00000000000..5a41be4fd95
--- /dev/null
+++ b/xlators/features/bit-rot/src/bitd/bit-rot-tbf.h
@@ -0,0 +1,70 @@
+/*
+ Copyright (c) 2015 Red Hat, Inc. <http://www.redhat.com>
+ This file is part of GlusterFS.
+
+ This file is licensed to you under your choice of the GNU Lesser
+ General Public License, version 3 or any later version (LGPLv3 or
+ later), or the GNU General Public License, version 2 (GPLv2), in all
+ cases as published by the Free Software Foundation.
+*/
+
+#include "list.h"
+#include "xlator.h"
+#include "locking.h"
+
+#ifndef __BIT_ROT_TBF_H__
+#define __BIT_ROT_TBF_H__
+
+typedef enum br_tbf_ops {
+ BR_TBF_OP_MIN = -1,
+ BR_TBF_OP_HASH = 0, /* checksum calculation */
+ BR_TBF_OP_READ = 1, /* inode read(s) */
+ BR_TBF_OP_READDIR = 2, /* dentry read(s) */
+ BR_TBF_OP_MAX = 3,
+} br_tbf_ops_t;
+
+/**
+ * Operation rate specification
+ */
+typedef struct br_tbf_opspec {
+ br_tbf_ops_t op;
+
+ unsigned long rate;
+
+ unsigned long maxlimit;
+} br_tbf_opspec_t;
+
+/**
+ * Token bucket for each operation type
+ */
+typedef struct br_tbf_bucket {
+ gf_lock_t lock;
+
+ pthread_t tokener; /* token generator thread */
+
+ unsigned long tokenrate; /* token generation rate */
+
+ unsigned long tokens; /* number of current tokens */
+
+ unsigned long maxtokens; /* maximum token in the bucket */
+
+ struct list_head queued; /* list of non-conformant requests */
+} br_tbf_bucket_t;
+
+typedef struct br_tbf {
+ br_tbf_bucket_t **bucket;
+} br_tbf_t;
+
+br_tbf_t *
+br_tbf_init (br_tbf_opspec_t *, unsigned int);
+
+int
+br_tbf_mod (br_tbf_t *, br_tbf_opspec_t *);
+
+void
+br_tbf_throttle (br_tbf_t *, br_tbf_ops_t, unsigned long);
+
+#define TBF_THROTTLE_BEGIN(tbf, op, tokens) (br_tbf_throttle (tbf, op, tokens))
+#define TBF_THROTTLE_END(tbf, op, tokens) (void)
+
+#endif /** __BIT_ROT_TBF_H__ */