From b411b3637fa71fce9cf2acf0639009500f5892fe Mon Sep 17 00:00:00 2001 From: Philipp Reisner Date: Fri, 25 Sep 2009 16:07:19 -0700 Subject: The DRBD driver Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg --- include/linux/drbd.h | 349 +++++++++++++++++++++++++++++++++++++++++ include/linux/drbd_limits.h | 137 ++++++++++++++++ include/linux/drbd_nl.h | 137 ++++++++++++++++ include/linux/drbd_tag_magic.h | 83 ++++++++++ include/linux/lru_cache.h | 294 ++++++++++++++++++++++++++++++++++ 5 files changed, 1000 insertions(+) create mode 100644 include/linux/drbd.h create mode 100644 include/linux/drbd_limits.h create mode 100644 include/linux/drbd_nl.h create mode 100644 include/linux/drbd_tag_magic.h create mode 100644 include/linux/lru_cache.h (limited to 'include') diff --git a/include/linux/drbd.h b/include/linux/drbd.h new file mode 100644 index 0000000..69dc711 --- /dev/null +++ b/include/linux/drbd.h @@ -0,0 +1,349 @@ +/* + drbd.h + Kernel module for 2.6.x Kernels + + This file is part of DRBD by Philipp Reisner and Lars Ellenberg. + + Copyright (C) 2001-2008, LINBIT Information Technologies GmbH. + Copyright (C) 2001-2008, Philipp Reisner . + Copyright (C) 2001-2008, Lars Ellenberg . + + drbd is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + drbd is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with drbd; see the file COPYING. If not, write to + the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. + +*/ +#ifndef DRBD_H +#define DRBD_H +#include +#include + +#ifdef __KERNEL__ +#include +#include +#else +#include +#include +#include + +/* Altough the Linux source code makes a difference between + generic endianness and the bitfields' endianness, there is no + architecture as of Linux-2.6.24-rc4 where the bitfileds' endianness + does not match the generic endianness. */ + +#if __BYTE_ORDER == __LITTLE_ENDIAN +#define __LITTLE_ENDIAN_BITFIELD +#elif __BYTE_ORDER == __BIG_ENDIAN +#define __BIG_ENDIAN_BITFIELD +#else +# error "sorry, weird endianness on this box" +#endif + +#endif + + +extern const char *drbd_buildtag(void); +#define REL_VERSION "8.3.3rc2" +#define API_VERSION 88 +#define PRO_VERSION_MIN 86 +#define PRO_VERSION_MAX 91 + + +enum drbd_io_error_p { + EP_PASS_ON, /* FIXME should the better be named "Ignore"? */ + EP_CALL_HELPER, + EP_DETACH +}; + +enum drbd_fencing_p { + FP_DONT_CARE, + FP_RESOURCE, + FP_STONITH +}; + +enum drbd_disconnect_p { + DP_RECONNECT, + DP_DROP_NET_CONF, + DP_FREEZE_IO +}; + +enum drbd_after_sb_p { + ASB_DISCONNECT, + ASB_DISCARD_YOUNGER_PRI, + ASB_DISCARD_OLDER_PRI, + ASB_DISCARD_ZERO_CHG, + ASB_DISCARD_LEAST_CHG, + ASB_DISCARD_LOCAL, + ASB_DISCARD_REMOTE, + ASB_CONSENSUS, + ASB_DISCARD_SECONDARY, + ASB_CALL_HELPER, + ASB_VIOLENTLY +}; + +/* KEEP the order, do not delete or insert. Only append. */ +enum drbd_ret_codes { + ERR_CODE_BASE = 100, + NO_ERROR = 101, + ERR_LOCAL_ADDR = 102, + ERR_PEER_ADDR = 103, + ERR_OPEN_DISK = 104, + ERR_OPEN_MD_DISK = 105, + ERR_DISK_NOT_BDEV = 107, + ERR_MD_NOT_BDEV = 108, + ERR_DISK_TO_SMALL = 111, + ERR_MD_DISK_TO_SMALL = 112, + ERR_BDCLAIM_DISK = 114, + ERR_BDCLAIM_MD_DISK = 115, + ERR_MD_IDX_INVALID = 116, + ERR_IO_MD_DISK = 118, + ERR_MD_INVALID = 119, + ERR_AUTH_ALG = 120, + ERR_AUTH_ALG_ND = 121, + ERR_NOMEM = 122, + ERR_DISCARD = 123, + ERR_DISK_CONFIGURED = 124, + ERR_NET_CONFIGURED = 125, + ERR_MANDATORY_TAG = 126, + ERR_MINOR_INVALID = 127, + ERR_INTR = 129, /* EINTR */ + ERR_RESIZE_RESYNC = 130, + ERR_NO_PRIMARY = 131, + ERR_SYNC_AFTER = 132, + ERR_SYNC_AFTER_CYCLE = 133, + ERR_PAUSE_IS_SET = 134, + ERR_PAUSE_IS_CLEAR = 135, + ERR_PACKET_NR = 137, + ERR_NO_DISK = 138, + ERR_NOT_PROTO_C = 139, + ERR_NOMEM_BITMAP = 140, + ERR_INTEGRITY_ALG = 141, /* DRBD 8.2 only */ + ERR_INTEGRITY_ALG_ND = 142, /* DRBD 8.2 only */ + ERR_CPU_MASK_PARSE = 143, /* DRBD 8.2 only */ + ERR_CSUMS_ALG = 144, /* DRBD 8.2 only */ + ERR_CSUMS_ALG_ND = 145, /* DRBD 8.2 only */ + ERR_VERIFY_ALG = 146, /* DRBD 8.2 only */ + ERR_VERIFY_ALG_ND = 147, /* DRBD 8.2 only */ + ERR_CSUMS_RESYNC_RUNNING= 148, /* DRBD 8.2 only */ + ERR_VERIFY_RUNNING = 149, /* DRBD 8.2 only */ + ERR_DATA_NOT_CURRENT = 150, + ERR_CONNECTED = 151, /* DRBD 8.3 only */ + + /* insert new ones above this line */ + AFTER_LAST_ERR_CODE +}; + +#define DRBD_PROT_A 1 +#define DRBD_PROT_B 2 +#define DRBD_PROT_C 3 + +enum drbd_role { + R_UNKNOWN = 0, + R_PRIMARY = 1, /* role */ + R_SECONDARY = 2, /* role */ + R_MASK = 3, +}; + +/* The order of these constants is important. + * The lower ones (=C_WF_REPORT_PARAMS ==> There is a socket + */ +enum drbd_conns { + C_STANDALONE, + C_DISCONNECTING, /* Temporal state on the way to StandAlone. */ + C_UNCONNECTED, /* >= C_UNCONNECTED -> inc_net() succeeds */ + + /* These temporal states are all used on the way + * from >= C_CONNECTED to Unconnected. + * The 'disconnect reason' states + * I do not allow to change beween them. */ + C_TIMEOUT, + C_BROKEN_PIPE, + C_NETWORK_FAILURE, + C_PROTOCOL_ERROR, + C_TEAR_DOWN, + + C_WF_CONNECTION, + C_WF_REPORT_PARAMS, /* we have a socket */ + C_CONNECTED, /* we have introduced each other */ + C_STARTING_SYNC_S, /* starting full sync by admin request. */ + C_STARTING_SYNC_T, /* stariing full sync by admin request. */ + C_WF_BITMAP_S, + C_WF_BITMAP_T, + C_WF_SYNC_UUID, + + /* All SyncStates are tested with this comparison + * xx >= C_SYNC_SOURCE && xx <= C_PAUSED_SYNC_T */ + C_SYNC_SOURCE, + C_SYNC_TARGET, + C_VERIFY_S, + C_VERIFY_T, + C_PAUSED_SYNC_S, + C_PAUSED_SYNC_T, + C_MASK = 31 +}; + +enum drbd_disk_state { + D_DISKLESS, + D_ATTACHING, /* In the process of reading the meta-data */ + D_FAILED, /* Becomes D_DISKLESS as soon as we told it the peer */ + /* when >= D_FAILED it is legal to access mdev->bc */ + D_NEGOTIATING, /* Late attaching state, we need to talk to the peer */ + D_INCONSISTENT, + D_OUTDATED, + D_UNKNOWN, /* Only used for the peer, never for myself */ + D_CONSISTENT, /* Might be D_OUTDATED, might be D_UP_TO_DATE ... */ + D_UP_TO_DATE, /* Only this disk state allows applications' IO ! */ + D_MASK = 15 +}; + +union drbd_state { +/* According to gcc's docs is the ... + * The order of allocation of bit-fields within a unit (C90 6.5.2.1, C99 6.7.2.1). + * Determined by ABI. + * pointed out by Maxim Uvarov q + * even though we transmit as "cpu_to_be32(state)", + * the offsets of the bitfields still need to be swapped + * on different endianess. + */ + struct { +#if defined(__LITTLE_ENDIAN_BITFIELD) + unsigned role:2 ; /* 3/4 primary/secondary/unknown */ + unsigned peer:2 ; /* 3/4 primary/secondary/unknown */ + unsigned conn:5 ; /* 17/32 cstates */ + unsigned disk:4 ; /* 8/16 from D_DISKLESS to D_UP_TO_DATE */ + unsigned pdsk:4 ; /* 8/16 from D_DISKLESS to D_UP_TO_DATE */ + unsigned susp:1 ; /* 2/2 IO suspended no/yes */ + unsigned aftr_isp:1 ; /* isp .. imposed sync pause */ + unsigned peer_isp:1 ; + unsigned user_isp:1 ; + unsigned _pad:11; /* 0 unused */ +#elif defined(__BIG_ENDIAN_BITFIELD) + unsigned _pad:11; /* 0 unused */ + unsigned user_isp:1 ; + unsigned peer_isp:1 ; + unsigned aftr_isp:1 ; /* isp .. imposed sync pause */ + unsigned susp:1 ; /* 2/2 IO suspended no/yes */ + unsigned pdsk:4 ; /* 8/16 from D_DISKLESS to D_UP_TO_DATE */ + unsigned disk:4 ; /* 8/16 from D_DISKLESS to D_UP_TO_DATE */ + unsigned conn:5 ; /* 17/32 cstates */ + unsigned peer:2 ; /* 3/4 primary/secondary/unknown */ + unsigned role:2 ; /* 3/4 primary/secondary/unknown */ +#else +# error "this endianess is not supported" +#endif + }; + unsigned int i; +}; + +enum drbd_state_ret_codes { + SS_CW_NO_NEED = 4, + SS_CW_SUCCESS = 3, + SS_NOTHING_TO_DO = 2, + SS_SUCCESS = 1, + SS_UNKNOWN_ERROR = 0, /* Used to sleep longer in _drbd_request_state */ + SS_TWO_PRIMARIES = -1, + SS_NO_UP_TO_DATE_DISK = -2, + SS_NO_LOCAL_DISK = -4, + SS_NO_REMOTE_DISK = -5, + SS_CONNECTED_OUTDATES = -6, + SS_PRIMARY_NOP = -7, + SS_RESYNC_RUNNING = -8, + SS_ALREADY_STANDALONE = -9, + SS_CW_FAILED_BY_PEER = -10, + SS_IS_DISKLESS = -11, + SS_DEVICE_IN_USE = -12, + SS_NO_NET_CONFIG = -13, + SS_NO_VERIFY_ALG = -14, /* drbd-8.2 only */ + SS_NEED_CONNECTION = -15, /* drbd-8.2 only */ + SS_LOWER_THAN_OUTDATED = -16, + SS_NOT_SUPPORTED = -17, /* drbd-8.2 only */ + SS_IN_TRANSIENT_STATE = -18, /* Retry after the next state change */ + SS_CONCURRENT_ST_CHG = -19, /* Concurrent cluster side state change! */ + SS_AFTER_LAST_ERROR = -20, /* Keep this at bottom */ +}; + +/* from drbd_strings.c */ +extern const char *drbd_conn_str(enum drbd_conns); +extern const char *drbd_role_str(enum drbd_role); +extern const char *drbd_disk_str(enum drbd_disk_state); +extern const char *drbd_set_st_err_str(enum drbd_state_ret_codes); + +#define SHARED_SECRET_MAX 64 + +#define MDF_CONSISTENT (1 << 0) +#define MDF_PRIMARY_IND (1 << 1) +#define MDF_CONNECTED_IND (1 << 2) +#define MDF_FULL_SYNC (1 << 3) +#define MDF_WAS_UP_TO_DATE (1 << 4) +#define MDF_PEER_OUT_DATED (1 << 5) +#define MDF_CRASHED_PRIMARY (1 << 6) + +enum drbd_uuid_index { + UI_CURRENT, + UI_BITMAP, + UI_HISTORY_START, + UI_HISTORY_END, + UI_SIZE, /* nl-packet: number of dirty bits */ + UI_FLAGS, /* nl-packet: flags */ + UI_EXTENDED_SIZE /* Everything. */ +}; + +enum drbd_timeout_flag { + UT_DEFAULT = 0, + UT_DEGRADED = 1, + UT_PEER_OUTDATED = 2, +}; + +#define UUID_JUST_CREATED ((__u64)4) + +#define DRBD_MAGIC 0x83740267 +#define BE_DRBD_MAGIC __constant_cpu_to_be32(DRBD_MAGIC) + +/* these are of type "int" */ +#define DRBD_MD_INDEX_INTERNAL -1 +#define DRBD_MD_INDEX_FLEX_EXT -2 +#define DRBD_MD_INDEX_FLEX_INT -3 + +/* Start of the new netlink/connector stuff */ + +#define DRBD_NL_CREATE_DEVICE 0x01 +#define DRBD_NL_SET_DEFAULTS 0x02 + +/* The following line should be moved over to linux/connector.h + * when the time comes */ +#ifndef CN_IDX_DRBD +# define CN_IDX_DRBD 0x4 +/* Ubuntu "intrepid ibex" release defined CN_IDX_DRBD as 0x6 */ +#endif +#define CN_VAL_DRBD 0x1 + +/* For searching a vacant cn_idx value */ +#define CN_IDX_STEP 6977 + +struct drbd_nl_cfg_req { + int packet_type; + unsigned int drbd_minor; + int flags; + unsigned short tag_list[]; +}; + +struct drbd_nl_cfg_reply { + int packet_type; + unsigned int minor; + int ret_code; /* enum ret_code or set_st_err_t */ + unsigned short tag_list[]; /* only used with get_* calls */ +}; + +#endif diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h new file mode 100644 index 0000000..9d067ce --- /dev/null +++ b/include/linux/drbd_limits.h @@ -0,0 +1,137 @@ +/* + drbd_limits.h + This file is part of DRBD by Philipp Reisner and Lars Ellenberg. +*/ + +/* + * Our current limitations. + * Some of them are hard limits, + * some of them are arbitrary range limits, that make it easier to provide + * feedback about nonsense settings for certain configurable values. + */ + +#ifndef DRBD_LIMITS_H +#define DRBD_LIMITS_H 1 + +#define DEBUG_RANGE_CHECK 0 + +#define DRBD_MINOR_COUNT_MIN 1 +#define DRBD_MINOR_COUNT_MAX 255 + +#define DRBD_DIALOG_REFRESH_MIN 0 +#define DRBD_DIALOG_REFRESH_MAX 600 + +/* valid port number */ +#define DRBD_PORT_MIN 1 +#define DRBD_PORT_MAX 0xffff + +/* startup { */ + /* if you want more than 3.4 days, disable */ +#define DRBD_WFC_TIMEOUT_MIN 0 +#define DRBD_WFC_TIMEOUT_MAX 300000 +#define DRBD_WFC_TIMEOUT_DEF 0 + +#define DRBD_DEGR_WFC_TIMEOUT_MIN 0 +#define DRBD_DEGR_WFC_TIMEOUT_MAX 300000 +#define DRBD_DEGR_WFC_TIMEOUT_DEF 0 + +#define DRBD_OUTDATED_WFC_TIMEOUT_MIN 0 +#define DRBD_OUTDATED_WFC_TIMEOUT_MAX 300000 +#define DRBD_OUTDATED_WFC_TIMEOUT_DEF 0 +/* }*/ + +/* net { */ + /* timeout, unit centi seconds + * more than one minute timeout is not usefull */ +#define DRBD_TIMEOUT_MIN 1 +#define DRBD_TIMEOUT_MAX 600 +#define DRBD_TIMEOUT_DEF 60 /* 6 seconds */ + + /* active connection retries when C_WF_CONNECTION */ +#define DRBD_CONNECT_INT_MIN 1 +#define DRBD_CONNECT_INT_MAX 120 +#define DRBD_CONNECT_INT_DEF 10 /* seconds */ + + /* keep-alive probes when idle */ +#define DRBD_PING_INT_MIN 1 +#define DRBD_PING_INT_MAX 120 +#define DRBD_PING_INT_DEF 10 + + /* timeout for the ping packets.*/ +#define DRBD_PING_TIMEO_MIN 1 +#define DRBD_PING_TIMEO_MAX 100 +#define DRBD_PING_TIMEO_DEF 5 + + /* max number of write requests between write barriers */ +#define DRBD_MAX_EPOCH_SIZE_MIN 1 +#define DRBD_MAX_EPOCH_SIZE_MAX 20000 +#define DRBD_MAX_EPOCH_SIZE_DEF 2048 + + /* I don't think that a tcp send buffer of more than 10M is usefull */ +#define DRBD_SNDBUF_SIZE_MIN 0 +#define DRBD_SNDBUF_SIZE_MAX (10<<20) +#define DRBD_SNDBUF_SIZE_DEF (2*65535) + +#define DRBD_RCVBUF_SIZE_MIN 0 +#define DRBD_RCVBUF_SIZE_MAX (10<<20) +#define DRBD_RCVBUF_SIZE_DEF (2*65535) + + /* @4k PageSize -> 128kB - 512MB */ +#define DRBD_MAX_BUFFERS_MIN 32 +#define DRBD_MAX_BUFFERS_MAX 131072 +#define DRBD_MAX_BUFFERS_DEF 2048 + + /* @4k PageSize -> 4kB - 512MB */ +#define DRBD_UNPLUG_WATERMARK_MIN 1 +#define DRBD_UNPLUG_WATERMARK_MAX 131072 +#define DRBD_UNPLUG_WATERMARK_DEF (DRBD_MAX_BUFFERS_DEF/16) + + /* 0 is disabled. + * 200 should be more than enough even for very short timeouts */ +#define DRBD_KO_COUNT_MIN 0 +#define DRBD_KO_COUNT_MAX 200 +#define DRBD_KO_COUNT_DEF 0 +/* } */ + +/* syncer { */ + /* FIXME allow rate to be zero? */ +#define DRBD_RATE_MIN 1 +/* channel bonding 10 GbE, or other hardware */ +#define DRBD_RATE_MAX (4 << 20) +#define DRBD_RATE_DEF 250 /* kb/second */ + + /* less than 7 would hit performance unneccessarily. + * 3833 is the largest prime that still does fit + * into 64 sectors of activity log */ +#define DRBD_AL_EXTENTS_MIN 7 +#define DRBD_AL_EXTENTS_MAX 3833 +#define DRBD_AL_EXTENTS_DEF 127 + +#define DRBD_AFTER_MIN -1 +#define DRBD_AFTER_MAX 255 +#define DRBD_AFTER_DEF -1 + +/* } */ + +/* drbdsetup XY resize -d Z + * you are free to reduce the device size to nothing, if you want to. + * the upper limit with 64bit kernel, enough ram and flexible meta data + * is 16 TB, currently. */ +/* DRBD_MAX_SECTORS */ +#define DRBD_DISK_SIZE_SECT_MIN 0 +#define DRBD_DISK_SIZE_SECT_MAX (16 * (2LLU << 30)) +#define DRBD_DISK_SIZE_SECT_DEF 0 /* = disabled = no user size... */ + +#define DRBD_ON_IO_ERROR_DEF EP_PASS_ON +#define DRBD_FENCING_DEF FP_DONT_CARE +#define DRBD_AFTER_SB_0P_DEF ASB_DISCONNECT +#define DRBD_AFTER_SB_1P_DEF ASB_DISCONNECT +#define DRBD_AFTER_SB_2P_DEF ASB_DISCONNECT +#define DRBD_RR_CONFLICT_DEF ASB_DISCONNECT + +#define DRBD_MAX_BIO_BVECS_MIN 0 +#define DRBD_MAX_BIO_BVECS_MAX 128 +#define DRBD_MAX_BIO_BVECS_DEF 0 + +#undef RANGE +#endif diff --git a/include/linux/drbd_nl.h b/include/linux/drbd_nl.h new file mode 100644 index 0000000..db5721a --- /dev/null +++ b/include/linux/drbd_nl.h @@ -0,0 +1,137 @@ +/* + PAKET( name, + TYPE ( pn, pr, member ) + ... + ) + + You may never reissue one of the pn arguments +*/ + +#if !defined(NL_PACKET) || !defined(NL_STRING) || !defined(NL_INTEGER) || !defined(NL_BIT) || !defined(NL_INT64) +#error "The macros NL_PACKET, NL_STRING, NL_INTEGER, NL_INT64 and NL_BIT needs to be defined" +#endif + +NL_PACKET(primary, 1, + NL_BIT( 1, T_MAY_IGNORE, overwrite_peer) +) + +NL_PACKET(secondary, 2, ) + +NL_PACKET(disk_conf, 3, + NL_INT64( 2, T_MAY_IGNORE, disk_size) + NL_STRING( 3, T_MANDATORY, backing_dev, 128) + NL_STRING( 4, T_MANDATORY, meta_dev, 128) + NL_INTEGER( 5, T_MANDATORY, meta_dev_idx) + NL_INTEGER( 6, T_MAY_IGNORE, on_io_error) + NL_INTEGER( 7, T_MAY_IGNORE, fencing) + NL_BIT( 37, T_MAY_IGNORE, use_bmbv) + NL_BIT( 53, T_MAY_IGNORE, no_disk_flush) + NL_BIT( 54, T_MAY_IGNORE, no_md_flush) + /* 55 max_bio_size was available in 8.2.6rc2 */ + NL_INTEGER( 56, T_MAY_IGNORE, max_bio_bvecs) + NL_BIT( 57, T_MAY_IGNORE, no_disk_barrier) + NL_BIT( 58, T_MAY_IGNORE, no_disk_drain) +) + +NL_PACKET(detach, 4, ) + +NL_PACKET(net_conf, 5, + NL_STRING( 8, T_MANDATORY, my_addr, 128) + NL_STRING( 9, T_MANDATORY, peer_addr, 128) + NL_STRING( 10, T_MAY_IGNORE, shared_secret, SHARED_SECRET_MAX) + NL_STRING( 11, T_MAY_IGNORE, cram_hmac_alg, SHARED_SECRET_MAX) + NL_STRING( 44, T_MAY_IGNORE, integrity_alg, SHARED_SECRET_MAX) + NL_INTEGER( 14, T_MAY_IGNORE, timeout) + NL_INTEGER( 15, T_MANDATORY, wire_protocol) + NL_INTEGER( 16, T_MAY_IGNORE, try_connect_int) + NL_INTEGER( 17, T_MAY_IGNORE, ping_int) + NL_INTEGER( 18, T_MAY_IGNORE, max_epoch_size) + NL_INTEGER( 19, T_MAY_IGNORE, max_buffers) + NL_INTEGER( 20, T_MAY_IGNORE, unplug_watermark) + NL_INTEGER( 21, T_MAY_IGNORE, sndbuf_size) + NL_INTEGER( 22, T_MAY_IGNORE, ko_count) + NL_INTEGER( 24, T_MAY_IGNORE, after_sb_0p) + NL_INTEGER( 25, T_MAY_IGNORE, after_sb_1p) + NL_INTEGER( 26, T_MAY_IGNORE, after_sb_2p) + NL_INTEGER( 39, T_MAY_IGNORE, rr_conflict) + NL_INTEGER( 40, T_MAY_IGNORE, ping_timeo) + NL_INTEGER( 67, T_MAY_IGNORE, rcvbuf_size) + /* 59 addr_family was available in GIT, never released */ + NL_BIT( 60, T_MANDATORY, mind_af) + NL_BIT( 27, T_MAY_IGNORE, want_lose) + NL_BIT( 28, T_MAY_IGNORE, two_primaries) + NL_BIT( 41, T_MAY_IGNORE, always_asbp) + NL_BIT( 61, T_MAY_IGNORE, no_cork) + NL_BIT( 62, T_MANDATORY, auto_sndbuf_size) +) + +NL_PACKET(disconnect, 6, ) + +NL_PACKET(resize, 7, + NL_INT64( 29, T_MAY_IGNORE, resize_size) +) + +NL_PACKET(syncer_conf, 8, + NL_INTEGER( 30, T_MAY_IGNORE, rate) + NL_INTEGER( 31, T_MAY_IGNORE, after) + NL_INTEGER( 32, T_MAY_IGNORE, al_extents) + NL_STRING( 52, T_MAY_IGNORE, verify_alg, SHARED_SECRET_MAX) + NL_STRING( 51, T_MAY_IGNORE, cpu_mask, 32) + NL_STRING( 64, T_MAY_IGNORE, csums_alg, SHARED_SECRET_MAX) + NL_BIT( 65, T_MAY_IGNORE, use_rle) +) + +NL_PACKET(invalidate, 9, ) +NL_PACKET(invalidate_peer, 10, ) +NL_PACKET(pause_sync, 11, ) +NL_PACKET(resume_sync, 12, ) +NL_PACKET(suspend_io, 13, ) +NL_PACKET(resume_io, 14, ) +NL_PACKET(outdate, 15, ) +NL_PACKET(get_config, 16, ) +NL_PACKET(get_state, 17, + NL_INTEGER( 33, T_MAY_IGNORE, state_i) +) + +NL_PACKET(get_uuids, 18, + NL_STRING( 34, T_MAY_IGNORE, uuids, (UI_SIZE*sizeof(__u64))) + NL_INTEGER( 35, T_MAY_IGNORE, uuids_flags) +) + +NL_PACKET(get_timeout_flag, 19, + NL_BIT( 36, T_MAY_IGNORE, use_degraded) +) + +NL_PACKET(call_helper, 20, + NL_STRING( 38, T_MAY_IGNORE, helper, 32) +) + +/* Tag nr 42 already allocated in drbd-8.1 development. */ + +NL_PACKET(sync_progress, 23, + NL_INTEGER( 43, T_MAY_IGNORE, sync_progress) +) + +NL_PACKET(dump_ee, 24, + NL_STRING( 45, T_MAY_IGNORE, dump_ee_reason, 32) + NL_STRING( 46, T_MAY_IGNORE, seen_digest, SHARED_SECRET_MAX) + NL_STRING( 47, T_MAY_IGNORE, calc_digest, SHARED_SECRET_MAX) + NL_INT64( 48, T_MAY_IGNORE, ee_sector) + NL_INT64( 49, T_MAY_IGNORE, ee_block_id) + NL_STRING( 50, T_MAY_IGNORE, ee_data, 32 << 10) +) + +NL_PACKET(start_ov, 25, + NL_INT64( 66, T_MAY_IGNORE, start_sector) +) + +NL_PACKET(new_c_uuid, 26, + NL_BIT( 63, T_MANDATORY, clear_bm) +) + +#undef NL_PACKET +#undef NL_INTEGER +#undef NL_INT64 +#undef NL_BIT +#undef NL_STRING + diff --git a/include/linux/drbd_tag_magic.h b/include/linux/drbd_tag_magic.h new file mode 100644 index 0000000..fcdff84 --- /dev/null +++ b/include/linux/drbd_tag_magic.h @@ -0,0 +1,83 @@ +#ifndef DRBD_TAG_MAGIC_H +#define DRBD_TAG_MAGIC_H + +#define TT_END 0 +#define TT_REMOVED 0xE000 + +/* declare packet_type enums */ +enum packet_types { +#define NL_PACKET(name, number, fields) P_ ## name = number, +#define NL_INTEGER(pn, pr, member) +#define NL_INT64(pn, pr, member) +#define NL_BIT(pn, pr, member) +#define NL_STRING(pn, pr, member, len) +#include "drbd_nl.h" + P_nl_after_last_packet, +}; + +/* These struct are used to deduce the size of the tag lists: */ +#define NL_PACKET(name, number, fields) \ + struct name ## _tag_len_struct { fields }; +#define NL_INTEGER(pn, pr, member) \ + int member; int tag_and_len ## member; +#define NL_INT64(pn, pr, member) \ + __u64 member; int tag_and_len ## member; +#define NL_BIT(pn, pr, member) \ + unsigned char member:1; int tag_and_len ## member; +#define NL_STRING(pn, pr, member, len) \ + unsigned char member[len]; int member ## _len; \ + int tag_and_len ## member; +#include "linux/drbd_nl.h" + +/* declate tag-list-sizes */ +static const int tag_list_sizes[] = { +#define NL_PACKET(name, number, fields) 2 fields , +#define NL_INTEGER(pn, pr, member) + 4 + 4 +#define NL_INT64(pn, pr, member) + 4 + 8 +#define NL_BIT(pn, pr, member) + 4 + 1 +#define NL_STRING(pn, pr, member, len) + 4 + (len) +#include "drbd_nl.h" +}; + +/* The two highest bits are used for the tag type */ +#define TT_MASK 0xC000 +#define TT_INTEGER 0x0000 +#define TT_INT64 0x4000 +#define TT_BIT 0x8000 +#define TT_STRING 0xC000 +/* The next bit indicates if processing of the tag is mandatory */ +#define T_MANDATORY 0x2000 +#define T_MAY_IGNORE 0x0000 +#define TN_MASK 0x1fff +/* The remaining 13 bits are used to enumerate the tags */ + +#define tag_type(T) ((T) & TT_MASK) +#define tag_number(T) ((T) & TN_MASK) + +/* declare tag enums */ +#define NL_PACKET(name, number, fields) fields +enum drbd_tags { +#define NL_INTEGER(pn, pr, member) T_ ## member = pn | TT_INTEGER | pr , +#define NL_INT64(pn, pr, member) T_ ## member = pn | TT_INT64 | pr , +#define NL_BIT(pn, pr, member) T_ ## member = pn | TT_BIT | pr , +#define NL_STRING(pn, pr, member, len) T_ ## member = pn | TT_STRING | pr , +#include "drbd_nl.h" +}; + +struct tag { + const char *name; + int type_n_flags; + int max_len; +}; + +/* declare tag names */ +#define NL_PACKET(name, number, fields) fields +static const struct tag tag_descriptions[] = { +#define NL_INTEGER(pn, pr, member) [ pn ] = { #member, TT_INTEGER | pr, sizeof(int) }, +#define NL_INT64(pn, pr, member) [ pn ] = { #member, TT_INT64 | pr, sizeof(__u64) }, +#define NL_BIT(pn, pr, member) [ pn ] = { #member, TT_BIT | pr, sizeof(int) }, +#define NL_STRING(pn, pr, member, len) [ pn ] = { #member, TT_STRING | pr, (len) }, +#include "drbd_nl.h" +}; + +#endif diff --git a/include/linux/lru_cache.h b/include/linux/lru_cache.h new file mode 100644 index 0000000..3a2b2d9 --- /dev/null +++ b/include/linux/lru_cache.h @@ -0,0 +1,294 @@ +/* + lru_cache.c + + This file is part of DRBD by Philipp Reisner and Lars Ellenberg. + + Copyright (C) 2003-2008, LINBIT Information Technologies GmbH. + Copyright (C) 2003-2008, Philipp Reisner . + Copyright (C) 2003-2008, Lars Ellenberg . + + drbd is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + drbd is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with drbd; see the file COPYING. If not, write to + the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. + + */ + +#ifndef LRU_CACHE_H +#define LRU_CACHE_H + +#include +#include +#include +#include /* for memset */ +#include + +/* +This header file (and its .c file; kernel-doc of functions see there) + define a helper framework to easily keep track of index:label associations, + and changes to an "active set" of objects, as well as pending transactions, + to persistently record those changes. + + We use an LRU policy if it is necessary to "cool down" a region currently in + the active set before we can "heat" a previously unused region. + + Because of this later property, it is called "lru_cache". + As it actually Tracks Objects in an Active SeT, we could also call it + toast (incidentally that is what may happen to the data on the + backend storage uppon next resync, if we don't get it right). + +What for? + +We replicate IO (more or less synchronously) to local and remote disk. + +For crash recovery after replication node failure, + we need to resync all regions that have been target of in-flight WRITE IO + (in use, or "hot", regions), as we don't know wether or not those WRITEs have + made it to stable storage. + + To avoid a "full resync", we need to persistently track these regions. + + This is known as "write intent log", and can be implemented as on-disk + (coarse or fine grained) bitmap, or other meta data. + + To avoid the overhead of frequent extra writes to this meta data area, + usually the condition is softened to regions that _may_ have been target of + in-flight WRITE IO, e.g. by only lazily clearing the on-disk write-intent + bitmap, trading frequency of meta data transactions against amount of + (possibly unneccessary) resync traffic. + + If we set a hard limit on the area that may be "hot" at any given time, we + limit the amount of resync traffic needed for crash recovery. + +For recovery after replication link failure, + we need to resync all blocks that have been changed on the other replica + in the mean time, or, if both replica have been changed independently [*], + all blocks that have been changed on either replica in the mean time. + [*] usually as a result of a cluster split-brain and insufficient protection. + but there are valid use cases to do this on purpose. + + Tracking those blocks can be implemented as "dirty bitmap". + Having it fine-grained reduces the amount of resync traffic. + It should also be persistent, to allow for reboots (or crashes) + while the replication link is down. + +There are various possible implementations for persistently storing +write intent log information, three of which are mentioned here. + +"Chunk dirtying" + The on-disk "dirty bitmap" may be re-used as "write-intent" bitmap as well. + To reduce the frequency of bitmap updates for write-intent log purposes, + one could dirty "chunks" (of some size) at a time of the (fine grained) + on-disk bitmap, while keeping the in-memory "dirty" bitmap as clean as + possible, flushing it to disk again when a previously "hot" (and on-disk + dirtied as full chunk) area "cools down" again (no IO in flight anymore, + and none expected in the near future either). + +"Explicit (coarse) write intent bitmap" + An other implementation could chose a (probably coarse) explicit bitmap, + for write-intent log purposes, additionally to the fine grained dirty bitmap. + +"Activity log" + Yet an other implementation may keep track of the hot regions, by starting + with an empty set, and writing down a journal of region numbers that have + become "hot", or have "cooled down" again. + + To be able to use a ring buffer for this journal of changes to the active + set, we not only record the actual changes to that set, but also record the + not changing members of the set in a round robin fashion. To do so, we use a + fixed (but configurable) number of slots which we can identify by index, and + associate region numbers (labels) with these indices. + For each transaction recording a change to the active set, we record the + change itself (index: -old_label, +new_label), and which index is associated + with which label (index: current_label) within a certain sliding window that + is moved further over the available indices with each such transaction. + + Thus, for crash recovery, if the ringbuffer is sufficiently large, we can + accurately reconstruct the active set. + + Sufficiently large depends only on maximum number of active objects, and the + size of the sliding window recording "index: current_label" associations within + each transaction. + + This is what we call the "activity log". + + Currently we need one activity log transaction per single label change, which + does not give much benefit over the "dirty chunks of bitmap" approach, other + than potentially less seeks. + + We plan to change the transaction format to support multiple changes per + transaction, which then would reduce several (disjoint, "random") updates to + the bitmap into one transaction to the activity log ring buffer. +*/ + +/* this defines an element in a tracked set + * .colision is for hash table lookup. + * When we process a new IO request, we know its sector, thus can deduce the + * region number (label) easily. To do the label -> object lookup without a + * full list walk, we use a simple hash table. + * + * .list is on one of three lists: + * in_use: currently in use (refcnt > 0, lc_number != LC_FREE) + * lru: unused but ready to be reused or recycled + * (ts_refcnt == 0, lc_number != LC_FREE), + * free: unused but ready to be recycled + * (ts_refcnt == 0, lc_number == LC_FREE), + * + * an element is said to be "in the active set", + * if either on "in_use" or "lru", i.e. lc_number != LC_FREE. + * + * DRBD currently (May 2009) only uses 61 elements on the resync lru_cache + * (total memory usage 2 pages), and up to 3833 elements on the act_log + * lru_cache, totalling ~215 kB for 64bit architechture, ~53 pages. + * + * We usually do not actually free these objects again, but only "recycle" + * them, as the change "index: -old_label, +LC_FREE" would need a transaction + * as well. Which also means that using a kmem_cache to allocate the objects + * from wastes some resources. + * But it avoids high order page allocations in kmalloc. + */ +struct lc_element { + struct hlist_node colision; + struct list_head list; /* LRU list or free list */ + unsigned refcnt; + /* back "pointer" into ts_cache->element[index], + * for paranoia, and for "ts_element_to_index" */ + unsigned lc_index; + /* if we want to track a larger set of objects, + * it needs to become arch independend u64 */ + unsigned lc_number; + + /* special label when on free list */ +#define LC_FREE (~0U) +}; + +struct lru_cache { + /* the least recently used item is kept at lru->prev */ + struct list_head lru; + struct list_head free; + struct list_head in_use; + + /* the pre-created kmem cache to allocate the objects from */ + struct kmem_cache *lc_cache; + + /* size of tracked objects, used to memset(,0,) them in lc_reset */ + size_t element_size; + /* offset of struct lc_element member in the tracked object */ + size_t element_off; + + /* number of elements (indices) */ + unsigned int nr_elements; + /* Arbitrary limit on maximum tracked objects. Practical limit is much + * lower due to allocation failures, probably. For typical use cases, + * nr_elements should be a few thousand at most. + * This also limits the maximum value of ts_element.ts_index, allowing the + * 8 high bits of .ts_index to be overloaded with flags in the future. */ +#define LC_MAX_ACTIVE (1<<24) + + /* statistics */ + unsigned used; /* number of lelements currently on in_use list */ + unsigned long hits, misses, starving, dirty, changed; + + /* see below: flag-bits for lru_cache */ + unsigned long flags; + + /* when changing the label of an index element */ + unsigned int new_number; + + /* for paranoia when changing the label of an index element */ + struct lc_element *changing_element; + + void *lc_private; + const char *name; + + /* nr_elements there */ + struct hlist_head *lc_slot; + struct lc_element **lc_element; +}; + + +/* flag-bits for lru_cache */ +enum { + /* debugging aid, to catch concurrent access early. + * user needs to guarantee exclusive access by proper locking! */ + __LC_PARANOIA, + /* if we need to change the set, but currently there is a changing + * transaction pending, we are "dirty", and must deferr further + * changing requests */ + __LC_DIRTY, + /* if we need to change the set, but currently there is no free nor + * unused element available, we are "starving", and must not give out + * further references, to guarantee that eventually some refcnt will + * drop to zero and we will be able to make progress again, changing + * the set, writing the transaction. + * if the statistics say we are frequently starving, + * nr_elements is too small. */ + __LC_STARVING, +}; +#define LC_PARANOIA (1<<__LC_PARANOIA) +#define LC_DIRTY (1<<__LC_DIRTY) +#define LC_STARVING (1<<__LC_STARVING) + +extern struct lru_cache *lc_create(const char *name, struct kmem_cache *cache, + unsigned e_count, size_t e_size, size_t e_off); +extern void lc_reset(struct lru_cache *lc); +extern void lc_destroy(struct lru_cache *lc); +extern void lc_set(struct lru_cache *lc, unsigned int enr, int index); +extern void lc_del(struct lru_cache *lc, struct lc_element *element); + +extern struct lc_element *lc_try_get(struct lru_cache *lc, unsigned int enr); +extern struct lc_element *lc_find(struct lru_cache *lc, unsigned int enr); +extern struct lc_element *lc_get(struct lru_cache *lc, unsigned int enr); +extern unsigned int lc_put(struct lru_cache *lc, struct lc_element *e); +extern void lc_changed(struct lru_cache *lc, struct lc_element *e); + +struct seq_file; +extern size_t lc_seq_printf_stats(struct seq_file *seq, struct lru_cache *lc); + +extern void lc_seq_dump_details(struct seq_file *seq, struct lru_cache *lc, char *utext, + void (*detail) (struct seq_file *, struct lc_element *)); + +/** + * lc_try_lock - can be used to stop lc_get() from changing the tracked set + * @lc: the lru cache to operate on + * + * Note that the reference counts and order on the active and lru lists may + * still change. Returns true if we aquired the lock. + */ +static inline int lc_try_lock(struct lru_cache *lc) +{ + return !test_and_set_bit(__LC_DIRTY, &lc->flags); +} + +/** + * lc_unlock - unlock @lc, allow lc_get() to change the set again + * @lc: the lru cache to operate on + */ +static inline void lc_unlock(struct lru_cache *lc) +{ + clear_bit(__LC_DIRTY, &lc->flags); + smp_mb__after_clear_bit(); +} + +static inline int lc_is_used(struct lru_cache *lc, unsigned int enr) +{ + struct lc_element *e = lc_find(lc, enr); + return e && e->refcnt; +} + +#define lc_entry(ptr, type, member) \ + container_of(ptr, type, member) + +extern struct lc_element *lc_element_by_index(struct lru_cache *lc, unsigned i); +extern unsigned int lc_index_of(struct lru_cache *lc, struct lc_element *e); + +#endif -- cgit v1.1