#!/usr/bin/env @PYTHON_SHEBANG@
#
# Print out ZFS ARC Statistics exported via kstat(1)
# For a definition of fields, or usage, use arcstat -v
#
# This script was originally a fork of the original arcstat.pl (0.1)
# by Neelakanth Nadgir, originally published on his Sun blog on
# 09/18/2007
#     http://blogs.sun.com/realneel/entry/zfs_arc_statistics
#
# A new version aimed to improve upon the original by adding features
# and fixing bugs as needed.  This version was maintained by Mike
# Harsch and was hosted in a public open source repository:
#    http://github.com/mharsch/arcstat
#
# but has since moved to the illumos-gate repository.
#
# This Python port was written by John Hixson for FreeNAS, introduced
# in commit e2c29f:
#    https://github.com/freenas/freenas
#
# and has been improved by many people since.
#
# CDDL HEADER START
#
# The contents of this file are subject to the terms of the
# Common Development and Distribution License, Version 1.0 only
# (the "License").  You may not use this file except in compliance
# with the License.
#
# You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
# or https://opensource.org/licenses/CDDL-1.0.
# See the License for the specific language governing permissions
# and limitations under the License.
#
# When distributing Covered Code, include this CDDL HEADER in each
# file and include the License file at usr/src/OPENSOLARIS.LICENSE.
# If applicable, add the following below this CDDL HEADER, with the
# fields enclosed by brackets "[]" replaced with your own identifying
# information: Portions Copyright [yyyy] [name of copyright owner]
#
# CDDL HEADER END
#
#
# Fields have a fixed width. Every interval, we fill the "v"
# hash with its corresponding value (v[field]=value) using calculate().
# @hdr is the array of fields that needs to be printed, so we
# just iterate over this array and print the values using our pretty printer.
#
# This script must remain compatible with Python 3.6+.
#

import sys
import time
import getopt
import re
import copy

from signal import signal, SIGINT, SIGWINCH, SIG_DFL


cols = {
    # HDR:        [Size, Scale, Description]
    "time":       [8, -1, "Time"],
    "hits":       [4, 1000, "ARC hits per second"],
    "iohs":       [4, 1000, "ARC I/O hits per second"],
    "miss":       [4, 1000, "ARC misses per second"],
    "read":       [4, 1000, "Total ARC accesses per second"],
    "hit%":       [4, 100, "ARC hit percentage"],
    "ioh%":       [4, 100, "ARC I/O hit percentage"],
    "miss%":      [5, 100, "ARC miss percentage"],
    "dhit":       [4, 1000, "Demand hits per second"],
    "dioh":       [4, 1000, "Demand I/O hits per second"],
    "dmis":       [4, 1000, "Demand misses per second"],
    "dh%":        [3, 100, "Demand hit percentage"],
    "di%":        [3, 100, "Demand I/O hit percentage"],
    "dm%":        [3, 100, "Demand miss percentage"],
    "ddhit":      [5, 1000, "Demand data hits per second"],
    "ddioh":      [5, 1000, "Demand data I/O hits per second"],
    "ddmis":      [5, 1000, "Demand data misses per second"],
    "ddh%":       [4, 100, "Demand data hit percentage"],
    "ddi%":       [4, 100, "Demand data I/O hit percentage"],
    "ddm%":       [4, 100, "Demand data miss percentage"],
    "dmhit":      [5, 1000, "Demand metadata hits per second"],
    "dmioh":      [5, 1000, "Demand metadata I/O hits per second"],
    "dmmis":      [5, 1000, "Demand metadata misses per second"],
    "dmh%":       [4, 100, "Demand metadata hit percentage"],
    "dmi%":       [4, 100, "Demand metadata I/O hit percentage"],
    "dmm%":       [4, 100, "Demand metadata miss percentage"],
    "phit":       [4, 1000, "Prefetch hits per second"],
    "pioh":       [4, 1000, "Prefetch I/O hits per second"],
    "pmis":       [4, 1000, "Prefetch misses per second"],
    "ph%":        [3, 100, "Prefetch hits percentage"],
    "pi%":        [3, 100, "Prefetch I/O hits percentage"],
    "pm%":        [3, 100, "Prefetch miss percentage"],
    "pdhit":      [5, 1000, "Prefetch data hits per second"],
    "pdioh":      [5, 1000, "Prefetch data I/O hits per second"],
    "pdmis":      [5, 1000, "Prefetch data misses per second"],
    "pdh%":       [4, 100, "Prefetch data hits percentage"],
    "pdi%":       [4, 100, "Prefetch data I/O hits percentage"],
    "pdm%":       [4, 100, "Prefetch data miss percentage"],
    "pmhit":      [5, 1000, "Prefetch metadata hits per second"],
    "pmioh":      [5, 1000, "Prefetch metadata I/O hits per second"],
    "pmmis":      [5, 1000, "Prefetch metadata misses per second"],
    "pmh%":       [4, 100, "Prefetch metadata hits percentage"],
    "pmi%":       [4, 100, "Prefetch metadata I/O hits percentage"],
    "pmm%":       [4, 100, "Prefetch metadata miss percentage"],
    "mhit":       [4, 1000, "Metadata hits per second"],
    "mioh":       [4, 1000, "Metadata I/O hits per second"],
    "mmis":       [4, 1000, "Metadata misses per second"],
    "mread":      [5, 1000, "Metadata accesses per second"],
    "mh%":        [3, 100, "Metadata hit percentage"],
    "mi%":        [3, 100, "Metadata I/O hit percentage"],
    "mm%":        [3, 100, "Metadata miss percentage"],
    "arcsz":      [5, 1024, "ARC size"],
    "size":       [5, 1024, "ARC size"],
    "c":          [5, 1024, "ARC target size"],
    "mfu":        [4, 1000, "MFU list hits per second"],
    "mru":        [4, 1000, "MRU list hits per second"],
    "mfug":       [4, 1000, "MFU ghost list hits per second"],
    "mrug":       [4, 1000, "MRU ghost list hits per second"],
    "unc":        [4, 1000, "Uncached list hits per second"],
    "eskip":      [5, 1000, "evict_skip per second"],
    "el2skip":    [7, 1000, "evict skip, due to l2 writes, per second"],
    "el2cach":    [7, 1024, "Size of L2 cached evictions per second"],
    "el2el":      [5, 1024, "Size of L2 eligible evictions per second"],
    "el2mfu":     [6, 1024, "Size of L2 eligible MFU evictions per second"],
    "el2mru":     [6, 1024, "Size of L2 eligible MRU evictions per second"],
    "el2inel":    [7, 1024, "Size of L2 ineligible evictions per second"],
    "mtxmis":     [6, 1000, "mutex_miss per second"],
    "dread":      [5, 1000, "Demand accesses per second"],
    "ddread":     [6, 1000, "Demand data accesses per second"],
    "dmread":     [6, 1000, "Demand metadata accesses per second"],
    "pread":      [5, 1000, "Prefetch accesses per second"],
    "pdread":     [6, 1000, "Prefetch data accesses per second"],
    "pmread":     [6, 1000, "Prefetch metadata accesses per second"],
    "l2hits":     [6, 1000, "L2ARC hits per second"],
    "l2miss":     [6, 1000, "L2ARC misses per second"],
    "l2read":     [6, 1000, "Total L2ARC accesses per second"],
    "l2hit%":     [6, 100, "L2ARC access hit percentage"],
    "l2miss%":    [7, 100, "L2ARC access miss percentage"],
    "l2pref":     [6, 1024, "L2ARC prefetch allocated size"],
    "l2mfu":      [5, 1024, "L2ARC MFU allocated size"],
    "l2mru":      [5, 1024, "L2ARC MRU allocated size"],
    "l2data":     [6, 1024, "L2ARC data allocated size"],
    "l2meta":     [6, 1024, "L2ARC metadata allocated size"],
    "l2pref%":    [7, 100, "L2ARC prefetch percentage"],
    "l2mfu%":     [6, 100, "L2ARC MFU percentage"],
    "l2mru%":     [6, 100, "L2ARC MRU percentage"],
    "l2data%":    [7, 100, "L2ARC data percentage"],
    "l2meta%":    [7, 100, "L2ARC metadata percentage"],
    "l2asize":    [7, 1024, "Actual (compressed) size of the L2ARC"],
    "l2size":     [6, 1024, "Size of the L2ARC"],
    "l2bytes":    [7, 1024, "Bytes read per second from the L2ARC"],
    "grow":       [4, 1000, "ARC grow disabled"],
    "need":       [5, 1024, "ARC reclaim need"],
    "free":       [5, 1024, "ARC free memory"],
    "avail":      [5, 1024, "ARC available memory"],
    "waste":      [5, 1024, "Wasted memory due to round up to pagesize"],
}

v = {}
hdr = ["time", "read", "ddread", "ddh%", "dmread", "dmh%", "pread", "ph%",
       "size", "c", "avail"]
xhdr = ["time", "mfu", "mru", "mfug", "mrug", "unc", "eskip", "mtxmis",
        "dread", "pread", "read"]
sint = 1               # Default interval is 1 second
count = 1              # Default count is 1
hdr_intr = 20          # Print header every 20 lines of output
opfile = None
sep = "  "              # Default separator is 2 spaces
l2exist = False
cmd = ("Usage: arcstat [-havxp] [-f fields] [-o file] [-s string] [interval "
       "[count]]\n")
cur = {}
d = {}
out = None
kstat = None
pretty_print = True


if sys.platform.startswith('freebsd'):
    # Requires py-sysctl on FreeBSD
    import sysctl

    def kstat_update():
        global kstat

        k = [ctl for ctl in sysctl.filter('kstat.zfs.misc.arcstats')
             if ctl.type != sysctl.CTLTYPE_NODE]

        if not k:
            sys.exit(1)

        kstat = {}

        for s in k:
            if not s:
                continue

            name, value = s.name, s.value
            # Trims 'kstat.zfs.misc.arcstats' from the name
            kstat[name[24:]] = int(value)

elif sys.platform.startswith('linux'):
    def kstat_update():
        global kstat

        k = [line.strip() for line in open('/proc/spl/kstat/zfs/arcstats')]

        if not k:
            sys.exit(1)

        del k[0:2]
        kstat = {}

        for s in k:
            if not s:
                continue

            name, unused, value = s.split()
            kstat[name] = int(value)


def detailed_usage():
    sys.stderr.write("%s\n" % cmd)
    sys.stderr.write("Field definitions are as follows:\n")
    for key in cols:
        sys.stderr.write("%11s : %s\n" % (key, cols[key][2]))
    sys.stderr.write("\n")

    sys.exit(0)


def usage():
    sys.stderr.write("%s\n" % cmd)
    sys.stderr.write("\t -h : Print this help message\n")
    sys.stderr.write("\t -a : Print all possible stats\n")
    sys.stderr.write("\t -v : List all possible field headers and definitions"
                     "\n")
    sys.stderr.write("\t -x : Print extended stats\n")
    sys.stderr.write("\t -f : Specify specific fields to print (see -v)\n")
    sys.stderr.write("\t -o : Redirect output to the specified file\n")
    sys.stderr.write("\t -s : Override default field separator with custom "
                     "character or string\n")
    sys.stderr.write("\t -p : Disable auto-scaling of numerical fields\n")
    sys.stderr.write("\nExamples:\n")
    sys.stderr.write("\tarcstat -o /tmp/a.log 2 10\n")
    sys.stderr.write("\tarcstat -s \",\" -o /tmp/a.log 2 10\n")
    sys.stderr.write("\tarcstat -v\n")
    sys.stderr.write("\tarcstat -f time,hit%,dh%,ph%,mh% 1\n")
    sys.stderr.write("\n")

    sys.exit(1)


def snap_stats():
    global cur
    global kstat

    prev = copy.deepcopy(cur)
    kstat_update()

    cur = kstat
    for key in cur:
        if re.match(key, "class"):
            continue
        if key in prev:
            d[key] = cur[key] - prev[key]
        else:
            d[key] = cur[key]


def prettynum(sz, scale, num=0):
    suffix = [' ', 'K', 'M', 'G', 'T', 'P', 'E', 'Z']
    index = 0
    save = 0

    # Special case for date field
    if scale == -1:
        return "%s" % num

    # Rounding error, return 0
    elif 0 < num < 1:
        num = 0

    while abs(num) > scale and index < 5:
        save = num
        num = num / scale
        index += 1

    if index == 0:
        return "%*d" % (sz, num)

    if abs(save / scale) < 10:
        return "%*.1f%s" % (sz - 1, num, suffix[index])
    else:
        return "%*d%s" % (sz - 1, num, suffix[index])


def print_values():
    global hdr
    global sep
    global v
    global pretty_print

    if pretty_print:
        fmt = lambda col: prettynum(cols[col][0], cols[col][1], v[col])
    else:
        fmt = lambda col: str(v[col])

    sys.stdout.write(sep.join(fmt(col) for col in hdr))
    sys.stdout.write("\n")
    sys.stdout.flush()


def print_header():
    global hdr
    global sep
    global pretty_print

    if pretty_print:
        fmt = lambda col: "%*s" % (cols[col][0], col)
    else:
        fmt = lambda col: col

    sys.stdout.write(sep.join(fmt(col) for col in hdr))
    sys.stdout.write("\n")


def get_terminal_lines():
    try:
        import fcntl
        import termios
        import struct
        data = fcntl.ioctl(sys.stdout.fileno(), termios.TIOCGWINSZ, '1234')
        sz = struct.unpack('hh', data)
        return sz[0]
    except Exception:
        pass


def update_hdr_intr():
    global hdr_intr

    lines = get_terminal_lines()
    if lines and lines > 3:
        hdr_intr = lines - 3


def resize_handler(signum, frame):
    update_hdr_intr()


def init():
    global sint
    global count
    global hdr
    global xhdr
    global opfile
    global sep
    global out
    global l2exist
    global pretty_print

    desired_cols = None
    aflag = False
    xflag = False
    hflag = False
    vflag = False
    i = 1

    try:
        opts, args = getopt.getopt(
            sys.argv[1:],
            "axo:hvs:f:p",
            [
                "all",
                "extended",
                "outfile",
                "help",
                "verbose",
                "separator",
                "columns",
                "parsable"
            ]
        )
    except getopt.error as msg:
        sys.stderr.write("Error: %s\n" % str(msg))
        usage()
        opts = None

    for opt, arg in opts:
        if opt in ('-a', '--all'):
            aflag = True
        if opt in ('-x', '--extended'):
            xflag = True
        if opt in ('-o', '--outfile'):
            opfile = arg
            i += 1
        if opt in ('-h', '--help'):
            hflag = True
        if opt in ('-v', '--verbose'):
            vflag = True
        if opt in ('-s', '--separator'):
            sep = arg
            i += 1
        if opt in ('-f', '--columns'):
            desired_cols = arg
            i += 1
        if opt in ('-p', '--parsable'):
            pretty_print = False
        i += 1

    argv = sys.argv[i:]
    sint = int(argv[0]) if argv else sint
    count = int(argv[1]) if len(argv) > 1 else (0 if len(argv) > 0 else 1)

    if hflag or (xflag and desired_cols):
        usage()

    if vflag:
        detailed_usage()

    if xflag:
        hdr = xhdr

    update_hdr_intr()

    # check if L2ARC exists
    snap_stats()
    l2_size = cur.get("l2_size")
    if l2_size:
        l2exist = True

    if desired_cols:
        hdr = desired_cols.split(",")

        invalid = []
        incompat = []
        for ele in hdr:
            if ele not in cols:
                invalid.append(ele)
            elif not l2exist and ele.startswith("l2"):
                sys.stdout.write("No L2ARC Here\n%s\n" % ele)
                incompat.append(ele)

        if len(invalid) > 0:
            sys.stderr.write("Invalid column definition! -- %s\n" % invalid)
            usage()

        if len(incompat) > 0:
            sys.stderr.write("Incompatible field specified! -- %s\n" %
                             incompat)
            usage()

    if aflag:
        if l2exist:
            hdr = cols.keys()
        else:
            hdr = [col for col in cols.keys() if not col.startswith("l2")]

    if opfile:
        try:
            out = open(opfile, "w")
            sys.stdout = out

        except IOError:
            sys.stderr.write("Cannot open %s for writing\n" % opfile)
            sys.exit(1)


def calculate():
    global d
    global v
    global l2exist

    v = dict()
    v["time"] = time.strftime("%H:%M:%S", time.localtime())
    v["hits"] = d["hits"] // sint
    v["iohs"] = d["iohits"] // sint
    v["miss"] = d["misses"] // sint
    v["read"] = v["hits"] + v["iohs"] + v["miss"]
    v["hit%"] = 100 * v["hits"] // v["read"] if v["read"] > 0 else 0
    v["ioh%"] = 100 * v["iohs"] // v["read"] if v["read"] > 0 else 0
    v["miss%"] = 100 - v["hit%"] - v["ioh%"] if v["read"] > 0 else 0

    v["dhit"] = (d["demand_data_hits"] + d["demand_metadata_hits"]) // sint
    v["dioh"] = (d["demand_data_iohits"] + d["demand_metadata_iohits"]) // sint
    v["dmis"] = (d["demand_data_misses"] + d["demand_metadata_misses"]) // sint

    v["dread"] = v["dhit"] + v["dioh"] + v["dmis"]
    v["dh%"] = 100 * v["dhit"] // v["dread"] if v["dread"] > 0 else 0
    v["di%"] = 100 * v["dioh"] // v["dread"] if v["dread"] > 0 else 0
    v["dm%"] = 100 - v["dh%"] - v["di%"] if v["dread"] > 0 else 0

    v["ddhit"] = d["demand_data_hits"] // sint
    v["ddioh"] = d["demand_data_iohits"] // sint
    v["ddmis"] = d["demand_data_misses"] // sint

    v["ddread"] = v["ddhit"] + v["ddioh"] + v["ddmis"]
    v["ddh%"] = 100 * v["ddhit"] // v["ddread"] if v["ddread"] > 0 else 0
    v["ddi%"] = 100 * v["ddioh"] // v["ddread"] if v["ddread"] > 0 else 0
    v["ddm%"] = 100 - v["ddh%"] - v["ddi%"] if v["ddread"] > 0 else 0

    v["dmhit"] = d["demand_metadata_hits"] // sint
    v["dmioh"] = d["demand_metadata_iohits"] // sint
    v["dmmis"] = d["demand_metadata_misses"] // sint

    v["dmread"] = v["dmhit"] + v["dmioh"] + v["dmmis"]
    v["dmh%"] = 100 * v["dmhit"] // v["dmread"] if v["dmread"] > 0 else 0
    v["dmi%"] = 100 * v["dmioh"] // v["dmread"] if v["dmread"] > 0 else 0
    v["dmm%"] = 100 - v["dmh%"] - v["dmi%"] if v["dmread"] > 0 else 0

    v["phit"] = (d["prefetch_data_hits"] + d["prefetch_metadata_hits"]) // sint
    v["pioh"] = (d["prefetch_data_iohits"] +
                 d["prefetch_metadata_iohits"]) // sint
    v["pmis"] = (d["prefetch_data_misses"] +
                 d["prefetch_metadata_misses"]) // sint

    v["pread"] = v["phit"] + v["pioh"] + v["pmis"]
    v["ph%"] = 100 * v["phit"] // v["pread"] if v["pread"] > 0 else 0
    v["pi%"] = 100 * v["pioh"] // v["pread"] if v["pread"] > 0 else 0
    v["pm%"] = 100 - v["ph%"] - v["pi%"] if v["pread"] > 0 else 0

    v["pdhit"] = d["prefetch_data_hits"] // sint
    v["pdioh"] = d["prefetch_data_iohits"] // sint
    v["pdmis"] = d["prefetch_data_misses"] // sint

    v["pdread"] = v["pdhit"] + v["pdioh"] + v["pdmis"]
    v["pdh%"] = 100 * v["pdhit"] // v["pdread"] if v["pdread"] > 0 else 0
    v["pdi%"] = 100 * v["pdioh"] // v["pdread"] if v["pdread"] > 0 else 0
    v["pdm%"] = 100 - v["pdh%"] - v["pdi%"] if v["pdread"] > 0 else 0

    v["pmhit"] = d["prefetch_metadata_hits"] // sint
    v["pmioh"] = d["prefetch_metadata_iohits"] // sint
    v["pmmis"] = d["prefetch_metadata_misses"] // sint

    v["pmread"] = v["pmhit"] + v["pmioh"] + v["pmmis"]
    v["pmh%"] = 100 * v["pmhit"] // v["pmread"] if v["pmread"] > 0 else 0
    v["pmi%"] = 100 * v["pmioh"] // v["pmread"] if v["pmread"] > 0 else 0
    v["pmm%"] = 100 - v["pmh%"] - v["pmi%"] if v["pmread"] > 0 else 0

    v["mhit"] = (d["prefetch_metadata_hits"] +
                 d["demand_metadata_hits"]) // sint
    v["mioh"] = (d["prefetch_metadata_iohits"] +
                 d["demand_metadata_iohits"]) // sint
    v["mmis"] = (d["prefetch_metadata_misses"] +
                 d["demand_metadata_misses"]) // sint

    v["mread"] = v["mhit"] + v["mioh"] + v["mmis"]
    v["mh%"] = 100 * v["mhit"] // v["mread"] if v["mread"] > 0 else 0
    v["mi%"] = 100 * v["mioh"] // v["mread"] if v["mread"] > 0 else 0
    v["mm%"] = 100 - v["mh%"] - v["mi%"] if v["mread"] > 0 else 0

    v["arcsz"] = cur["size"]
    v["size"] = cur["size"]
    v["c"] = cur["c"]
    v["mfu"] = d["mfu_hits"] // sint
    v["mru"] = d["mru_hits"] // sint
    v["mrug"] = d["mru_ghost_hits"] // sint
    v["mfug"] = d["mfu_ghost_hits"] // sint
    v["unc"] = d["uncached_hits"] // sint
    v["eskip"] = d["evict_skip"] // sint
    v["el2skip"] = d["evict_l2_skip"] // sint
    v["el2cach"] = d["evict_l2_cached"] // sint
    v["el2el"] = d["evict_l2_eligible"] // sint
    v["el2mfu"] = d["evict_l2_eligible_mfu"] // sint
    v["el2mru"] = d["evict_l2_eligible_mru"] // sint
    v["el2inel"] = d["evict_l2_ineligible"] // sint
    v["mtxmis"] = d["mutex_miss"] // sint

    if l2exist:
        v["l2hits"] = d["l2_hits"] // sint
        v["l2miss"] = d["l2_misses"] // sint
        v["l2read"] = v["l2hits"] + v["l2miss"]
        v["l2hit%"] = 100 * v["l2hits"] // v["l2read"] if v["l2read"] > 0 else 0

        v["l2miss%"] = 100 - v["l2hit%"] if v["l2read"] > 0 else 0
        v["l2asize"] = cur["l2_asize"]
        v["l2size"] = cur["l2_size"]
        v["l2bytes"] = d["l2_read_bytes"] // sint

        v["l2pref"] = cur["l2_prefetch_asize"]
        v["l2mfu"] = cur["l2_mfu_asize"]
        v["l2mru"] = cur["l2_mru_asize"]
        v["l2data"] = cur["l2_bufc_data_asize"]
        v["l2meta"] = cur["l2_bufc_metadata_asize"]
        v["l2pref%"] = 100 * v["l2pref"] // v["l2asize"]
        v["l2mfu%"] = 100 * v["l2mfu"] // v["l2asize"]
        v["l2mru%"] = 100 * v["l2mru"] // v["l2asize"]
        v["l2data%"] = 100 * v["l2data"] // v["l2asize"]
        v["l2meta%"] = 100 * v["l2meta"] // v["l2asize"]

    v["grow"] = 0 if cur["arc_no_grow"] else 1
    v["need"] = cur["arc_need_free"]
    v["free"] = cur["memory_free_bytes"]
    v["avail"] = cur["memory_available_bytes"]
    v["waste"] = cur["abd_chunk_waste_size"]


def main():
    global sint
    global count
    global hdr_intr

    i = 0
    count_flag = 0

    init()
    if count > 0:
        count_flag = 1

    signal(SIGINT, SIG_DFL)
    signal(SIGWINCH, resize_handler)
    while True:
        if i == 0:
            print_header()

        snap_stats()
        calculate()
        print_values()

        if count_flag == 1:
            if count <= 1:
                break
            count -= 1

        i = 0 if i >= hdr_intr else i + 1
        time.sleep(sint)

    if out:
        out.close()


if __name__ == '__main__':
    main()